From bf4237a188f872e535de8cbfc7903c1387b83b01 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
Date: Wed, 29 Jan 2020 17:38:19 +0100
Subject: [PATCH 001/474] clk: rockchip: convert rk3399 pll type to use
 readl_relaxed_poll_timeout

Instead of open coding the polling of the lock status, use the handy
readl_relaxed_poll_timeout for this. As the pll locking is normally
blazingly fast and we don't want to incur additional delays, we're
not doing any sleeps similar to for example the imx clk-pllv4
and define a very safe but still short timeout of 1ms.

Suggested-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20200129163821.1547295-1-heiko@sntech.de
---
 drivers/clk/rockchip/clk-pll.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/clk/rockchip/clk-pll.c b/drivers/clk/rockchip/clk-pll.c
index 10560d963baf..28b04aad31ad 100644
--- a/drivers/clk/rockchip/clk-pll.c
+++ b/drivers/clk/rockchip/clk-pll.c
@@ -589,19 +589,20 @@ static const struct clk_ops rockchip_rk3066_pll_clk_ops = {
 static int rockchip_rk3399_pll_wait_lock(struct rockchip_clk_pll *pll)
 {
 	u32 pllcon;
-	int delay = 24000000;
+	int ret;
 
-	/* poll check the lock status in rk3399 xPLLCON2 */
-	while (delay > 0) {
-		pllcon = readl_relaxed(pll->reg_base + RK3399_PLLCON(2));
-		if (pllcon & RK3399_PLLCON2_LOCK_STATUS)
-			return 0;
+	/*
+	 * Lock time typical 250, max 500 input clock cycles @24MHz
+	 * So define a very safe maximum of 1000us, meaning 24000 cycles.
+	 */
+	ret = readl_relaxed_poll_timeout(pll->reg_base + RK3399_PLLCON(2),
+					 pllcon,
+					 pllcon & RK3399_PLLCON2_LOCK_STATUS,
+					 0, 1000);
+	if (ret)
+		pr_err("%s: timeout waiting for pll to lock\n", __func__);
 
-		delay--;
-	}
-
-	pr_err("%s: timeout waiting for pll to lock\n", __func__);
-	return -ETIMEDOUT;
+	return ret;
 }
 
 static void rockchip_rk3399_pll_get_params(struct rockchip_clk_pll *pll,

From 3507df1a4615113ae6509e0f14f6546f0d1c84b4 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
Date: Wed, 29 Jan 2020 17:38:20 +0100
Subject: [PATCH 002/474] clk: rockchip: convert basic pll lock_wait to use
 regmap_read_poll_timeout

Instead of open coding the polling of the lock status, use the
handy regmap_read_poll_timeout for this. As the pll locking is
normally blazingly fast and we don't want to incur additional
delays, we're not doing any sleeps similar to for example the imx
clk-pllv4 and define a very safe but still short timeout of 1ms.

Suggested-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20200129163821.1547295-2-heiko@sntech.de
---
 drivers/clk/rockchip/clk-pll.c | 21 ++++++---------------
 1 file changed, 6 insertions(+), 15 deletions(-)

diff --git a/drivers/clk/rockchip/clk-pll.c b/drivers/clk/rockchip/clk-pll.c
index 28b04aad31ad..945f8b2cacc1 100644
--- a/drivers/clk/rockchip/clk-pll.c
+++ b/drivers/clk/rockchip/clk-pll.c
@@ -86,23 +86,14 @@ static int rockchip_pll_wait_lock(struct rockchip_clk_pll *pll)
 {
 	struct regmap *grf = pll->ctx->grf;
 	unsigned int val;
-	int delay = 24000000, ret;
+	int ret;
 
-	while (delay > 0) {
-		ret = regmap_read(grf, pll->lock_offset, &val);
-		if (ret) {
-			pr_err("%s: failed to read pll lock status: %d\n",
-			       __func__, ret);
-			return ret;
-		}
+	ret = regmap_read_poll_timeout(grf, pll->lock_offset, val,
+				       val & BIT(pll->lock_shift), 0, 1000);
+	if (ret)
+		pr_err("%s: timeout waiting for pll to lock\n", __func__);
 
-		if (val & BIT(pll->lock_shift))
-			return 0;
-		delay--;
-	}
-
-	pr_err("%s: timeout waiting for pll to lock\n", __func__);
-	return -ETIMEDOUT;
+	return ret;
 }
 
 /**

From 7f6ffbb885d147557bdca471c37b7b1204005798 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
Date: Wed, 29 Jan 2020 17:38:21 +0100
Subject: [PATCH 003/474] clk: rockchip: convert rk3036 pll type to use
 internal lock status

The rk3036 pll type exposes its lock status in both its pllcon registers
as well as the General Register Files. To remove one dependency convert
it to the "internal" lock status, similar to how rk3399 handles it.

Signed-off-by: Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20200129163821.1547295-3-heiko@sntech.de
---
 drivers/clk/rockchip/clk-pll.c | 26 +++++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/drivers/clk/rockchip/clk-pll.c b/drivers/clk/rockchip/clk-pll.c
index 945f8b2cacc1..4c6c9167ef50 100644
--- a/drivers/clk/rockchip/clk-pll.c
+++ b/drivers/clk/rockchip/clk-pll.c
@@ -12,6 +12,7 @@
 #include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/clk-provider.h>
+#include <linux/iopoll.h>
 #include <linux/regmap.h>
 #include <linux/clk.h>
 #include "clk.h"
@@ -109,12 +110,31 @@ static int rockchip_pll_wait_lock(struct rockchip_clk_pll *pll)
 #define RK3036_PLLCON1_REFDIV_SHIFT		0
 #define RK3036_PLLCON1_POSTDIV2_MASK		0x7
 #define RK3036_PLLCON1_POSTDIV2_SHIFT		6
+#define RK3036_PLLCON1_LOCK_STATUS		BIT(10)
 #define RK3036_PLLCON1_DSMPD_MASK		0x1
 #define RK3036_PLLCON1_DSMPD_SHIFT		12
+#define RK3036_PLLCON1_PWRDOWN			BIT(13)
 #define RK3036_PLLCON2_FRAC_MASK		0xffffff
 #define RK3036_PLLCON2_FRAC_SHIFT		0
 
-#define RK3036_PLLCON1_PWRDOWN			(1 << 13)
+static int rockchip_rk3036_pll_wait_lock(struct rockchip_clk_pll *pll)
+{
+	u32 pllcon;
+	int ret;
+
+	/*
+	 * Lock time typical 250, max 500 input clock cycles @24MHz
+	 * So define a very safe maximum of 1000us, meaning 24000 cycles.
+	 */
+	ret = readl_relaxed_poll_timeout(pll->reg_base + RK3036_PLLCON(1),
+					 pllcon,
+					 pllcon & RK3036_PLLCON1_LOCK_STATUS,
+					 0, 1000);
+	if (ret)
+		pr_err("%s: timeout waiting for pll to lock\n", __func__);
+
+	return ret;
+}
 
 static void rockchip_rk3036_pll_get_params(struct rockchip_clk_pll *pll,
 					struct rockchip_pll_rate_table *rate)
@@ -212,7 +232,7 @@ static int rockchip_rk3036_pll_set_params(struct rockchip_clk_pll *pll,
 	writel_relaxed(pllcon, pll->reg_base + RK3036_PLLCON(2));
 
 	/* wait for the pll to lock */
-	ret = rockchip_pll_wait_lock(pll);
+	ret = rockchip_rk3036_pll_wait_lock(pll);
 	if (ret) {
 		pr_warn("%s: pll update unsuccessful, trying to restore old params\n",
 			__func__);
@@ -251,7 +271,7 @@ static int rockchip_rk3036_pll_enable(struct clk_hw *hw)
 
 	writel(HIWORD_UPDATE(0, RK3036_PLLCON1_PWRDOWN, 0),
 	       pll->reg_base + RK3036_PLLCON(1));
-	rockchip_pll_wait_lock(pll);
+	rockchip_rk3036_pll_wait_lock(pll);
 
 	return 0;
 }

From 1627f683636df70fb25358b0a7b39a24e8fce5bf Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Myl=C3=A8ne=20Josserand?= <mylene.josserand@collabora.com>
Date: Tue, 2 Jun 2020 10:06:43 +0200
Subject: [PATCH 004/474] clk: rockchip: Handle clock tree for rk3288w variant
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The revision rk3288w has a different clock tree about "hclk_vio"
clock, according to the BSP kernel code.

This patch handles this difference by detecting which device-tree
we are using. If it is a "rockchip,rk3288-cru", let's register
the clock tree as it was before. If the device-tree node is
"rockchip,rk3288w-cru", we will apply the difference with this
version of this SoC.

Noticed that this new device-tree compatible must be handled in
bootloader such as u-boot.

Signed-off-by: Mylène Josserand <mylene.josserand@collabora.com>
Link: https://lore.kernel.org/r/20200602080644.11333-2-mylene.josserand@collabora.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 drivers/clk/rockchip/clk-rk3288.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/rockchip/clk-rk3288.c b/drivers/clk/rockchip/clk-rk3288.c
index cc2a177bbdbf..204976e2d0cb 100644
--- a/drivers/clk/rockchip/clk-rk3288.c
+++ b/drivers/clk/rockchip/clk-rk3288.c
@@ -425,8 +425,6 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	COMPOSITE(0, "aclk_vio0", mux_pll_src_cpll_gpll_usb480m_p, CLK_IGNORE_UNUSED,
 			RK3288_CLKSEL_CON(31), 6, 2, MFLAGS, 0, 5, DFLAGS,
 			RK3288_CLKGATE_CON(3), 0, GFLAGS),
-	DIV(0, "hclk_vio", "aclk_vio0", 0,
-			RK3288_CLKSEL_CON(28), 8, 5, DFLAGS),
 	COMPOSITE(0, "aclk_vio1", mux_pll_src_cpll_gpll_usb480m_p, CLK_IGNORE_UNUSED,
 			RK3288_CLKSEL_CON(31), 14, 2, MFLAGS, 8, 5, DFLAGS,
 			RK3288_CLKGATE_CON(3), 2, GFLAGS),
@@ -819,6 +817,16 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	INVERTER(0, "pclk_isp", "pclk_isp_in", RK3288_CLKSEL_CON(29), 3, IFLAGS),
 };
 
+static struct rockchip_clk_branch rk3288w_hclkvio_branch[] __initdata = {
+	DIV(0, "hclk_vio", "aclk_vio1", 0,
+			RK3288_CLKSEL_CON(28), 8, 5, DFLAGS),
+};
+
+static struct rockchip_clk_branch rk3288_hclkvio_branch[] __initdata = {
+	DIV(0, "hclk_vio", "aclk_vio0", 0,
+			RK3288_CLKSEL_CON(28), 8, 5, DFLAGS),
+};
+
 static const char *const rk3288_critical_clocks[] __initconst = {
 	"aclk_cpu",
 	"aclk_peri",
@@ -936,6 +944,14 @@ static void __init rk3288_clk_init(struct device_node *np)
 				   RK3288_GRF_SOC_STATUS1);
 	rockchip_clk_register_branches(ctx, rk3288_clk_branches,
 				  ARRAY_SIZE(rk3288_clk_branches));
+
+	if (of_device_is_compatible(np, "rockchip,rk3288w-cru"))
+		rockchip_clk_register_branches(ctx, rk3288w_hclkvio_branch,
+					       ARRAY_SIZE(rk3288w_hclkvio_branch));
+	else
+		rockchip_clk_register_branches(ctx, rk3288_hclkvio_branch,
+					       ARRAY_SIZE(rk3288_hclkvio_branch));
+
 	rockchip_clk_protect_critical(rk3288_critical_clocks,
 				      ARRAY_SIZE(rk3288_critical_clocks));
 

From 00bd404144241155653bb0d0c15be51e4e6983aa Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Myl=C3=A8ne=20Josserand?= <mylene.josserand@collabora.com>
Date: Tue, 2 Jun 2020 10:06:44 +0200
Subject: [PATCH 005/474] dt-bindings: clocks: add rk3288w variant compatible
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the possible compatible "rockchip,rk3288w-cru" that handles
the difference between the rk3288 and the new revision rk3288w.

This compatible will be added by bootloaders.

Signed-off-by: Mylène Josserand <mylene.josserand@collabora.com>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20200602080644.11333-3-mylene.josserand@collabora.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 .../devicetree/bindings/clock/rockchip,rk3288-cru.txt     | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/clock/rockchip,rk3288-cru.txt b/Documentation/devicetree/bindings/clock/rockchip,rk3288-cru.txt
index 8cb47c39ba53..bf3a9ec19241 100644
--- a/Documentation/devicetree/bindings/clock/rockchip,rk3288-cru.txt
+++ b/Documentation/devicetree/bindings/clock/rockchip,rk3288-cru.txt
@@ -4,9 +4,15 @@ The RK3288 clock controller generates and supplies clock to various
 controllers within the SoC and also implements a reset controller for SoC
 peripherals.
 
+A revision of this SoC is available: rk3288w. The clock tree is a bit
+different so another dt-compatible is available. Noticed that it is only
+setting the difference but there is no automatic revision detection. This
+should be performed by bootloaders.
+
 Required Properties:
 
-- compatible: should be "rockchip,rk3288-cru"
+- compatible: should be "rockchip,rk3288-cru" or "rockchip,rk3288w-cru" in
+  case of this revision of Rockchip rk3288.
 - reg: physical base address of the controller and length of memory mapped
   region.
 - #clock-cells: should be 1.

From 4a95a1b20da31db0c1ca5289a892fef21f691f27 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 11 Jun 2020 11:54:01 +0100
Subject: [PATCH 006/474] KVM: arm64: Enable Address Authentication at EL2 if
 available

While initializing EL2, enable Address Authentication if detected
from EL1. We still use the EL1-provided keys though.

Acked-by: Andrew Scull <ascull@google.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp-init.S | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 6e6ed5581eed..1587d146726a 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -104,6 +104,11 @@ alternative_else_nop_endif
 	 */
 	mov_q	x4, (SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
 CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
+alternative_if ARM64_HAS_ADDRESS_AUTH
+	mov_q	x5, (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \
+		     SCTLR_ELx_ENDA | SCTLR_ELx_ENDB)
+	orr	x4, x4, x5
+alternative_else_nop_endif
 	msr	sctlr_el2, x4
 	isb
 

From dfb0589c8fff9dde809b9013335a6b8019b299b8 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 11 Jun 2020 12:18:58 +0100
Subject: [PATCH 007/474] KVM: arm64: Allow ARM64_PTR_AUTH when ARM64_VHE=n

We currently prevent PtrAuth from even being built if KVM is selected,
but VHE isn't. It is a bit of a pointless restriction, since we also
check this at run time (rejecting the enabling of PtrAuth for the
vcpu if we're not running with VHE).

Just drop this apparently useless restriction.

Acked-by: Andrew Scull <ascull@google.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/Kconfig | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 31380da53689..d719ea9c596d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1516,7 +1516,6 @@ menu "ARMv8.3 architectural features"
 config ARM64_PTR_AUTH
 	bool "Enable support for pointer authentication"
 	default y
-	depends on !KVM || ARM64_VHE
 	depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC
 	# GCC 9.1 and later inserts a .note.gnu.property section note for PAC
 	# which is only understood by binutils starting with version 2.33.1.
@@ -1543,8 +1542,7 @@ config ARM64_PTR_AUTH
 
 	  The feature is detected at runtime. If the feature is not present in
 	  hardware it will not be advertised to userspace/KVM guest nor will it
-	  be enabled. However, KVM guest also require VHE mode and hence
-	  CONFIG_ARM64_VHE=y option to use this feature.
+	  be enabled.
 
 	  If the feature is present on the boot CPU but not on a late CPU, then
 	  the late CPU will be parked. Also, if the boot CPU does not have

From aff7cce0d337f5468470d614ef83a507dcf4c93f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 11 Jun 2020 13:20:28 +0100
Subject: [PATCH 008/474] KVM: arm64: Allow PtrAuth to be enabled from
 userspace on non-VHE systems

Now that the scene is set for enabling PtrAuth on non-VHE, drop
the restrictions preventing userspace from enabling it.

Acked-by: Andrew Scull <ascull@google.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/reset.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index d3b209023727..2a929789fe2e 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -42,6 +42,11 @@ static u32 kvm_ipa_limit;
 #define VCPU_RESET_PSTATE_SVC	(PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
 				 PSR_AA32_I_BIT | PSR_AA32_F_BIT)
 
+static bool system_has_full_ptr_auth(void)
+{
+	return system_supports_address_auth() && system_supports_generic_auth();
+}
+
 /**
  * kvm_arch_vm_ioctl_check_extension
  *
@@ -80,8 +85,7 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_ARM_PTRAUTH_ADDRESS:
 	case KVM_CAP_ARM_PTRAUTH_GENERIC:
-		r = has_vhe() && system_supports_address_auth() &&
-				 system_supports_generic_auth();
+		r = system_has_full_ptr_auth();
 		break;
 	default:
 		r = 0;
@@ -205,19 +209,14 @@ static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
 
 static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
 {
-	/* Support ptrauth only if the system supports these capabilities. */
-	if (!has_vhe())
-		return -EINVAL;
-
-	if (!system_supports_address_auth() ||
-	    !system_supports_generic_auth())
-		return -EINVAL;
 	/*
 	 * For now make sure that both address/generic pointer authentication
-	 * features are requested by the userspace together.
+	 * features are requested by the userspace together and the system
+	 * supports these capabilities.
 	 */
 	if (!test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
-	    !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features))
+	    !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features) ||
+	    !system_has_full_ptr_auth())
 		return -EINVAL;
 
 	vcpu->arch.flags |= KVM_ARM64_GUEST_HAS_PTRAUTH;

From 655169cec7bbf84f59faa9f824edb581eaecf78d Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 11 Jun 2020 11:26:09 +0100
Subject: [PATCH 009/474] KVM: arm64: Check HCR_EL2 instead of shadow copy to
 swap PtrAuth registers

When save/restoring PtrAuth registers between host and guest, it is
pretty useless to fetch the in-memory state, while we have the right
state in the HCR_EL2 system register. Use that instead.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_ptrauth.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_ptrauth.h b/arch/arm64/include/asm/kvm_ptrauth.h
index 6301813dcace..f1830173fa9e 100644
--- a/arch/arm64/include/asm/kvm_ptrauth.h
+++ b/arch/arm64/include/asm/kvm_ptrauth.h
@@ -74,7 +74,7 @@ alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF
 	b	1001f
 alternative_else_nop_endif
 1000:
-	ldr	\reg1, [\g_ctxt, #(VCPU_HCR_EL2 - VCPU_CONTEXT)]
+	mrs	\reg1, hcr_el2
 	and	\reg1, \reg1, #(HCR_API | HCR_APK)
 	cbz	\reg1, 1001f
 	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
@@ -90,7 +90,7 @@ alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF
 	b	2001f
 alternative_else_nop_endif
 2000:
-	ldr	\reg1, [\g_ctxt, #(VCPU_HCR_EL2 - VCPU_CONTEXT)]
+	mrs	\reg1, hcr_el2
 	and	\reg1, \reg1, #(HCR_API | HCR_APK)
 	cbz	\reg1, 2001f
 	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1

From 11ac16a4290b72efa8328cb144b727f3cbbdfa6a Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Mon, 15 Jun 2020 21:03:30 +0100
Subject: [PATCH 010/474] KVM: arm64: Simplify PtrAuth alternative patching

We currently decide to execute the PtrAuth save/restore code based
on a set of branches that evaluate as (ARM64_HAS_ADDRESS_AUTH_ARCH ||
ARM64_HAS_ADDRESS_AUTH_IMP_DEF). This can be easily replaced by
a much simpler test as the ARM64_HAS_ADDRESS_AUTH capability is
exactly this expression.

Suggested-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_ptrauth.h | 30 ++++++++++------------------
 1 file changed, 11 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_ptrauth.h b/arch/arm64/include/asm/kvm_ptrauth.h
index f1830173fa9e..0ddf98c3ba9f 100644
--- a/arch/arm64/include/asm/kvm_ptrauth.h
+++ b/arch/arm64/include/asm/kvm_ptrauth.h
@@ -61,44 +61,36 @@
 
 /*
  * Both ptrauth_switch_to_guest and ptrauth_switch_to_host macros will
- * check for the presence of one of the cpufeature flag
- * ARM64_HAS_ADDRESS_AUTH_ARCH or ARM64_HAS_ADDRESS_AUTH_IMP_DEF and
+ * check for the presence ARM64_HAS_ADDRESS_AUTH, which is defined as
+ * (ARM64_HAS_ADDRESS_AUTH_ARCH || ARM64_HAS_ADDRESS_AUTH_IMP_DEF) and
  * then proceed ahead with the save/restore of Pointer Authentication
- * key registers.
+ * key registers if enabled for the guest.
  */
 .macro ptrauth_switch_to_guest g_ctxt, reg1, reg2, reg3
-alternative_if ARM64_HAS_ADDRESS_AUTH_ARCH
-	b	1000f
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	.L__skip_switch\@
 alternative_else_nop_endif
-alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF
-	b	1001f
-alternative_else_nop_endif
-1000:
 	mrs	\reg1, hcr_el2
 	and	\reg1, \reg1, #(HCR_API | HCR_APK)
-	cbz	\reg1, 1001f
+	cbz	\reg1, .L__skip_switch\@
 	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
 	ptrauth_restore_state	\reg1, \reg2, \reg3
-1001:
+.L__skip_switch\@:
 .endm
 
 .macro ptrauth_switch_to_host g_ctxt, h_ctxt, reg1, reg2, reg3
-alternative_if ARM64_HAS_ADDRESS_AUTH_ARCH
-	b	2000f
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	.L__skip_switch\@
 alternative_else_nop_endif
-alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF
-	b	2001f
-alternative_else_nop_endif
-2000:
 	mrs	\reg1, hcr_el2
 	and	\reg1, \reg1, #(HCR_API | HCR_APK)
-	cbz	\reg1, 2001f
+	cbz	\reg1, .L__skip_switch\@
 	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
 	ptrauth_save_state	\reg1, \reg2, \reg3
 	add	\reg1, \h_ctxt, #CPU_APIAKEYLO_EL1
 	ptrauth_restore_state	\reg1, \reg2, \reg3
 	isb
-2001:
+.L__skip_switch\@:
 .endm
 
 #else /* !CONFIG_ARM64_PTR_AUTH */

From 3180cfabf6fbf982ca6d1a6eb56334647cc1416b Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sebastian.reichel@collabora.com>
Date: Mon, 29 Jun 2020 13:41:23 +0200
Subject: [PATCH 011/474] rtc: cpcap: fix range

Unbreak CPCAP driver, which has one more bit in the day counter
increasing the max. range from 2014 to 2058. The original commit
introducing the range limit was obviously wrong, since the driver
has only been written in 2017 (3 years after 14 bits would have
run out).

Fixes: d2377f8cc5a7 ("rtc: cpcap: set range")
Reported-by: Sicelo A. Mhlongo <absicsz@gmail.com>
Reported-by: Dev Null <devnull@uvos.xyz>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Tested-by: Merlijn Wajer <merlijn@wizzup.org>
Acked-by: Tony Lindgren <tony@atomide.com>
Acked-by: Merlijn Wajer <merlijn@wizzup.org>
Link: https://lore.kernel.org/r/20200629114123.27956-1-sebastian.reichel@collabora.com
---
 drivers/rtc/rtc-cpcap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-cpcap.c b/drivers/rtc/rtc-cpcap.c
index a603f1f21125..800667d73a6f 100644
--- a/drivers/rtc/rtc-cpcap.c
+++ b/drivers/rtc/rtc-cpcap.c
@@ -261,7 +261,7 @@ static int cpcap_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(rtc->rtc_dev);
 
 	rtc->rtc_dev->ops = &cpcap_rtc_ops;
-	rtc->rtc_dev->range_max = (1 << 14) * SECS_PER_DAY - 1;
+	rtc->rtc_dev->range_max = (timeu64_t) (DAY_MASK + 1) * SECS_PER_DAY - 1;
 
 	err = cpcap_get_vendor(dev, rtc->regmap, &rtc->vendor);
 	if (err)

From 05513a706b4f8f978c0ecc97b6d99793fbaaaf17 Mon Sep 17 00:00:00 2001
From: "Tales L. da Aparecida" <tales.aparecida@gmail.com>
Date: Tue, 23 Jun 2020 22:21:19 -0300
Subject: [PATCH 012/474] rtc: imxdi: fix trivial typos

Fix typos 'pionter' -> 'pointer' and 'softwere' -> 'software'

Signed-off-by: Tales L. da Aparecida <tales.aparecida@gmail.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20200624012119.54768-1-tales.aparecida@gmail.com
---
 drivers/rtc/rtc-imxdi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-imxdi.c b/drivers/rtc/rtc-imxdi.c
index f21dc6b16d88..8d141d8a5490 100644
--- a/drivers/rtc/rtc-imxdi.c
+++ b/drivers/rtc/rtc-imxdi.c
@@ -95,7 +95,7 @@
 
 /**
  * struct imxdi_dev - private imxdi rtc data
- * @pdev: pionter to platform dev
+ * @pdev: pointer to platform dev
  * @rtc: pointer to rtc struct
  * @ioaddr: IO registers pointer
  * @clk: input reference clock
@@ -350,7 +350,7 @@ static int di_handle_invalid_and_failure_state(struct imxdi_dev *imxdi, u32 dsr)
 			 * the tamper register is locked. We cannot disable the
 			 * tamper detection. The TDCHL can only be reset by a
 			 * DRYICE POR, but we cannot force a DRYICE POR in
-			 * softwere because we are still in "FAILURE STATE".
+			 * software because we are still in "FAILURE STATE".
 			 * We need a DRYICE POR via battery power cycling....
 			 */
 			/*

From 0a7f99aad259d223ce69c03e792c7e2bfcf8c2c6 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
Date: Fri, 3 Jul 2020 17:49:48 +0200
Subject: [PATCH 013/474] clk: rockchip: use separate compatibles for
 rk3288w-cru

Commit 1627f683636d ("clk: rockchip: Handle clock tree for rk3288w variant")
added the check for rk3288w-specific clock-tree changes but in turn would
require a double-compatible due to re-using the main rockchip,rk3288-cru
compatible as entry point.

The binding change actually describes the compatibles as one or the other
so adapt the code accordingly and add a real second entry-point for the
clock controller.

Signed-off-by: Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
Reviewed-by: Ezequiel Garcia <ezequiel@collabora.com>
Reviewed-by: Jagan Teki <jagan@amarulasolutions.com>
Tested-by: Jagan Teki <jagan@amarulasolutions.com> # rock-pi-n8
Link: https://lore.kernel.org/r/20200703154948.260369-1-heiko@sntech.de
---
 drivers/clk/rockchip/clk-rk3288.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/rockchip/clk-rk3288.c b/drivers/clk/rockchip/clk-rk3288.c
index 204976e2d0cb..93c794695c46 100644
--- a/drivers/clk/rockchip/clk-rk3288.c
+++ b/drivers/clk/rockchip/clk-rk3288.c
@@ -15,6 +15,11 @@
 #define RK3288_GRF_SOC_CON(x)	(0x244 + x * 4)
 #define RK3288_GRF_SOC_STATUS1	0x284
 
+enum rk3288_variant {
+	RK3288_CRU,
+	RK3288W_CRU,
+};
+
 enum rk3288_plls {
 	apll, dpll, cpll, gpll, npll,
 };
@@ -922,7 +927,8 @@ static struct syscore_ops rk3288_clk_syscore_ops = {
 	.resume = rk3288_clk_resume,
 };
 
-static void __init rk3288_clk_init(struct device_node *np)
+static void __init rk3288_common_init(struct device_node *np,
+				      enum rk3288_variant soc)
 {
 	struct rockchip_clk_provider *ctx;
 
@@ -945,7 +951,7 @@ static void __init rk3288_clk_init(struct device_node *np)
 	rockchip_clk_register_branches(ctx, rk3288_clk_branches,
 				  ARRAY_SIZE(rk3288_clk_branches));
 
-	if (of_device_is_compatible(np, "rockchip,rk3288w-cru"))
+	if (soc == RK3288W_CRU)
 		rockchip_clk_register_branches(ctx, rk3288w_hclkvio_branch,
 					       ARRAY_SIZE(rk3288w_hclkvio_branch));
 	else
@@ -970,4 +976,15 @@ static void __init rk3288_clk_init(struct device_node *np)
 
 	rockchip_clk_of_add_provider(np, ctx);
 }
+
+static void __init rk3288_clk_init(struct device_node *np)
+{
+	rk3288_common_init(np, RK3288_CRU);
+}
 CLK_OF_DECLARE(rk3288_cru, "rockchip,rk3288-cru", rk3288_clk_init);
+
+static void __init rk3288w_clk_init(struct device_node *np)
+{
+	rk3288_common_init(np, RK3288W_CRU);
+}
+CLK_OF_DECLARE(rk3288w_cru, "rockchip,rk3288w-cru", rk3288w_clk_init);

From a47dee5513cd7b6d1e20dfecd458363f24a19cdc Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Mon, 25 May 2020 09:45:21 +0100
Subject: [PATCH 014/474] KVM: arm64: Allow in-atomic injection of SPIs

On a system that uses SPIs to implement MSIs (as it would be
the case on a GICv2 system exposing a GICv2m to its guests),
we deny the possibility of injecting SPIs on the in-atomic
fast-path.

This results in a very large amount of context-switches
(roughly equivalent to twice the interrupt rate) on the host,
and suboptimal performance for the guest (as measured with
a test workload involving a virtio interface backed by vhost-net).
Given that GICv2 systems are usually on the low-end of the spectrum
performance wise, they could do without the aggravation.

We solved this for GICv3+ITS by having a translation cache. But
SPIs do not need any extra infrastructure, and can be immediately
injected in the virtual distributor as the locking is already
heavy enough that we don't need to worry about anything.

This halves the number of context switches for the same workload.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/vgic/vgic-irqfd.c | 24 +++++++++++++++++++-----
 arch/arm64/kvm/vgic/vgic-its.c   |  3 +--
 2 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-irqfd.c b/arch/arm64/kvm/vgic/vgic-irqfd.c
index d8cdfea5cc96..79f8899b234c 100644
--- a/arch/arm64/kvm/vgic/vgic-irqfd.c
+++ b/arch/arm64/kvm/vgic/vgic-irqfd.c
@@ -100,19 +100,33 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 
 /**
  * kvm_arch_set_irq_inatomic: fast-path for irqfd injection
- *
- * Currently only direct MSI injection is supported.
  */
 int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 			      struct kvm *kvm, int irq_source_id, int level,
 			      bool line_status)
 {
-	if (e->type == KVM_IRQ_ROUTING_MSI && vgic_has_its(kvm) && level) {
+	if (!level)
+		return -EWOULDBLOCK;
+
+	switch (e->type) {
+	case KVM_IRQ_ROUTING_MSI: {
 		struct kvm_msi msi;
 
+		if (!vgic_has_its(kvm))
+			break;
+
 		kvm_populate_msi(e, &msi);
-		if (!vgic_its_inject_cached_translation(kvm, &msi))
-			return 0;
+		return vgic_its_inject_cached_translation(kvm, &msi);
+	}
+
+	case KVM_IRQ_ROUTING_IRQCHIP:
+		/*
+		 * Injecting SPIs is always possible in atomic context
+		 * as long as the damn vgic is initialized.
+		 */
+		if (unlikely(!vgic_initialized(kvm)))
+			break;
+		return vgic_irqfd_set_irq(e, kvm, irq_source_id, 1, line_status);
 	}
 
 	return -EWOULDBLOCK;
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index c012a52b19f5..40cbaca81333 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -757,9 +757,8 @@ int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi)
 
 	db = (u64)msi->address_hi << 32 | msi->address_lo;
 	irq = vgic_its_check_cache(kvm, db, msi->devid, msi->data);
-
 	if (!irq)
-		return -1;
+		return -EWOULDBLOCK;
 
 	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 	irq->pending_latch = true;

From 2da3ffa6e840b9f8fc65a71326c43b716992861d Mon Sep 17 00:00:00 2001
From: Andrew Scull <ascull@google.com>
Date: Thu, 18 Jun 2020 10:36:16 +0100
Subject: [PATCH 015/474] arm64: kvm: Remove kern_hyp_va from get_vcpu_ptr

get_vcpu_ptr is an assembly accessor for the percpu value
kvm_host_data->host_ctxt.__hyp_running_vcpu. kern_hyp_va only applies to
nVHE however __hyp_running_vcpu is always assigned a pointer that has
already had kern_hyp_va applied in __kvm_vcpu_run_nvhe.

kern_hyp_va is currently idempotent as it just masks and inserts the
tag, but this could change in future and the second application is
unnecessary.

Signed-off-by: Andrew Scull <ascull@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: James Morse <james.morse@arm.com>
Link: https://lore.kernel.org/r/20200618093616.164413-1-ascull@google.com
---
 arch/arm64/include/asm/kvm_asm.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 352aaebf4198..ac71d0939f2e 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -143,7 +143,6 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
 .macro get_vcpu_ptr vcpu, ctxt
 	get_host_ctxt \ctxt, \vcpu
 	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
-	kern_hyp_va	\vcpu
 .endm
 
 #endif

From 6b33e0d64f8501b51d32069e08d3ed68c58c25b4 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Mon, 22 Jun 2020 11:33:13 +0000
Subject: [PATCH 016/474] KVM: arm64: Drop the target_table[] indirection

KVM for 32bit arm had a get/set target mechanism to allow for
micro-architecture differences that are visible in system registers
to be described.

KVM's user-space can query the supported targets for a CPU, and
create vCPUs for that target. The target can override the handling
of system registers to provide different reset or RES0 behaviour.
On 32bit arm this was used to provide different ACTLR reset values
for A7 and A15.

On 64bit arm, the first few CPUs out of the gate used this mechanism,
before it was deemed redundant in commit bca556ac468a ("arm64/kvm:
Add generic v8 KVM target"). All future CPUs use the
KVM_ARM_TARGET_GENERIC_V8 target.

The 64bit target_table[] stuff exists to preserve the ABI to
user-space. As all targets registers genericv8_target_table, there
is no reason to look the target up.

Until we can merge genericv8_target_table with the main sys_regs
array, kvm_register_target_sys_reg_table() becomes
kvm_check_target_sys_reg_table(), which uses BUG_ON() in keeping
with the other callers in this file.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200622113317.20477-2-james.morse@arm.com
---
 arch/arm64/include/asm/kvm_coproc.h  |  3 +--
 arch/arm64/kvm/sys_regs.c            | 16 ++++------------
 arch/arm64/kvm/sys_regs.h            |  2 ++
 arch/arm64/kvm/sys_regs_generic_v8.c | 15 ++-------------
 4 files changed, 9 insertions(+), 27 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_coproc.h b/arch/arm64/include/asm/kvm_coproc.h
index 0185ee8b8b5e..4bf0d6d05e0f 100644
--- a/arch/arm64/include/asm/kvm_coproc.h
+++ b/arch/arm64/include/asm/kvm_coproc.h
@@ -24,8 +24,7 @@ struct kvm_sys_reg_target_table {
 	struct kvm_sys_reg_table table32;
 };
 
-void kvm_register_target_sys_reg_table(unsigned int target,
-				       struct kvm_sys_reg_target_table *table);
+void kvm_check_target_sys_reg_table(struct kvm_sys_reg_target_table *table);
 
 int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index baf5ce9225ce..6333a7cd92d3 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2109,17 +2109,10 @@ static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n,
 	return 0;
 }
 
-/* Target specific emulation tables */
-static struct kvm_sys_reg_target_table *target_tables[KVM_ARM_NUM_TARGETS];
-
-void kvm_register_target_sys_reg_table(unsigned int target,
-				       struct kvm_sys_reg_target_table *table)
+void kvm_check_target_sys_reg_table(struct kvm_sys_reg_target_table *table)
 {
-	if (check_sysreg_table(table->table64.table, table->table64.num, false) ||
-	    check_sysreg_table(table->table32.table, table->table32.num, true))
-		return;
-
-	target_tables[target] = table;
+	BUG_ON(check_sysreg_table(table->table64.table, table->table64.num, false));
+	BUG_ON(check_sysreg_table(table->table32.table, table->table32.num, true));
 }
 
 /* Get specific register table for this target. */
@@ -2127,9 +2120,8 @@ static const struct sys_reg_desc *get_target_table(unsigned target,
 						   bool mode_is_64,
 						   size_t *num)
 {
-	struct kvm_sys_reg_target_table *table;
+	struct kvm_sys_reg_target_table *table = &genericv8_target_table;
 
-	table = target_tables[target];
 	if (mode_is_64) {
 		*num = table->table64.num;
 		return table->table64.table;
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index 5a6fc30f5989..933609e883bf 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -165,4 +165,6 @@ const struct sys_reg_desc *find_reg_by_id(u64 id,
 	CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)),	\
 	Op2(sys_reg_Op2(reg))
 
+extern struct kvm_sys_reg_target_table genericv8_target_table;
+
 #endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index aa9d356451eb..a82cc2ccfd44 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -59,7 +59,7 @@ static const struct sys_reg_desc genericv8_cp15_regs[] = {
 	  access_actlr },
 };
 
-static struct kvm_sys_reg_target_table genericv8_target_table = {
+struct kvm_sys_reg_target_table genericv8_target_table = {
 	.table64 = {
 		.table = genericv8_sys_regs,
 		.num = ARRAY_SIZE(genericv8_sys_regs),
@@ -78,18 +78,7 @@ static int __init sys_reg_genericv8_init(void)
 		BUG_ON(cmp_sys_reg(&genericv8_sys_regs[i-1],
 			       &genericv8_sys_regs[i]) >= 0);
 
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_AEM_V8,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_FOUNDATION_V8,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A53,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A57,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_XGENE_POTENZA,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_GENERIC_V8,
-					  &genericv8_target_table);
+	kvm_check_target_sys_reg_table(&genericv8_target_table);
 
 	return 0;
 }

From 04343ae312ef0d80d601ea1b784b6b039ae9c82a Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Mon, 22 Jun 2020 11:33:14 +0000
Subject: [PATCH 017/474] KVM: arm64: Tolerate an empty target_table list

Before emptying the target_table lists, and then removing their
infrastructure, add some tolerance to an empty list.

Instead of bugging-out on an empty list, pretend we already
reached the end in the two-list-walk.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200622113317.20477-3-james.morse@arm.com
---
 arch/arm64/kvm/sys_regs.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 6333a7cd92d3..fb448bfc83ec 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2809,7 +2809,10 @@ static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind)
 	i2 = sys_reg_descs;
 	end2 = sys_reg_descs + ARRAY_SIZE(sys_reg_descs);
 
-	BUG_ON(i1 == end1 || i2 == end2);
+	if (i1 == end1)
+		i1 = NULL;
+
+	BUG_ON(i2 == end2);
 
 	/* Walk carefully, as both tables may refer to the same register. */
 	while (i1 || i2) {

From af4738290d9dfe3787f60e40f709a4f78a115943 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Mon, 22 Jun 2020 11:33:15 +0000
Subject: [PATCH 018/474] KVM: arm64: Move ACTLR_EL1 emulation to the
 sys_reg_descs array

The only entry in the genericv8_sys_regs arrays is for emulation of
ACTLR_EL1. As all targets emulate this in the same way, move it to
sys_reg_descs[].

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200622113317.20477-4-james.morse@arm.com
---
 arch/arm64/kvm/sys_regs.c            | 28 ++++++++++++++++++++++++++
 arch/arm64/kvm/sys_regs_generic_v8.c | 30 ----------------------------
 2 files changed, 28 insertions(+), 30 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index fb448bfc83ec..f8407cfa9032 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -242,6 +242,25 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_actlr(struct kvm_vcpu *vcpu,
+			 struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	p->regval = vcpu_read_sys_reg(vcpu, ACTLR_EL1);
+
+	if (p->is_aarch32) {
+		if (r->Op2 & 2)
+			p->regval = upper_32_bits(p->regval);
+		else
+			p->regval = lower_32_bits(p->regval);
+	}
+
+	return true;
+}
+
 /*
  * Trap handler for the GICv3 SGI generation system register.
  * Forward the request to the VGIC emulation.
@@ -615,6 +634,12 @@ static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	vcpu_write_sys_reg(vcpu, amair, AMAIR_EL1);
 }
 
+static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+	u64 actlr = read_sysreg(actlr_el1);
+	vcpu_write_sys_reg(vcpu, actlr, ACTLR_EL1);
+}
+
 static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	u64 mpidr;
@@ -1518,6 +1543,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_UNALLOCATED(7,7),
 
 	{ SYS_DESC(SYS_SCTLR_EL1), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
+	{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
 	{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
 	{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
 	{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
@@ -1957,6 +1983,8 @@ static const struct sys_reg_desc cp14_64_regs[] = {
 static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn( 0), CRm( 0), Op2( 1), access_ctr },
 	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR },
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 1), access_actlr },
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 3), access_actlr },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR },
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index a82cc2ccfd44..a7e21e61beea 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -19,44 +19,14 @@
 
 #include "sys_regs.h"
 
-static bool access_actlr(struct kvm_vcpu *vcpu,
-			 struct sys_reg_params *p,
-			 const struct sys_reg_desc *r)
-{
-	if (p->is_write)
-		return ignore_write(vcpu, p);
-
-	p->regval = vcpu_read_sys_reg(vcpu, ACTLR_EL1);
-
-	if (p->is_aarch32) {
-		if (r->Op2 & 2)
-			p->regval = upper_32_bits(p->regval);
-		else
-			p->regval = lower_32_bits(p->regval);
-	}
-
-	return true;
-}
-
-static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
-{
-	__vcpu_sys_reg(vcpu, ACTLR_EL1) = read_sysreg(actlr_el1);
-}
-
 /*
  * Implementation specific sys-reg registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
  */
 static const struct sys_reg_desc genericv8_sys_regs[] = {
-	{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
 };
 
 static const struct sys_reg_desc genericv8_cp15_regs[] = {
-	/* ACTLR */
-	{ Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b001),
-	  access_actlr },
-	{ Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b011),
-	  access_actlr },
 };
 
 struct kvm_sys_reg_target_table genericv8_target_table = {

From dcaffa7bf911578a6d69165d712501996c587fbe Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Mon, 22 Jun 2020 11:33:16 +0000
Subject: [PATCH 019/474] KVM: arm64: Remove target_table from exit handlers

Whenever KVM searches for a register (e.g. due to a guest exit), it
works with two tables, as the target table overrides the sys_regs array.

Now that everything is in the sys_regs array, and the target table is
empty, stop doing that.

Remove the second table and its size from all the functions that take
it.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200622113317.20477-5-james.morse@arm.com
---
 arch/arm64/kvm/sys_regs.c | 87 +++++++--------------------------------
 1 file changed, 16 insertions(+), 71 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index f8407cfa9032..14333005b476 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2269,9 +2269,7 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
  */
 static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 			    const struct sys_reg_desc *global,
-			    size_t nr_global,
-			    const struct sys_reg_desc *target_specific,
-			    size_t nr_specific)
+			    size_t nr_global)
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
@@ -2298,14 +2296,11 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 	}
 
 	/*
-	 * Try to emulate the coprocessor access using the target
-	 * specific table first, and using the global table afterwards.
-	 * If either of the tables contains a handler, handle the
+	 * If the table contains a handler, handle the
 	 * potential register operation in the case of a read and return
 	 * with success.
 	 */
-	if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
-	    !emulate_cp(vcpu, &params, global, nr_global)) {
+	if (!emulate_cp(vcpu, &params, global, nr_global)) {
 		/* Split up the value between registers for the read side */
 		if (!params.is_write) {
 			vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval));
@@ -2326,9 +2321,7 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
  */
 static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 			    const struct sys_reg_desc *global,
-			    size_t nr_global,
-			    const struct sys_reg_desc *target_specific,
-			    size_t nr_specific)
+			    size_t nr_global)
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
@@ -2344,8 +2337,7 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 	params.Op1 = (hsr >> 14) & 0x7;
 	params.Op2 = (hsr >> 17) & 0x7;
 
-	if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
-	    !emulate_cp(vcpu, &params, global, nr_global)) {
+	if (!emulate_cp(vcpu, &params, global, nr_global)) {
 		if (!params.is_write)
 			vcpu_set_reg(vcpu, Rt, params.regval);
 		return 1;
@@ -2357,38 +2349,22 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 
 int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	const struct sys_reg_desc *target_specific;
-	size_t num;
-
-	target_specific = get_target_table(vcpu->arch.target, false, &num);
-	return kvm_handle_cp_64(vcpu,
-				cp15_64_regs, ARRAY_SIZE(cp15_64_regs),
-				target_specific, num);
+	return kvm_handle_cp_64(vcpu, cp15_64_regs, ARRAY_SIZE(cp15_64_regs));
 }
 
 int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	const struct sys_reg_desc *target_specific;
-	size_t num;
-
-	target_specific = get_target_table(vcpu->arch.target, false, &num);
-	return kvm_handle_cp_32(vcpu,
-				cp15_regs, ARRAY_SIZE(cp15_regs),
-				target_specific, num);
+	return kvm_handle_cp_32(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs));
 }
 
 int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	return kvm_handle_cp_64(vcpu,
-				cp14_64_regs, ARRAY_SIZE(cp14_64_regs),
-				NULL, 0);
+	return kvm_handle_cp_64(vcpu, cp14_64_regs, ARRAY_SIZE(cp14_64_regs));
 }
 
 int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	return kvm_handle_cp_32(vcpu,
-				cp14_regs, ARRAY_SIZE(cp14_regs),
-				NULL, 0);
+	return kvm_handle_cp_32(vcpu, cp14_regs, ARRAY_SIZE(cp14_regs));
 }
 
 static bool is_imp_def_sys_reg(struct sys_reg_params *params)
@@ -2400,15 +2376,9 @@ static bool is_imp_def_sys_reg(struct sys_reg_params *params)
 static int emulate_sys_reg(struct kvm_vcpu *vcpu,
 			   struct sys_reg_params *params)
 {
-	size_t num;
-	const struct sys_reg_desc *table, *r;
+	const struct sys_reg_desc *r;
 
-	table = get_target_table(vcpu->arch.target, true, &num);
-
-	/* Search target-specific then generic table. */
-	r = find_reg(params, table, num);
-	if (!r)
-		r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
+	r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
 
 	if (likely(r)) {
 		perform_access(vcpu, params, r);
@@ -2512,8 +2482,7 @@ const struct sys_reg_desc *find_reg_by_id(u64 id,
 static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
 						    u64 id)
 {
-	size_t num;
-	const struct sys_reg_desc *table, *r;
+	const struct sys_reg_desc *r;
 	struct sys_reg_params params;
 
 	/* We only do sys_reg for now. */
@@ -2523,10 +2492,7 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
 	if (!index_to_params(id, &params))
 		return NULL;
 
-	table = get_target_table(vcpu->arch.target, true, &num);
-	r = find_reg(&params, table, num);
-	if (!r)
-		r = find_reg(&params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
+	r = find_reg(&params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
 
 	/* Not saved in the sys_reg array and not otherwise accessible? */
 	if (r && !(r->reg || r->get_user))
@@ -2826,38 +2792,17 @@ static int walk_one_sys_reg(const struct kvm_vcpu *vcpu,
 /* Assumed ordered tables, see kvm_sys_reg_table_init. */
 static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind)
 {
-	const struct sys_reg_desc *i1, *i2, *end1, *end2;
+	const struct sys_reg_desc *i2, *end2;
 	unsigned int total = 0;
-	size_t num;
 	int err;
 
-	/* We check for duplicates here, to allow arch-specific overrides. */
-	i1 = get_target_table(vcpu->arch.target, true, &num);
-	end1 = i1 + num;
 	i2 = sys_reg_descs;
 	end2 = sys_reg_descs + ARRAY_SIZE(sys_reg_descs);
 
-	if (i1 == end1)
-		i1 = NULL;
-
-	BUG_ON(i2 == end2);
-
-	/* Walk carefully, as both tables may refer to the same register. */
-	while (i1 || i2) {
-		int cmp = cmp_sys_reg(i1, i2);
-		/* target-specific overrides generic entry. */
-		if (cmp <= 0)
-			err = walk_one_sys_reg(vcpu, i1, &uind, &total);
-		else
-			err = walk_one_sys_reg(vcpu, i2, &uind, &total);
-
+	while (i2 != end2) {
+		err = walk_one_sys_reg(vcpu, i2++, &uind, &total);
 		if (err)
 			return err;
-
-		if (cmp <= 0 && ++i1 == end1)
-			i1 = NULL;
-		if (cmp >= 0 && ++i2 == end2)
-			i2 = NULL;
 	}
 	return total;
 }

From 750ed56693803e992ed09ac9c46e07226dd4d350 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Mon, 22 Jun 2020 11:33:17 +0000
Subject: [PATCH 020/474] KVM: arm64: Remove the target table

Finally, remove the target table. Merge the code that checks the
tables into kvm_reset_sys_regs() as there is now only one table.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200622113317.20477-6-james.morse@arm.com
---
 arch/arm64/include/asm/kvm_coproc.h  |  7 ----
 arch/arm64/kvm/Makefile              |  2 +-
 arch/arm64/kvm/sys_regs.c            | 57 ++++++----------------------
 arch/arm64/kvm/sys_regs.h            |  2 -
 arch/arm64/kvm/sys_regs_generic_v8.c | 55 ---------------------------
 5 files changed, 12 insertions(+), 111 deletions(-)
 delete mode 100644 arch/arm64/kvm/sys_regs_generic_v8.c

diff --git a/arch/arm64/include/asm/kvm_coproc.h b/arch/arm64/include/asm/kvm_coproc.h
index 4bf0d6d05e0f..147f3a77e6a5 100644
--- a/arch/arm64/include/asm/kvm_coproc.h
+++ b/arch/arm64/include/asm/kvm_coproc.h
@@ -19,13 +19,6 @@ struct kvm_sys_reg_table {
 	size_t num;
 };
 
-struct kvm_sys_reg_target_table {
-	struct kvm_sys_reg_table table64;
-	struct kvm_sys_reg_table table32;
-};
-
-void kvm_check_target_sys_reg_table(struct kvm_sys_reg_target_table *table);
-
 int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 8d3d9513cbfe..48cda50aa225 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -14,7 +14,7 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 $(KVM)/vfio.o $(KVM)/irqchip.o \
 	 arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \
 	 inject_fault.o regmap.o va_layout.o hyp.o hyp-init.o handle_exit.o \
-	 guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o \
+	 guest.o debug.o reset.o sys_regs.o \
 	 vgic-sys-reg-v3.o fpsimd.o pmu.o \
 	 aarch32.o arch_timer.o \
 	 vgic/vgic.o vgic/vgic-init.o \
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 14333005b476..41a4d3d2a312 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2137,28 +2137,6 @@ static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n,
 	return 0;
 }
 
-void kvm_check_target_sys_reg_table(struct kvm_sys_reg_target_table *table)
-{
-	BUG_ON(check_sysreg_table(table->table64.table, table->table64.num, false));
-	BUG_ON(check_sysreg_table(table->table32.table, table->table32.num, true));
-}
-
-/* Get specific register table for this target. */
-static const struct sys_reg_desc *get_target_table(unsigned target,
-						   bool mode_is_64,
-						   size_t *num)
-{
-	struct kvm_sys_reg_target_table *table = &genericv8_target_table;
-
-	if (mode_is_64) {
-		*num = table->table64.num;
-		return table->table64.table;
-	} else {
-		*num = table->table32.num;
-		return table->table32.table;
-	}
-}
-
 static int match_sys_reg(const void *key, const void *elt)
 {
 	const unsigned long pval = (unsigned long)key;
@@ -2393,14 +2371,20 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
-static void reset_sys_reg_descs(struct kvm_vcpu *vcpu,
-				const struct sys_reg_desc *table, size_t num)
+/**
+ * kvm_reset_sys_regs - sets system registers to reset value
+ * @vcpu: The VCPU pointer
+ *
+ * This function finds the right table above and sets the registers on the
+ * virtual CPU struct to their architecturally defined reset values.
+ */
+void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
 {
 	unsigned long i;
 
-	for (i = 0; i < num; i++)
-		if (table[i].reset)
-			table[i].reset(vcpu, &table[i]);
+	for (i = 0; i < ARRAY_SIZE(sys_reg_descs); i++)
+		if (sys_reg_descs[i].reset)
+			sys_reg_descs[i].reset(vcpu, &sys_reg_descs[i]);
 }
 
 /**
@@ -2869,22 +2853,3 @@ void kvm_sys_reg_table_init(void)
 	/* Clear all higher bits. */
 	cache_levels &= (1 << (i*3))-1;
 }
-
-/**
- * kvm_reset_sys_regs - sets system registers to reset value
- * @vcpu: The VCPU pointer
- *
- * This function finds the right table above and sets the registers on the
- * virtual CPU struct to their architecturally defined reset values.
- */
-void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
-{
-	size_t num;
-	const struct sys_reg_desc *table;
-
-	/* Generic chip reset first (so target could override). */
-	reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
-
-	table = get_target_table(vcpu->arch.target, true, &num);
-	reset_sys_reg_descs(vcpu, table, num);
-}
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index 933609e883bf..5a6fc30f5989 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -165,6 +165,4 @@ const struct sys_reg_desc *find_reg_by_id(u64 id,
 	CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)),	\
 	Op2(sys_reg_Op2(reg))
 
-extern struct kvm_sys_reg_target_table genericv8_target_table;
-
 #endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
deleted file mode 100644
index a7e21e61beea..000000000000
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ /dev/null
@@ -1,55 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2012,2013 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * Based on arch/arm/kvm/coproc_a15.c:
- * Copyright (C) 2012 - Virtual Open Systems and Columbia University
- * Authors: Rusty Russell <rusty@rustcorp.au>
- *          Christoffer Dall <c.dall@virtualopensystems.com>
- */
-#include <linux/kvm_host.h>
-#include <asm/cputype.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_coproc.h>
-#include <asm/sysreg.h>
-#include <linux/init.h>
-
-#include "sys_regs.h"
-
-/*
- * Implementation specific sys-reg registers.
- * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
- */
-static const struct sys_reg_desc genericv8_sys_regs[] = {
-};
-
-static const struct sys_reg_desc genericv8_cp15_regs[] = {
-};
-
-struct kvm_sys_reg_target_table genericv8_target_table = {
-	.table64 = {
-		.table = genericv8_sys_regs,
-		.num = ARRAY_SIZE(genericv8_sys_regs),
-	},
-	.table32 = {
-		.table = genericv8_cp15_regs,
-		.num = ARRAY_SIZE(genericv8_cp15_regs),
-	},
-};
-
-static int __init sys_reg_genericv8_init(void)
-{
-	unsigned int i;
-
-	for (i = 1; i < ARRAY_SIZE(genericv8_sys_regs); i++)
-		BUG_ON(cmp_sys_reg(&genericv8_sys_regs[i-1],
-			       &genericv8_sys_regs[i]) >= 0);
-
-	kvm_check_target_sys_reg_table(&genericv8_target_table);
-
-	return 0;
-}
-late_initcall(sys_reg_genericv8_init);

From b38b298aa4397e2dc74a89b4dd3eac9e59b64c96 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:06 +0100
Subject: [PATCH 021/474] KVM: arm64: Fix symbol dependency in
 __hyp_call_panic_nvhe

__hyp_call_panic_nvhe contains inline assembly which did not declare
its dependency on the __hyp_panic_string symbol.

The static-declared string has previously been kept alive because of a use in
__hyp_call_panic_vhe. Fix this in preparation for separating the source files
between VHE and nVHE when the two users land in two different compilation
units. The static variable otherwise gets dropped when compiling the nVHE
source file, causing an undefined symbol linker error later.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-2-dbrazdil@google.com
---
 arch/arm64/kvm/hyp/switch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index db1c4487d95d..9270b14157b5 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -897,7 +897,7 @@ static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
 	 * making sure it is a kernel address and not a PC-relative
 	 * reference.
 	 */
-	asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va));
+	asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string));
 
 	__hyp_do_panic(str_va,
 		       spsr, elr,

From 7b2399ea5640b2e5f576af08b91091a26f240ea4 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:07 +0100
Subject: [PATCH 022/474] KVM: arm64: Move __smccc_workaround_1_smc to .rodata

This snippet of assembly is used by cpu_errata.c to overwrite parts of KVM hyp
vector. Move it to its own source file and change its ELF section to .rodata.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-3-dbrazdil@google.com
---
 arch/arm64/kvm/hyp/Makefile    |  1 +
 arch/arm64/kvm/hyp/hyp-entry.S | 16 ----------------
 arch/arm64/kvm/hyp/smccc_wa.S  | 32 ++++++++++++++++++++++++++++++++
 3 files changed, 33 insertions(+), 16 deletions(-)
 create mode 100644 arch/arm64/kvm/hyp/smccc_wa.S

diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 8c9880783839..5d8357ddc234 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -7,6 +7,7 @@ ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \
 		$(DISABLE_STACKLEAK_PLUGIN)
 
 obj-$(CONFIG_KVM) += hyp.o
+obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
 hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
 	 debug-sr.o entry.o switch.o fpsimd.o tlb.o hyp-entry.o
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 9c5cfb04170e..d362fad97cc8 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -318,20 +318,4 @@ SYM_CODE_START(__bp_harden_hyp_vecs)
 1:	.org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ
 	.org 1b
 SYM_CODE_END(__bp_harden_hyp_vecs)
-
-	.popsection
-
-SYM_CODE_START(__smccc_workaround_1_smc)
-	esb
-	sub	sp, sp, #(8 * 4)
-	stp	x2, x3, [sp, #(8 * 0)]
-	stp	x0, x1, [sp, #(8 * 2)]
-	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_1
-	smc	#0
-	ldp	x2, x3, [sp, #(8 * 0)]
-	ldp	x0, x1, [sp, #(8 * 2)]
-	add	sp, sp, #(8 * 4)
-1:	.org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
-	.org 1b
-SYM_CODE_END(__smccc_workaround_1_smc)
 #endif
diff --git a/arch/arm64/kvm/hyp/smccc_wa.S b/arch/arm64/kvm/hyp/smccc_wa.S
new file mode 100644
index 000000000000..b0441dbdf68b
--- /dev/null
+++ b/arch/arm64/kvm/hyp/smccc_wa.S
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015-2018 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <linux/arm-smccc.h>
+#include <linux/linkage.h>
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+
+	/*
+	 * This is not executed directly and is instead copied into the vectors
+	 * by install_bp_hardening_cb().
+	 */
+	.data
+	.pushsection	.rodata
+	.global		__smccc_workaround_1_smc
+SYM_DATA_START(__smccc_workaround_1_smc)
+	esb
+	sub	sp, sp, #(8 * 4)
+	stp	x2, x3, [sp, #(8 * 0)]
+	stp	x0, x1, [sp, #(8 * 2)]
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_1
+	smc	#0
+	ldp	x2, x3, [sp, #(8 * 0)]
+	ldp	x0, x1, [sp, #(8 * 2)]
+	add	sp, sp, #(8 * 4)
+1:	.org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
+	.org 1b
+SYM_DATA_END(__smccc_workaround_1_smc)

From 7621712918ad4f5e6356193d9058debf657a6254 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:08 +0100
Subject: [PATCH 023/474] KVM: arm64: Add build rules for separate VHE/nVHE
 object files

Add new folders arch/arm64/kvm/hyp/{vhe,nvhe} and Makefiles for building code
that runs in EL2 under VHE/nVHE KVM, repsectivelly. Add an include folder for
hyp-specific header files which will include code common to VHE/nVHE.

Build nVHE code with -D__KVM_NVHE_HYPERVISOR__, VHE code with
-D__KVM_VHE_HYPERVISOR__.

Under nVHE compile each source file into a `.hyp.tmp.o` object first, then
prefix all its symbols with "__kvm_nvhe_" using `objcopy` and produce
a `.hyp.o`. Suffixes were chosen so that it would be possible for VHE and nVHE
to share some source files, but compiled with different CFLAGS.

The nVHE ELF symbol prefix is added to kallsyms.c as ignored. EL2-only symbols
will never appear in EL1 stack traces.

Due to symbol prefixing, add a section in image-vars.h for aliases of symbols
that are defined in nVHE EL2 and accessed by kernel in EL1 or vice versa.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-4-dbrazdil@google.com
---
 arch/arm64/kernel/image-vars.h   | 14 +++++++++++++
 arch/arm64/kvm/hyp/Makefile      | 10 +++++++---
 arch/arm64/kvm/hyp/nvhe/Makefile | 34 ++++++++++++++++++++++++++++++++
 arch/arm64/kvm/hyp/vhe/Makefile  | 17 ++++++++++++++++
 scripts/kallsyms.c               |  1 +
 5 files changed, 73 insertions(+), 3 deletions(-)
 create mode 100644 arch/arm64/kvm/hyp/nvhe/Makefile
 create mode 100644 arch/arm64/kvm/hyp/vhe/Makefile

diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index be0a63ffed23..3dc27da47712 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -51,4 +51,18 @@ __efistub__ctype		= _ctype;
 
 #endif
 
+#ifdef CONFIG_KVM
+
+/*
+ * KVM nVHE code has its own symbol namespace prefixed with __kvm_nvhe_, to
+ * separate it from the kernel proper. The following symbols are legally
+ * accessed by it, therefore provide aliases to make them linkable.
+ * Do not include symbols which may not be safely accessed under hypervisor
+ * memory mappings.
+ */
+
+#define KVM_NVHE_ALIAS(sym) __kvm_nvhe_##sym = sym;
+
+#endif /* CONFIG_KVM */
+
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 5d8357ddc234..9c5dfe6ff80b 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -3,10 +3,14 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \
-		$(DISABLE_STACKLEAK_PLUGIN)
+incdir := $(srctree)/$(src)/include
+subdir-asflags-y := -I$(incdir)
+subdir-ccflags-y := -I$(incdir)				\
+		    -fno-stack-protector		\
+		    -DDISABLE_BRANCH_PROFILING		\
+		    $(DISABLE_STACKLEAK_PLUGIN)
 
-obj-$(CONFIG_KVM) += hyp.o
+obj-$(CONFIG_KVM) += hyp.o nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
 hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
new file mode 100644
index 000000000000..955f4188e00f
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Kernel-based Virtual Machine module, HYP/nVHE part
+#
+
+asflags-y := -D__KVM_NVHE_HYPERVISOR__
+ccflags-y := -D__KVM_NVHE_HYPERVISOR__
+
+obj-y :=
+
+obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
+extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
+
+$(obj)/%.hyp.tmp.o: $(src)/%.c FORCE
+	$(call if_changed_rule,cc_o_c)
+$(obj)/%.hyp.tmp.o: $(src)/%.S FORCE
+	$(call if_changed_rule,as_o_S)
+$(obj)/%.hyp.o: $(obj)/%.hyp.tmp.o FORCE
+	$(call if_changed,hypcopy)
+
+quiet_cmd_hypcopy = HYPCOPY $@
+      cmd_hypcopy = $(OBJCOPY) --prefix-symbols=__kvm_nvhe_ $< $@
+
+# KVM nVHE code is run at a different exception code with a different map, so
+# compiler instrumentation that inserts callbacks or checks into the code may
+# cause crashes. Just disable it.
+GCOV_PROFILE	:= n
+KASAN_SANITIZE	:= n
+UBSAN_SANITIZE	:= n
+KCOV_INSTRUMENT	:= n
+
+# Skip objtool checking for this directory because nVHE code is compiled with
+# non-standard build rules.
+OBJECT_FILES_NON_STANDARD := y
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
new file mode 100644
index 000000000000..e04375546081
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Kernel-based Virtual Machine module, HYP/nVHE part
+#
+
+asflags-y := -D__KVM_VHE_HYPERVISOR__
+ccflags-y := -D__KVM_VHE_HYPERVISOR__
+
+obj-y :=
+
+# KVM code is run at a different exception code with a different map, so
+# compiler instrumentation that inserts callbacks or checks into the code may
+# cause crashes. Just disable it.
+GCOV_PROFILE	:= n
+KASAN_SANITIZE	:= n
+UBSAN_SANITIZE	:= n
+KCOV_INSTRUMENT	:= n
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 6dc3078649fa..0096cd965332 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -109,6 +109,7 @@ static bool is_ignored_symbol(const char *name, char type)
 		".LASANPC",		/* s390 kasan local symbols */
 		"__crc_",		/* modversions */
 		"__efistub_",		/* arm64 EFI stub namespace */
+		"__kvm_nvhe_",		/* arm64 non-VHE KVM namespace */
 		NULL
 	};
 

From 53b671128bd7f9ea41ae1a06106d88eb4cf66623 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:09 +0100
Subject: [PATCH 024/474] KVM: arm64: Use build-time defines in has_vhe()

Build system compiles hyp code with macros specifying if the code belongs
to VHE or nVHE. Use these macros to evaluate has_vhe() at compile time.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-5-dbrazdil@google.com
---
 arch/arm64/include/asm/virt.h | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 5051b388c654..09977acc007d 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -85,10 +85,17 @@ static inline bool is_kernel_in_hyp_mode(void)
 
 static __always_inline bool has_vhe(void)
 {
-	if (cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN))
+	/*
+	 * The following macros are defined for code specic to VHE/nVHE.
+	 * If has_vhe() is inlined into those compilation units, it can
+	 * be determined statically. Otherwise fall back to caps.
+	 */
+	if (__is_defined(__KVM_VHE_HYPERVISOR__))
 		return true;
-
-	return false;
+	else if (__is_defined(__KVM_NVHE_HYPERVISOR__))
+		return false;
+	else
+		return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN);
 }
 
 #endif /* __ASSEMBLY__ */

From f50b6f6ae131b6ee7d5dd738961eda0c00b7f027 Mon Sep 17 00:00:00 2001
From: Andrew Scull <ascull@google.com>
Date: Thu, 25 Jun 2020 14:14:10 +0100
Subject: [PATCH 025/474] KVM: arm64: Handle calls to prefixed hyp functions

Once hyp functions are moved to a hyp object, they will have prefixed symbols.
This change declares and gets the address of the prefixed version for calls to
the hyp functions.

To aid migration, the hyp functions that have not yet moved have their prefixed
versions aliased to their non-prefixed version. This begins with all the hyp
functions being listed and will reduce to none of them once the migration is
complete.

Signed-off-by: Andrew Scull <ascull@google.com>

[David: Extracted kvm_call_hyp nVHE branches into own helper macros, added
        comments around symbol aliases.]

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-6-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_asm.h  | 19 +++++++++++++++++++
 arch/arm64/include/asm/kvm_host.h | 17 ++++++++++++++---
 arch/arm64/kernel/image-vars.h    | 26 ++++++++++++++++++++++++++
 3 files changed, 59 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 352aaebf4198..6a682d66a640 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -42,6 +42,24 @@
 
 #include <linux/mm.h>
 
+/*
+ * Translate name of a symbol defined in nVHE hyp to the name seen
+ * by kernel proper. All nVHE symbols are prefixed by the build system
+ * to avoid clashes with the VHE variants.
+ */
+#define kvm_nvhe_sym(sym)	__kvm_nvhe_##sym
+
+#define DECLARE_KVM_VHE_SYM(sym)	extern char sym[]
+#define DECLARE_KVM_NVHE_SYM(sym)	extern char kvm_nvhe_sym(sym)[]
+
+/*
+ * Define a pair of symbols sharing the same name but one defined in
+ * VHE and the other in nVHE hyp implementations.
+ */
+#define DECLARE_KVM_HYP_SYM(sym)		\
+	DECLARE_KVM_VHE_SYM(sym);		\
+	DECLARE_KVM_NVHE_SYM(sym)
+
 /* Translate a kernel address of @sym into its equivalent linear mapping */
 #define kvm_ksym_ref(sym)						\
 	({								\
@@ -50,6 +68,7 @@
 			val = lm_alias(&sym);				\
 		val;							\
 	 })
+#define kvm_ksym_ref_nvhe(sym)	kvm_ksym_ref(kvm_nvhe_sym(sym))
 
 struct kvm;
 struct kvm_vcpu;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index c3e6fcc664b1..49d1a5cd8f8f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -448,6 +448,18 @@ void kvm_arm_resume_guest(struct kvm *kvm);
 
 u64 __kvm_call_hyp(void *hypfn, ...);
 
+#define kvm_call_hyp_nvhe(f, ...)					\
+	do {								\
+		DECLARE_KVM_NVHE_SYM(f);				\
+		__kvm_call_hyp(kvm_ksym_ref_nvhe(f), ##__VA_ARGS__);	\
+	} while(0)
+
+#define kvm_call_hyp_nvhe_ret(f, ...)					\
+	({								\
+		DECLARE_KVM_NVHE_SYM(f);				\
+		__kvm_call_hyp(kvm_ksym_ref_nvhe(f), ##__VA_ARGS__);	\
+	})
+
 /*
  * The couple of isb() below are there to guarantee the same behaviour
  * on VHE as on !VHE, where the eret to EL1 acts as a context
@@ -459,7 +471,7 @@ u64 __kvm_call_hyp(void *hypfn, ...);
 			f(__VA_ARGS__);					\
 			isb();						\
 		} else {						\
-			__kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__); \
+			kvm_call_hyp_nvhe(f, ##__VA_ARGS__);		\
 		}							\
 	} while(0)
 
@@ -471,8 +483,7 @@ u64 __kvm_call_hyp(void *hypfn, ...);
 			ret = f(__VA_ARGS__);				\
 			isb();						\
 		} else {						\
-			ret = __kvm_call_hyp(kvm_ksym_ref(f),		\
-					     ##__VA_ARGS__);		\
+			ret = kvm_call_hyp_nvhe_ret(f, ##__VA_ARGS__);	\
 		}							\
 									\
 		ret;							\
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 3dc27da47712..36444bac6a05 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -63,6 +63,32 @@ __efistub__ctype		= _ctype;
 
 #define KVM_NVHE_ALIAS(sym) __kvm_nvhe_##sym = sym;
 
+/* Symbols defined in debug-sr.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__kvm_get_mdcr_el2);
+
+/* Symbols defined in switch.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__kvm_vcpu_run_nvhe);
+
+/* Symbols defined in sysreg-sr.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__kvm_enable_ssbs);
+
+/* Symbols defined in timer-sr.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__kvm_timer_set_cntvoff);
+
+/* Symbols defined in tlb.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__kvm_flush_vm_context);
+KVM_NVHE_ALIAS(__kvm_tlb_flush_local_vmid);
+KVM_NVHE_ALIAS(__kvm_tlb_flush_vmid);
+KVM_NVHE_ALIAS(__kvm_tlb_flush_vmid_ipa);
+
+/* Symbols defined in vgic-v3-sr.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__vgic_v3_get_ich_vtr_el2);
+KVM_NVHE_ALIAS(__vgic_v3_init_lrs);
+KVM_NVHE_ALIAS(__vgic_v3_read_vmcr);
+KVM_NVHE_ALIAS(__vgic_v3_restore_aprs);
+KVM_NVHE_ALIAS(__vgic_v3_save_aprs);
+KVM_NVHE_ALIAS(__vgic_v3_write_vmcr);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */

From b877e9849d41e7d2100d2933e0a3971d0ddec011 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:11 +0100
Subject: [PATCH 026/474] KVM: arm64: Build hyp-entry.S separately for VHE/nVHE

hyp-entry.S contains implementation of KVM hyp vectors. This code is mostly
shared between VHE/nVHE, therefore compile it under both VHE and nVHE build
rules. nVHE-specific host HVC handler is hidden behind __KVM_NVHE_HYPERVISOR__.

Adjust code which selects which KVM hyp vecs to install to choose the correct
VHE/nVHE symbol.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-7-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_asm.h | 22 +++++++++++++++++-----
 arch/arm64/include/asm/mmu.h     |  7 -------
 arch/arm64/kernel/image-vars.h   | 24 ++++++++++++++++++++++++
 arch/arm64/kvm/arm.c             |  2 +-
 arch/arm64/kvm/hyp/Makefile      |  4 ++--
 arch/arm64/kvm/hyp/hyp-entry.S   |  2 ++
 arch/arm64/kvm/hyp/nvhe/Makefile |  2 +-
 arch/arm64/kvm/hyp/vhe/Makefile  |  2 +-
 8 files changed, 48 insertions(+), 17 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 6a682d66a640..6026cbd204ae 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -60,12 +60,17 @@
 	DECLARE_KVM_VHE_SYM(sym);		\
 	DECLARE_KVM_NVHE_SYM(sym)
 
-/* Translate a kernel address of @sym into its equivalent linear mapping */
-#define kvm_ksym_ref(sym)						\
+#define CHOOSE_VHE_SYM(sym)	sym
+#define CHOOSE_NVHE_SYM(sym)	kvm_nvhe_sym(sym)
+#define CHOOSE_HYP_SYM(sym)	(has_vhe() ? CHOOSE_VHE_SYM(sym) \
+					   : CHOOSE_NVHE_SYM(sym))
+
+/* Translate a kernel address @ptr into its equivalent linear mapping */
+#define kvm_ksym_ref(ptr)						\
 	({								\
-		void *val = &sym;					\
+		void *val = (ptr);					\
 		if (!is_kernel_in_hyp_mode())				\
-			val = lm_alias(&sym);				\
+			val = lm_alias((ptr));				\
 		val;							\
 	 })
 #define kvm_ksym_ref_nvhe(sym)	kvm_ksym_ref(kvm_nvhe_sym(sym))
@@ -76,7 +81,14 @@ struct kvm_vcpu;
 extern char __kvm_hyp_init[];
 extern char __kvm_hyp_init_end[];
 
-extern char __kvm_hyp_vector[];
+DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
+#define __kvm_hyp_vector	CHOOSE_HYP_SYM(__kvm_hyp_vector)
+
+#ifdef CONFIG_KVM_INDIRECT_VECTORS
+extern atomic_t arm64_el2_vector_last_slot;
+DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
+#define __bp_harden_hyp_vecs	CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
+#endif
 
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 8444df000181..a7a5ecaa2e83 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -45,13 +45,6 @@ struct bp_hardening_data {
 	bp_hardening_cb_t	fn;
 };
 
-#if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) ||	\
-     defined(CONFIG_HARDEN_EL2_VECTORS))
-
-extern char __bp_harden_hyp_vecs[];
-extern atomic_t arm64_el2_vector_last_slot;
-#endif  /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */
-
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 36444bac6a05..f28da486b75a 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -66,8 +66,17 @@ __efistub__ctype		= _ctype;
 /* Symbols defined in debug-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_get_mdcr_el2);
 
+/* Symbols defined in entry.S (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__guest_exit);
+KVM_NVHE_ALIAS(abort_guest_exit_end);
+KVM_NVHE_ALIAS(abort_guest_exit_start);
+
+/* Symbols defined in hyp-init.S (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__kvm_handle_stub_hvc);
+
 /* Symbols defined in switch.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_vcpu_run_nvhe);
+KVM_NVHE_ALIAS(hyp_panic);
 
 /* Symbols defined in sysreg-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_enable_ssbs);
@@ -89,6 +98,21 @@ KVM_NVHE_ALIAS(__vgic_v3_restore_aprs);
 KVM_NVHE_ALIAS(__vgic_v3_save_aprs);
 KVM_NVHE_ALIAS(__vgic_v3_write_vmcr);
 
+/* Alternative callbacks for init-time patching of nVHE hyp code. */
+KVM_NVHE_ALIAS(arm64_enable_wa2_handling);
+KVM_NVHE_ALIAS(kvm_patch_vector_branch);
+KVM_NVHE_ALIAS(kvm_update_va_mask);
+
+/* Global kernel state accessed by nVHE hyp code. */
+KVM_NVHE_ALIAS(arm64_ssbd_callback_required);
+KVM_NVHE_ALIAS(kvm_host_data);
+
+/* Kernel constant needed to compute idmap addresses. */
+KVM_NVHE_ALIAS(kimage_voffset);
+
+/* Kernel symbols used to call panic() from nVHE hyp code (via ERET). */
+KVM_NVHE_ALIAS(panic);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 90cb90561446..34b551385153 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1285,7 +1285,7 @@ static void cpu_init_hyp_mode(void)
 	 * so that we can use adr_l to access per-cpu variables in EL2.
 	 */
 	tpidr_el2 = ((unsigned long)this_cpu_ptr(&kvm_host_data) -
-		     (unsigned long)kvm_ksym_ref(kvm_host_data));
+		     (unsigned long)kvm_ksym_ref(&kvm_host_data));
 
 	pgd_ptr = kvm_mmu_get_httbr();
 	hyp_stack_ptr = __this_cpu_read(kvm_arm_hyp_stack_page) + PAGE_SIZE;
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 9c5dfe6ff80b..8b0cf85080b5 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -10,11 +10,11 @@ subdir-ccflags-y := -I$(incdir)				\
 		    -DDISABLE_BRANCH_PROFILING		\
 		    $(DISABLE_STACKLEAK_PLUGIN)
 
-obj-$(CONFIG_KVM) += hyp.o nvhe/
+obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
 hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
-	 debug-sr.o entry.o switch.o fpsimd.o tlb.o hyp-entry.o
+	 debug-sr.o entry.o switch.o fpsimd.o tlb.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index d362fad97cc8..7e3c72fa634f 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -40,6 +40,7 @@ el1_sync:				// Guest trapped into EL2
 	ccmp	x0, #ESR_ELx_EC_HVC32, #4, ne
 	b.ne	el1_trap
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 	mrs	x1, vttbr_el2		// If vttbr is valid, the guest
 	cbnz	x1, el1_hvc_guest	// called HVC
 
@@ -74,6 +75,7 @@ el1_sync:				// Guest trapped into EL2
 
 	eret
 	sb
+#endif /* __KVM_NVHE_HYPERVISOR__ */
 
 el1_hvc_guest:
 	/*
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 955f4188e00f..79eb8eed96a1 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y :=
+obj-y := ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index e04375546081..323029e02b4e 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y :=
+obj-y := ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may

From 208243c752a7eeef4236f7b7d67e806ee356e3f8 Mon Sep 17 00:00:00 2001
From: Andrew Scull <ascull@google.com>
Date: Thu, 25 Jun 2020 14:14:12 +0100
Subject: [PATCH 027/474] KVM: arm64: Move hyp-init.S to nVHE

hyp-init.S contains the identity mapped initialisation code for the
non-VHE code that runs at EL2. It is only used for non-VHE.

Adjust code that calls into this to use the prefixed symbol name.

Signed-off-by: Andrew Scull <ascull@google.com>
Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-8-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_asm.h         | 5 ++---
 arch/arm64/kernel/image-vars.h           | 9 ++++++---
 arch/arm64/kvm/Makefile                  | 2 +-
 arch/arm64/kvm/hyp/nvhe/Makefile         | 2 +-
 arch/arm64/kvm/{ => hyp/nvhe}/hyp-init.S | 0
 5 files changed, 10 insertions(+), 8 deletions(-)
 rename arch/arm64/kvm/{ => hyp/nvhe}/hyp-init.S (100%)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 6026cbd204ae..3476abb046e3 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -78,10 +78,9 @@
 struct kvm;
 struct kvm_vcpu;
 
-extern char __kvm_hyp_init[];
-extern char __kvm_hyp_init_end[];
-
+DECLARE_KVM_NVHE_SYM(__kvm_hyp_init);
 DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
+#define __kvm_hyp_init		CHOOSE_NVHE_SYM(__kvm_hyp_init)
 #define __kvm_hyp_vector	CHOOSE_HYP_SYM(__kvm_hyp_vector)
 
 #ifdef CONFIG_KVM_INDIRECT_VECTORS
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index f28da486b75a..63186c91b614 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -71,9 +71,6 @@ KVM_NVHE_ALIAS(__guest_exit);
 KVM_NVHE_ALIAS(abort_guest_exit_end);
 KVM_NVHE_ALIAS(abort_guest_exit_start);
 
-/* Symbols defined in hyp-init.S (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__kvm_handle_stub_hvc);
-
 /* Symbols defined in switch.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_vcpu_run_nvhe);
 KVM_NVHE_ALIAS(hyp_panic);
@@ -113,6 +110,12 @@ KVM_NVHE_ALIAS(kimage_voffset);
 /* Kernel symbols used to call panic() from nVHE hyp code (via ERET). */
 KVM_NVHE_ALIAS(panic);
 
+/* Vectors installed by hyp-init on reset HVC. */
+KVM_NVHE_ALIAS(__hyp_stub_vectors);
+
+/* IDMAP TCR_EL1.T0SZ as computed by the EL1 init code */
+KVM_NVHE_ALIAS(idmap_t0sz);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 8d3d9513cbfe..152d8845a1a2 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_KVM) += hyp/
 kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 $(KVM)/vfio.o $(KVM)/irqchip.o \
 	 arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \
-	 inject_fault.o regmap.o va_layout.o hyp.o hyp-init.o handle_exit.o \
+	 inject_fault.o regmap.o va_layout.o hyp.o handle_exit.o \
 	 guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o \
 	 vgic-sys-reg-v3.o fpsimd.o pmu.o \
 	 aarch32.o arch_timer.o \
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 79eb8eed96a1..bf2d8dea5400 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := ../hyp-entry.o
+obj-y := hyp-init.o ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
similarity index 100%
rename from arch/arm64/kvm/hyp-init.S
rename to arch/arm64/kvm/hyp/nvhe/hyp-init.S

From e03fa29164ec1db1a81dc0168d0017a9e0366c7c Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:13 +0100
Subject: [PATCH 028/474] KVM: arm64: Duplicate hyp/tlb.c for VHE/nVHE

tlb.c contains code for flushing the TLB, with code shared between VHE/nVHE.
Because common code is small, duplicate tlb.c and specialize each copy for
VHE/nVHE.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-9-dbrazdil@google.com
---
 arch/arm64/kernel/image-vars.h      |  14 +--
 arch/arm64/kvm/hyp/Makefile         |   2 +-
 arch/arm64/kvm/hyp/nvhe/Makefile    |   2 +-
 arch/arm64/kvm/hyp/{ => nvhe}/tlb.c |  96 +----------------
 arch/arm64/kvm/hyp/vhe/Makefile     |   2 +-
 arch/arm64/kvm/hyp/vhe/tlb.c        | 161 ++++++++++++++++++++++++++++
 6 files changed, 177 insertions(+), 100 deletions(-)
 rename arch/arm64/kvm/hyp/{ => nvhe}/tlb.c (61%)
 create mode 100644 arch/arm64/kvm/hyp/vhe/tlb.c

diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 63186c91b614..f029f3ea7ffe 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -81,12 +81,6 @@ KVM_NVHE_ALIAS(__kvm_enable_ssbs);
 /* Symbols defined in timer-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_timer_set_cntvoff);
 
-/* Symbols defined in tlb.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__kvm_flush_vm_context);
-KVM_NVHE_ALIAS(__kvm_tlb_flush_local_vmid);
-KVM_NVHE_ALIAS(__kvm_tlb_flush_vmid);
-KVM_NVHE_ALIAS(__kvm_tlb_flush_vmid_ipa);
-
 /* Symbols defined in vgic-v3-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__vgic_v3_get_ich_vtr_el2);
 KVM_NVHE_ALIAS(__vgic_v3_init_lrs);
@@ -116,6 +110,14 @@ KVM_NVHE_ALIAS(__hyp_stub_vectors);
 /* IDMAP TCR_EL1.T0SZ as computed by the EL1 init code */
 KVM_NVHE_ALIAS(idmap_t0sz);
 
+/* Kernel symbol used by icache_is_vpipt(). */
+KVM_NVHE_ALIAS(__icache_flags);
+
+/* Kernel symbols needed for cpus_have_final/const_caps checks. */
+KVM_NVHE_ALIAS(arm64_const_caps_ready);
+KVM_NVHE_ALIAS(cpu_hwcap_keys);
+KVM_NVHE_ALIAS(cpu_hwcaps);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 8b0cf85080b5..87d3cce2b26e 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
 hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
-	 debug-sr.o entry.o switch.o fpsimd.o tlb.o
+	 debug-sr.o entry.o switch.o fpsimd.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index bf2d8dea5400..a5316e97d373 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := hyp-init.o ../hyp-entry.o
+obj-y := tlb.o hyp-init.o ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
similarity index 61%
rename from arch/arm64/kvm/hyp/tlb.c
rename to arch/arm64/kvm/hyp/nvhe/tlb.c
index d063a576d511..deb48c8c00ee 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -4,64 +4,16 @@
  * Author: Marc Zyngier <marc.zyngier@arm.com>
  */
 
-#include <linux/irqflags.h>
-
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 #include <asm/tlbflush.h>
 
 struct tlb_inv_context {
-	unsigned long	flags;
 	u64		tcr;
-	u64		sctlr;
 };
 
-static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
-						 struct tlb_inv_context *cxt)
-{
-	u64 val;
-
-	local_irq_save(cxt->flags);
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		/*
-		 * For CPUs that are affected by ARM errata 1165522 or 1530923,
-		 * we cannot trust stage-1 to be in a correct state at that
-		 * point. Since we do not want to force a full load of the
-		 * vcpu state, we prevent the EL1 page-table walker to
-		 * allocate new TLBs. This is done by setting the EPD bits
-		 * in the TCR_EL1 register. We also need to prevent it to
-		 * allocate IPA->PA walks, so we enable the S1 MMU...
-		 */
-		val = cxt->tcr = read_sysreg_el1(SYS_TCR);
-		val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
-		write_sysreg_el1(val, SYS_TCR);
-		val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR);
-		val |= SCTLR_ELx_M;
-		write_sysreg_el1(val, SYS_SCTLR);
-	}
-
-	/*
-	 * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
-	 * most TLB operations target EL2/EL0. In order to affect the
-	 * guest TLBs (EL1/EL0), we need to change one of these two
-	 * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
-	 * let's flip TGE before executing the TLB operation.
-	 *
-	 * ARM erratum 1165522 requires some special handling (again),
-	 * as we need to make sure both stages of translation are in
-	 * place before clearing TGE. __load_guest_stage2() already
-	 * has an ISB in order to deal with this.
-	 */
-	__load_guest_stage2(kvm);
-	val = read_sysreg(hcr_el2);
-	val &= ~HCR_TGE;
-	write_sysreg(val, hcr_el2);
-	isb();
-}
-
-static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
-						  struct tlb_inv_context *cxt)
+static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
+					     struct tlb_inv_context *cxt)
 {
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		u64 val;
@@ -84,37 +36,8 @@ static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
 	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
 }
 
-static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
-					     struct tlb_inv_context *cxt)
-{
-	if (has_vhe())
-		__tlb_switch_to_guest_vhe(kvm, cxt);
-	else
-		__tlb_switch_to_guest_nvhe(kvm, cxt);
-}
-
-static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
-						struct tlb_inv_context *cxt)
-{
-	/*
-	 * We're done with the TLB operation, let's restore the host's
-	 * view of HCR_EL2.
-	 */
-	write_sysreg(0, vttbr_el2);
-	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
-	isb();
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		/* Restore the registers to what they were */
-		write_sysreg_el1(cxt->tcr, SYS_TCR);
-		write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
-	}
-
-	local_irq_restore(cxt->flags);
-}
-
-static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
-						 struct tlb_inv_context *cxt)
+static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
+					    struct tlb_inv_context *cxt)
 {
 	write_sysreg(0, vttbr_el2);
 
@@ -126,15 +49,6 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
 	}
 }
 
-static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
-					    struct tlb_inv_context *cxt)
-{
-	if (has_vhe())
-		__tlb_switch_to_host_vhe(kvm, cxt);
-	else
-		__tlb_switch_to_host_nvhe(kvm, cxt);
-}
-
 void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
 	struct tlb_inv_context cxt;
@@ -183,7 +97,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	 * The moral of this story is: if you have a VPIPT I-cache, then
 	 * you should be running with VHE enabled.
 	 */
-	if (!has_vhe() && icache_is_vpipt())
+	if (icache_is_vpipt())
 		__flush_icache_all();
 
 	__tlb_switch_to_host(kvm, &cxt);
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 323029e02b4e..704140fc5d66 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y := ../hyp-entry.o
+obj-y := tlb.o ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
new file mode 100644
index 000000000000..b275101e9c9c
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <linux/irqflags.h>
+
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/tlbflush.h>
+
+struct tlb_inv_context {
+	unsigned long	flags;
+	u64		tcr;
+	u64		sctlr;
+};
+
+static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
+{
+	u64 val;
+
+	local_irq_save(cxt->flags);
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		/*
+		 * For CPUs that are affected by ARM errata 1165522 or 1530923,
+		 * we cannot trust stage-1 to be in a correct state at that
+		 * point. Since we do not want to force a full load of the
+		 * vcpu state, we prevent the EL1 page-table walker to
+		 * allocate new TLBs. This is done by setting the EPD bits
+		 * in the TCR_EL1 register. We also need to prevent it to
+		 * allocate IPA->PA walks, so we enable the S1 MMU...
+		 */
+		val = cxt->tcr = read_sysreg_el1(SYS_TCR);
+		val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
+		write_sysreg_el1(val, SYS_TCR);
+		val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR);
+		val |= SCTLR_ELx_M;
+		write_sysreg_el1(val, SYS_SCTLR);
+	}
+
+	/*
+	 * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
+	 * most TLB operations target EL2/EL0. In order to affect the
+	 * guest TLBs (EL1/EL0), we need to change one of these two
+	 * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
+	 * let's flip TGE before executing the TLB operation.
+	 *
+	 * ARM erratum 1165522 requires some special handling (again),
+	 * as we need to make sure both stages of translation are in
+	 * place before clearing TGE. __load_guest_stage2() already
+	 * has an ISB in order to deal with this.
+	 */
+	__load_guest_stage2(kvm);
+	val = read_sysreg(hcr_el2);
+	val &= ~HCR_TGE;
+	write_sysreg(val, hcr_el2);
+	isb();
+}
+
+static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
+{
+	/*
+	 * We're done with the TLB operation, let's restore the host's
+	 * view of HCR_EL2.
+	 */
+	write_sysreg(0, vttbr_el2);
+	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+	isb();
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		/* Restore the registers to what they were */
+		write_sysreg_el1(cxt->tcr, SYS_TCR);
+		write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
+	}
+
+	local_irq_restore(cxt->flags);
+}
+
+void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+{
+	struct tlb_inv_context cxt;
+
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(kvm, &cxt);
+
+	/*
+	 * We could do so much better if we had the VA as well.
+	 * Instead, we invalidate Stage-2 for this IPA, and the
+	 * whole of Stage-1. Weep...
+	 */
+	ipa >>= 12;
+	__tlbi(ipas2e1is, ipa);
+
+	/*
+	 * We have to ensure completion of the invalidation at Stage-2,
+	 * since a table walk on another CPU could refill a TLB with a
+	 * complete (S1 + S2) walk based on the old Stage-2 mapping if
+	 * the Stage-1 invalidation happened first.
+	 */
+	dsb(ish);
+	__tlbi(vmalle1is);
+	dsb(ish);
+	isb();
+
+	__tlb_switch_to_host(kvm, &cxt);
+}
+
+void __kvm_tlb_flush_vmid(struct kvm *kvm)
+{
+	struct tlb_inv_context cxt;
+
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(kvm, &cxt);
+
+	__tlbi(vmalls12e1is);
+	dsb(ish);
+	isb();
+
+	__tlb_switch_to_host(kvm, &cxt);
+}
+
+void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct tlb_inv_context cxt;
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(kvm, &cxt);
+
+	__tlbi(vmalle1);
+	dsb(nsh);
+	isb();
+
+	__tlb_switch_to_host(kvm, &cxt);
+}
+
+void __kvm_flush_vm_context(void)
+{
+	dsb(ishst);
+	__tlbi(alle1is);
+
+	/*
+	 * VIPT and PIPT caches are not affected by VMID, so no maintenance
+	 * is necessary across a VMID rollover.
+	 *
+	 * VPIPT caches constrain lookup and maintenance to the active VMID,
+	 * so we need to invalidate lines with a stale VMID to avoid an ABA
+	 * race after multiple rollovers.
+	 *
+	 */
+	if (icache_is_vpipt())
+		asm volatile("ic ialluis");
+
+	dsb(ish);
+}

From 09cf57eba304246141367b95c89801fd2047ac96 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:14 +0100
Subject: [PATCH 029/474] KVM: arm64: Split hyp/switch.c to VHE/nVHE

switch.c implements context-switching for KVM, with large parts shared between
VHE/nVHE. These common routines are moved to a header file, VHE-specific code
is moved to vhe/switch.c and nVHE-specific code is moved to nvhe/switch.c.

Previously __kvm_vcpu_run needed a different symbol name for VHE/nVHE. This
is cleaned up and the caller in arm.c simplified.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-10-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_asm.h        |   4 +-
 arch/arm64/include/asm/kvm_hyp.h        |   6 +
 arch/arm64/kernel/image-vars.h          |  37 +-
 arch/arm64/kvm/arm.c                    |   6 +-
 arch/arm64/kvm/hyp/Makefile             |   2 +-
 arch/arm64/kvm/hyp/hyp-entry.S          |   2 +
 arch/arm64/kvm/hyp/include/hyp/switch.h | 509 +++++++++++++
 arch/arm64/kvm/hyp/nvhe/Makefile        |   2 +-
 arch/arm64/kvm/hyp/nvhe/switch.c        | 271 +++++++
 arch/arm64/kvm/hyp/switch.c             | 936 ------------------------
 arch/arm64/kvm/hyp/sysreg-sr.c          |   4 +-
 arch/arm64/kvm/hyp/vhe/Makefile         |   2 +-
 arch/arm64/kvm/hyp/vhe/switch.c         | 219 ++++++
 13 files changed, 1048 insertions(+), 952 deletions(-)
 create mode 100644 arch/arm64/kvm/hyp/include/hyp/switch.h
 create mode 100644 arch/arm64/kvm/hyp/nvhe/switch.c
 delete mode 100644 arch/arm64/kvm/hyp/switch.c
 create mode 100644 arch/arm64/kvm/hyp/vhe/switch.c

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 3476abb046e3..5a91aaae78d2 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -96,9 +96,7 @@ extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
-extern int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu);
-
-extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu);
+extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern void __kvm_enable_ssbs(void);
 
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index ce3080834bfa..82fa05d15b8b 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -81,11 +81,17 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu);
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
 
+#ifndef __KVM_NVHE_HYPERVISOR__
 void activate_traps_vhe_load(struct kvm_vcpu *vcpu);
 void deactivate_traps_vhe_put(void);
+#endif
 
 u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
+
+void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt);
+#ifdef __KVM_NVHE_HYPERVISOR__
 void __noreturn __hyp_do_panic(unsigned long, ...);
+#endif
 
 #endif /* __ARM64_KVM_HYP_H__ */
 
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index f029f3ea7ffe..06fe9833104a 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -63,30 +63,50 @@ __efistub__ctype		= _ctype;
 
 #define KVM_NVHE_ALIAS(sym) __kvm_nvhe_##sym = sym;
 
+/* Symbols defined in aarch32.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(kvm_skip_instr32);
+
 /* Symbols defined in debug-sr.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__debug_switch_to_guest);
+KVM_NVHE_ALIAS(__debug_switch_to_host);
 KVM_NVHE_ALIAS(__kvm_get_mdcr_el2);
 
 /* Symbols defined in entry.S (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__guest_enter);
 KVM_NVHE_ALIAS(__guest_exit);
 KVM_NVHE_ALIAS(abort_guest_exit_end);
 KVM_NVHE_ALIAS(abort_guest_exit_start);
 
-/* Symbols defined in switch.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__kvm_vcpu_run_nvhe);
-KVM_NVHE_ALIAS(hyp_panic);
+/* Symbols defined in fpsimd.S (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__fpsimd_restore_state);
+KVM_NVHE_ALIAS(__fpsimd_save_state);
 
 /* Symbols defined in sysreg-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_enable_ssbs);
+KVM_NVHE_ALIAS(__sysreg32_restore_state);
+KVM_NVHE_ALIAS(__sysreg32_save_state);
+KVM_NVHE_ALIAS(__sysreg_restore_state_nvhe);
+KVM_NVHE_ALIAS(__sysreg_save_state_nvhe);
 
 /* Symbols defined in timer-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_timer_set_cntvoff);
+KVM_NVHE_ALIAS(__timer_disable_traps);
+KVM_NVHE_ALIAS(__timer_enable_traps);
+
+/* Symbols defined in vgic-v2-cpuif-proxy.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__vgic_v2_perform_cpuif_access);
 
 /* Symbols defined in vgic-v3-sr.c (not yet compiled with nVHE build rules). */
+KVM_NVHE_ALIAS(__vgic_v3_activate_traps);
+KVM_NVHE_ALIAS(__vgic_v3_deactivate_traps);
 KVM_NVHE_ALIAS(__vgic_v3_get_ich_vtr_el2);
 KVM_NVHE_ALIAS(__vgic_v3_init_lrs);
+KVM_NVHE_ALIAS(__vgic_v3_perform_cpuif_access);
 KVM_NVHE_ALIAS(__vgic_v3_read_vmcr);
 KVM_NVHE_ALIAS(__vgic_v3_restore_aprs);
+KVM_NVHE_ALIAS(__vgic_v3_restore_state);
 KVM_NVHE_ALIAS(__vgic_v3_save_aprs);
+KVM_NVHE_ALIAS(__vgic_v3_save_state);
 KVM_NVHE_ALIAS(__vgic_v3_write_vmcr);
 
 /* Alternative callbacks for init-time patching of nVHE hyp code. */
@@ -97,11 +117,13 @@ KVM_NVHE_ALIAS(kvm_update_va_mask);
 /* Global kernel state accessed by nVHE hyp code. */
 KVM_NVHE_ALIAS(arm64_ssbd_callback_required);
 KVM_NVHE_ALIAS(kvm_host_data);
+KVM_NVHE_ALIAS(kvm_vgic_global_state);
 
 /* Kernel constant needed to compute idmap addresses. */
 KVM_NVHE_ALIAS(kimage_voffset);
 
 /* Kernel symbols used to call panic() from nVHE hyp code (via ERET). */
+KVM_NVHE_ALIAS(__hyp_panic_string);
 KVM_NVHE_ALIAS(panic);
 
 /* Vectors installed by hyp-init on reset HVC. */
@@ -118,6 +140,15 @@ KVM_NVHE_ALIAS(arm64_const_caps_ready);
 KVM_NVHE_ALIAS(cpu_hwcap_keys);
 KVM_NVHE_ALIAS(cpu_hwcaps);
 
+/* Static keys which are set if a vGIC trap should be handled in hyp. */
+KVM_NVHE_ALIAS(vgic_v2_cpuif_trap);
+KVM_NVHE_ALIAS(vgic_v3_cpuif_trap);
+
+/* Static key checked in pmr_sync(). */
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+KVM_NVHE_ALIAS(gic_pmr_sync);
+#endif
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 34b551385153..26780b78a523 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -748,11 +748,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		trace_kvm_entry(*vcpu_pc(vcpu));
 		guest_enter_irqoff();
 
-		if (has_vhe()) {
-			ret = kvm_vcpu_run_vhe(vcpu);
-		} else {
-			ret = kvm_call_hyp_ret(__kvm_vcpu_run_nvhe, vcpu);
-		}
+		ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
 		vcpu->stat.exits++;
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 87d3cce2b26e..7462d3a8a6f2 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
 hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
-	 debug-sr.o entry.o switch.o fpsimd.o
+	 debug-sr.o entry.o fpsimd.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 7e3c72fa634f..8316ee67d6a0 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -182,6 +182,7 @@ el2_error:
 	eret
 	sb
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 SYM_FUNC_START(__hyp_do_panic)
 	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
 		      PSR_MODE_EL1h)
@@ -191,6 +192,7 @@ SYM_FUNC_START(__hyp_do_panic)
 	eret
 	sb
 SYM_FUNC_END(__hyp_do_panic)
+#endif
 
 SYM_CODE_START(__hyp_panic)
 	get_host_ctxt x0, x1
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
new file mode 100644
index 000000000000..65d2a879b93b
--- /dev/null
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -0,0 +1,509 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_HYP_SWITCH_H__
+#define __ARM64_KVM_HYP_SWITCH_H__
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+extern const char __hyp_panic_string[];
+
+/* Check whether the FP regs were dirtied while in the host-side run loop: */
+static inline bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * When the system doesn't support FP/SIMD, we cannot rely on
+	 * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an
+	 * abort on the very first access to FP and thus we should never
+	 * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always
+	 * trap the accesses.
+	 */
+	if (!system_supports_fpsimd() ||
+	    vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
+		vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
+				      KVM_ARM64_FP_HOST);
+
+	return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED);
+}
+
+/* Save the 32-bit only FPSIMD system register state */
+static inline void __hyp_text __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
+{
+	if (!vcpu_el1_is_32bit(vcpu))
+		return;
+
+	vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
+}
+
+static inline void __hyp_text __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * We are about to set CPTR_EL2.TFP to trap all floating point
+	 * register accesses to EL2, however, the ARM ARM clearly states that
+	 * traps are only taken to EL2 if the operation would not otherwise
+	 * trap to EL1.  Therefore, always make sure that for 32-bit guests,
+	 * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
+	 * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to
+	 * it will cause an exception.
+	 */
+	if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) {
+		write_sysreg(1 << 30, fpexc32_el2);
+		isb();
+	}
+}
+
+static inline void __hyp_text __activate_traps_common(struct kvm_vcpu *vcpu)
+{
+	/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
+	write_sysreg(1 << 15, hstr_el2);
+
+	/*
+	 * Make sure we trap PMU access from EL0 to EL2. Also sanitize
+	 * PMSELR_EL0 to make sure it never contains the cycle
+	 * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
+	 * EL1 instead of being trapped to EL2.
+	 */
+	write_sysreg(0, pmselr_el0);
+	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+}
+
+static inline void __hyp_text __deactivate_traps_common(void)
+{
+	write_sysreg(0, hstr_el2);
+	write_sysreg(0, pmuserenr_el0);
+}
+
+static inline void __hyp_text ___activate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 hcr = vcpu->arch.hcr_el2;
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
+		hcr |= HCR_TVM;
+
+	write_sysreg(hcr, hcr_el2);
+
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
+		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
+}
+
+static inline void __hyp_text ___deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * If we pended a virtual abort, preserve it until it gets
+	 * cleared. See D1.14.3 (Virtual Interrupts) for details, but
+	 * the crucial bit is "On taking a vSError interrupt,
+	 * HCR_EL2.VSE is cleared to 0."
+	 */
+	if (vcpu->arch.hcr_el2 & HCR_VSE) {
+		vcpu->arch.hcr_el2 &= ~HCR_VSE;
+		vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
+	}
+}
+
+static inline void __hyp_text __activate_vm(struct kvm *kvm)
+{
+	__load_guest_stage2(kvm);
+}
+
+static inline bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
+{
+	u64 par, tmp;
+
+	/*
+	 * Resolve the IPA the hard way using the guest VA.
+	 *
+	 * Stage-1 translation already validated the memory access
+	 * rights. As such, we can use the EL1 translation regime, and
+	 * don't have to distinguish between EL0 and EL1 access.
+	 *
+	 * We do need to save/restore PAR_EL1 though, as we haven't
+	 * saved the guest context yet, and we may return early...
+	 */
+	par = read_sysreg(par_el1);
+	asm volatile("at s1e1r, %0" : : "r" (far));
+	isb();
+
+	tmp = read_sysreg(par_el1);
+	write_sysreg(par, par_el1);
+
+	if (unlikely(tmp & SYS_PAR_EL1_F))
+		return false; /* Translation failed, back to guest */
+
+	/* Convert PAR to HPFAR format */
+	*hpfar = PAR_TO_HPFAR(tmp);
+	return true;
+}
+
+static inline bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
+{
+	u8 ec;
+	u64 esr;
+	u64 hpfar, far;
+
+	esr = vcpu->arch.fault.esr_el2;
+	ec = ESR_ELx_EC(esr);
+
+	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
+		return true;
+
+	far = read_sysreg_el2(SYS_FAR);
+
+	/*
+	 * The HPFAR can be invalid if the stage 2 fault did not
+	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
+	 * bit is clear) and one of the two following cases are true:
+	 *   1. The fault was due to a permission fault
+	 *   2. The processor carries errata 834220
+	 *
+	 * Therefore, for all non S1PTW faults where we either have a
+	 * permission fault or the errata workaround is enabled, we
+	 * resolve the IPA using the AT instruction.
+	 */
+	if (!(esr & ESR_ELx_S1PTW) &&
+	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
+	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+		if (!__translate_far_to_hpfar(far, &hpfar))
+			return false;
+	} else {
+		hpfar = read_sysreg(hpfar_el2);
+	}
+
+	vcpu->arch.fault.far_el2 = far;
+	vcpu->arch.fault.hpfar_el2 = hpfar;
+	return true;
+}
+
+/* Check for an FPSIMD/SVE trap and handle as appropriate */
+static inline bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
+{
+	bool vhe, sve_guest, sve_host;
+	u8 hsr_ec;
+
+	if (!system_supports_fpsimd())
+		return false;
+
+	/*
+	 * Currently system_supports_sve() currently implies has_vhe(),
+	 * so the check is redundant. However, has_vhe() can be determined
+	 * statically and helps the compiler remove dead code.
+	 */
+	if (has_vhe() && system_supports_sve()) {
+		sve_guest = vcpu_has_sve(vcpu);
+		sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE;
+		vhe = true;
+	} else {
+		sve_guest = false;
+		sve_host = false;
+		vhe = has_vhe();
+	}
+
+	hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+	if (hsr_ec != ESR_ELx_EC_FP_ASIMD &&
+	    hsr_ec != ESR_ELx_EC_SVE)
+		return false;
+
+	/* Don't handle SVE traps for non-SVE vcpus here: */
+	if (!sve_guest)
+		if (hsr_ec != ESR_ELx_EC_FP_ASIMD)
+			return false;
+
+	/* Valid trap.  Switch the context: */
+
+	if (vhe) {
+		u64 reg = read_sysreg(cpacr_el1) | CPACR_EL1_FPEN;
+
+		if (sve_guest)
+			reg |= CPACR_EL1_ZEN;
+
+		write_sysreg(reg, cpacr_el1);
+	} else {
+		write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP,
+			     cptr_el2);
+	}
+
+	isb();
+
+	if (vcpu->arch.flags & KVM_ARM64_FP_HOST) {
+		/*
+		 * In the SVE case, VHE is assumed: it is enforced by
+		 * Kconfig and kvm_arch_init().
+		 */
+		if (sve_host) {
+			struct thread_struct *thread = container_of(
+				vcpu->arch.host_fpsimd_state,
+				struct thread_struct, uw.fpsimd_state);
+
+			sve_save_state(sve_pffr(thread),
+				       &vcpu->arch.host_fpsimd_state->fpsr);
+		} else {
+			__fpsimd_save_state(vcpu->arch.host_fpsimd_state);
+		}
+
+		vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
+	}
+
+	if (sve_guest) {
+		sve_load_state(vcpu_sve_pffr(vcpu),
+			       &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
+			       sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
+		write_sysreg_s(vcpu->arch.ctxt.sys_regs[ZCR_EL1], SYS_ZCR_EL12);
+	} else {
+		__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
+	}
+
+	/* Skip restoring fpexc32 for AArch64 guests */
+	if (!(read_sysreg(hcr_el2) & HCR_RW))
+		write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2],
+			     fpexc32_el2);
+
+	vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;
+
+	return true;
+}
+
+static inline bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
+{
+	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
+	int rt = kvm_vcpu_sys_get_rt(vcpu);
+	u64 val = vcpu_get_reg(vcpu, rt);
+
+	/*
+	 * The normal sysreg handling code expects to see the traps,
+	 * let's not do anything here.
+	 */
+	if (vcpu->arch.hcr_el2 & HCR_TVM)
+		return false;
+
+	switch (sysreg) {
+	case SYS_SCTLR_EL1:
+		write_sysreg_el1(val, SYS_SCTLR);
+		break;
+	case SYS_TTBR0_EL1:
+		write_sysreg_el1(val, SYS_TTBR0);
+		break;
+	case SYS_TTBR1_EL1:
+		write_sysreg_el1(val, SYS_TTBR1);
+		break;
+	case SYS_TCR_EL1:
+		write_sysreg_el1(val, SYS_TCR);
+		break;
+	case SYS_ESR_EL1:
+		write_sysreg_el1(val, SYS_ESR);
+		break;
+	case SYS_FAR_EL1:
+		write_sysreg_el1(val, SYS_FAR);
+		break;
+	case SYS_AFSR0_EL1:
+		write_sysreg_el1(val, SYS_AFSR0);
+		break;
+	case SYS_AFSR1_EL1:
+		write_sysreg_el1(val, SYS_AFSR1);
+		break;
+	case SYS_MAIR_EL1:
+		write_sysreg_el1(val, SYS_MAIR);
+		break;
+	case SYS_AMAIR_EL1:
+		write_sysreg_el1(val, SYS_AMAIR);
+		break;
+	case SYS_CONTEXTIDR_EL1:
+		write_sysreg_el1(val, SYS_CONTEXTIDR);
+		break;
+	default:
+		return false;
+	}
+
+	__kvm_skip_instr(vcpu);
+	return true;
+}
+
+static inline bool __hyp_text esr_is_ptrauth_trap(u32 esr)
+{
+	u32 ec = ESR_ELx_EC(esr);
+
+	if (ec == ESR_ELx_EC_PAC)
+		return true;
+
+	if (ec != ESR_ELx_EC_SYS64)
+		return false;
+
+	switch (esr_sys64_to_sysreg(esr)) {
+	case SYS_APIAKEYLO_EL1:
+	case SYS_APIAKEYHI_EL1:
+	case SYS_APIBKEYLO_EL1:
+	case SYS_APIBKEYHI_EL1:
+	case SYS_APDAKEYLO_EL1:
+	case SYS_APDAKEYHI_EL1:
+	case SYS_APDBKEYLO_EL1:
+	case SYS_APDBKEYHI_EL1:
+	case SYS_APGAKEYLO_EL1:
+	case SYS_APGAKEYHI_EL1:
+		return true;
+	}
+
+	return false;
+}
+
+#define __ptrauth_save_key(regs, key)						\
+({										\
+	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
+	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
+})
+
+static inline bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *ctxt;
+	u64 val;
+
+	if (!vcpu_has_ptrauth(vcpu) ||
+	    !esr_is_ptrauth_trap(kvm_vcpu_get_hsr(vcpu)))
+		return false;
+
+	ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	__ptrauth_save_key(ctxt->sys_regs, APIA);
+	__ptrauth_save_key(ctxt->sys_regs, APIB);
+	__ptrauth_save_key(ctxt->sys_regs, APDA);
+	__ptrauth_save_key(ctxt->sys_regs, APDB);
+	__ptrauth_save_key(ctxt->sys_regs, APGA);
+
+	vcpu_ptrauth_enable(vcpu);
+
+	val = read_sysreg(hcr_el2);
+	val |= (HCR_API | HCR_APK);
+	write_sysreg(val, hcr_el2);
+
+	return true;
+}
+
+/*
+ * Return true when we were able to fixup the guest exit and should return to
+ * the guest, false when we should restore the host state and return to the
+ * main run loop.
+ */
+static inline bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
+		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
+
+	/*
+	 * We're using the raw exception code in order to only process
+	 * the trap if no SError is pending. We will come back to the
+	 * same PC once the SError has been injected, and replay the
+	 * trapping instruction.
+	 */
+	if (*exit_code != ARM_EXCEPTION_TRAP)
+		goto exit;
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
+	    handle_tx2_tvm(vcpu))
+		return true;
+
+	/*
+	 * We trap the first access to the FP/SIMD to save the host context
+	 * and restore the guest context lazily.
+	 * If FP/SIMD is not implemented, handle the trap and inject an
+	 * undefined instruction exception to the guest.
+	 * Similarly for trapped SVE accesses.
+	 */
+	if (__hyp_handle_fpsimd(vcpu))
+		return true;
+
+	if (__hyp_handle_ptrauth(vcpu))
+		return true;
+
+	if (!__populate_fault_info(vcpu))
+		return true;
+
+	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
+		bool valid;
+
+		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
+			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+			kvm_vcpu_dabt_isvalid(vcpu) &&
+			!kvm_vcpu_dabt_isextabt(vcpu) &&
+			!kvm_vcpu_dabt_iss1tw(vcpu);
+
+		if (valid) {
+			int ret = __vgic_v2_perform_cpuif_access(vcpu);
+
+			if (ret == 1)
+				return true;
+
+			/* Promote an illegal access to an SError.*/
+			if (ret == -1)
+				*exit_code = ARM_EXCEPTION_EL1_SERROR;
+
+			goto exit;
+		}
+	}
+
+	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
+	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
+	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
+		int ret = __vgic_v3_perform_cpuif_access(vcpu);
+
+		if (ret == 1)
+			return true;
+	}
+
+exit:
+	/* Return to the host kernel and handle the exit */
+	return false;
+}
+
+static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
+{
+	if (!cpus_have_final_cap(ARM64_SSBD))
+		return false;
+
+	return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
+}
+
+static inline void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ARM64_SSBD
+	/*
+	 * The host runs with the workaround always present. If the
+	 * guest wants it disabled, so be it...
+	 */
+	if (__needs_ssbd_off(vcpu) &&
+	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
+		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL);
+#endif
+}
+
+static inline void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ARM64_SSBD
+	/*
+	 * If the guest has disabled the workaround, bring it back on.
+	 */
+	if (__needs_ssbd_off(vcpu) &&
+	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
+		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL);
+#endif
+}
+
+#endif /* __ARM64_KVM_HYP_SWITCH_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index a5316e97d373..8b3ac38eaa44 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := tlb.o hyp-init.o ../hyp-entry.o
+obj-y := switch.o tlb.o hyp-init.o ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
new file mode 100644
index 000000000000..7f6b8d3dc637
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/switch.h>
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	___activate_traps(vcpu);
+	__activate_traps_common(vcpu);
+
+	val = CPTR_EL2_DEFAULT;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM;
+	if (!update_fp_enabled(vcpu)) {
+		val |= CPTR_EL2_TFP;
+		__activate_traps_fpsimd32(vcpu);
+	}
+
+	write_sysreg(val, cptr_el2);
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
+
+		isb();
+		/*
+		 * At this stage, and thanks to the above isb(), S2 is
+		 * configured and enabled. We can now restore the guest's S1
+		 * configuration: SCTLR, and only then TCR.
+		 */
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		isb();
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	}
+}
+
+static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 mdcr_el2;
+
+	___deactivate_traps(vcpu);
+
+	mdcr_el2 = read_sysreg(mdcr_el2);
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		u64 val;
+
+		/*
+		 * Set the TCR and SCTLR registers in the exact opposite
+		 * sequence as __activate_traps (first prevent walks,
+		 * then force the MMU on). A generous sprinkling of isb()
+		 * ensure that things happen in this exact order.
+		 */
+		val = read_sysreg_el1(SYS_TCR);
+		write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR);
+		isb();
+		val = read_sysreg_el1(SYS_SCTLR);
+		write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR);
+		isb();
+	}
+
+	__deactivate_traps_common();
+
+	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
+	mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
+
+	write_sysreg(mdcr_el2, mdcr_el2);
+	write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
+	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
+}
+
+static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
+{
+	write_sysreg(0, vttbr_el2);
+}
+
+/* Save VGICv3 state on non-VHE systems */
+static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
+{
+	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
+		__vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
+		__vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
+	}
+}
+
+/* Restore VGICv3 state on non_VEH systems */
+static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
+{
+	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
+		__vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
+		__vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3);
+	}
+}
+
+/**
+ * Disable host events, enable guest events
+ */
+static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_host_data *host;
+	struct kvm_pmu_events *pmu;
+
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	pmu = &host->pmu_events;
+
+	if (pmu->events_host)
+		write_sysreg(pmu->events_host, pmcntenclr_el0);
+
+	if (pmu->events_guest)
+		write_sysreg(pmu->events_guest, pmcntenset_el0);
+
+	return (pmu->events_host || pmu->events_guest);
+}
+
+/**
+ * Disable guest events, enable host events
+ */
+static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_host_data *host;
+	struct kvm_pmu_events *pmu;
+
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	pmu = &host->pmu_events;
+
+	if (pmu->events_guest)
+		write_sysreg(pmu->events_guest, pmcntenclr_el0);
+
+	if (pmu->events_host)
+		write_sysreg(pmu->events_host, pmcntenset_el0);
+}
+
+/* Switch to the guest for legacy non-VHE systems */
+int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	bool pmu_switch_needed;
+	u64 exit_code;
+
+	/*
+	 * Having IRQs masked via PMR when entering the guest means the GIC
+	 * will not signal the CPU of interrupts of lower priority, and the
+	 * only way to get out will be via guest exceptions.
+	 * Naturally, we want to avoid this.
+	 */
+	if (system_uses_irq_prio_masking()) {
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+		pmr_sync();
+	}
+
+	vcpu = kern_hyp_va(vcpu);
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	host_ctxt->__hyp_running_vcpu = vcpu;
+	guest_ctxt = &vcpu->arch.ctxt;
+
+	pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
+
+	__sysreg_save_state_nvhe(host_ctxt);
+
+	/*
+	 * We must restore the 32-bit state before the sysregs, thanks
+	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+	 *
+	 * Also, and in order to be able to deal with erratum #1319537 (A57)
+	 * and #1319367 (A72), we must ensure that all VM-related sysreg are
+	 * restored before we enable S2 translation.
+	 */
+	__sysreg32_restore_state(vcpu);
+	__sysreg_restore_state_nvhe(guest_ctxt);
+
+	__activate_vm(kern_hyp_va(vcpu->kvm));
+	__activate_traps(vcpu);
+
+	__hyp_vgic_restore_state(vcpu);
+	__timer_enable_traps(vcpu);
+
+	__debug_switch_to_guest(vcpu);
+
+	__set_guest_arch_workaround_state(vcpu);
+
+	do {
+		/* Jump in the fire! */
+		exit_code = __guest_enter(vcpu, host_ctxt);
+
+		/* And we're baaack! */
+	} while (fixup_guest_exit(vcpu, &exit_code));
+
+	__set_host_arch_workaround_state(vcpu);
+
+	__sysreg_save_state_nvhe(guest_ctxt);
+	__sysreg32_save_state(vcpu);
+	__timer_disable_traps(vcpu);
+	__hyp_vgic_save_state(vcpu);
+
+	__deactivate_traps(vcpu);
+	__deactivate_vm(vcpu);
+
+	__sysreg_restore_state_nvhe(host_ctxt);
+
+	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
+		__fpsimd_save_fpexc32(vcpu);
+
+	/*
+	 * This must come after restoring the host sysregs, since a non-VHE
+	 * system may enable SPE here and make use of the TTBRs.
+	 */
+	__debug_switch_to_host(vcpu);
+
+	if (pmu_switch_needed)
+		__pmu_switch_to_host(host_ctxt);
+
+	/* Returning to host will clear PSR.I, remask PMR if needed */
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQOFF);
+
+	return exit_code;
+}
+
+void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
+{
+	u64 spsr = read_sysreg_el2(SYS_SPSR);
+	u64 elr = read_sysreg_el2(SYS_ELR);
+	u64 par = read_sysreg(par_el1);
+	struct kvm_vcpu *vcpu = host_ctxt->__hyp_running_vcpu;
+	unsigned long str_va;
+
+	if (read_sysreg(vttbr_el2)) {
+		__timer_disable_traps(vcpu);
+		__deactivate_traps(vcpu);
+		__deactivate_vm(vcpu);
+		__sysreg_restore_state_nvhe(host_ctxt);
+	}
+
+	/*
+	 * Force the panic string to be loaded from the literal pool,
+	 * making sure it is a kernel address and not a PC-relative
+	 * reference.
+	 */
+	asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string));
+
+	__hyp_do_panic(str_va,
+		       spsr, elr,
+		       read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR),
+		       read_sysreg(hpfar_el2), par, vcpu);
+	unreachable();
+}
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
deleted file mode 100644
index 9270b14157b5..000000000000
--- a/arch/arm64/kvm/hyp/switch.c
+++ /dev/null
@@ -1,936 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2015 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- */
-
-#include <linux/arm-smccc.h>
-#include <linux/kvm_host.h>
-#include <linux/types.h>
-#include <linux/jump_label.h>
-#include <uapi/linux/psci.h>
-
-#include <kvm/arm_psci.h>
-
-#include <asm/barrier.h>
-#include <asm/cpufeature.h>
-#include <asm/kprobes.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_hyp.h>
-#include <asm/kvm_mmu.h>
-#include <asm/fpsimd.h>
-#include <asm/debug-monitors.h>
-#include <asm/processor.h>
-#include <asm/thread_info.h>
-
-/* Check whether the FP regs were dirtied while in the host-side run loop: */
-static bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * When the system doesn't support FP/SIMD, we cannot rely on
-	 * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an
-	 * abort on the very first access to FP and thus we should never
-	 * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always
-	 * trap the accesses.
-	 */
-	if (!system_supports_fpsimd() ||
-	    vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
-		vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
-				      KVM_ARM64_FP_HOST);
-
-	return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED);
-}
-
-/* Save the 32-bit only FPSIMD system register state */
-static void __hyp_text __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
-{
-	if (!vcpu_el1_is_32bit(vcpu))
-		return;
-
-	vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
-}
-
-static void __hyp_text __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * We are about to set CPTR_EL2.TFP to trap all floating point
-	 * register accesses to EL2, however, the ARM ARM clearly states that
-	 * traps are only taken to EL2 if the operation would not otherwise
-	 * trap to EL1.  Therefore, always make sure that for 32-bit guests,
-	 * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
-	 * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to
-	 * it will cause an exception.
-	 */
-	if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) {
-		write_sysreg(1 << 30, fpexc32_el2);
-		isb();
-	}
-}
-
-static void __hyp_text __activate_traps_common(struct kvm_vcpu *vcpu)
-{
-	/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
-	write_sysreg(1 << 15, hstr_el2);
-
-	/*
-	 * Make sure we trap PMU access from EL0 to EL2. Also sanitize
-	 * PMSELR_EL0 to make sure it never contains the cycle
-	 * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
-	 * EL1 instead of being trapped to EL2.
-	 */
-	write_sysreg(0, pmselr_el0);
-	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
-	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
-}
-
-static void __hyp_text __deactivate_traps_common(void)
-{
-	write_sysreg(0, hstr_el2);
-	write_sysreg(0, pmuserenr_el0);
-}
-
-static void activate_traps_vhe(struct kvm_vcpu *vcpu)
-{
-	u64 val;
-
-	val = read_sysreg(cpacr_el1);
-	val |= CPACR_EL1_TTA;
-	val &= ~CPACR_EL1_ZEN;
-
-	/*
-	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
-	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
-	 * except for some missing controls, such as TAM.
-	 * In this case, CPTR_EL2.TAM has the same position with or without
-	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
-	 * shift value for trapping the AMU accesses.
-	 */
-
-	val |= CPTR_EL2_TAM;
-
-	if (update_fp_enabled(vcpu)) {
-		if (vcpu_has_sve(vcpu))
-			val |= CPACR_EL1_ZEN;
-	} else {
-		val &= ~CPACR_EL1_FPEN;
-		__activate_traps_fpsimd32(vcpu);
-	}
-
-	write_sysreg(val, cpacr_el1);
-
-	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
-}
-NOKPROBE_SYMBOL(activate_traps_vhe);
-
-static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
-{
-	u64 val;
-
-	__activate_traps_common(vcpu);
-
-	val = CPTR_EL2_DEFAULT;
-	val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM;
-	if (!update_fp_enabled(vcpu)) {
-		val |= CPTR_EL2_TFP;
-		__activate_traps_fpsimd32(vcpu);
-	}
-
-	write_sysreg(val, cptr_el2);
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
-
-		isb();
-		/*
-		 * At this stage, and thanks to the above isb(), S2 is
-		 * configured and enabled. We can now restore the guest's S1
-		 * configuration: SCTLR, and only then TCR.
-		 */
-		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
-		isb();
-		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
-	}
-}
-
-static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
-{
-	u64 hcr = vcpu->arch.hcr_el2;
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
-		hcr |= HCR_TVM;
-
-	write_sysreg(hcr, hcr_el2);
-
-	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
-		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
-
-	if (has_vhe())
-		activate_traps_vhe(vcpu);
-	else
-		__activate_traps_nvhe(vcpu);
-}
-
-static void deactivate_traps_vhe(void)
-{
-	extern char vectors[];	/* kernel exception vectors */
-	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
-
-	/*
-	 * ARM errata 1165522 and 1530923 require the actual execution of the
-	 * above before we can switch to the EL2/EL0 translation regime used by
-	 * the host.
-	 */
-	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
-
-	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
-	write_sysreg(vectors, vbar_el1);
-}
-NOKPROBE_SYMBOL(deactivate_traps_vhe);
-
-static void __hyp_text __deactivate_traps_nvhe(void)
-{
-	u64 mdcr_el2 = read_sysreg(mdcr_el2);
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		u64 val;
-
-		/*
-		 * Set the TCR and SCTLR registers in the exact opposite
-		 * sequence as __activate_traps_nvhe (first prevent walks,
-		 * then force the MMU on). A generous sprinkling of isb()
-		 * ensure that things happen in this exact order.
-		 */
-		val = read_sysreg_el1(SYS_TCR);
-		write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR);
-		isb();
-		val = read_sysreg_el1(SYS_SCTLR);
-		write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR);
-		isb();
-	}
-
-	__deactivate_traps_common();
-
-	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
-	mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
-
-	write_sysreg(mdcr_el2, mdcr_el2);
-	write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
-	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
-}
-
-static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * If we pended a virtual abort, preserve it until it gets
-	 * cleared. See D1.14.3 (Virtual Interrupts) for details, but
-	 * the crucial bit is "On taking a vSError interrupt,
-	 * HCR_EL2.VSE is cleared to 0."
-	 */
-	if (vcpu->arch.hcr_el2 & HCR_VSE) {
-		vcpu->arch.hcr_el2 &= ~HCR_VSE;
-		vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
-	}
-
-	if (has_vhe())
-		deactivate_traps_vhe();
-	else
-		__deactivate_traps_nvhe();
-}
-
-void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
-{
-	__activate_traps_common(vcpu);
-}
-
-void deactivate_traps_vhe_put(void)
-{
-	u64 mdcr_el2 = read_sysreg(mdcr_el2);
-
-	mdcr_el2 &= MDCR_EL2_HPMN_MASK |
-		    MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
-		    MDCR_EL2_TPMS;
-
-	write_sysreg(mdcr_el2, mdcr_el2);
-
-	__deactivate_traps_common();
-}
-
-static void __hyp_text __activate_vm(struct kvm *kvm)
-{
-	__load_guest_stage2(kvm);
-}
-
-static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
-{
-	write_sysreg(0, vttbr_el2);
-}
-
-/* Save VGICv3 state on non-VHE systems */
-static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
-{
-	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
-		__vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
-		__vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
-	}
-}
-
-/* Restore VGICv3 state on non_VEH systems */
-static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
-{
-	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
-		__vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
-		__vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3);
-	}
-}
-
-static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
-{
-	u64 par, tmp;
-
-	/*
-	 * Resolve the IPA the hard way using the guest VA.
-	 *
-	 * Stage-1 translation already validated the memory access
-	 * rights. As such, we can use the EL1 translation regime, and
-	 * don't have to distinguish between EL0 and EL1 access.
-	 *
-	 * We do need to save/restore PAR_EL1 though, as we haven't
-	 * saved the guest context yet, and we may return early...
-	 */
-	par = read_sysreg(par_el1);
-	asm volatile("at s1e1r, %0" : : "r" (far));
-	isb();
-
-	tmp = read_sysreg(par_el1);
-	write_sysreg(par, par_el1);
-
-	if (unlikely(tmp & SYS_PAR_EL1_F))
-		return false; /* Translation failed, back to guest */
-
-	/* Convert PAR to HPFAR format */
-	*hpfar = PAR_TO_HPFAR(tmp);
-	return true;
-}
-
-static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
-{
-	u8 ec;
-	u64 esr;
-	u64 hpfar, far;
-
-	esr = vcpu->arch.fault.esr_el2;
-	ec = ESR_ELx_EC(esr);
-
-	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
-		return true;
-
-	far = read_sysreg_el2(SYS_FAR);
-
-	/*
-	 * The HPFAR can be invalid if the stage 2 fault did not
-	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
-	 * bit is clear) and one of the two following cases are true:
-	 *   1. The fault was due to a permission fault
-	 *   2. The processor carries errata 834220
-	 *
-	 * Therefore, for all non S1PTW faults where we either have a
-	 * permission fault or the errata workaround is enabled, we
-	 * resolve the IPA using the AT instruction.
-	 */
-	if (!(esr & ESR_ELx_S1PTW) &&
-	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
-	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
-		if (!__translate_far_to_hpfar(far, &hpfar))
-			return false;
-	} else {
-		hpfar = read_sysreg(hpfar_el2);
-	}
-
-	vcpu->arch.fault.far_el2 = far;
-	vcpu->arch.fault.hpfar_el2 = hpfar;
-	return true;
-}
-
-/* Check for an FPSIMD/SVE trap and handle as appropriate */
-static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
-{
-	bool vhe, sve_guest, sve_host;
-	u8 hsr_ec;
-
-	if (!system_supports_fpsimd())
-		return false;
-
-	if (system_supports_sve()) {
-		sve_guest = vcpu_has_sve(vcpu);
-		sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE;
-		vhe = true;
-	} else {
-		sve_guest = false;
-		sve_host = false;
-		vhe = has_vhe();
-	}
-
-	hsr_ec = kvm_vcpu_trap_get_class(vcpu);
-	if (hsr_ec != ESR_ELx_EC_FP_ASIMD &&
-	    hsr_ec != ESR_ELx_EC_SVE)
-		return false;
-
-	/* Don't handle SVE traps for non-SVE vcpus here: */
-	if (!sve_guest)
-		if (hsr_ec != ESR_ELx_EC_FP_ASIMD)
-			return false;
-
-	/* Valid trap.  Switch the context: */
-
-	if (vhe) {
-		u64 reg = read_sysreg(cpacr_el1) | CPACR_EL1_FPEN;
-
-		if (sve_guest)
-			reg |= CPACR_EL1_ZEN;
-
-		write_sysreg(reg, cpacr_el1);
-	} else {
-		write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP,
-			     cptr_el2);
-	}
-
-	isb();
-
-	if (vcpu->arch.flags & KVM_ARM64_FP_HOST) {
-		/*
-		 * In the SVE case, VHE is assumed: it is enforced by
-		 * Kconfig and kvm_arch_init().
-		 */
-		if (sve_host) {
-			struct thread_struct *thread = container_of(
-				vcpu->arch.host_fpsimd_state,
-				struct thread_struct, uw.fpsimd_state);
-
-			sve_save_state(sve_pffr(thread),
-				       &vcpu->arch.host_fpsimd_state->fpsr);
-		} else {
-			__fpsimd_save_state(vcpu->arch.host_fpsimd_state);
-		}
-
-		vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
-	}
-
-	if (sve_guest) {
-		sve_load_state(vcpu_sve_pffr(vcpu),
-			       &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
-			       sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
-		write_sysreg_s(vcpu->arch.ctxt.sys_regs[ZCR_EL1], SYS_ZCR_EL12);
-	} else {
-		__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
-	}
-
-	/* Skip restoring fpexc32 for AArch64 guests */
-	if (!(read_sysreg(hcr_el2) & HCR_RW))
-		write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2],
-			     fpexc32_el2);
-
-	vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;
-
-	return true;
-}
-
-static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
-{
-	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
-	int rt = kvm_vcpu_sys_get_rt(vcpu);
-	u64 val = vcpu_get_reg(vcpu, rt);
-
-	/*
-	 * The normal sysreg handling code expects to see the traps,
-	 * let's not do anything here.
-	 */
-	if (vcpu->arch.hcr_el2 & HCR_TVM)
-		return false;
-
-	switch (sysreg) {
-	case SYS_SCTLR_EL1:
-		write_sysreg_el1(val, SYS_SCTLR);
-		break;
-	case SYS_TTBR0_EL1:
-		write_sysreg_el1(val, SYS_TTBR0);
-		break;
-	case SYS_TTBR1_EL1:
-		write_sysreg_el1(val, SYS_TTBR1);
-		break;
-	case SYS_TCR_EL1:
-		write_sysreg_el1(val, SYS_TCR);
-		break;
-	case SYS_ESR_EL1:
-		write_sysreg_el1(val, SYS_ESR);
-		break;
-	case SYS_FAR_EL1:
-		write_sysreg_el1(val, SYS_FAR);
-		break;
-	case SYS_AFSR0_EL1:
-		write_sysreg_el1(val, SYS_AFSR0);
-		break;
-	case SYS_AFSR1_EL1:
-		write_sysreg_el1(val, SYS_AFSR1);
-		break;
-	case SYS_MAIR_EL1:
-		write_sysreg_el1(val, SYS_MAIR);
-		break;
-	case SYS_AMAIR_EL1:
-		write_sysreg_el1(val, SYS_AMAIR);
-		break;
-	case SYS_CONTEXTIDR_EL1:
-		write_sysreg_el1(val, SYS_CONTEXTIDR);
-		break;
-	default:
-		return false;
-	}
-
-	__kvm_skip_instr(vcpu);
-	return true;
-}
-
-static bool __hyp_text esr_is_ptrauth_trap(u32 esr)
-{
-	u32 ec = ESR_ELx_EC(esr);
-
-	if (ec == ESR_ELx_EC_PAC)
-		return true;
-
-	if (ec != ESR_ELx_EC_SYS64)
-		return false;
-
-	switch (esr_sys64_to_sysreg(esr)) {
-	case SYS_APIAKEYLO_EL1:
-	case SYS_APIAKEYHI_EL1:
-	case SYS_APIBKEYLO_EL1:
-	case SYS_APIBKEYHI_EL1:
-	case SYS_APDAKEYLO_EL1:
-	case SYS_APDAKEYHI_EL1:
-	case SYS_APDBKEYLO_EL1:
-	case SYS_APDBKEYHI_EL1:
-	case SYS_APGAKEYLO_EL1:
-	case SYS_APGAKEYHI_EL1:
-		return true;
-	}
-
-	return false;
-}
-
-#define __ptrauth_save_key(regs, key)						\
-({										\
-	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
-	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
-})
-
-static bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *ctxt;
-	u64 val;
-
-	if (!vcpu_has_ptrauth(vcpu) ||
-	    !esr_is_ptrauth_trap(kvm_vcpu_get_hsr(vcpu)))
-		return false;
-
-	ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	__ptrauth_save_key(ctxt->sys_regs, APIA);
-	__ptrauth_save_key(ctxt->sys_regs, APIB);
-	__ptrauth_save_key(ctxt->sys_regs, APDA);
-	__ptrauth_save_key(ctxt->sys_regs, APDB);
-	__ptrauth_save_key(ctxt->sys_regs, APGA);
-
-	vcpu_ptrauth_enable(vcpu);
-
-	val = read_sysreg(hcr_el2);
-	val |= (HCR_API | HCR_APK);
-	write_sysreg(val, hcr_el2);
-
-	return true;
-}
-
-/*
- * Return true when we were able to fixup the guest exit and should return to
- * the guest, false when we should restore the host state and return to the
- * main run loop.
- */
-static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
-{
-	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
-		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
-
-	/*
-	 * We're using the raw exception code in order to only process
-	 * the trap if no SError is pending. We will come back to the
-	 * same PC once the SError has been injected, and replay the
-	 * trapping instruction.
-	 */
-	if (*exit_code != ARM_EXCEPTION_TRAP)
-		goto exit;
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
-	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
-	    handle_tx2_tvm(vcpu))
-		return true;
-
-	/*
-	 * We trap the first access to the FP/SIMD to save the host context
-	 * and restore the guest context lazily.
-	 * If FP/SIMD is not implemented, handle the trap and inject an
-	 * undefined instruction exception to the guest.
-	 * Similarly for trapped SVE accesses.
-	 */
-	if (__hyp_handle_fpsimd(vcpu))
-		return true;
-
-	if (__hyp_handle_ptrauth(vcpu))
-		return true;
-
-	if (!__populate_fault_info(vcpu))
-		return true;
-
-	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
-		bool valid;
-
-		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
-			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
-			kvm_vcpu_dabt_isvalid(vcpu) &&
-			!kvm_vcpu_dabt_isextabt(vcpu) &&
-			!kvm_vcpu_dabt_iss1tw(vcpu);
-
-		if (valid) {
-			int ret = __vgic_v2_perform_cpuif_access(vcpu);
-
-			if (ret == 1)
-				return true;
-
-			/* Promote an illegal access to an SError.*/
-			if (ret == -1)
-				*exit_code = ARM_EXCEPTION_EL1_SERROR;
-
-			goto exit;
-		}
-	}
-
-	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
-	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
-	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
-		int ret = __vgic_v3_perform_cpuif_access(vcpu);
-
-		if (ret == 1)
-			return true;
-	}
-
-exit:
-	/* Return to the host kernel and handle the exit */
-	return false;
-}
-
-static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
-{
-	if (!cpus_have_final_cap(ARM64_SSBD))
-		return false;
-
-	return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
-}
-
-static void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
-{
-#ifdef CONFIG_ARM64_SSBD
-	/*
-	 * The host runs with the workaround always present. If the
-	 * guest wants it disabled, so be it...
-	 */
-	if (__needs_ssbd_off(vcpu) &&
-	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL);
-#endif
-}
-
-static void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
-{
-#ifdef CONFIG_ARM64_SSBD
-	/*
-	 * If the guest has disabled the workaround, bring it back on.
-	 */
-	if (__needs_ssbd_off(vcpu) &&
-	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
-		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL);
-#endif
-}
-
-/**
- * Disable host events, enable guest events
- */
-static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
-{
-	struct kvm_host_data *host;
-	struct kvm_pmu_events *pmu;
-
-	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
-	pmu = &host->pmu_events;
-
-	if (pmu->events_host)
-		write_sysreg(pmu->events_host, pmcntenclr_el0);
-
-	if (pmu->events_guest)
-		write_sysreg(pmu->events_guest, pmcntenset_el0);
-
-	return (pmu->events_host || pmu->events_guest);
-}
-
-/**
- * Disable guest events, enable host events
- */
-static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
-{
-	struct kvm_host_data *host;
-	struct kvm_pmu_events *pmu;
-
-	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
-	pmu = &host->pmu_events;
-
-	if (pmu->events_guest)
-		write_sysreg(pmu->events_guest, pmcntenclr_el0);
-
-	if (pmu->events_host)
-		write_sysreg(pmu->events_host, pmcntenset_el0);
-}
-
-/* Switch to the guest for VHE systems running in EL2 */
-static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *host_ctxt;
-	struct kvm_cpu_context *guest_ctxt;
-	u64 exit_code;
-
-	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	host_ctxt->__hyp_running_vcpu = vcpu;
-	guest_ctxt = &vcpu->arch.ctxt;
-
-	sysreg_save_host_state_vhe(host_ctxt);
-
-	/*
-	 * ARM erratum 1165522 requires us to configure both stage 1 and
-	 * stage 2 translation for the guest context before we clear
-	 * HCR_EL2.TGE.
-	 *
-	 * We have already configured the guest's stage 1 translation in
-	 * kvm_vcpu_load_sysregs above.  We must now call __activate_vm
-	 * before __activate_traps, because __activate_vm configures
-	 * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
-	 * (among other things).
-	 */
-	__activate_vm(vcpu->kvm);
-	__activate_traps(vcpu);
-
-	sysreg_restore_guest_state_vhe(guest_ctxt);
-	__debug_switch_to_guest(vcpu);
-
-	__set_guest_arch_workaround_state(vcpu);
-
-	do {
-		/* Jump in the fire! */
-		exit_code = __guest_enter(vcpu, host_ctxt);
-
-		/* And we're baaack! */
-	} while (fixup_guest_exit(vcpu, &exit_code));
-
-	__set_host_arch_workaround_state(vcpu);
-
-	sysreg_save_guest_state_vhe(guest_ctxt);
-
-	__deactivate_traps(vcpu);
-
-	sysreg_restore_host_state_vhe(host_ctxt);
-
-	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
-		__fpsimd_save_fpexc32(vcpu);
-
-	__debug_switch_to_host(vcpu);
-
-	return exit_code;
-}
-NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe);
-
-int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
-{
-	int ret;
-
-	local_daif_mask();
-
-	/*
-	 * Having IRQs masked via PMR when entering the guest means the GIC
-	 * will not signal the CPU of interrupts of lower priority, and the
-	 * only way to get out will be via guest exceptions.
-	 * Naturally, we want to avoid this.
-	 *
-	 * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
-	 * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
-	 */
-	pmr_sync();
-
-	ret = __kvm_vcpu_run_vhe(vcpu);
-
-	/*
-	 * local_daif_restore() takes care to properly restore PSTATE.DAIF
-	 * and the GIC PMR if the host is using IRQ priorities.
-	 */
-	local_daif_restore(DAIF_PROCCTX_NOIRQ);
-
-	/*
-	 * When we exit from the guest we change a number of CPU configuration
-	 * parameters, such as traps.  Make sure these changes take effect
-	 * before running the host or additional guests.
-	 */
-	isb();
-
-	return ret;
-}
-
-/* Switch to the guest for legacy non-VHE systems */
-int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *host_ctxt;
-	struct kvm_cpu_context *guest_ctxt;
-	bool pmu_switch_needed;
-	u64 exit_code;
-
-	/*
-	 * Having IRQs masked via PMR when entering the guest means the GIC
-	 * will not signal the CPU of interrupts of lower priority, and the
-	 * only way to get out will be via guest exceptions.
-	 * Naturally, we want to avoid this.
-	 */
-	if (system_uses_irq_prio_masking()) {
-		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
-		pmr_sync();
-	}
-
-	vcpu = kern_hyp_va(vcpu);
-
-	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	host_ctxt->__hyp_running_vcpu = vcpu;
-	guest_ctxt = &vcpu->arch.ctxt;
-
-	pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
-
-	__sysreg_save_state_nvhe(host_ctxt);
-
-	/*
-	 * We must restore the 32-bit state before the sysregs, thanks
-	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
-	 *
-	 * Also, and in order to be able to deal with erratum #1319537 (A57)
-	 * and #1319367 (A72), we must ensure that all VM-related sysreg are
-	 * restored before we enable S2 translation.
-	 */
-	__sysreg32_restore_state(vcpu);
-	__sysreg_restore_state_nvhe(guest_ctxt);
-
-	__activate_vm(kern_hyp_va(vcpu->kvm));
-	__activate_traps(vcpu);
-
-	__hyp_vgic_restore_state(vcpu);
-	__timer_enable_traps(vcpu);
-
-	__debug_switch_to_guest(vcpu);
-
-	__set_guest_arch_workaround_state(vcpu);
-
-	do {
-		/* Jump in the fire! */
-		exit_code = __guest_enter(vcpu, host_ctxt);
-
-		/* And we're baaack! */
-	} while (fixup_guest_exit(vcpu, &exit_code));
-
-	__set_host_arch_workaround_state(vcpu);
-
-	__sysreg_save_state_nvhe(guest_ctxt);
-	__sysreg32_save_state(vcpu);
-	__timer_disable_traps(vcpu);
-	__hyp_vgic_save_state(vcpu);
-
-	__deactivate_traps(vcpu);
-	__deactivate_vm(vcpu);
-
-	__sysreg_restore_state_nvhe(host_ctxt);
-
-	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
-		__fpsimd_save_fpexc32(vcpu);
-
-	/*
-	 * This must come after restoring the host sysregs, since a non-VHE
-	 * system may enable SPE here and make use of the TTBRs.
-	 */
-	__debug_switch_to_host(vcpu);
-
-	if (pmu_switch_needed)
-		__pmu_switch_to_host(host_ctxt);
-
-	/* Returning to host will clear PSR.I, remask PMR if needed */
-	if (system_uses_irq_prio_masking())
-		gic_write_pmr(GIC_PRIO_IRQOFF);
-
-	return exit_code;
-}
-
-static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
-
-static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
-					     struct kvm_cpu_context *__host_ctxt)
-{
-	struct kvm_vcpu *vcpu;
-	unsigned long str_va;
-
-	vcpu = __host_ctxt->__hyp_running_vcpu;
-
-	if (read_sysreg(vttbr_el2)) {
-		__timer_disable_traps(vcpu);
-		__deactivate_traps(vcpu);
-		__deactivate_vm(vcpu);
-		__sysreg_restore_state_nvhe(__host_ctxt);
-	}
-
-	/*
-	 * Force the panic string to be loaded from the literal pool,
-	 * making sure it is a kernel address and not a PC-relative
-	 * reference.
-	 */
-	asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string));
-
-	__hyp_do_panic(str_va,
-		       spsr, elr,
-		       read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR),
-		       read_sysreg(hpfar_el2), par, vcpu);
-}
-
-static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par,
-				 struct kvm_cpu_context *host_ctxt)
-{
-	struct kvm_vcpu *vcpu;
-	vcpu = host_ctxt->__hyp_running_vcpu;
-
-	__deactivate_traps(vcpu);
-	sysreg_restore_host_state_vhe(host_ctxt);
-
-	panic(__hyp_panic_string,
-	      spsr,  elr,
-	      read_sysreg_el2(SYS_ESR),   read_sysreg_el2(SYS_FAR),
-	      read_sysreg(hpfar_el2), par, vcpu);
-}
-NOKPROBE_SYMBOL(__hyp_call_panic_vhe);
-
-void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
-{
-	u64 spsr = read_sysreg_el2(SYS_SPSR);
-	u64 elr = read_sysreg_el2(SYS_ELR);
-	u64 par = read_sysreg(par_el1);
-
-	if (!has_vhe())
-		__hyp_call_panic_nvhe(spsr, elr, par, host_ctxt);
-	else
-		__hyp_call_panic_vhe(spsr, elr, par, host_ctxt);
-
-	unreachable();
-}
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index cc7e957f5b2c..2493439a5c54 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -114,7 +114,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 		/*
 		 * Must only be done for guest registers, hence the context
 		 * test. We're coming from the host, so SCTLR.M is already
-		 * set. Pairs with __activate_traps_nvhe().
+		 * set. Pairs with nVHE's __activate_traps().
 		 */
 		write_sysreg_el1((ctxt->sys_regs[TCR_EL1] |
 				  TCR_EPD1_MASK | TCR_EPD0_MASK),
@@ -142,7 +142,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	    ctxt->__hyp_running_vcpu) {
 		/*
 		 * Must only be done for host registers, hence the context
-		 * test. Pairs with __deactivate_traps_nvhe().
+		 * test. Pairs with nVHE's __deactivate_traps().
 		 */
 		isb();
 		/*
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 704140fc5d66..9f71cd3ba50d 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y := tlb.o ../hyp-entry.o
+obj-y := switch.o tlb.o ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
new file mode 100644
index 000000000000..e8d76cab44e4
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/switch.h>
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
+
+static void __activate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	___activate_traps(vcpu);
+
+	val = read_sysreg(cpacr_el1);
+	val |= CPACR_EL1_TTA;
+	val &= ~CPACR_EL1_ZEN;
+
+	/*
+	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
+	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
+	 * except for some missing controls, such as TAM.
+	 * In this case, CPTR_EL2.TAM has the same position with or without
+	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
+	 * shift value for trapping the AMU accesses.
+	 */
+
+	val |= CPTR_EL2_TAM;
+
+	if (update_fp_enabled(vcpu)) {
+		if (vcpu_has_sve(vcpu))
+			val |= CPACR_EL1_ZEN;
+	} else {
+		val &= ~CPACR_EL1_FPEN;
+		__activate_traps_fpsimd32(vcpu);
+	}
+
+	write_sysreg(val, cpacr_el1);
+
+	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
+}
+NOKPROBE_SYMBOL(__activate_traps);
+
+static void __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	extern char vectors[];	/* kernel exception vectors */
+
+	___deactivate_traps(vcpu);
+
+	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+
+	/*
+	 * ARM errata 1165522 and 1530923 require the actual execution of the
+	 * above before we can switch to the EL2/EL0 translation regime used by
+	 * the host.
+	 */
+	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
+
+	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
+	write_sysreg(vectors, vbar_el1);
+}
+NOKPROBE_SYMBOL(__deactivate_traps);
+
+void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
+{
+	__activate_traps_common(vcpu);
+}
+
+void deactivate_traps_vhe_put(void)
+{
+	u64 mdcr_el2 = read_sysreg(mdcr_el2);
+
+	mdcr_el2 &= MDCR_EL2_HPMN_MASK |
+		    MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
+		    MDCR_EL2_TPMS;
+
+	write_sysreg(mdcr_el2, mdcr_el2);
+
+	__deactivate_traps_common();
+}
+
+/* Switch to the guest for VHE systems running in EL2 */
+static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	u64 exit_code;
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	host_ctxt->__hyp_running_vcpu = vcpu;
+	guest_ctxt = &vcpu->arch.ctxt;
+
+	sysreg_save_host_state_vhe(host_ctxt);
+
+	/*
+	 * ARM erratum 1165522 requires us to configure both stage 1 and
+	 * stage 2 translation for the guest context before we clear
+	 * HCR_EL2.TGE.
+	 *
+	 * We have already configured the guest's stage 1 translation in
+	 * kvm_vcpu_load_sysregs above.  We must now call __activate_vm
+	 * before __activate_traps, because __activate_vm configures
+	 * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
+	 * (among other things).
+	 */
+	__activate_vm(vcpu->kvm);
+	__activate_traps(vcpu);
+
+	sysreg_restore_guest_state_vhe(guest_ctxt);
+	__debug_switch_to_guest(vcpu);
+
+	__set_guest_arch_workaround_state(vcpu);
+
+	do {
+		/* Jump in the fire! */
+		exit_code = __guest_enter(vcpu, host_ctxt);
+
+		/* And we're baaack! */
+	} while (fixup_guest_exit(vcpu, &exit_code));
+
+	__set_host_arch_workaround_state(vcpu);
+
+	sysreg_save_guest_state_vhe(guest_ctxt);
+
+	__deactivate_traps(vcpu);
+
+	sysreg_restore_host_state_vhe(host_ctxt);
+
+	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
+		__fpsimd_save_fpexc32(vcpu);
+
+	__debug_switch_to_host(vcpu);
+
+	return exit_code;
+}
+NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe);
+
+int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	local_daif_mask();
+
+	/*
+	 * Having IRQs masked via PMR when entering the guest means the GIC
+	 * will not signal the CPU of interrupts of lower priority, and the
+	 * only way to get out will be via guest exceptions.
+	 * Naturally, we want to avoid this.
+	 *
+	 * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
+	 * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
+	 */
+	pmr_sync();
+
+	ret = __kvm_vcpu_run_vhe(vcpu);
+
+	/*
+	 * local_daif_restore() takes care to properly restore PSTATE.DAIF
+	 * and the GIC PMR if the host is using IRQ priorities.
+	 */
+	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+
+	/*
+	 * When we exit from the guest we change a number of CPU configuration
+	 * parameters, such as traps.  Make sure these changes take effect
+	 * before running the host or additional guests.
+	 */
+	isb();
+
+	return ret;
+}
+
+static void __hyp_call_panic(u64 spsr, u64 elr, u64 par,
+			     struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_vcpu *vcpu;
+	vcpu = host_ctxt->__hyp_running_vcpu;
+
+	__deactivate_traps(vcpu);
+	sysreg_restore_host_state_vhe(host_ctxt);
+
+	panic(__hyp_panic_string,
+	      spsr, elr,
+	      read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR),
+	      read_sysreg(hpfar_el2), par, vcpu);
+}
+NOKPROBE_SYMBOL(__hyp_call_panic);
+
+void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
+{
+	u64 spsr = read_sysreg_el2(SYS_SPSR);
+	u64 elr = read_sysreg_el2(SYS_ELR);
+	u64 par = read_sysreg(par_el1);
+
+	__hyp_call_panic(spsr, elr, par, host_ctxt);
+	unreachable();
+}

From d400c5b2025c9aeca76213d6bd4138ec39da5cef Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:15 +0100
Subject: [PATCH 030/474] KVM: arm64: Split hyp/debug-sr.c to VHE/nVHE

debug-sr.c contains KVM's code for context-switching debug registers, with some
code shared between VHE/nVHE. These common routines are moved to a header file,
VHE-specific code is moved to vhe/debug-sr.c and nVHE-specific code to
nvhe/debug-sr.c.

Functions are slightly refactored to move code hidden behind `has_vhe()` checks
to the corresponding .c files.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-11-dbrazdil@google.com
---
 arch/arm64/kernel/image-vars.h                |  5 --
 arch/arm64/kvm/hyp/Makefile                   |  2 +-
 .../{debug-sr.c => include/hyp/debug-sr.h}    | 78 +++----------------
 arch/arm64/kvm/hyp/nvhe/Makefile              |  2 +-
 arch/arm64/kvm/hyp/nvhe/debug-sr.c            | 77 ++++++++++++++++++
 arch/arm64/kvm/hyp/vhe/Makefile               |  2 +-
 arch/arm64/kvm/hyp/vhe/debug-sr.c             | 26 +++++++
 7 files changed, 118 insertions(+), 74 deletions(-)
 rename arch/arm64/kvm/hyp/{debug-sr.c => include/hyp/debug-sr.h} (71%)
 create mode 100644 arch/arm64/kvm/hyp/nvhe/debug-sr.c
 create mode 100644 arch/arm64/kvm/hyp/vhe/debug-sr.c

diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 06fe9833104a..c44ca4e7dd66 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -66,11 +66,6 @@ __efistub__ctype		= _ctype;
 /* Symbols defined in aarch32.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(kvm_skip_instr32);
 
-/* Symbols defined in debug-sr.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__debug_switch_to_guest);
-KVM_NVHE_ALIAS(__debug_switch_to_host);
-KVM_NVHE_ALIAS(__kvm_get_mdcr_el2);
-
 /* Symbols defined in entry.S (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__guest_enter);
 KVM_NVHE_ALIAS(__guest_exit);
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 7462d3a8a6f2..fc09025d2e97 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
 hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
-	 debug-sr.o entry.o fpsimd.o
+	 entry.o fpsimd.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
similarity index 71%
rename from arch/arm64/kvm/hyp/debug-sr.c
rename to arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index e95af204fec7..e041dbd23243 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -4,6 +4,9 @@
  * Author: Marc Zyngier <marc.zyngier@arm.com>
  */
 
+#ifndef __ARM64_KVM_HYP_DEBUG_SR_H__
+#define __ARM64_KVM_HYP_DEBUG_SR_H__
+
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 
@@ -85,53 +88,9 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
-static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
-{
-	u64 reg;
-
-	/* Clear pmscr in case of early return */
-	*pmscr_el1 = 0;
-
-	/* SPE present on this CPU? */
-	if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
-						  ID_AA64DFR0_PMSVER_SHIFT))
-		return;
-
-	/* Yes; is it owned by EL3? */
-	reg = read_sysreg_s(SYS_PMBIDR_EL1);
-	if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT))
-		return;
-
-	/* No; is the host actually using the thing? */
-	reg = read_sysreg_s(SYS_PMBLIMITR_EL1);
-	if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT)))
-		return;
-
-	/* Yes; save the control register and disable data generation */
-	*pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
-	write_sysreg_s(0, SYS_PMSCR_EL1);
-	isb();
-
-	/* Now drain all buffered data to memory */
-	psb_csync();
-	dsb(nsh);
-}
-
-static void __hyp_text __debug_restore_spe_nvhe(u64 pmscr_el1)
-{
-	if (!pmscr_el1)
-		return;
-
-	/* The host page table is installed, but not yet synchronised */
-	isb();
-
-	/* Re-enable data generation */
-	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
-}
-
-static void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
-					  struct kvm_guest_debug_arch *dbg,
-					  struct kvm_cpu_context *ctxt)
+static inline void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
+						 struct kvm_guest_debug_arch *dbg,
+						 struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -148,9 +107,9 @@ static void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
 	ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
 }
 
-static void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
-					     struct kvm_guest_debug_arch *dbg,
-					     struct kvm_cpu_context *ctxt)
+static inline void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
+						    struct kvm_guest_debug_arch *dbg,
+						    struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -168,20 +127,13 @@ static void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
 	write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
 }
 
-void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+static inline void __hyp_text __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
 	struct kvm_guest_debug_arch *host_dbg;
 	struct kvm_guest_debug_arch *guest_dbg;
 
-	/*
-	 * Non-VHE: Disable and flush SPE data generation
-	 * VHE: The vcpu can run, but it can't hide.
-	 */
-	if (!has_vhe())
-		__debug_save_spe_nvhe(&vcpu->arch.host_debug_state.pmscr_el1);
-
 	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
 		return;
 
@@ -194,16 +146,13 @@ void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
 	__debug_restore_state(vcpu, guest_dbg, guest_ctxt);
 }
 
-void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
+static inline void __hyp_text __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
 	struct kvm_guest_debug_arch *host_dbg;
 	struct kvm_guest_debug_arch *guest_dbg;
 
-	if (!has_vhe())
-		__debug_restore_spe_nvhe(vcpu->arch.host_debug_state.pmscr_el1);
-
 	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
 		return;
 
@@ -218,7 +167,4 @@ void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
 	vcpu->arch.flags &= ~KVM_ARM64_DEBUG_DIRTY;
 }
 
-u32 __hyp_text __kvm_get_mdcr_el2(void)
-{
-	return read_sysreg(mdcr_el2);
-}
+#endif /* __ARM64_KVM_HYP_DEBUG_SR_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 8b3ac38eaa44..b3cb67b63d67 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := switch.o tlb.o hyp-init.o ../hyp-entry.o
+obj-y := debug-sr.o switch.o tlb.o hyp-init.o ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
new file mode 100644
index 000000000000..828c0d48e790
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/debug-sr.h>
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/debug-monitors.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+
+static void __hyp_text __debug_save_spe(u64 *pmscr_el1)
+{
+	u64 reg;
+
+	/* Clear pmscr in case of early return */
+	*pmscr_el1 = 0;
+
+	/* SPE present on this CPU? */
+	if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
+						  ID_AA64DFR0_PMSVER_SHIFT))
+		return;
+
+	/* Yes; is it owned by EL3? */
+	reg = read_sysreg_s(SYS_PMBIDR_EL1);
+	if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT))
+		return;
+
+	/* No; is the host actually using the thing? */
+	reg = read_sysreg_s(SYS_PMBLIMITR_EL1);
+	if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT)))
+		return;
+
+	/* Yes; save the control register and disable data generation */
+	*pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
+	write_sysreg_s(0, SYS_PMSCR_EL1);
+	isb();
+
+	/* Now drain all buffered data to memory */
+	psb_csync();
+	dsb(nsh);
+}
+
+static void __hyp_text __debug_restore_spe(u64 pmscr_el1)
+{
+	if (!pmscr_el1)
+		return;
+
+	/* The host page table is installed, but not yet synchronised */
+	isb();
+
+	/* Re-enable data generation */
+	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
+}
+
+void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	/* Disable and flush SPE data generation */
+	__debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
+	__debug_switch_to_guest_common(vcpu);
+}
+
+void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
+{
+	__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
+	__debug_switch_to_host_common(vcpu);
+}
+
+u32 __hyp_text __kvm_get_mdcr_el2(void)
+{
+	return read_sysreg(mdcr_el2);
+}
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 9f71cd3ba50d..62bdaf272b03 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y := switch.o tlb.o ../hyp-entry.o
+obj-y := debug-sr.o switch.o tlb.o ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/vhe/debug-sr.c b/arch/arm64/kvm/hyp/vhe/debug-sr.c
new file mode 100644
index 000000000000..f1e2e5a00933
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/debug-sr.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/debug-sr.h>
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_hyp.h>
+
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	__debug_switch_to_guest_common(vcpu);
+}
+
+void __debug_switch_to_host(struct kvm_vcpu *vcpu)
+{
+	__debug_switch_to_host_common(vcpu);
+}
+
+u32 __kvm_get_mdcr_el2(void)
+{
+	return read_sysreg(mdcr_el2);
+}

From 13aeb9b400c5d7c5e979fdbbf994c787487f7889 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:16 +0100
Subject: [PATCH 031/474] KVM: arm64: Split hyp/sysreg-sr.c to VHE/nVHE

sysreg-sr.c contains KVM's code for saving/restoring system registers, with
some code shared between VHE/nVHE. These common routines are moved to
a header file, VHE-specific code is moved to vhe/sysreg-sr.c and nVHE-specific
code to nvhe/sysreg-sr.c.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-12-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_host.h             |   6 +-
 arch/arm64/include/asm/kvm_hyp.h              |   5 +-
 arch/arm64/kernel/image-vars.h                |   7 -
 arch/arm64/kvm/arm.c                          |   8 +-
 arch/arm64/kvm/hyp/Makefile                   |   4 +-
 .../{sysreg-sr.c => include/hyp/sysreg-sr.h}  | 158 ++----------------
 arch/arm64/kvm/hyp/nvhe/Makefile              |   2 +-
 arch/arm64/kvm/hyp/nvhe/switch.c              |   1 +
 arch/arm64/kvm/hyp/nvhe/sysreg-sr.c           |  46 +++++
 arch/arm64/kvm/hyp/vhe/Makefile               |   2 +-
 arch/arm64/kvm/hyp/vhe/switch.c               |   2 +-
 arch/arm64/kvm/hyp/vhe/sysreg-sr.c            | 114 +++++++++++++
 12 files changed, 191 insertions(+), 164 deletions(-)
 rename arch/arm64/kvm/hyp/{sysreg-sr.c => include/hyp/sysreg-sr.h} (56%)
 create mode 100644 arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
 create mode 100644 arch/arm64/kvm/hyp/vhe/sysreg-sr.c

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 49d1a5cd8f8f..e0920df1d0c1 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -338,7 +338,7 @@ struct kvm_vcpu_arch {
 	struct vcpu_reset_state	reset_state;
 
 	/* True when deferrable sysregs are loaded on the physical CPU,
-	 * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
+	 * see kvm_vcpu_load_sysregs_vhe and kvm_vcpu_put_sysregs_vhe. */
 	bool sysregs_loaded_on_cpu;
 
 	/* Guest PV state */
@@ -639,8 +639,8 @@ static inline int kvm_arm_have_ssbd(void)
 	}
 }
 
-void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
-void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);
+void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
+void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
 
 int kvm_set_ipa_limit(void);
 
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 82fa05d15b8b..997c5bda1ac7 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -66,14 +66,15 @@ int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu);
 void __timer_enable_traps(struct kvm_vcpu *vcpu);
 void __timer_disable_traps(struct kvm_vcpu *vcpu);
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt);
 void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt);
+#else
 void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt);
 void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt);
 void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt);
 void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt);
-void __sysreg32_save_state(struct kvm_vcpu *vcpu);
-void __sysreg32_restore_state(struct kvm_vcpu *vcpu);
+#endif
 
 void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
 void __debug_switch_to_host(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index c44ca4e7dd66..59eb55893eaf 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -76,13 +76,6 @@ KVM_NVHE_ALIAS(abort_guest_exit_start);
 KVM_NVHE_ALIAS(__fpsimd_restore_state);
 KVM_NVHE_ALIAS(__fpsimd_save_state);
 
-/* Symbols defined in sysreg-sr.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__kvm_enable_ssbs);
-KVM_NVHE_ALIAS(__sysreg32_restore_state);
-KVM_NVHE_ALIAS(__sysreg32_save_state);
-KVM_NVHE_ALIAS(__sysreg_restore_state_nvhe);
-KVM_NVHE_ALIAS(__sysreg_save_state_nvhe);
-
 /* Symbols defined in timer-sr.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__kvm_timer_set_cntvoff);
 KVM_NVHE_ALIAS(__timer_disable_traps);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 26780b78a523..0bf2cf5614c6 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -351,7 +351,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_vgic_load(vcpu);
 	kvm_timer_vcpu_load(vcpu);
-	kvm_vcpu_load_sysregs(vcpu);
+	if (has_vhe())
+		kvm_vcpu_load_sysregs_vhe(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
 	kvm_vcpu_pmu_restore_guest(vcpu);
 	if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
@@ -369,7 +370,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	kvm_arch_vcpu_put_fp(vcpu);
-	kvm_vcpu_put_sysregs(vcpu);
+	if (has_vhe())
+		kvm_vcpu_put_sysregs_vhe(vcpu);
 	kvm_timer_vcpu_put(vcpu);
 	kvm_vgic_put(vcpu);
 	kvm_vcpu_pmu_restore_host(vcpu);
@@ -1302,7 +1304,7 @@ static void cpu_init_hyp_mode(void)
 	 */
 	if (this_cpu_has_cap(ARM64_SSBS) &&
 	    arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
-		kvm_call_hyp(__kvm_enable_ssbs);
+		kvm_call_hyp_nvhe(__kvm_enable_ssbs);
 	}
 }
 
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index fc09025d2e97..f49797237818 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -13,8 +13,8 @@ subdir-ccflags-y := -I$(incdir)				\
 obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
-hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
-	 entry.o fpsimd.o
+hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o entry.o \
+	 fpsimd.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
similarity index 56%
rename from arch/arm64/kvm/hyp/sysreg-sr.c
rename to arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 2493439a5c54..3e0585fbd403 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -4,6 +4,9 @@
  * Author: Marc Zyngier <marc.zyngier@arm.com>
  */
 
+#ifndef __ARM64_KVM_HYP_SYSREG_SR_H__
+#define __ARM64_KVM_HYP_SYSREG_SR_H__
+
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 
@@ -12,30 +15,18 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 
-/*
- * Non-VHE: Both host and guest must save everything.
- *
- * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
- * pstate, which are handled as part of the el2 return state) on every
- * switch (sp_el0 is being dealt with in the assembly code).
- * tpidr_el0 and tpidrro_el0 only need to be switched when going
- * to host userspace or a different VCPU.  EL1 registers only need to be
- * switched when potentially going to run a different VCPU.  The latter two
- * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put.
- */
-
-static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
+static inline void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
 }
 
-static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
+static inline void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
 	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
 }
 
-static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
+static inline void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
 	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(SYS_SCTLR);
@@ -60,7 +51,7 @@ static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(SYS_SPSR);
 }
 
-static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
+static inline void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->gp_regs.regs.pc		= read_sysreg_el2(SYS_ELR);
 	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(SYS_SPSR);
@@ -69,39 +60,18 @@ static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ct
 		ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
 }
 
-void __hyp_text __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
-{
-	__sysreg_save_el1_state(ctxt);
-	__sysreg_save_common_state(ctxt);
-	__sysreg_save_user_state(ctxt);
-	__sysreg_save_el2_return_state(ctxt);
-}
-
-void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt)
-{
-	__sysreg_save_common_state(ctxt);
-}
-NOKPROBE_SYMBOL(sysreg_save_host_state_vhe);
-
-void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt)
-{
-	__sysreg_save_common_state(ctxt);
-	__sysreg_save_el2_return_state(ctxt);
-}
-NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe);
-
-static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
+static inline void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
 }
 
-static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
+static inline void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[TPIDR_EL0],		tpidr_el0);
 	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0],	tpidrro_el0);
 }
 
-static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
+static inline void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
 	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
@@ -160,8 +130,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR);
 }
 
-static void __hyp_text
-__sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
+static inline void __hyp_text __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
 {
 	u64 pstate = ctxt->gp_regs.regs.pstate;
 	u64 mode = pstate & PSR_AA32_MODE_MASK;
@@ -187,28 +156,7 @@ __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
 		write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
 }
 
-void __hyp_text __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
-{
-	__sysreg_restore_el1_state(ctxt);
-	__sysreg_restore_common_state(ctxt);
-	__sysreg_restore_user_state(ctxt);
-	__sysreg_restore_el2_return_state(ctxt);
-}
-
-void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt)
-{
-	__sysreg_restore_common_state(ctxt);
-}
-NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe);
-
-void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt)
-{
-	__sysreg_restore_common_state(ctxt);
-	__sysreg_restore_el2_return_state(ctxt);
-}
-NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
-
-void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
+static inline void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
 {
 	u64 *spsr, *sysreg;
 
@@ -230,7 +178,7 @@ void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
 		sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2);
 }
 
-void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
+static inline void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 {
 	u64 *spsr, *sysreg;
 
@@ -252,82 +200,4 @@ void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 		write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2);
 }
 
-/**
- * kvm_vcpu_load_sysregs - Load guest system registers to the physical CPU
- *
- * @vcpu: The VCPU pointer
- *
- * Load system registers that do not affect the host's execution, for
- * example EL1 system registers on a VHE system where the host kernel
- * runs at EL2.  This function is called from KVM's vcpu_load() function
- * and loading system register state early avoids having to load them on
- * every entry to the VM.
- */
-void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
-	struct kvm_cpu_context *host_ctxt;
-
-	if (!has_vhe())
-		return;
-
-	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	__sysreg_save_user_state(host_ctxt);
-
-	/*
-	 * Load guest EL1 and user state
-	 *
-	 * We must restore the 32-bit state before the sysregs, thanks
-	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
-	 */
-	__sysreg32_restore_state(vcpu);
-	__sysreg_restore_user_state(guest_ctxt);
-	__sysreg_restore_el1_state(guest_ctxt);
-
-	vcpu->arch.sysregs_loaded_on_cpu = true;
-
-	activate_traps_vhe_load(vcpu);
-}
-
-/**
- * kvm_vcpu_put_sysregs - Restore host system registers to the physical CPU
- *
- * @vcpu: The VCPU pointer
- *
- * Save guest system registers that do not affect the host's execution, for
- * example EL1 system registers on a VHE system where the host kernel
- * runs at EL2.  This function is called from KVM's vcpu_put() function
- * and deferring saving system register state until we're no longer running the
- * VCPU avoids having to save them on every exit from the VM.
- */
-void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
-	struct kvm_cpu_context *host_ctxt;
-
-	if (!has_vhe())
-		return;
-
-	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	deactivate_traps_vhe_put();
-
-	__sysreg_save_el1_state(guest_ctxt);
-	__sysreg_save_user_state(guest_ctxt);
-	__sysreg32_save_state(vcpu);
-
-	/* Restore host user state */
-	__sysreg_restore_user_state(host_ctxt);
-
-	vcpu->arch.sysregs_loaded_on_cpu = false;
-}
-
-void __hyp_text __kvm_enable_ssbs(void)
-{
-	u64 tmp;
-
-	asm volatile(
-	"mrs	%0, sctlr_el2\n"
-	"orr	%0, %0, %1\n"
-	"msr	sctlr_el2, %0"
-	: "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS));
-}
+#endif /* __ARM64_KVM_HYP_SYSREG_SR_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index b3cb67b63d67..61a8160f0dd9 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := debug-sr.o switch.o tlb.o hyp-init.o ../hyp-entry.o
+obj-y := sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 7f6b8d3dc637..f08bfb951df6 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -5,6 +5,7 @@
  */
 
 #include <hyp/switch.h>
+#include <hyp/sysreg-sr.h>
 
 #include <linux/arm-smccc.h>
 #include <linux/kvm_host.h>
diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
new file mode 100644
index 000000000000..710cf28ab1ec
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/sysreg-sr.h>
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+
+/*
+ * Non-VHE: Both host and guest must save everything.
+ */
+
+void __hyp_text __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_save_el1_state(ctxt);
+	__sysreg_save_common_state(ctxt);
+	__sysreg_save_user_state(ctxt);
+	__sysreg_save_el2_return_state(ctxt);
+}
+
+void __hyp_text __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_restore_el1_state(ctxt);
+	__sysreg_restore_common_state(ctxt);
+	__sysreg_restore_user_state(ctxt);
+	__sysreg_restore_el2_return_state(ctxt);
+}
+
+void __hyp_text __kvm_enable_ssbs(void)
+{
+	u64 tmp;
+
+	asm volatile(
+	"mrs	%0, sctlr_el2\n"
+	"orr	%0, %0, %1\n"
+	"msr	sctlr_el2, %0"
+	: "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS));
+}
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 62bdaf272b03..2801582a739a 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y := debug-sr.o switch.o tlb.o ../hyp-entry.o
+obj-y := sysreg-sr.o debug-sr.o switch.o tlb.o ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index e8d76cab44e4..c0d33deba77e 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -120,7 +120,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	 * HCR_EL2.TGE.
 	 *
 	 * We have already configured the guest's stage 1 translation in
-	 * kvm_vcpu_load_sysregs above.  We must now call __activate_vm
+	 * kvm_vcpu_load_sysregs_vhe above.  We must now call __activate_vm
 	 * before __activate_traps, because __activate_vm configures
 	 * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
 	 * (among other things).
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
new file mode 100644
index 000000000000..996471e4c138
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/sysreg-sr.h>
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+
+/*
+ * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
+ * pstate, which are handled as part of the el2 return state) on every
+ * switch (sp_el0 is being dealt with in the assembly code).
+ * tpidr_el0 and tpidrro_el0 only need to be switched when going
+ * to host userspace or a different VCPU.  EL1 registers only need to be
+ * switched when potentially going to run a different VCPU.  The latter two
+ * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put.
+ */
+
+void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_save_common_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_save_host_state_vhe);
+
+void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_save_common_state(ctxt);
+	__sysreg_save_el2_return_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe);
+
+void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_restore_common_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe);
+
+void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_restore_common_state(ctxt);
+	__sysreg_restore_el2_return_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
+
+/**
+ * kvm_vcpu_load_sysregs_vhe - Load guest system registers to the physical CPU
+ *
+ * @vcpu: The VCPU pointer
+ *
+ * Load system registers that do not affect the host's execution, for
+ * example EL1 system registers on a VHE system where the host kernel
+ * runs at EL2.  This function is called from KVM's vcpu_load() function
+ * and loading system register state early avoids having to load them on
+ * every entry to the VM.
+ */
+void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
+	struct kvm_cpu_context *host_ctxt;
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	__sysreg_save_user_state(host_ctxt);
+
+	/*
+	 * Load guest EL1 and user state
+	 *
+	 * We must restore the 32-bit state before the sysregs, thanks
+	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+	 */
+	__sysreg32_restore_state(vcpu);
+	__sysreg_restore_user_state(guest_ctxt);
+	__sysreg_restore_el1_state(guest_ctxt);
+
+	vcpu->arch.sysregs_loaded_on_cpu = true;
+
+	activate_traps_vhe_load(vcpu);
+}
+
+/**
+ * kvm_vcpu_put_sysregs_vhe - Restore host system registers to the physical CPU
+ *
+ * @vcpu: The VCPU pointer
+ *
+ * Save guest system registers that do not affect the host's execution, for
+ * example EL1 system registers on a VHE system where the host kernel
+ * runs at EL2.  This function is called from KVM's vcpu_put() function
+ * and deferring saving system register state until we're no longer running the
+ * VCPU avoids having to save them on every exit from the VM.
+ */
+void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
+	struct kvm_cpu_context *host_ctxt;
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	deactivate_traps_vhe_put();
+
+	__sysreg_save_el1_state(guest_ctxt);
+	__sysreg_save_user_state(guest_ctxt);
+	__sysreg32_save_state(vcpu);
+
+	/* Restore host user state */
+	__sysreg_restore_user_state(host_ctxt);
+
+	vcpu->arch.sysregs_loaded_on_cpu = false;
+}

From 9aebdea494b5d2d5fe0ba54d71e9d6c5acfe76b4 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:17 +0100
Subject: [PATCH 032/474] KVM: arm64: Duplicate hyp/timer-sr.c for VHE/nVHE

timer-sr.c contains a HVC handler for setting CNTVOFF_EL2 and two helper
functions for controlling access to physical counter. The former is used by
both VHE/nVHE and is duplicated, the latter are used only by nVHE and moved
to nvhe/timer-sr.c.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-13-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_hyp.h         |  2 ++
 arch/arm64/kernel/image-vars.h           |  5 -----
 arch/arm64/kvm/hyp/Makefile              |  2 +-
 arch/arm64/kvm/hyp/nvhe/Makefile         |  3 ++-
 arch/arm64/kvm/hyp/{ => nvhe}/timer-sr.c |  2 +-
 arch/arm64/kvm/hyp/vhe/Makefile          |  2 +-
 arch/arm64/kvm/hyp/vhe/timer-sr.c        | 12 ++++++++++++
 7 files changed, 19 insertions(+), 9 deletions(-)
 rename arch/arm64/kvm/hyp/{ => nvhe}/timer-sr.c (95%)
 create mode 100644 arch/arm64/kvm/hyp/vhe/timer-sr.c

diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 997c5bda1ac7..19f8b40fe6cf 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -63,8 +63,10 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if);
 void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if);
 int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu);
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 void __timer_enable_traps(struct kvm_vcpu *vcpu);
 void __timer_disable_traps(struct kvm_vcpu *vcpu);
+#endif
 
 #ifdef __KVM_NVHE_HYPERVISOR__
 void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt);
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 59eb55893eaf..2757d3512704 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -76,11 +76,6 @@ KVM_NVHE_ALIAS(abort_guest_exit_start);
 KVM_NVHE_ALIAS(__fpsimd_restore_state);
 KVM_NVHE_ALIAS(__fpsimd_save_state);
 
-/* Symbols defined in timer-sr.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__kvm_timer_set_cntvoff);
-KVM_NVHE_ALIAS(__timer_disable_traps);
-KVM_NVHE_ALIAS(__timer_enable_traps);
-
 /* Symbols defined in vgic-v2-cpuif-proxy.c (not yet compiled with nVHE build rules). */
 KVM_NVHE_ALIAS(__vgic_v2_perform_cpuif_access);
 
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index f49797237818..ef1aa7fe8f5a 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -13,7 +13,7 @@ subdir-ccflags-y := -I$(incdir)				\
 obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
 
-hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o entry.o \
+hyp-y := vgic-v3-sr.o aarch32.o vgic-v2-cpuif-proxy.o entry.o \
 	 fpsimd.o
 
 # KVM code is run at a different exception code with a different map, so
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 61a8160f0dd9..0f4c544f07db 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,7 +6,8 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o ../hyp-entry.o
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o \
+	 ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/timer-sr.c b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
similarity index 95%
rename from arch/arm64/kvm/hyp/timer-sr.c
rename to arch/arm64/kvm/hyp/nvhe/timer-sr.c
index fb5c0be33223..42c8ed71d06e 100644
--- a/arch/arm64/kvm/hyp/timer-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
@@ -10,7 +10,7 @@
 
 #include <asm/kvm_hyp.h>
 
-void __hyp_text __kvm_timer_set_cntvoff(u64 cntvoff)
+void __kvm_timer_set_cntvoff(u64 cntvoff)
 {
 	write_sysreg(cntvoff, cntvoff_el2);
 }
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 2801582a739a..a1dbbc5409bd 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,7 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y := sysreg-sr.o debug-sr.o switch.o tlb.o ../hyp-entry.o
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/vhe/timer-sr.c b/arch/arm64/kvm/hyp/vhe/timer-sr.c
new file mode 100644
index 000000000000..4cda674a8be6
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/timer-sr.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <asm/kvm_hyp.h>
+
+void __kvm_timer_set_cntvoff(u64 cntvoff)
+{
+	write_sysreg(cntvoff, cntvoff_el2);
+}

From c04dd455eb311d2d289c9d81d080eaf11a06cebf Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:18 +0100
Subject: [PATCH 033/474] KVM: arm64: Compile remaining hyp/ files for both
 VHE/nVHE

The following files in hyp/ contain only code shared by VHE/nVHE:
  vgic-v3-sr.c, aarch32.c, vgic-v2-cpuif-proxy.c, entry.S, fpsimd.S
Compile them under both configurations. Deletions in image-vars.h reflect
eliminated dependencies of nVHE code on the rest of the kernel.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-14-dbrazdil@google.com
---
 arch/arm64/kernel/image-vars.h   | 29 -----------------------------
 arch/arm64/kvm/hyp/Makefile      | 13 +------------
 arch/arm64/kvm/hyp/nvhe/Makefile |  5 +++--
 arch/arm64/kvm/hyp/vhe/Makefile  |  4 +++-
 4 files changed, 7 insertions(+), 44 deletions(-)

diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 2757d3512704..9e897c500237 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -63,35 +63,6 @@ __efistub__ctype		= _ctype;
 
 #define KVM_NVHE_ALIAS(sym) __kvm_nvhe_##sym = sym;
 
-/* Symbols defined in aarch32.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(kvm_skip_instr32);
-
-/* Symbols defined in entry.S (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__guest_enter);
-KVM_NVHE_ALIAS(__guest_exit);
-KVM_NVHE_ALIAS(abort_guest_exit_end);
-KVM_NVHE_ALIAS(abort_guest_exit_start);
-
-/* Symbols defined in fpsimd.S (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__fpsimd_restore_state);
-KVM_NVHE_ALIAS(__fpsimd_save_state);
-
-/* Symbols defined in vgic-v2-cpuif-proxy.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__vgic_v2_perform_cpuif_access);
-
-/* Symbols defined in vgic-v3-sr.c (not yet compiled with nVHE build rules). */
-KVM_NVHE_ALIAS(__vgic_v3_activate_traps);
-KVM_NVHE_ALIAS(__vgic_v3_deactivate_traps);
-KVM_NVHE_ALIAS(__vgic_v3_get_ich_vtr_el2);
-KVM_NVHE_ALIAS(__vgic_v3_init_lrs);
-KVM_NVHE_ALIAS(__vgic_v3_perform_cpuif_access);
-KVM_NVHE_ALIAS(__vgic_v3_read_vmcr);
-KVM_NVHE_ALIAS(__vgic_v3_restore_aprs);
-KVM_NVHE_ALIAS(__vgic_v3_restore_state);
-KVM_NVHE_ALIAS(__vgic_v3_save_aprs);
-KVM_NVHE_ALIAS(__vgic_v3_save_state);
-KVM_NVHE_ALIAS(__vgic_v3_write_vmcr);
-
 /* Alternative callbacks for init-time patching of nVHE hyp code. */
 KVM_NVHE_ALIAS(arm64_enable_wa2_handling);
 KVM_NVHE_ALIAS(kvm_patch_vector_branch);
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index ef1aa7fe8f5a..f54f0e89a71c 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -10,16 +10,5 @@ subdir-ccflags-y := -I$(incdir)				\
 		    -DDISABLE_BRANCH_PROFILING		\
 		    $(DISABLE_STACKLEAK_PLUGIN)
 
-obj-$(CONFIG_KVM) += hyp.o vhe/ nvhe/
+obj-$(CONFIG_KVM) += vhe/ nvhe/
 obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
-
-hyp-y := vgic-v3-sr.o aarch32.o vgic-v2-cpuif-proxy.o entry.o \
-	 fpsimd.o
-
-# KVM code is run at a different exception code with a different map, so
-# compiler instrumentation that inserts callbacks or checks into the code may
-# cause crashes. Just disable it.
-GCOV_PROFILE	:= n
-KASAN_SANITIZE	:= n
-UBSAN_SANITIZE	:= n
-KCOV_INSTRUMENT	:= n
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 0f4c544f07db..ad8729f5e814 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,8 +6,9 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o \
-	 ../hyp-entry.o
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o
+obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
+	 ../fpsimd.o ../hyp-entry.o
 
 obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
 extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index a1dbbc5409bd..090fd1e14be2 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,7 +6,9 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o ../hyp-entry.o
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o
+obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
+	 ../fpsimd.o ../hyp-entry.o
 
 # KVM code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may

From c50cb04303cb88c517715b078e3e010c024af1a5 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:19 +0100
Subject: [PATCH 034/474] KVM: arm64: Remove __hyp_text macro, use build rules
 instead

With nVHE code now fully separated from the rest of the kernel, the effects of
the __hyp_text macro (which had to be applied on all nVHE code) can be
achieved with build rules instead. The macro used to:
  (a) move code to .hyp.text ELF section, now done by renaming .text using
      `objcopy`, and
  (b) `notrace` and `__noscs` would negate effects of CC_FLAGS_FTRACE and
      CC_FLAGS_SCS, respectivelly, now those flags are  erased from
      KBUILD_CFLAGS (same way as in EFI stub).

Note that by removing __hyp_text from code shared with VHE, all VHE code is now
compiled into .text and without `notrace` and `__noscs`.

Use of '.pushsection .hyp.text' removed from assembly files as this is now also
covered by the build rules.

For MAINTAINERS: if needed to re-run, uses of macro were removed with the
following command. Formatting was fixed up manually.

  find arch/arm64/kvm/hyp -type f -name '*.c' -o -name '*.h' \
       -exec sed -i 's/ __hyp_text//g' {} +

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-15-dbrazdil@google.com
---
 arch/arm64/include/asm/kvm_emulate.h       |   2 +-
 arch/arm64/include/asm/kvm_hyp.h           |   2 -
 arch/arm64/kvm/hyp/aarch32.c               |   6 +-
 arch/arm64/kvm/hyp/entry.S                 |   1 -
 arch/arm64/kvm/hyp/fpsimd.S                |   1 -
 arch/arm64/kvm/hyp/hyp-entry.S             |   1 -
 arch/arm64/kvm/hyp/include/hyp/debug-sr.h  |  16 +--
 arch/arm64/kvm/hyp/include/hyp/switch.h    |  36 +++---
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h |  20 ++--
 arch/arm64/kvm/hyp/nvhe/Makefile           |   8 +-
 arch/arm64/kvm/hyp/nvhe/debug-sr.c         |  10 +-
 arch/arm64/kvm/hyp/nvhe/switch.c           |  18 +--
 arch/arm64/kvm/hyp/nvhe/sysreg-sr.c        |   6 +-
 arch/arm64/kvm/hyp/nvhe/timer-sr.c         |   4 +-
 arch/arm64/kvm/hyp/nvhe/tlb.c              |  14 +--
 arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c   |   4 +-
 arch/arm64/kvm/hyp/vgic-v3-sr.c            | 130 +++++++++------------
 17 files changed, 132 insertions(+), 147 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 4d0f8ea600ba..269a76cd51ff 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -516,7 +516,7 @@ static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_i
  * Skip an instruction which has been emulated at hyp while most guest sysregs
  * are live.
  */
-static __always_inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu)
+static __always_inline void __kvm_skip_instr(struct kvm_vcpu *vcpu)
 {
 	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
 	vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR);
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 19f8b40fe6cf..46689e7db46c 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -12,8 +12,6 @@
 #include <asm/alternative.h>
 #include <asm/sysreg.h>
 
-#define __hyp_text __section(.hyp.text) notrace __noscs
-
 #define read_sysreg_elx(r,nvh,vh)					\
 	({								\
 		u64 reg;						\
diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c
index 25c0e47d57cb..f9ff67dfbf0b 100644
--- a/arch/arm64/kvm/hyp/aarch32.c
+++ b/arch/arm64/kvm/hyp/aarch32.c
@@ -44,7 +44,7 @@ static const unsigned short cc_map[16] = {
 /*
  * Check if a trapped instruction should have been executed or not.
  */
-bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
+bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
 {
 	unsigned long cpsr;
 	u32 cpsr_cond;
@@ -93,7 +93,7 @@ bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
  *
  * IT[7:0] -> CPSR[26:25],CPSR[15:10]
  */
-static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
+static void kvm_adjust_itstate(struct kvm_vcpu *vcpu)
 {
 	unsigned long itbits, cond;
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
@@ -123,7 +123,7 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
  * kvm_skip_instr - skip a trapped instruction and proceed to the next
  * @vcpu: The vcpu pointer
  */
-void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
+void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
 {
 	u32 pc = *vcpu_pc(vcpu);
 	bool is_thumb;
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index 90186cf6473e..dfb4e6d359ab 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -21,7 +21,6 @@
 #define CPU_SP_EL0_OFFSET	(CPU_XREG_OFFSET(30) + 8)
 
 	.text
-	.pushsection	.hyp.text, "ax"
 
 /*
  * We treat x18 as callee-saved as the host may use it as a platform
diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S
index 5b8ff517ff10..01f114aa47b0 100644
--- a/arch/arm64/kvm/hyp/fpsimd.S
+++ b/arch/arm64/kvm/hyp/fpsimd.S
@@ -9,7 +9,6 @@
 #include <asm/fpsimdmacros.h>
 
 	.text
-	.pushsection	.hyp.text, "ax"
 
 SYM_FUNC_START(__fpsimd_save_state)
 	fpsimd_save	x0, 1
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 8316ee67d6a0..689fccbc9de7 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -16,7 +16,6 @@
 #include <asm/mmu.h>
 
 	.text
-	.pushsection	.hyp.text, "ax"
 
 .macro do_el2_call
 	/*
diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index e041dbd23243..24e8acf9ec10 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -88,9 +88,9 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
-static inline void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
-						 struct kvm_guest_debug_arch *dbg,
-						 struct kvm_cpu_context *ctxt)
+static inline void __debug_save_state(struct kvm_vcpu *vcpu,
+				      struct kvm_guest_debug_arch *dbg,
+				      struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -107,9 +107,9 @@ static inline void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
 	ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
 }
 
-static inline void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
-						    struct kvm_guest_debug_arch *dbg,
-						    struct kvm_cpu_context *ctxt)
+static inline void __debug_restore_state(struct kvm_vcpu *vcpu,
+					 struct kvm_guest_debug_arch *dbg,
+					 struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -127,7 +127,7 @@ static inline void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
 	write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
 }
 
-static inline void __hyp_text __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
+static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
@@ -146,7 +146,7 @@ static inline void __hyp_text __debug_switch_to_guest_common(struct kvm_vcpu *vc
 	__debug_restore_state(vcpu, guest_dbg, guest_ctxt);
 }
 
-static inline void __hyp_text __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
+static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 65d2a879b93b..8f622688fa64 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -30,7 +30,7 @@
 extern const char __hyp_panic_string[];
 
 /* Check whether the FP regs were dirtied while in the host-side run loop: */
-static inline bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
+static inline bool update_fp_enabled(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * When the system doesn't support FP/SIMD, we cannot rely on
@@ -48,7 +48,7 @@ static inline bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
 }
 
 /* Save the 32-bit only FPSIMD system register state */
-static inline void __hyp_text __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
+static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
 {
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
@@ -56,7 +56,7 @@ static inline void __hyp_text __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
 	vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
 }
 
-static inline void __hyp_text __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
+static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * We are about to set CPTR_EL2.TFP to trap all floating point
@@ -73,7 +73,7 @@ static inline void __hyp_text __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 	}
 }
 
-static inline void __hyp_text __activate_traps_common(struct kvm_vcpu *vcpu)
+static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 {
 	/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
 	write_sysreg(1 << 15, hstr_el2);
@@ -89,13 +89,13 @@ static inline void __hyp_text __activate_traps_common(struct kvm_vcpu *vcpu)
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 }
 
-static inline void __hyp_text __deactivate_traps_common(void)
+static inline void __deactivate_traps_common(void)
 {
 	write_sysreg(0, hstr_el2);
 	write_sysreg(0, pmuserenr_el0);
 }
 
-static inline void __hyp_text ___activate_traps(struct kvm_vcpu *vcpu)
+static inline void ___activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 hcr = vcpu->arch.hcr_el2;
 
@@ -108,7 +108,7 @@ static inline void __hyp_text ___activate_traps(struct kvm_vcpu *vcpu)
 		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
 }
 
-static inline void __hyp_text ___deactivate_traps(struct kvm_vcpu *vcpu)
+static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * If we pended a virtual abort, preserve it until it gets
@@ -122,12 +122,12 @@ static inline void __hyp_text ___deactivate_traps(struct kvm_vcpu *vcpu)
 	}
 }
 
-static inline void __hyp_text __activate_vm(struct kvm *kvm)
+static inline void __activate_vm(struct kvm *kvm)
 {
 	__load_guest_stage2(kvm);
 }
 
-static inline bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
+static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
 {
 	u64 par, tmp;
 
@@ -156,7 +156,7 @@ static inline bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
 	return true;
 }
 
-static inline bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
+static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)
 {
 	u8 ec;
 	u64 esr;
@@ -196,7 +196,7 @@ static inline bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 }
 
 /* Check for an FPSIMD/SVE trap and handle as appropriate */
-static inline bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
+static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 {
 	bool vhe, sve_guest, sve_host;
 	u8 hsr_ec;
@@ -283,7 +283,7 @@ static inline bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static inline bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
+static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
 {
 	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
 	int rt = kvm_vcpu_sys_get_rt(vcpu);
@@ -338,7 +338,7 @@ static inline bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static inline bool __hyp_text esr_is_ptrauth_trap(u32 esr)
+static inline bool esr_is_ptrauth_trap(u32 esr)
 {
 	u32 ec = ESR_ELx_EC(esr);
 
@@ -371,7 +371,7 @@ static inline bool __hyp_text esr_is_ptrauth_trap(u32 esr)
 	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
 })
 
-static inline bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
+static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *ctxt;
 	u64 val;
@@ -401,7 +401,7 @@ static inline bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
  * the guest, false when we should restore the host state and return to the
  * main run loop.
  */
-static inline bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
 		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
@@ -473,7 +473,7 @@ static inline bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_
 	return false;
 }
 
-static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
+static inline bool __needs_ssbd_off(struct kvm_vcpu *vcpu)
 {
 	if (!cpus_have_final_cap(ARM64_SSBD))
 		return false;
@@ -481,7 +481,7 @@ static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
 	return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
 }
 
-static inline void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
+static inline void __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_ARM64_SSBD
 	/*
@@ -494,7 +494,7 @@ static inline void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu
 #endif
 }
 
-static inline void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
+static inline void __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_ARM64_SSBD
 	/*
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 3e0585fbd403..6e04e061f762 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -15,18 +15,18 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 
-static inline void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
 }
 
-static inline void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
 	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
 }
 
-static inline void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
 	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(SYS_SCTLR);
@@ -51,7 +51,7 @@ static inline void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ct
 	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(SYS_SPSR);
 }
 
-static inline void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->gp_regs.regs.pc		= read_sysreg_el2(SYS_ELR);
 	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(SYS_SPSR);
@@ -60,18 +60,18 @@ static inline void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_cont
 		ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
 }
 
-static inline void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
 }
 
-static inline void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[TPIDR_EL0],		tpidr_el0);
 	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0],	tpidrro_el0);
 }
 
-static inline void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
 	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
@@ -130,7 +130,7 @@ static inline void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context
 	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR);
 }
 
-static inline void __hyp_text __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
 {
 	u64 pstate = ctxt->gp_regs.regs.pstate;
 	u64 mode = pstate & PSR_AA32_MODE_MASK;
@@ -156,7 +156,7 @@ static inline void __hyp_text __sysreg_restore_el2_return_state(struct kvm_cpu_c
 		write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
 }
 
-static inline void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
+static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
 {
 	u64 *spsr, *sysreg;
 
@@ -178,7 +178,7 @@ static inline void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
 		sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2);
 }
 
-static inline void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
+static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 {
 	u64 *spsr, *sysreg;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index ad8729f5e814..0b34414557d6 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -21,7 +21,13 @@ $(obj)/%.hyp.o: $(obj)/%.hyp.tmp.o FORCE
 	$(call if_changed,hypcopy)
 
 quiet_cmd_hypcopy = HYPCOPY $@
-      cmd_hypcopy = $(OBJCOPY) --prefix-symbols=__kvm_nvhe_ $< $@
+      cmd_hypcopy = $(OBJCOPY)	--prefix-symbols=__kvm_nvhe_		\
+				--rename-section=.text=.hyp.text	\
+				$< $@
+
+# Remove ftrace and Shadow Call Stack CFLAGS.
+# This is equivalent to the 'notrace' and '__noscs' annotations.
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS), $(KBUILD_CFLAGS))
 
 # KVM nVHE code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
index 828c0d48e790..91a711aa8382 100644
--- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
@@ -14,7 +14,7 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 
-static void __hyp_text __debug_save_spe(u64 *pmscr_el1)
+static void __debug_save_spe(u64 *pmscr_el1)
 {
 	u64 reg;
 
@@ -46,7 +46,7 @@ static void __hyp_text __debug_save_spe(u64 *pmscr_el1)
 	dsb(nsh);
 }
 
-static void __hyp_text __debug_restore_spe(u64 pmscr_el1)
+static void __debug_restore_spe(u64 pmscr_el1)
 {
 	if (!pmscr_el1)
 		return;
@@ -58,20 +58,20 @@ static void __hyp_text __debug_restore_spe(u64 pmscr_el1)
 	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
 }
 
-void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
 {
 	/* Disable and flush SPE data generation */
 	__debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
 	__debug_switch_to_guest_common(vcpu);
 }
 
-void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
+void __debug_switch_to_host(struct kvm_vcpu *vcpu)
 {
 	__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
 	__debug_switch_to_host_common(vcpu);
 }
 
-u32 __hyp_text __kvm_get_mdcr_el2(void)
+u32 __kvm_get_mdcr_el2(void)
 {
 	return read_sysreg(mdcr_el2);
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index f08bfb951df6..a1dcf59bd45e 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -27,7 +27,7 @@
 #include <asm/processor.h>
 #include <asm/thread_info.h>
 
-static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
+static void __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
 
@@ -58,7 +58,7 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
+static void __deactivate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 mdcr_el2;
 
@@ -93,13 +93,13 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
 }
 
-static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
+static void __deactivate_vm(struct kvm_vcpu *vcpu)
 {
 	write_sysreg(0, vttbr_el2);
 }
 
 /* Save VGICv3 state on non-VHE systems */
-static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
+static void __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
 {
 	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
 		__vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
@@ -108,7 +108,7 @@ static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
 }
 
 /* Restore VGICv3 state on non_VEH systems */
-static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
+static void __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
 {
 	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
 		__vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
@@ -119,7 +119,7 @@ static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
 /**
  * Disable host events, enable guest events
  */
-static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
+static bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
 {
 	struct kvm_host_data *host;
 	struct kvm_pmu_events *pmu;
@@ -139,7 +139,7 @@ static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
 /**
  * Disable guest events, enable host events
  */
-static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
+static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
 {
 	struct kvm_host_data *host;
 	struct kvm_pmu_events *pmu;
@@ -155,7 +155,7 @@ static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
 }
 
 /* Switch to the guest for legacy non-VHE systems */
-int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
@@ -242,7 +242,7 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	return exit_code;
 }
 
-void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
+void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
 {
 	u64 spsr = read_sysreg_el2(SYS_SPSR);
 	u64 elr = read_sysreg_el2(SYS_ELR);
diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
index 710cf28ab1ec..88a25fc8fcd3 100644
--- a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
@@ -18,7 +18,7 @@
  * Non-VHE: Both host and guest must save everything.
  */
 
-void __hyp_text __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
+void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
 {
 	__sysreg_save_el1_state(ctxt);
 	__sysreg_save_common_state(ctxt);
@@ -26,7 +26,7 @@ void __hyp_text __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
 	__sysreg_save_el2_return_state(ctxt);
 }
 
-void __hyp_text __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
+void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
 {
 	__sysreg_restore_el1_state(ctxt);
 	__sysreg_restore_common_state(ctxt);
@@ -34,7 +34,7 @@ void __hyp_text __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
 	__sysreg_restore_el2_return_state(ctxt);
 }
 
-void __hyp_text __kvm_enable_ssbs(void)
+void __kvm_enable_ssbs(void)
 {
 	u64 tmp;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/timer-sr.c b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
index 42c8ed71d06e..9072e71693ba 100644
--- a/arch/arm64/kvm/hyp/nvhe/timer-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
@@ -19,7 +19,7 @@ void __kvm_timer_set_cntvoff(u64 cntvoff)
  * Should only be called on non-VHE systems.
  * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
  */
-void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu)
+void __timer_disable_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
 
@@ -33,7 +33,7 @@ void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu)
  * Should only be called on non-VHE systems.
  * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
  */
-void __hyp_text __timer_enable_traps(struct kvm_vcpu *vcpu)
+void __timer_enable_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index deb48c8c00ee..d4475f8340c4 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -12,8 +12,7 @@ struct tlb_inv_context {
 	u64		tcr;
 };
 
-static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
-					     struct tlb_inv_context *cxt)
+static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
 {
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		u64 val;
@@ -36,8 +35,7 @@ static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
 	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
 }
 
-static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
-					    struct tlb_inv_context *cxt)
+static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
 {
 	write_sysreg(0, vttbr_el2);
 
@@ -49,7 +47,7 @@ static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
 	}
 }
 
-void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
 	struct tlb_inv_context cxt;
 
@@ -103,7 +101,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	__tlb_switch_to_host(kvm, &cxt);
 }
 
-void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
+void __kvm_tlb_flush_vmid(struct kvm *kvm)
 {
 	struct tlb_inv_context cxt;
 
@@ -120,7 +118,7 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 	__tlb_switch_to_host(kvm, &cxt);
 }
 
-void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
 	struct tlb_inv_context cxt;
@@ -135,7 +133,7 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 	__tlb_switch_to_host(kvm, &cxt);
 }
 
-void __hyp_text __kvm_flush_vm_context(void)
+void __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
 	__tlbi(alle1is);
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 4f3a087e36d5..bd1bab551d48 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -13,7 +13,7 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 
-static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
+static bool __is_be(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu))
 		return !!(read_sysreg_el2(SYS_SPSR) & PSR_AA32_E_BIT);
@@ -32,7 +32,7 @@ static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
  *  0: Not a GICV access
  * -1: Illegal GICV access successfully performed
  */
-int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
+int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
 	struct vgic_dist *vgic = &kvm->arch.vgic;
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 10ed539835c1..d31eb6266f2e 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -16,7 +16,7 @@
 #define vtr_to_nr_pre_bits(v)		((((u32)(v) >> 26) & 7) + 1)
 #define vtr_to_nr_apr_regs(v)		(1 << (vtr_to_nr_pre_bits(v) - 5))
 
-static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
+static u64 __gic_v3_get_lr(unsigned int lr)
 {
 	switch (lr & 0xf) {
 	case 0:
@@ -56,7 +56,7 @@ static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
 	unreachable();
 }
 
-static void __hyp_text __gic_v3_set_lr(u64 val, int lr)
+static void __gic_v3_set_lr(u64 val, int lr)
 {
 	switch (lr & 0xf) {
 	case 0:
@@ -110,7 +110,7 @@ static void __hyp_text __gic_v3_set_lr(u64 val, int lr)
 	}
 }
 
-static void __hyp_text __vgic_v3_write_ap0rn(u32 val, int n)
+static void __vgic_v3_write_ap0rn(u32 val, int n)
 {
 	switch (n) {
 	case 0:
@@ -128,7 +128,7 @@ static void __hyp_text __vgic_v3_write_ap0rn(u32 val, int n)
 	}
 }
 
-static void __hyp_text __vgic_v3_write_ap1rn(u32 val, int n)
+static void __vgic_v3_write_ap1rn(u32 val, int n)
 {
 	switch (n) {
 	case 0:
@@ -146,7 +146,7 @@ static void __hyp_text __vgic_v3_write_ap1rn(u32 val, int n)
 	}
 }
 
-static u32 __hyp_text __vgic_v3_read_ap0rn(int n)
+static u32 __vgic_v3_read_ap0rn(int n)
 {
 	u32 val;
 
@@ -170,7 +170,7 @@ static u32 __hyp_text __vgic_v3_read_ap0rn(int n)
 	return val;
 }
 
-static u32 __hyp_text __vgic_v3_read_ap1rn(int n)
+static u32 __vgic_v3_read_ap1rn(int n)
 {
 	u32 val;
 
@@ -194,7 +194,7 @@ static u32 __hyp_text __vgic_v3_read_ap1rn(int n)
 	return val;
 }
 
-void __hyp_text __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 used_lrs = cpu_if->used_lrs;
 
@@ -229,7 +229,7 @@ void __hyp_text __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
 	}
 }
 
-void __hyp_text __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 used_lrs = cpu_if->used_lrs;
 	int i;
@@ -255,7 +255,7 @@ void __hyp_text __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if)
 	}
 }
 
-void __hyp_text __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
 {
 	/*
 	 * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a
@@ -302,7 +302,7 @@ void __hyp_text __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
 		write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
 }
 
-void __hyp_text __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 val;
 
@@ -328,7 +328,7 @@ void __hyp_text __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
 		write_gicreg(0, ICH_HCR_EL2);
 }
 
-void __hyp_text __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 val;
 	u32 nr_pre_bits;
@@ -361,7 +361,7 @@ void __hyp_text __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
 	}
 }
 
-void __hyp_text __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 val;
 	u32 nr_pre_bits;
@@ -394,7 +394,7 @@ void __hyp_text __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
 	}
 }
 
-void __hyp_text __vgic_v3_init_lrs(void)
+void __vgic_v3_init_lrs(void)
 {
 	int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2));
 	int i;
@@ -403,28 +403,28 @@ void __hyp_text __vgic_v3_init_lrs(void)
 		__gic_v3_set_lr(0, i);
 }
 
-u64 __hyp_text __vgic_v3_get_ich_vtr_el2(void)
+u64 __vgic_v3_get_ich_vtr_el2(void)
 {
 	return read_gicreg(ICH_VTR_EL2);
 }
 
-u64 __hyp_text __vgic_v3_read_vmcr(void)
+u64 __vgic_v3_read_vmcr(void)
 {
 	return read_gicreg(ICH_VMCR_EL2);
 }
 
-void __hyp_text __vgic_v3_write_vmcr(u32 vmcr)
+void __vgic_v3_write_vmcr(u32 vmcr)
 {
 	write_gicreg(vmcr, ICH_VMCR_EL2);
 }
 
-static int __hyp_text __vgic_v3_bpr_min(void)
+static int __vgic_v3_bpr_min(void)
 {
 	/* See Pseudocode for VPriorityGroup */
 	return 8 - vtr_to_nr_pre_bits(read_gicreg(ICH_VTR_EL2));
 }
 
-static int __hyp_text __vgic_v3_get_group(struct kvm_vcpu *vcpu)
+static int __vgic_v3_get_group(struct kvm_vcpu *vcpu)
 {
 	u32 esr = kvm_vcpu_get_hsr(vcpu);
 	u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
@@ -434,9 +434,8 @@ static int __hyp_text __vgic_v3_get_group(struct kvm_vcpu *vcpu)
 
 #define GICv3_IDLE_PRIORITY	0xff
 
-static int __hyp_text __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu,
-						    u32 vmcr,
-						    u64 *lr_val)
+static int __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu, u32 vmcr,
+					 u64 *lr_val)
 {
 	unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
 	u8 priority = GICv3_IDLE_PRIORITY;
@@ -474,8 +473,8 @@ static int __hyp_text __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu,
 	return lr;
 }
 
-static int __hyp_text __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu,
-					       int intid, u64 *lr_val)
+static int __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, int intid,
+				    u64 *lr_val)
 {
 	unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
 	int i;
@@ -494,7 +493,7 @@ static int __hyp_text __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu,
 	return -1;
 }
 
-static int __hyp_text __vgic_v3_get_highest_active_priority(void)
+static int __vgic_v3_get_highest_active_priority(void)
 {
 	u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2));
 	u32 hap = 0;
@@ -526,12 +525,12 @@ static int __hyp_text __vgic_v3_get_highest_active_priority(void)
 	return GICv3_IDLE_PRIORITY;
 }
 
-static unsigned int __hyp_text __vgic_v3_get_bpr0(u32 vmcr)
+static unsigned int __vgic_v3_get_bpr0(u32 vmcr)
 {
 	return (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
 }
 
-static unsigned int __hyp_text __vgic_v3_get_bpr1(u32 vmcr)
+static unsigned int __vgic_v3_get_bpr1(u32 vmcr)
 {
 	unsigned int bpr;
 
@@ -550,7 +549,7 @@ static unsigned int __hyp_text __vgic_v3_get_bpr1(u32 vmcr)
  * Convert a priority to a preemption level, taking the relevant BPR
  * into account by zeroing the sub-priority bits.
  */
-static u8 __hyp_text __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp)
+static u8 __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp)
 {
 	unsigned int bpr;
 
@@ -568,7 +567,7 @@ static u8 __hyp_text __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp)
  * matter what the guest does with its BPR, we can always set/get the
  * same value of a priority.
  */
-static void __hyp_text __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp)
+static void __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp)
 {
 	u8 pre, ap;
 	u32 val;
@@ -587,7 +586,7 @@ static void __hyp_text __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp)
 	}
 }
 
-static int __hyp_text __vgic_v3_clear_highest_active_priority(void)
+static int __vgic_v3_clear_highest_active_priority(void)
 {
 	u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2));
 	u32 hap = 0;
@@ -625,7 +624,7 @@ static int __hyp_text __vgic_v3_clear_highest_active_priority(void)
 	return GICv3_IDLE_PRIORITY;
 }
 
-static void __hyp_text __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u64 lr_val;
 	u8 lr_prio, pmr;
@@ -661,7 +660,7 @@ static void __hyp_text __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int r
 	vcpu_set_reg(vcpu, rt, ICC_IAR1_EL1_SPURIOUS);
 }
 
-static void __hyp_text __vgic_v3_clear_active_lr(int lr, u64 lr_val)
+static void __vgic_v3_clear_active_lr(int lr, u64 lr_val)
 {
 	lr_val &= ~ICH_LR_ACTIVE_BIT;
 	if (lr_val & ICH_LR_HW) {
@@ -674,7 +673,7 @@ static void __hyp_text __vgic_v3_clear_active_lr(int lr, u64 lr_val)
 	__gic_v3_set_lr(lr_val, lr);
 }
 
-static void __hyp_text __vgic_v3_bump_eoicount(void)
+static void __vgic_v3_bump_eoicount(void)
 {
 	u32 hcr;
 
@@ -683,8 +682,7 @@ static void __hyp_text __vgic_v3_bump_eoicount(void)
 	write_gicreg(hcr, ICH_HCR_EL2);
 }
 
-static void __hyp_text __vgic_v3_write_dir(struct kvm_vcpu *vcpu,
-					   u32 vmcr, int rt)
+static void __vgic_v3_write_dir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 vid = vcpu_get_reg(vcpu, rt);
 	u64 lr_val;
@@ -707,7 +705,7 @@ static void __hyp_text __vgic_v3_write_dir(struct kvm_vcpu *vcpu,
 	__vgic_v3_clear_active_lr(lr, lr_val);
 }
 
-static void __hyp_text __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 vid = vcpu_get_reg(vcpu, rt);
 	u64 lr_val;
@@ -744,17 +742,17 @@ static void __hyp_text __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int
 	__vgic_v3_clear_active_lr(lr, lr_val);
 }
 
-static void __hyp_text __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG0_MASK));
 }
 
-static void __hyp_text __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG1_MASK));
 }
 
-static void __hyp_text __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u64 val = vcpu_get_reg(vcpu, rt);
 
@@ -766,7 +764,7 @@ static void __hyp_text __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr,
 	__vgic_v3_write_vmcr(vmcr);
 }
 
-static void __hyp_text __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u64 val = vcpu_get_reg(vcpu, rt);
 
@@ -778,17 +776,17 @@ static void __hyp_text __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr,
 	__vgic_v3_write_vmcr(vmcr);
 }
 
-static void __hyp_text __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr0(vmcr));
 }
 
-static void __hyp_text __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr1(vmcr));
 }
 
-static void __hyp_text __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u64 val = vcpu_get_reg(vcpu, rt);
 	u8 bpr_min = __vgic_v3_bpr_min() - 1;
@@ -805,7 +803,7 @@ static void __hyp_text __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int
 	__vgic_v3_write_vmcr(vmcr);
 }
 
-static void __hyp_text __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u64 val = vcpu_get_reg(vcpu, rt);
 	u8 bpr_min = __vgic_v3_bpr_min();
@@ -825,7 +823,7 @@ static void __hyp_text __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int
 	__vgic_v3_write_vmcr(vmcr);
 }
 
-static void __hyp_text __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
+static void __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
 {
 	u32 val;
 
@@ -837,7 +835,7 @@ static void __hyp_text __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n
 	vcpu_set_reg(vcpu, rt, val);
 }
 
-static void __hyp_text __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
+static void __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
 {
 	u32 val = vcpu_get_reg(vcpu, rt);
 
@@ -847,56 +845,49 @@ static void __hyp_text __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int
 		__vgic_v3_write_ap1rn(val, n);
 }
 
-static void __hyp_text __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu,
+static void __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu,
 					    u32 vmcr, int rt)
 {
 	__vgic_v3_read_apxrn(vcpu, rt, 0);
 }
 
-static void __hyp_text __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu,
+static void __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu,
 					    u32 vmcr, int rt)
 {
 	__vgic_v3_read_apxrn(vcpu, rt, 1);
 }
 
-static void __hyp_text __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu,
-					    u32 vmcr, int rt)
+static void __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	__vgic_v3_read_apxrn(vcpu, rt, 2);
 }
 
-static void __hyp_text __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu,
-					    u32 vmcr, int rt)
+static void __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	__vgic_v3_read_apxrn(vcpu, rt, 3);
 }
 
-static void __hyp_text __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu,
-					     u32 vmcr, int rt)
+static void __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	__vgic_v3_write_apxrn(vcpu, rt, 0);
 }
 
-static void __hyp_text __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu,
-					     u32 vmcr, int rt)
+static void __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	__vgic_v3_write_apxrn(vcpu, rt, 1);
 }
 
-static void __hyp_text __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu,
-					     u32 vmcr, int rt)
+static void __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	__vgic_v3_write_apxrn(vcpu, rt, 2);
 }
 
-static void __hyp_text __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu,
-					     u32 vmcr, int rt)
+static void __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	__vgic_v3_write_apxrn(vcpu, rt, 3);
 }
 
-static void __hyp_text __vgic_v3_read_hppir(struct kvm_vcpu *vcpu,
-					    u32 vmcr, int rt)
+static void __vgic_v3_read_hppir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u64 lr_val;
 	int lr, lr_grp, grp;
@@ -915,16 +906,14 @@ static void __hyp_text __vgic_v3_read_hppir(struct kvm_vcpu *vcpu,
 	vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK);
 }
 
-static void __hyp_text __vgic_v3_read_pmr(struct kvm_vcpu *vcpu,
-					  u32 vmcr, int rt)
+static void __vgic_v3_read_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	vmcr &= ICH_VMCR_PMR_MASK;
 	vmcr >>= ICH_VMCR_PMR_SHIFT;
 	vcpu_set_reg(vcpu, rt, vmcr);
 }
 
-static void __hyp_text __vgic_v3_write_pmr(struct kvm_vcpu *vcpu,
-					   u32 vmcr, int rt)
+static void __vgic_v3_write_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 val = vcpu_get_reg(vcpu, rt);
 
@@ -936,15 +925,13 @@ static void __hyp_text __vgic_v3_write_pmr(struct kvm_vcpu *vcpu,
 	write_gicreg(vmcr, ICH_VMCR_EL2);
 }
 
-static void __hyp_text __vgic_v3_read_rpr(struct kvm_vcpu *vcpu,
-					  u32 vmcr, int rt)
+static void __vgic_v3_read_rpr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 val = __vgic_v3_get_highest_active_priority();
 	vcpu_set_reg(vcpu, rt, val);
 }
 
-static void __hyp_text __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu,
-					   u32 vmcr, int rt)
+static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 vtr, val;
 
@@ -965,8 +952,7 @@ static void __hyp_text __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu,
 	vcpu_set_reg(vcpu, rt, val);
 }
 
-static void __hyp_text __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu,
-					    u32 vmcr, int rt)
+static void __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 val = vcpu_get_reg(vcpu, rt);
 
@@ -983,7 +969,7 @@ static void __hyp_text __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu,
 	write_gicreg(vmcr, ICH_VMCR_EL2);
 }
 
-int __hyp_text __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
+int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
 {
 	int rt;
 	u32 esr;

From f9a026e3d38ba81cd274725f1caaf64322a86aa5 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 25 Jun 2020 14:14:20 +0100
Subject: [PATCH 035/474] KVM: arm64: Lift instrumentation restrictions on VHE

With VHE and nVHE executable code completely separated, remove build config
that disabled GCOV/KASAN/UBSAN/KCOV instrumentation for VHE as these now
execute under the same memory mappings as the rest of the kernel.

No violations are currently being reported by either KASAN or UBSAN.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200625131420.71444-16-dbrazdil@google.com
---
 arch/arm64/kvm/hyp/vhe/Makefile | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 090fd1e14be2..461e97c375cc 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -9,11 +9,3 @@ ccflags-y := -D__KVM_VHE_HYPERVISOR__
 obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o
 obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
 	 ../fpsimd.o ../hyp-entry.o
-
-# KVM code is run at a different exception code with a different map, so
-# compiler instrumentation that inserts callbacks or checks into the code may
-# cause crashes. Just disable it.
-GCOV_PROFILE	:= n
-KASAN_SANITIZE	:= n
-UBSAN_SANITIZE	:= n
-KCOV_INSTRUMENT	:= n

From 731532176716e2775a5d21115bb9c5c61e0cb704 Mon Sep 17 00:00:00 2001
From: Alexander Graf <graf@amazon.com>
Date: Wed, 1 Jul 2020 16:02:06 +0200
Subject: [PATCH 036/474] KVM: arm64: vgic-its: Change default outer
 cacheability for {PEND, PROP}BASER

PENDBASER and PROPBASER define the outer caching mode for LPI tables.
The memory backing them may not be outer sharable, so we mark them as nC
by default. This however, breaks Windows on ARM which only accepts
SameAsInner or RaWaWb as values for outer cachability.

We do today already allow the outer mode to be set to SameAsInner
explicitly, so the easy fix is to default to that instead of nC for
situations when an OS asks for a not fulfillable cachability request.

This fixes booting Windows in KVM with vgicv3 and ITS enabled for me.

Signed-off-by: Alexander Graf <graf@amazon.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200701140206.8664-1-graf@amazon.com
---
 arch/arm64/kvm/vgic/vgic-mmio-v3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index d2339a2b9fb9..5c786b915cd3 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -389,7 +389,7 @@ u64 vgic_sanitise_outer_cacheability(u64 field)
 	case GIC_BASER_CACHE_nC:
 		return field;
 	default:
-		return GIC_BASER_CACHE_nC;
+		return GIC_BASER_CACHE_SameAsInner;
 	}
 }
 

From 95fa0ba83e66dea0d3af48ad69842ae8c1dd9af2 Mon Sep 17 00:00:00 2001
From: Peng Hao <richard.peng@oppo.com>
Date: Wed, 1 Jul 2020 08:07:09 -0400
Subject: [PATCH 037/474] KVM: arm64: Drop long gone function parameter
 documentation

update_vmid() just has one parameter "vmid".The other parameter
"kvm" is no longer used.

Signed-off-by: Peng Hao <richard.peng@oppo.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200701120709.388377-1-richard.peng@oppo.com
---
 arch/arm64/kvm/arm.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 90cb90561446..5bf9bf54b22c 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -466,7 +466,6 @@ static bool need_new_vmid_gen(struct kvm_vmid *vmid)
 
 /**
  * update_vmid - Update the vmid with a valid VMID for the current generation
- * @kvm: The guest that struct vmid belongs to
  * @vmid: The stage-2 VMID information struct
  */
 static void update_vmid(struct kvm_vmid *vmid)

From 3a949f4c93548751a377691b2a208063da05e369 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Tue, 30 Jun 2020 11:57:05 +1000
Subject: [PATCH 038/474] KVM: arm64: Rename HSR to ESR

kvm/arm32 isn't supported since commit 541ad0150ca4 ("arm: Remove
32bit KVM host support"). So HSR isn't meaningful since then. This
renames HSR to ESR accordingly. This shouldn't cause any functional
changes:

   * Rename kvm_vcpu_get_hsr() to kvm_vcpu_get_esr() to make the
     function names self-explanatory.
   * Rename variables from @hsr to @esr to make them self-explanatory.

Note that the renaming on uapi and tracepoint will cause ABI changes,
which we should avoid. Specificly, there are 4 related source files
in this regard:

   * arch/arm64/include/uapi/asm/kvm.h  (struct kvm_debug_exit_arch::hsr)
   * arch/arm64/kvm/handle_exit.c       (struct kvm_debug_exit_arch::hsr)
   * arch/arm64/kvm/trace_arm.h         (tracepoints)
   * arch/arm64/kvm/trace_handle_exit.h (tracepoints)

Signed-off-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Acked-by: Andrew Scull <ascull@google.com>
Link: https://lore.kernel.org/r/20200630015705.103366-1-gshan@redhat.com
---
 arch/arm64/include/asm/kvm_emulate.h | 34 ++++++++++++++--------------
 arch/arm64/kvm/handle_exit.c         | 32 +++++++++++++-------------
 arch/arm64/kvm/hyp/aarch32.c         |  2 +-
 arch/arm64/kvm/hyp/switch.c          | 14 ++++++------
 arch/arm64/kvm/hyp/vgic-v3-sr.c      |  4 ++--
 arch/arm64/kvm/mmu.c                 |  6 ++---
 arch/arm64/kvm/sys_regs.c            | 28 +++++++++++------------
 7 files changed, 60 insertions(+), 60 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 4d0f8ea600ba..c9ba0df47f7d 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -259,14 +259,14 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 	return mode != PSR_MODE_EL0t;
 }
 
-static __always_inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu)
+static __always_inline u32 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.fault.esr_el2;
 }
 
 static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 
 	if (esr & ESR_ELx_CV)
 		return (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT;
@@ -291,64 +291,64 @@ static inline u64 kvm_vcpu_get_disr(const struct kvm_vcpu *vcpu)
 
 static inline u32 kvm_vcpu_hvc_get_imm(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_xVC_IMM_MASK;
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_xVC_IMM_MASK;
 }
 
 static __always_inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_ISV);
 }
 
 static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_hsr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC);
+	return kvm_vcpu_get_esr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC);
 }
 
 static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_SSE);
 }
 
 static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_SF);
 }
 
 static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 {
-	return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
+	return (kvm_vcpu_get_esr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
 }
 
 static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW);
 }
 
 static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) ||
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR) ||
 		kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
 }
 
 static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_CM);
 }
 
 static __always_inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
 {
-	return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
+	return 1 << ((kvm_vcpu_get_esr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
 }
 
 /* This one is not specific to Data Abort */
 static __always_inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_IL);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_IL);
 }
 
 static __always_inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu)
 {
-	return ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
+	return ESR_ELx_EC(kvm_vcpu_get_esr(vcpu));
 }
 
 static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
@@ -358,12 +358,12 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
 
 static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC;
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC;
 }
 
 static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE;
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
 }
 
 static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
@@ -387,7 +387,7 @@ static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
 
 static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 	return ESR_ELx_SYS64_ISS_RT(esr);
 }
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 5a02d4c90559..98ab33139982 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -89,7 +89,7 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu, struct kvm_run *run)
  */
 static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
+	if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
 		vcpu->stat.wfe_exit_stat++;
 		kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
@@ -119,13 +119,13 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
  */
 static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 	int ret = 0;
 
 	run->exit_reason = KVM_EXIT_DEBUG;
-	run->debug.arch.hsr = hsr;
+	run->debug.arch.hsr = esr;
 
-	switch (ESR_ELx_EC(hsr)) {
+	switch (ESR_ELx_EC(esr)) {
 	case ESR_ELx_EC_WATCHPT_LOW:
 		run->debug.arch.far = vcpu->arch.fault.far_el2;
 		/* fall through */
@@ -135,8 +135,8 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	case ESR_ELx_EC_BRK64:
 		break;
 	default:
-		kvm_err("%s: un-handled case hsr: %#08x\n",
-			__func__, (unsigned int) hsr);
+		kvm_err("%s: un-handled case esr: %#08x\n",
+			__func__, (unsigned int) esr);
 		ret = -1;
 		break;
 	}
@@ -146,10 +146,10 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 
-	kvm_pr_unimpl("Unknown exception class: hsr: %#08x -- %s\n",
-		      hsr, esr_get_class_string(hsr));
+	kvm_pr_unimpl("Unknown exception class: esr: %#08x -- %s\n",
+		      esr, esr_get_class_string(esr));
 
 	kvm_inject_undefined(vcpu);
 	return 1;
@@ -200,10 +200,10 @@ static exit_handle_fn arm_exit_handlers[] = {
 
 static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 {
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
-	u8 hsr_ec = ESR_ELx_EC(hsr);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
+	u8 esr_ec = ESR_ELx_EC(esr);
 
-	return arm_exit_handlers[hsr_ec];
+	return arm_exit_handlers[esr_ec];
 }
 
 /*
@@ -241,15 +241,15 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		       int exception_index)
 {
 	if (ARM_SERROR_PENDING(exception_index)) {
-		u8 hsr_ec = ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
+		u8 esr_ec = ESR_ELx_EC(kvm_vcpu_get_esr(vcpu));
 
 		/*
 		 * HVC/SMC already have an adjusted PC, which we need
 		 * to correct in order to return to after having
 		 * injected the SError.
 		 */
-		if (hsr_ec == ESR_ELx_EC_HVC32 || hsr_ec == ESR_ELx_EC_HVC64 ||
-		    hsr_ec == ESR_ELx_EC_SMC32 || hsr_ec == ESR_ELx_EC_SMC64) {
+		if (esr_ec == ESR_ELx_EC_HVC32 || esr_ec == ESR_ELx_EC_HVC64 ||
+		    esr_ec == ESR_ELx_EC_SMC32 || esr_ec == ESR_ELx_EC_SMC64) {
 			u32 adj =  kvm_vcpu_trap_il_is32bit(vcpu) ? 4 : 2;
 			*vcpu_pc(vcpu) -= adj;
 		}
@@ -307,5 +307,5 @@ void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	exception_index = ARM_EXCEPTION_CODE(exception_index);
 
 	if (exception_index == ARM_EXCEPTION_EL1_SERROR)
-		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_hsr(vcpu));
+		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_esr(vcpu));
 }
diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c
index 25c0e47d57cb..1e948704d60f 100644
--- a/arch/arm64/kvm/hyp/aarch32.c
+++ b/arch/arm64/kvm/hyp/aarch32.c
@@ -51,7 +51,7 @@ bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
 	int cond;
 
 	/* Top two bits non-zero?  Unconditional. */
-	if (kvm_vcpu_get_hsr(vcpu) >> 30)
+	if (kvm_vcpu_get_esr(vcpu) >> 30)
 		return true;
 
 	/* Is condition field valid? */
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index db1c4487d95d..5164074c1ae1 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -356,7 +356,7 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 {
 	bool vhe, sve_guest, sve_host;
-	u8 hsr_ec;
+	u8 esr_ec;
 
 	if (!system_supports_fpsimd())
 		return false;
@@ -371,14 +371,14 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 		vhe = has_vhe();
 	}
 
-	hsr_ec = kvm_vcpu_trap_get_class(vcpu);
-	if (hsr_ec != ESR_ELx_EC_FP_ASIMD &&
-	    hsr_ec != ESR_ELx_EC_SVE)
+	esr_ec = kvm_vcpu_trap_get_class(vcpu);
+	if (esr_ec != ESR_ELx_EC_FP_ASIMD &&
+	    esr_ec != ESR_ELx_EC_SVE)
 		return false;
 
 	/* Don't handle SVE traps for non-SVE vcpus here: */
 	if (!sve_guest)
-		if (hsr_ec != ESR_ELx_EC_FP_ASIMD)
+		if (esr_ec != ESR_ELx_EC_FP_ASIMD)
 			return false;
 
 	/* Valid trap.  Switch the context: */
@@ -437,7 +437,7 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 
 static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
 {
-	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
+	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
 	int rt = kvm_vcpu_sys_get_rt(vcpu);
 	u64 val = vcpu_get_reg(vcpu, rt);
 
@@ -529,7 +529,7 @@ static bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 	u64 val;
 
 	if (!vcpu_has_ptrauth(vcpu) ||
-	    !esr_is_ptrauth_trap(kvm_vcpu_get_hsr(vcpu)))
+	    !esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu)))
 		return false;
 
 	ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 10ed539835c1..bee0a74671ca 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -426,7 +426,7 @@ static int __hyp_text __vgic_v3_bpr_min(void)
 
 static int __hyp_text __vgic_v3_get_group(struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 	u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
 
 	return crm != 8;
@@ -992,7 +992,7 @@ int __hyp_text __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
 	bool is_read;
 	u32 sysreg;
 
-	esr = kvm_vcpu_get_hsr(vcpu);
+	esr = kvm_vcpu_get_esr(vcpu);
 	if (vcpu_mode_is_32bit(vcpu)) {
 		if (!kvm_condition_valid(vcpu)) {
 			__kvm_skip_instr(vcpu);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8c0035cab6b6..36506112480e 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2079,7 +2079,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * For RAS the host kernel may handle this abort.
 		 * There is no need to pass the error into the guest.
 		 */
-		if (!kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_hsr(vcpu)))
+		if (!kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
 			return 1;
 
 		if (unlikely(!is_iabt)) {
@@ -2088,7 +2088,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		}
 	}
 
-	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu),
+	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
 	/* Check the stage-2 fault is trans. fault or write fault */
@@ -2097,7 +2097,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
 			kvm_vcpu_trap_get_class(vcpu),
 			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
-			(unsigned long)kvm_vcpu_get_hsr(vcpu));
+			(unsigned long)kvm_vcpu_get_esr(vcpu));
 		return -EFAULT;
 	}
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index baf5ce9225ce..a96dd62a90ce 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2220,10 +2220,10 @@ static int emulate_cp(struct kvm_vcpu *vcpu,
 static void unhandled_cp_access(struct kvm_vcpu *vcpu,
 				struct sys_reg_params *params)
 {
-	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+	u8 esr_ec = kvm_vcpu_trap_get_class(vcpu);
 	int cp = -1;
 
-	switch(hsr_ec) {
+	switch (esr_ec) {
 	case ESR_ELx_EC_CP15_32:
 	case ESR_ELx_EC_CP15_64:
 		cp = 15;
@@ -2254,17 +2254,17 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 			    size_t nr_specific)
 {
 	struct sys_reg_params params;
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 	int Rt = kvm_vcpu_sys_get_rt(vcpu);
-	int Rt2 = (hsr >> 10) & 0x1f;
+	int Rt2 = (esr >> 10) & 0x1f;
 
 	params.is_aarch32 = true;
 	params.is_32bit = false;
-	params.CRm = (hsr >> 1) & 0xf;
-	params.is_write = ((hsr & 1) == 0);
+	params.CRm = (esr >> 1) & 0xf;
+	params.is_write = ((esr & 1) == 0);
 
 	params.Op0 = 0;
-	params.Op1 = (hsr >> 16) & 0xf;
+	params.Op1 = (esr >> 16) & 0xf;
 	params.Op2 = 0;
 	params.CRn = 0;
 
@@ -2311,18 +2311,18 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 			    size_t nr_specific)
 {
 	struct sys_reg_params params;
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 	int Rt  = kvm_vcpu_sys_get_rt(vcpu);
 
 	params.is_aarch32 = true;
 	params.is_32bit = true;
-	params.CRm = (hsr >> 1) & 0xf;
+	params.CRm = (esr >> 1) & 0xf;
 	params.regval = vcpu_get_reg(vcpu, Rt);
-	params.is_write = ((hsr & 1) == 0);
-	params.CRn = (hsr >> 10) & 0xf;
+	params.is_write = ((esr & 1) == 0);
+	params.CRn = (esr >> 10) & 0xf;
 	params.Op0 = 0;
-	params.Op1 = (hsr >> 14) & 0x7;
-	params.Op2 = (hsr >> 17) & 0x7;
+	params.Op1 = (esr >> 14) & 0x7;
+	params.Op2 = (esr >> 17) & 0x7;
 
 	if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
 	    !emulate_cp(vcpu, &params, global, nr_global)) {
@@ -2421,7 +2421,7 @@ static void reset_sys_reg_descs(struct kvm_vcpu *vcpu,
 int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	struct sys_reg_params params;
-	unsigned long esr = kvm_vcpu_get_hsr(vcpu);
+	unsigned long esr = kvm_vcpu_get_esr(vcpu);
 	int Rt = kvm_vcpu_sys_get_rt(vcpu);
 	int ret;
 

From a0e50aa3f4a8a5c9fb791b8f32d624e2a1a735bd Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@arm.com>
Date: Fri, 4 Jan 2019 21:09:05 +0100
Subject: [PATCH 039/474] KVM: arm64: Factor out stage 2 page table data from
 struct kvm

As we are about to reuse our stage 2 page table manipulation code for
shadow stage 2 page tables in the context of nested virtualization, we
are going to manage multiple stage 2 page tables for a single VM.

This requires some pretty invasive changes to our data structures,
which moves the vmid and pgd pointers into a separate structure and
change pretty much all of our mmu code to operate on this structure
instead.

The new structure is called struct kvm_s2_mmu.

There is no intended functional change by this patch alone.

Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
[Designed data structure layout in collaboration]
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Co-developed-by: Marc Zyngier <maz@kernel.org>
[maz: Moved the last_vcpu_ran down to the S2 MMU structure as well]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_asm.h        |   7 +-
 arch/arm64/include/asm/kvm_host.h       |  32 ++-
 arch/arm64/include/asm/kvm_mmu.h        |  16 +-
 arch/arm64/kvm/arm.c                    |  36 +--
 arch/arm64/kvm/hyp/include/hyp/switch.h |   4 +-
 arch/arm64/kvm/hyp/nvhe/switch.c        |   2 +-
 arch/arm64/kvm/hyp/nvhe/tlb.c           |  33 ++-
 arch/arm64/kvm/hyp/vhe/switch.c         |   2 +-
 arch/arm64/kvm/hyp/vhe/tlb.c            |  26 +--
 arch/arm64/kvm/mmu.c                    | 280 +++++++++++++-----------
 10 files changed, 240 insertions(+), 198 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 5a91aaae78d2..18d39b30d9c9 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -77,6 +77,7 @@
 
 struct kvm;
 struct kvm_vcpu;
+struct kvm_s2_mmu;
 
 DECLARE_KVM_NVHE_SYM(__kvm_hyp_init);
 DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
@@ -90,9 +91,9 @@ DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
 #endif
 
 extern void __kvm_flush_vm_context(void);
-extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
-extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
-extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
+extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa);
+extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
+extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e0920df1d0c1..85a529eeeae3 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -66,19 +66,34 @@ struct kvm_vmid {
 	u32    vmid;
 };
 
-struct kvm_arch {
+struct kvm_s2_mmu {
 	struct kvm_vmid vmid;
 
-	/* stage2 entry level table */
-	pgd_t *pgd;
-	phys_addr_t pgd_phys;
-
-	/* VTCR_EL2 value for this VM */
-	u64    vtcr;
+	/*
+	 * stage2 entry level table
+	 *
+	 * Two kvm_s2_mmu structures in the same VM can point to the same
+	 * pgd here.  This happens when running a guest using a
+	 * translation regime that isn't affected by its own stage-2
+	 * translation, such as a non-VHE hypervisor running at vEL2, or
+	 * for vEL1/EL0 with vHCR_EL2.VM == 0.  In that case, we use the
+	 * canonical stage-2 page tables.
+	 */
+	pgd_t		*pgd;
+	phys_addr_t	pgd_phys;
 
 	/* The last vcpu id that ran on each physical CPU */
 	int __percpu *last_vcpu_ran;
 
+	struct kvm *kvm;
+};
+
+struct kvm_arch {
+	struct kvm_s2_mmu mmu;
+
+	/* VTCR_EL2 value for this VM */
+	u64    vtcr;
+
 	/* The maximum number of vCPUs depends on the used GIC model */
 	int max_vcpus;
 
@@ -254,6 +269,9 @@ struct kvm_vcpu_arch {
 	void *sve_state;
 	unsigned int sve_max_vl;
 
+	/* Stage 2 paging state used by the hardware on next switch */
+	struct kvm_s2_mmu *hw_mmu;
+
 	/* HYP configuration */
 	u64 hcr_el2;
 	u32 mdcr_el2;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index b12bfc1f051a..22157ded04ca 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -134,8 +134,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 void free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);
-int kvm_alloc_stage2_pgd(struct kvm *kvm);
-void kvm_free_stage2_pgd(struct kvm *kvm);
+int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu);
+void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable);
 
@@ -577,13 +577,13 @@ static inline u64 kvm_vttbr_baddr_mask(struct kvm *kvm)
 	return vttbr_baddr_mask(kvm_phys_shift(kvm), kvm_stage2_levels(kvm));
 }
 
-static __always_inline u64 kvm_get_vttbr(struct kvm *kvm)
+static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
 {
-	struct kvm_vmid *vmid = &kvm->arch.vmid;
+	struct kvm_vmid *vmid = &mmu->vmid;
 	u64 vmid_field, baddr;
 	u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0;
 
-	baddr = kvm->arch.pgd_phys;
+	baddr = mmu->pgd_phys;
 	vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT;
 	return kvm_phys_to_vttbr(baddr) | vmid_field | cnp;
 }
@@ -592,10 +592,10 @@ static __always_inline u64 kvm_get_vttbr(struct kvm *kvm)
  * Must be called from hyp code running at EL2 with an updated VTTBR
  * and interrupts disabled.
  */
-static __always_inline void __load_guest_stage2(struct kvm *kvm)
+static __always_inline void __load_guest_stage2(struct kvm_s2_mmu *mmu)
 {
-	write_sysreg(kvm->arch.vtcr, vtcr_el2);
-	write_sysreg(kvm_get_vttbr(kvm), vttbr_el2);
+	write_sysreg(kern_hyp_va(mmu->kvm)->arch.vtcr, vtcr_el2);
+	write_sysreg(kvm_get_vttbr(mmu), vttbr_el2);
 
 	/*
 	 * ARM errata 1165522 and 1530923 require the actual execution of the
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 0bf2cf5614c6..beb0e68cccaa 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -106,22 +106,15 @@ static int kvm_arm_default_max_vcpus(void)
  */
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
-	int ret, cpu;
+	int ret;
 
 	ret = kvm_arm_setup_stage2(kvm, type);
 	if (ret)
 		return ret;
 
-	kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran));
-	if (!kvm->arch.last_vcpu_ran)
-		return -ENOMEM;
-
-	for_each_possible_cpu(cpu)
-		*per_cpu_ptr(kvm->arch.last_vcpu_ran, cpu) = -1;
-
-	ret = kvm_alloc_stage2_pgd(kvm);
+	ret = kvm_init_stage2_mmu(kvm, &kvm->arch.mmu);
 	if (ret)
-		goto out_fail_alloc;
+		return ret;
 
 	ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP);
 	if (ret)
@@ -129,18 +122,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	kvm_vgic_early_init(kvm);
 
-	/* Mark the initial VMID generation invalid */
-	kvm->arch.vmid.vmid_gen = 0;
-
 	/* The maximum number of VCPUs is limited by the host's GIC model */
 	kvm->arch.max_vcpus = kvm_arm_default_max_vcpus();
 
 	return ret;
 out_free_stage2_pgd:
-	kvm_free_stage2_pgd(kvm);
-out_fail_alloc:
-	free_percpu(kvm->arch.last_vcpu_ran);
-	kvm->arch.last_vcpu_ran = NULL;
+	kvm_free_stage2_pgd(&kvm->arch.mmu);
 	return ret;
 }
 
@@ -160,9 +147,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 
 	kvm_vgic_destroy(kvm);
 
-	free_percpu(kvm->arch.last_vcpu_ran);
-	kvm->arch.last_vcpu_ran = NULL;
-
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (kvm->vcpus[i]) {
 			kvm_vcpu_destroy(kvm->vcpus[i]);
@@ -279,6 +263,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 	kvm_arm_pvtime_vcpu_init(&vcpu->arch);
 
+	vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
+
 	err = kvm_vgic_vcpu_init(vcpu);
 	if (err)
 		return err;
@@ -334,16 +320,18 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
+	struct kvm_s2_mmu *mmu;
 	int *last_ran;
 
-	last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran);
+	mmu = vcpu->arch.hw_mmu;
+	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
 	/*
 	 * We might get preempted before the vCPU actually runs, but
 	 * over-invalidation doesn't affect correctness.
 	 */
 	if (*last_ran != vcpu->vcpu_id) {
-		kvm_call_hyp(__kvm_tlb_flush_local_vmid, vcpu);
+		kvm_call_hyp(__kvm_tlb_flush_local_vmid, mmu);
 		*last_ran = vcpu->vcpu_id;
 	}
 
@@ -680,7 +668,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		cond_resched();
 
-		update_vmid(&vcpu->kvm->arch.vmid);
+		update_vmid(&vcpu->arch.hw_mmu->vmid);
 
 		check_vcpu_requests(vcpu);
 
@@ -729,7 +717,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		smp_store_mb(vcpu->mode, IN_GUEST_MODE);
 
-		if (ret <= 0 || need_new_vmid_gen(&vcpu->kvm->arch.vmid) ||
+		if (ret <= 0 || need_new_vmid_gen(&vcpu->arch.hw_mmu->vmid) ||
 		    kvm_request_pending(vcpu)) {
 			vcpu->mode = OUTSIDE_GUEST_MODE;
 			isb(); /* Ensure work in x_flush_hwstate is committed */
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 8f622688fa64..5c03441b5b6c 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -122,9 +122,9 @@ static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
 	}
 }
 
-static inline void __activate_vm(struct kvm *kvm)
+static inline void __activate_vm(struct kvm_s2_mmu *mmu)
 {
-	__load_guest_stage2(kvm);
+	__load_guest_stage2(mmu);
 }
 
 static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index a1dcf59bd45e..37321b2157d9 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -194,7 +194,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_state_nvhe(guest_ctxt);
 
-	__activate_vm(kern_hyp_va(vcpu->kvm));
+	__activate_vm(kern_hyp_va(vcpu->arch.hw_mmu));
 	__activate_traps(vcpu);
 
 	__hyp_vgic_restore_state(vcpu);
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index d4475f8340c4..11dbe031f0ba 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -12,7 +12,8 @@ struct tlb_inv_context {
 	u64		tcr;
 };
 
-static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
+static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
+				  struct tlb_inv_context *cxt)
 {
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		u64 val;
@@ -30,12 +31,10 @@ static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
 		isb();
 	}
 
-	/* __load_guest_stage2() includes an ISB for the workaround. */
-	__load_guest_stage2(kvm);
-	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
+	__load_guest_stage2(mmu);
 }
 
-static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
+static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
 {
 	write_sysreg(0, vttbr_el2);
 
@@ -47,15 +46,15 @@ static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
 	}
 }
 
-void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
 {
 	struct tlb_inv_context cxt;
 
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	kvm = kern_hyp_va(kvm);
-	__tlb_switch_to_guest(kvm, &cxt);
+	mmu = kern_hyp_va(mmu);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -98,39 +97,39 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	if (icache_is_vpipt())
 		__flush_icache_all();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_vmid(struct kvm *kvm)
+void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	kvm = kern_hyp_va(kvm);
-	__tlb_switch_to_guest(kvm, &cxt);
+	mmu = kern_hyp_va(mmu);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 {
-	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
+	mmu = kern_hyp_va(mmu);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
 void __kvm_flush_vm_context(void)
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index c0d33deba77e..c52d714e0d75 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -125,7 +125,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	 * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
 	 * (among other things).
 	 */
-	__activate_vm(vcpu->kvm);
+	__activate_vm(vcpu->arch.hw_mmu);
 	__activate_traps(vcpu);
 
 	sysreg_restore_guest_state_vhe(guest_ctxt);
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index b275101e9c9c..ada1d56f0709 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -16,7 +16,8 @@ struct tlb_inv_context {
 	u64		sctlr;
 };
 
-static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
+static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
+				  struct tlb_inv_context *cxt)
 {
 	u64 val;
 
@@ -52,14 +53,14 @@ static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
 	 * place before clearing TGE. __load_guest_stage2() already
 	 * has an ISB in order to deal with this.
 	 */
-	__load_guest_stage2(kvm);
+	__load_guest_stage2(mmu);
 	val = read_sysreg(hcr_el2);
 	val &= ~HCR_TGE;
 	write_sysreg(val, hcr_el2);
 	isb();
 }
 
-static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
+static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
 {
 	/*
 	 * We're done with the TLB operation, let's restore the host's
@@ -78,14 +79,14 @@ static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
 	local_irq_restore(cxt->flags);
 }
 
-void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
 {
 	struct tlb_inv_context cxt;
 
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -106,38 +107,37 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_vmid(struct kvm *kvm)
+void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 {
-	struct kvm *kvm = vcpu->kvm;
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(kvm, &cxt);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
 void __kvm_flush_vm_context(void)
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8c0035cab6b6..2c6d59b509a5 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -55,12 +55,12 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot)
  */
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
-	kvm_call_hyp(__kvm_tlb_flush_vmid, kvm);
+	kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
 }
 
-static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+static void kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
 {
-	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
+	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ipa);
 }
 
 /*
@@ -90,37 +90,39 @@ static bool kvm_is_device_pfn(unsigned long pfn)
 
 /**
  * stage2_dissolve_pmd() - clear and flush huge PMD entry
- * @kvm:	pointer to kvm structure.
+ * @mmu:	pointer to mmu structure to operate on
  * @addr:	IPA
  * @pmd:	pmd pointer for IPA
  *
  * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs.
  */
-static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
+static void stage2_dissolve_pmd(struct kvm_s2_mmu *mmu, phys_addr_t addr, pmd_t *pmd)
 {
 	if (!pmd_thp_or_huge(*pmd))
 		return;
 
 	pmd_clear(pmd);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr);
 	put_page(virt_to_page(pmd));
 }
 
 /**
  * stage2_dissolve_pud() - clear and flush huge PUD entry
- * @kvm:	pointer to kvm structure.
+ * @mmu:	pointer to mmu structure to operate on
  * @addr:	IPA
  * @pud:	pud pointer for IPA
  *
  * Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs.
  */
-static void stage2_dissolve_pud(struct kvm *kvm, phys_addr_t addr, pud_t *pudp)
+static void stage2_dissolve_pud(struct kvm_s2_mmu *mmu, phys_addr_t addr, pud_t *pudp)
 {
+	struct kvm *kvm = mmu->kvm;
+
 	if (!stage2_pud_huge(kvm, *pudp))
 		return;
 
 	stage2_pud_clear(kvm, pudp);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr);
 	put_page(virt_to_page(pudp));
 }
 
@@ -156,40 +158,44 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
 	return p;
 }
 
-static void clear_stage2_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
+static void clear_stage2_pgd_entry(struct kvm_s2_mmu *mmu, pgd_t *pgd, phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d_table __maybe_unused = stage2_p4d_offset(kvm, pgd, 0UL);
 	stage2_pgd_clear(kvm, pgd);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr);
 	stage2_p4d_free(kvm, p4d_table);
 	put_page(virt_to_page(pgd));
 }
 
-static void clear_stage2_p4d_entry(struct kvm *kvm, p4d_t *p4d, phys_addr_t addr)
+static void clear_stage2_p4d_entry(struct kvm_s2_mmu *mmu, p4d_t *p4d, phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud_table __maybe_unused = stage2_pud_offset(kvm, p4d, 0);
 	stage2_p4d_clear(kvm, p4d);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr);
 	stage2_pud_free(kvm, pud_table);
 	put_page(virt_to_page(p4d));
 }
 
-static void clear_stage2_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
+static void clear_stage2_pud_entry(struct kvm_s2_mmu *mmu, pud_t *pud, phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	pmd_t *pmd_table __maybe_unused = stage2_pmd_offset(kvm, pud, 0);
+
 	VM_BUG_ON(stage2_pud_huge(kvm, *pud));
 	stage2_pud_clear(kvm, pud);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr);
 	stage2_pmd_free(kvm, pmd_table);
 	put_page(virt_to_page(pud));
 }
 
-static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
+static void clear_stage2_pmd_entry(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr_t addr)
 {
 	pte_t *pte_table = pte_offset_kernel(pmd, 0);
 	VM_BUG_ON(pmd_thp_or_huge(*pmd));
 	pmd_clear(pmd);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr);
 	free_page((unsigned long)pte_table);
 	put_page(virt_to_page(pmd));
 }
@@ -255,7 +261,7 @@ static inline void kvm_pgd_populate(pgd_t *pgdp, p4d_t *p4dp)
  * we then fully enforce cacheability of RAM, no matter what the guest
  * does.
  */
-static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
+static void unmap_stage2_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd,
 		       phys_addr_t addr, phys_addr_t end)
 {
 	phys_addr_t start_addr = addr;
@@ -267,7 +273,7 @@ static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
 			pte_t old_pte = *pte;
 
 			kvm_set_pte(pte, __pte(0));
-			kvm_tlb_flush_vmid_ipa(kvm, addr);
+			kvm_tlb_flush_vmid_ipa(mmu, addr);
 
 			/* No need to invalidate the cache for device mappings */
 			if (!kvm_is_device_pfn(pte_pfn(old_pte)))
@@ -277,13 +283,14 @@ static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
-	if (stage2_pte_table_empty(kvm, start_pte))
-		clear_stage2_pmd_entry(kvm, pmd, start_addr);
+	if (stage2_pte_table_empty(mmu->kvm, start_pte))
+		clear_stage2_pmd_entry(mmu, pmd, start_addr);
 }
 
-static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
+static void unmap_stage2_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
 		       phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	phys_addr_t next, start_addr = addr;
 	pmd_t *pmd, *start_pmd;
 
@@ -295,24 +302,25 @@ static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
 				pmd_t old_pmd = *pmd;
 
 				pmd_clear(pmd);
-				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				kvm_tlb_flush_vmid_ipa(mmu, addr);
 
 				kvm_flush_dcache_pmd(old_pmd);
 
 				put_page(virt_to_page(pmd));
 			} else {
-				unmap_stage2_ptes(kvm, pmd, addr, next);
+				unmap_stage2_ptes(mmu, pmd, addr, next);
 			}
 		}
 	} while (pmd++, addr = next, addr != end);
 
 	if (stage2_pmd_table_empty(kvm, start_pmd))
-		clear_stage2_pud_entry(kvm, pud, start_addr);
+		clear_stage2_pud_entry(mmu, pud, start_addr);
 }
 
-static void unmap_stage2_puds(struct kvm *kvm, p4d_t *p4d,
+static void unmap_stage2_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
 		       phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	phys_addr_t next, start_addr = addr;
 	pud_t *pud, *start_pud;
 
@@ -324,22 +332,23 @@ static void unmap_stage2_puds(struct kvm *kvm, p4d_t *p4d,
 				pud_t old_pud = *pud;
 
 				stage2_pud_clear(kvm, pud);
-				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				kvm_tlb_flush_vmid_ipa(mmu, addr);
 				kvm_flush_dcache_pud(old_pud);
 				put_page(virt_to_page(pud));
 			} else {
-				unmap_stage2_pmds(kvm, pud, addr, next);
+				unmap_stage2_pmds(mmu, pud, addr, next);
 			}
 		}
 	} while (pud++, addr = next, addr != end);
 
 	if (stage2_pud_table_empty(kvm, start_pud))
-		clear_stage2_p4d_entry(kvm, p4d, start_addr);
+		clear_stage2_p4d_entry(mmu, p4d, start_addr);
 }
 
-static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd,
+static void unmap_stage2_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
 		       phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	phys_addr_t next, start_addr = addr;
 	p4d_t *p4d, *start_p4d;
 
@@ -347,11 +356,11 @@ static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd,
 	do {
 		next = stage2_p4d_addr_end(kvm, addr, end);
 		if (!stage2_p4d_none(kvm, *p4d))
-			unmap_stage2_puds(kvm, p4d, addr, next);
+			unmap_stage2_puds(mmu, p4d, addr, next);
 	} while (p4d++, addr = next, addr != end);
 
 	if (stage2_p4d_table_empty(kvm, start_p4d))
-		clear_stage2_pgd_entry(kvm, pgd, start_addr);
+		clear_stage2_pgd_entry(mmu, pgd, start_addr);
 }
 
 /**
@@ -365,8 +374,9 @@ static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd,
  * destroying the VM), otherwise another faulting VCPU may come in and mess
  * with things behind our backs.
  */
-static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
+static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
 {
+	struct kvm *kvm = mmu->kvm;
 	pgd_t *pgd;
 	phys_addr_t addr = start, end = start + size;
 	phys_addr_t next;
@@ -374,18 +384,18 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	assert_spin_locked(&kvm->mmu_lock);
 	WARN_ON(size & ~PAGE_MASK);
 
-	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
 	do {
 		/*
 		 * Make sure the page table is still active, as another thread
 		 * could have possibly freed the page table, while we released
 		 * the lock.
 		 */
-		if (!READ_ONCE(kvm->arch.pgd))
+		if (!READ_ONCE(mmu->pgd))
 			break;
 		next = stage2_pgd_addr_end(kvm, addr, end);
 		if (!stage2_pgd_none(kvm, *pgd))
-			unmap_stage2_p4ds(kvm, pgd, addr, next);
+			unmap_stage2_p4ds(mmu, pgd, addr, next);
 		/*
 		 * If the range is too large, release the kvm->mmu_lock
 		 * to prevent starvation and lockup detector warnings.
@@ -395,7 +405,7 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	} while (pgd++, addr = next, addr != end);
 }
 
-static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
+static void stage2_flush_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd,
 			      phys_addr_t addr, phys_addr_t end)
 {
 	pte_t *pte;
@@ -407,9 +417,10 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
-static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
+static void stage2_flush_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
 			      phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pmd_t *pmd;
 	phys_addr_t next;
 
@@ -420,14 +431,15 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
 			if (pmd_thp_or_huge(*pmd))
 				kvm_flush_dcache_pmd(*pmd);
 			else
-				stage2_flush_ptes(kvm, pmd, addr, next);
+				stage2_flush_ptes(mmu, pmd, addr, next);
 		}
 	} while (pmd++, addr = next, addr != end);
 }
 
-static void stage2_flush_puds(struct kvm *kvm, p4d_t *p4d,
+static void stage2_flush_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
 			      phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud;
 	phys_addr_t next;
 
@@ -438,14 +450,15 @@ static void stage2_flush_puds(struct kvm *kvm, p4d_t *p4d,
 			if (stage2_pud_huge(kvm, *pud))
 				kvm_flush_dcache_pud(*pud);
 			else
-				stage2_flush_pmds(kvm, pud, addr, next);
+				stage2_flush_pmds(mmu, pud, addr, next);
 		}
 	} while (pud++, addr = next, addr != end);
 }
 
-static void stage2_flush_p4ds(struct kvm *kvm, pgd_t *pgd,
+static void stage2_flush_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
 			      phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d;
 	phys_addr_t next;
 
@@ -453,23 +466,24 @@ static void stage2_flush_p4ds(struct kvm *kvm, pgd_t *pgd,
 	do {
 		next = stage2_p4d_addr_end(kvm, addr, end);
 		if (!stage2_p4d_none(kvm, *p4d))
-			stage2_flush_puds(kvm, p4d, addr, next);
+			stage2_flush_puds(mmu, p4d, addr, next);
 	} while (p4d++, addr = next, addr != end);
 }
 
 static void stage2_flush_memslot(struct kvm *kvm,
 				 struct kvm_memory_slot *memslot)
 {
+	struct kvm_s2_mmu *mmu = &kvm->arch.mmu;
 	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
 	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
 	phys_addr_t next;
 	pgd_t *pgd;
 
-	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
 	do {
 		next = stage2_pgd_addr_end(kvm, addr, end);
 		if (!stage2_pgd_none(kvm, *pgd))
-			stage2_flush_p4ds(kvm, pgd, addr, next);
+			stage2_flush_p4ds(mmu, pgd, addr, next);
 
 		if (next != end)
 			cond_resched_lock(&kvm->mmu_lock);
@@ -996,21 +1010,23 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 }
 
 /**
- * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
- * @kvm:	The KVM struct pointer for the VM.
+ * kvm_init_stage2_mmu - Initialise a S2 MMU strucrure
+ * @kvm:	The pointer to the KVM structure
+ * @mmu:	The pointer to the s2 MMU structure
  *
  * Allocates only the stage-2 HW PGD level table(s) of size defined by
- * stage2_pgd_size(kvm).
+ * stage2_pgd_size(mmu->kvm).
  *
  * Note we don't need locking here as this is only called when the VM is
  * created, which can only be done once.
  */
-int kvm_alloc_stage2_pgd(struct kvm *kvm)
+int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
 {
 	phys_addr_t pgd_phys;
 	pgd_t *pgd;
+	int cpu;
 
-	if (kvm->arch.pgd != NULL) {
+	if (mmu->pgd != NULL) {
 		kvm_err("kvm_arch already initialized?\n");
 		return -EINVAL;
 	}
@@ -1024,8 +1040,20 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
 	if (WARN_ON(pgd_phys & ~kvm_vttbr_baddr_mask(kvm)))
 		return -EINVAL;
 
-	kvm->arch.pgd = pgd;
-	kvm->arch.pgd_phys = pgd_phys;
+	mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran));
+	if (!mmu->last_vcpu_ran) {
+		free_pages_exact(pgd, stage2_pgd_size(kvm));
+		return -ENOMEM;
+	}
+
+	for_each_possible_cpu(cpu)
+		*per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1;
+
+	mmu->kvm = kvm;
+	mmu->pgd = pgd;
+	mmu->pgd_phys = pgd_phys;
+	mmu->vmid.vmid_gen = 0;
+
 	return 0;
 }
 
@@ -1064,7 +1092,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
 
 		if (!(vma->vm_flags & VM_PFNMAP)) {
 			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
-			unmap_stage2_range(kvm, gpa, vm_end - vm_start);
+			unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
 		}
 		hva = vm_end;
 	} while (hva < reg_end);
@@ -1096,39 +1124,34 @@ void stage2_unmap_vm(struct kvm *kvm)
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
-/**
- * kvm_free_stage2_pgd - free all stage-2 tables
- * @kvm:	The KVM struct pointer for the VM.
- *
- * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all
- * underlying level-2 and level-3 tables before freeing the actual level-1 table
- * and setting the struct pointer to NULL.
- */
-void kvm_free_stage2_pgd(struct kvm *kvm)
+void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 {
+	struct kvm *kvm = mmu->kvm;
 	void *pgd = NULL;
 
 	spin_lock(&kvm->mmu_lock);
-	if (kvm->arch.pgd) {
-		unmap_stage2_range(kvm, 0, kvm_phys_size(kvm));
-		pgd = READ_ONCE(kvm->arch.pgd);
-		kvm->arch.pgd = NULL;
-		kvm->arch.pgd_phys = 0;
+	if (mmu->pgd) {
+		unmap_stage2_range(mmu, 0, kvm_phys_size(kvm));
+		pgd = READ_ONCE(mmu->pgd);
+		mmu->pgd = NULL;
 	}
 	spin_unlock(&kvm->mmu_lock);
 
 	/* Free the HW pgd, one page at a time */
-	if (pgd)
+	if (pgd) {
 		free_pages_exact(pgd, stage2_pgd_size(kvm));
+		free_percpu(mmu->last_vcpu_ran);
+	}
 }
 
-static p4d_t *stage2_get_p4d(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static p4d_t *stage2_get_p4d(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache,
 			     phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	pgd_t *pgd;
 	p4d_t *p4d;
 
-	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
 	if (stage2_pgd_none(kvm, *pgd)) {
 		if (!cache)
 			return NULL;
@@ -1140,13 +1163,14 @@ static p4d_t *stage2_get_p4d(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	return stage2_p4d_offset(kvm, pgd, addr);
 }
 
-static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static pud_t *stage2_get_pud(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache,
 			     phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d;
 	pud_t *pud;
 
-	p4d = stage2_get_p4d(kvm, cache, addr);
+	p4d = stage2_get_p4d(mmu, cache, addr);
 	if (stage2_p4d_none(kvm, *p4d)) {
 		if (!cache)
 			return NULL;
@@ -1158,13 +1182,14 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	return stage2_pud_offset(kvm, p4d, addr);
 }
 
-static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static pmd_t *stage2_get_pmd(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache,
 			     phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud;
 	pmd_t *pmd;
 
-	pud = stage2_get_pud(kvm, cache, addr);
+	pud = stage2_get_pud(mmu, cache, addr);
 	if (!pud || stage2_pud_huge(kvm, *pud))
 		return NULL;
 
@@ -1179,13 +1204,14 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	return stage2_pmd_offset(kvm, pud, addr);
 }
 
-static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
-			       *cache, phys_addr_t addr, const pmd_t *new_pmd)
+static int stage2_set_pmd_huge(struct kvm_s2_mmu *mmu,
+			       struct kvm_mmu_memory_cache *cache,
+			       phys_addr_t addr, const pmd_t *new_pmd)
 {
 	pmd_t *pmd, old_pmd;
 
 retry:
-	pmd = stage2_get_pmd(kvm, cache, addr);
+	pmd = stage2_get_pmd(mmu, cache, addr);
 	VM_BUG_ON(!pmd);
 
 	old_pmd = *pmd;
@@ -1218,7 +1244,7 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 		 * get handled accordingly.
 		 */
 		if (!pmd_thp_or_huge(old_pmd)) {
-			unmap_stage2_range(kvm, addr & S2_PMD_MASK, S2_PMD_SIZE);
+			unmap_stage2_range(mmu, addr & S2_PMD_MASK, S2_PMD_SIZE);
 			goto retry;
 		}
 		/*
@@ -1234,7 +1260,7 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 		 */
 		WARN_ON_ONCE(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
 		pmd_clear(pmd);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr);
 	} else {
 		get_page(virt_to_page(pmd));
 	}
@@ -1243,13 +1269,15 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 	return 0;
 }
 
-static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static int stage2_set_pud_huge(struct kvm_s2_mmu *mmu,
+			       struct kvm_mmu_memory_cache *cache,
 			       phys_addr_t addr, const pud_t *new_pudp)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pudp, old_pud;
 
 retry:
-	pudp = stage2_get_pud(kvm, cache, addr);
+	pudp = stage2_get_pud(mmu, cache, addr);
 	VM_BUG_ON(!pudp);
 
 	old_pud = *pudp;
@@ -1268,13 +1296,13 @@ static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cac
 		 * the range for this block and retry.
 		 */
 		if (!stage2_pud_huge(kvm, old_pud)) {
-			unmap_stage2_range(kvm, addr & S2_PUD_MASK, S2_PUD_SIZE);
+			unmap_stage2_range(mmu, addr & S2_PUD_MASK, S2_PUD_SIZE);
 			goto retry;
 		}
 
 		WARN_ON_ONCE(kvm_pud_pfn(old_pud) != kvm_pud_pfn(*new_pudp));
 		stage2_pud_clear(kvm, pudp);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr);
 	} else {
 		get_page(virt_to_page(pudp));
 	}
@@ -1289,9 +1317,10 @@ static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cac
  * leaf-entry is returned in the appropriate level variable - pudpp,
  * pmdpp, ptepp.
  */
-static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
+static bool stage2_get_leaf_entry(struct kvm_s2_mmu *mmu, phys_addr_t addr,
 				  pud_t **pudpp, pmd_t **pmdpp, pte_t **ptepp)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
@@ -1300,7 +1329,7 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
 	*pmdpp = NULL;
 	*ptepp = NULL;
 
-	pudp = stage2_get_pud(kvm, NULL, addr);
+	pudp = stage2_get_pud(mmu, NULL, addr);
 	if (!pudp || stage2_pud_none(kvm, *pudp) || !stage2_pud_present(kvm, *pudp))
 		return false;
 
@@ -1326,14 +1355,14 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
 	return true;
 }
 
-static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
+static bool stage2_is_exec(struct kvm_s2_mmu *mmu, phys_addr_t addr)
 {
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 	bool found;
 
-	found = stage2_get_leaf_entry(kvm, addr, &pudp, &pmdp, &ptep);
+	found = stage2_get_leaf_entry(mmu, addr, &pudp, &pmdp, &ptep);
 	if (!found)
 		return false;
 
@@ -1345,10 +1374,12 @@ static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
 		return kvm_s2pte_exec(ptep);
 }
 
-static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static int stage2_set_pte(struct kvm_s2_mmu *mmu,
+			  struct kvm_mmu_memory_cache *cache,
 			  phys_addr_t addr, const pte_t *new_pte,
 			  unsigned long flags)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte, old_pte;
@@ -1358,7 +1389,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	VM_BUG_ON(logging_active && !cache);
 
 	/* Create stage-2 page table mapping - Levels 0 and 1 */
-	pud = stage2_get_pud(kvm, cache, addr);
+	pud = stage2_get_pud(mmu, cache, addr);
 	if (!pud) {
 		/*
 		 * Ignore calls from kvm_set_spte_hva for unallocated
@@ -1372,7 +1403,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	 * on to allocate page.
 	 */
 	if (logging_active)
-		stage2_dissolve_pud(kvm, addr, pud);
+		stage2_dissolve_pud(mmu, addr, pud);
 
 	if (stage2_pud_none(kvm, *pud)) {
 		if (!cache)
@@ -1396,7 +1427,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	 * allocate page.
 	 */
 	if (logging_active)
-		stage2_dissolve_pmd(kvm, addr, pmd);
+		stage2_dissolve_pmd(mmu, addr, pmd);
 
 	/* Create stage-2 page mappings - Level 2 */
 	if (pmd_none(*pmd)) {
@@ -1420,7 +1451,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 			return 0;
 
 		kvm_set_pte(pte, __pte(0));
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr);
 	} else {
 		get_page(virt_to_page(pte));
 	}
@@ -1486,8 +1517,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 		if (ret)
 			goto out;
 		spin_lock(&kvm->mmu_lock);
-		ret = stage2_set_pte(kvm, &cache, addr, &pte,
-						KVM_S2PTE_FLAG_IS_IOMAP);
+		ret = stage2_set_pte(&kvm->arch.mmu, &cache, addr, &pte,
+				     KVM_S2PTE_FLAG_IS_IOMAP);
 		spin_unlock(&kvm->mmu_lock);
 		if (ret)
 			goto out;
@@ -1526,9 +1557,10 @@ static void stage2_wp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end)
  * @addr:	range start address
  * @end:	range end address
  */
-static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud,
+static void stage2_wp_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
 			   phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pmd_t *pmd;
 	phys_addr_t next;
 
@@ -1549,13 +1581,14 @@ static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud,
 
 /**
  * stage2_wp_puds - write protect P4D range
- * @pgd:	pointer to pgd entry
+ * @p4d:	pointer to p4d entry
  * @addr:	range start address
  * @end:	range end address
  */
-static void  stage2_wp_puds(struct kvm *kvm, p4d_t *p4d,
+static void  stage2_wp_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
 			    phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud;
 	phys_addr_t next;
 
@@ -1567,7 +1600,7 @@ static void  stage2_wp_puds(struct kvm *kvm, p4d_t *p4d,
 				if (!kvm_s2pud_readonly(pud))
 					kvm_set_s2pud_readonly(pud);
 			} else {
-				stage2_wp_pmds(kvm, pud, addr, next);
+				stage2_wp_pmds(mmu, pud, addr, next);
 			}
 		}
 	} while (pud++, addr = next, addr != end);
@@ -1579,9 +1612,10 @@ static void  stage2_wp_puds(struct kvm *kvm, p4d_t *p4d,
  * @addr:	range start address
  * @end:	range end address
  */
-static void  stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd,
+static void  stage2_wp_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
 			    phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d;
 	phys_addr_t next;
 
@@ -1589,7 +1623,7 @@ static void  stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd,
 	do {
 		next = stage2_p4d_addr_end(kvm, addr, end);
 		if (!stage2_p4d_none(kvm, *p4d))
-			stage2_wp_puds(kvm, p4d, addr, next);
+			stage2_wp_puds(mmu, p4d, addr, next);
 	} while (p4d++, addr = next, addr != end);
 }
 
@@ -1599,12 +1633,13 @@ static void  stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd,
  * @addr:	Start address of range
  * @end:	End address of range
  */
-static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
+static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pgd_t *pgd;
 	phys_addr_t next;
 
-	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
 	do {
 		/*
 		 * Release kvm_mmu_lock periodically if the memory region is
@@ -1616,11 +1651,11 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 		 * the lock.
 		 */
 		cond_resched_lock(&kvm->mmu_lock);
-		if (!READ_ONCE(kvm->arch.pgd))
+		if (!READ_ONCE(mmu->pgd))
 			break;
 		next = stage2_pgd_addr_end(kvm, addr, end);
 		if (stage2_pgd_present(kvm, *pgd))
-			stage2_wp_p4ds(kvm, pgd, addr, next);
+			stage2_wp_p4ds(mmu, pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -1650,7 +1685,7 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
 
 	spin_lock(&kvm->mmu_lock);
-	stage2_wp_range(kvm, start, end);
+	stage2_wp_range(&kvm->arch.mmu, start, end);
 	spin_unlock(&kvm->mmu_lock);
 	kvm_flush_remote_tlbs(kvm);
 }
@@ -1674,7 +1709,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
 	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
 
-	stage2_wp_range(kvm, start, end);
+	stage2_wp_range(&kvm->arch.mmu, start, end);
 }
 
 /*
@@ -1837,6 +1872,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	pgprot_t mem_type = PAGE_S2;
 	bool logging_active = memslot_is_logging(memslot);
 	unsigned long vma_pagesize, flags = 0;
+	struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
 
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
@@ -1958,7 +1994,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * execute permissions, and we preserve whatever we have.
 	 */
 	needs_exec = exec_fault ||
-		(fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa));
+		(fault_status == FSC_PERM && stage2_is_exec(mmu, fault_ipa));
 
 	if (vma_pagesize == PUD_SIZE) {
 		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
@@ -1970,7 +2006,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		if (needs_exec)
 			new_pud = kvm_s2pud_mkexec(new_pud);
 
-		ret = stage2_set_pud_huge(kvm, memcache, fault_ipa, &new_pud);
+		ret = stage2_set_pud_huge(mmu, memcache, fault_ipa, &new_pud);
 	} else if (vma_pagesize == PMD_SIZE) {
 		pmd_t new_pmd = kvm_pfn_pmd(pfn, mem_type);
 
@@ -1982,7 +2018,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		if (needs_exec)
 			new_pmd = kvm_s2pmd_mkexec(new_pmd);
 
-		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
+		ret = stage2_set_pmd_huge(mmu, memcache, fault_ipa, &new_pmd);
 	} else {
 		pte_t new_pte = kvm_pfn_pte(pfn, mem_type);
 
@@ -1994,7 +2030,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		if (needs_exec)
 			new_pte = kvm_s2pte_mkexec(new_pte);
 
-		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags);
+		ret = stage2_set_pte(mmu, memcache, fault_ipa, &new_pte, flags);
 	}
 
 out_unlock:
@@ -2023,7 +2059,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 
 	spin_lock(&vcpu->kvm->mmu_lock);
 
-	if (!stage2_get_leaf_entry(vcpu->kvm, fault_ipa, &pud, &pmd, &pte))
+	if (!stage2_get_leaf_entry(vcpu->arch.hw_mmu, fault_ipa, &pud, &pmd, &pte))
 		goto out;
 
 	if (pud) {		/* HugeTLB */
@@ -2197,14 +2233,14 @@ static int handle_hva_to_gpa(struct kvm *kvm,
 
 static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
-	unmap_stage2_range(kvm, gpa, size);
+	unmap_stage2_range(&kvm->arch.mmu, gpa, size);
 	return 0;
 }
 
 int kvm_unmap_hva_range(struct kvm *kvm,
 			unsigned long start, unsigned long end)
 {
-	if (!kvm->arch.pgd)
+	if (!kvm->arch.mmu.pgd)
 		return 0;
 
 	trace_kvm_unmap_hva_range(start, end);
@@ -2224,7 +2260,7 @@ static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data
 	 * therefore stage2_set_pte() never needs to clear out a huge PMD
 	 * through this calling path.
 	 */
-	stage2_set_pte(kvm, NULL, gpa, pte, 0);
+	stage2_set_pte(&kvm->arch.mmu, NULL, gpa, pte, 0);
 	return 0;
 }
 
@@ -2235,7 +2271,7 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 	kvm_pfn_t pfn = pte_pfn(pte);
 	pte_t stage2_pte;
 
-	if (!kvm->arch.pgd)
+	if (!kvm->arch.mmu.pgd)
 		return 0;
 
 	trace_kvm_set_spte_hva(hva);
@@ -2258,7 +2294,7 @@ static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 	pte_t *pte;
 
 	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
-	if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte))
+	if (!stage2_get_leaf_entry(&kvm->arch.mmu, gpa, &pud, &pmd, &pte))
 		return 0;
 
 	if (pud)
@@ -2276,7 +2312,7 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *
 	pte_t *pte;
 
 	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
-	if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte))
+	if (!stage2_get_leaf_entry(&kvm->arch.mmu, gpa, &pud, &pmd, &pte))
 		return 0;
 
 	if (pud)
@@ -2289,7 +2325,7 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
-	if (!kvm->arch.pgd)
+	if (!kvm->arch.mmu.pgd)
 		return 0;
 	trace_kvm_age_hva(start, end);
 	return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
@@ -2297,7 +2333,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 {
-	if (!kvm->arch.pgd)
+	if (!kvm->arch.mmu.pgd)
 		return 0;
 	trace_kvm_test_age_hva(hva);
 	return handle_hva_to_gpa(kvm, hva, hva + PAGE_SIZE,
@@ -2510,7 +2546,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 
 	spin_lock(&kvm->mmu_lock);
 	if (ret)
-		unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
+		unmap_stage2_range(&kvm->arch.mmu, mem->guest_phys_addr, mem->memory_size);
 	else
 		stage2_flush_memslot(kvm, memslot);
 	spin_unlock(&kvm->mmu_lock);
@@ -2529,7 +2565,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
-	kvm_free_stage2_pgd(kvm);
+	kvm_free_stage2_pgd(&kvm->arch.mmu);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
@@ -2539,7 +2575,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	phys_addr_t size = slot->npages << PAGE_SHIFT;
 
 	spin_lock(&kvm->mmu_lock);
-	unmap_stage2_range(kvm, gpa, size);
+	unmap_stage2_range(&kvm->arch.mmu, gpa, size);
 	spin_unlock(&kvm->mmu_lock);
 }
 

From efaa5b93afde088411b67a0dde34e67aedc6e72f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 2 Jan 2019 12:34:25 +0000
Subject: [PATCH 040/474] KVM: arm64: Use TTL hint in when invalidating stage-2
 translations

Since we often have a precise idea of the level we're dealing with
when invalidating TLBs, we can provide it to as a hint to our
invalidation helper.

Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_asm.h |  3 ++-
 arch/arm64/kvm/hyp/nvhe/tlb.c    |  5 +++--
 arch/arm64/kvm/hyp/vhe/tlb.c     |  5 +++--
 arch/arm64/kvm/mmu.c             | 29 +++++++++++++++--------------
 4 files changed, 23 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 18d39b30d9c9..61f654a4ae00 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -91,7 +91,8 @@ DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
 #endif
 
 extern void __kvm_flush_vm_context(void);
-extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa);
+extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
+				     int level);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
 extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
 
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 11dbe031f0ba..69eae608d670 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -46,7 +46,8 @@ static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
 	}
 }
 
-void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
+			      phys_addr_t ipa, int level)
 {
 	struct tlb_inv_context cxt;
 
@@ -62,7 +63,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
 	 * whole of Stage-1. Weep...
 	 */
 	ipa >>= 12;
-	__tlbi(ipas2e1is, ipa);
+	__tlbi_level(ipas2e1is, ipa, level);
 
 	/*
 	 * We have to ensure completion of the invalidation at Stage-2,
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index ada1d56f0709..fd7895945bbc 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -79,7 +79,8 @@ static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
 	local_irq_restore(cxt->flags);
 }
 
-void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
+			      phys_addr_t ipa, int level)
 {
 	struct tlb_inv_context cxt;
 
@@ -94,7 +95,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
 	 * whole of Stage-1. Weep...
 	 */
 	ipa >>= 12;
-	__tlbi(ipas2e1is, ipa);
+	__tlbi_level(ipas2e1is, ipa, level);
 
 	/*
 	 * We have to ensure completion of the invalidation at Stage-2,
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 2c6d59b509a5..41eedbfd961e 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -58,9 +58,10 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 	kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
 }
 
-static void kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa)
+static void kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
+				   int level)
 {
-	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ipa);
+	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ipa, level);
 }
 
 /*
@@ -102,7 +103,7 @@ static void stage2_dissolve_pmd(struct kvm_s2_mmu *mmu, phys_addr_t addr, pmd_t
 		return;
 
 	pmd_clear(pmd);
-	kvm_tlb_flush_vmid_ipa(mmu, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL);
 	put_page(virt_to_page(pmd));
 }
 
@@ -122,7 +123,7 @@ static void stage2_dissolve_pud(struct kvm_s2_mmu *mmu, phys_addr_t addr, pud_t
 		return;
 
 	stage2_pud_clear(kvm, pudp);
-	kvm_tlb_flush_vmid_ipa(mmu, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL);
 	put_page(virt_to_page(pudp));
 }
 
@@ -163,7 +164,7 @@ static void clear_stage2_pgd_entry(struct kvm_s2_mmu *mmu, pgd_t *pgd, phys_addr
 	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d_table __maybe_unused = stage2_p4d_offset(kvm, pgd, 0UL);
 	stage2_pgd_clear(kvm, pgd);
-	kvm_tlb_flush_vmid_ipa(mmu, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
 	stage2_p4d_free(kvm, p4d_table);
 	put_page(virt_to_page(pgd));
 }
@@ -173,7 +174,7 @@ static void clear_stage2_p4d_entry(struct kvm_s2_mmu *mmu, p4d_t *p4d, phys_addr
 	struct kvm *kvm = mmu->kvm;
 	pud_t *pud_table __maybe_unused = stage2_pud_offset(kvm, p4d, 0);
 	stage2_p4d_clear(kvm, p4d);
-	kvm_tlb_flush_vmid_ipa(mmu, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
 	stage2_pud_free(kvm, pud_table);
 	put_page(virt_to_page(p4d));
 }
@@ -185,7 +186,7 @@ static void clear_stage2_pud_entry(struct kvm_s2_mmu *mmu, pud_t *pud, phys_addr
 
 	VM_BUG_ON(stage2_pud_huge(kvm, *pud));
 	stage2_pud_clear(kvm, pud);
-	kvm_tlb_flush_vmid_ipa(mmu, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
 	stage2_pmd_free(kvm, pmd_table);
 	put_page(virt_to_page(pud));
 }
@@ -195,7 +196,7 @@ static void clear_stage2_pmd_entry(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr
 	pte_t *pte_table = pte_offset_kernel(pmd, 0);
 	VM_BUG_ON(pmd_thp_or_huge(*pmd));
 	pmd_clear(pmd);
-	kvm_tlb_flush_vmid_ipa(mmu, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
 	free_page((unsigned long)pte_table);
 	put_page(virt_to_page(pmd));
 }
@@ -273,7 +274,7 @@ static void unmap_stage2_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd,
 			pte_t old_pte = *pte;
 
 			kvm_set_pte(pte, __pte(0));
-			kvm_tlb_flush_vmid_ipa(mmu, addr);
+			kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PTE_LEVEL);
 
 			/* No need to invalidate the cache for device mappings */
 			if (!kvm_is_device_pfn(pte_pfn(old_pte)))
@@ -302,7 +303,7 @@ static void unmap_stage2_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
 				pmd_t old_pmd = *pmd;
 
 				pmd_clear(pmd);
-				kvm_tlb_flush_vmid_ipa(mmu, addr);
+				kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL);
 
 				kvm_flush_dcache_pmd(old_pmd);
 
@@ -332,7 +333,7 @@ static void unmap_stage2_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
 				pud_t old_pud = *pud;
 
 				stage2_pud_clear(kvm, pud);
-				kvm_tlb_flush_vmid_ipa(mmu, addr);
+				kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL);
 				kvm_flush_dcache_pud(old_pud);
 				put_page(virt_to_page(pud));
 			} else {
@@ -1260,7 +1261,7 @@ static int stage2_set_pmd_huge(struct kvm_s2_mmu *mmu,
 		 */
 		WARN_ON_ONCE(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
 		pmd_clear(pmd);
-		kvm_tlb_flush_vmid_ipa(mmu, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL);
 	} else {
 		get_page(virt_to_page(pmd));
 	}
@@ -1302,7 +1303,7 @@ static int stage2_set_pud_huge(struct kvm_s2_mmu *mmu,
 
 		WARN_ON_ONCE(kvm_pud_pfn(old_pud) != kvm_pud_pfn(*new_pudp));
 		stage2_pud_clear(kvm, pudp);
-		kvm_tlb_flush_vmid_ipa(mmu, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL);
 	} else {
 		get_page(virt_to_page(pudp));
 	}
@@ -1451,7 +1452,7 @@ static int stage2_set_pte(struct kvm_s2_mmu *mmu,
 			return 0;
 
 		kvm_set_pte(pte, __pte(0));
-		kvm_tlb_flush_vmid_ipa(mmu, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PTE_LEVEL);
 	} else {
 		get_page(virt_to_page(pte));
 	}

From 1b422dd7fc3c85556df656e3d8f1475ce99f93a0 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 26 Jun 2019 19:57:41 +0100
Subject: [PATCH 041/474] KVM: arm64: Introduce accessor for ctxt->sys_reg

In order to allow the disintegration of the per-vcpu sysreg array,
let's introduce a new helper (ctxt_sys_reg()) that returns the
in-memory copy of a system register, picked from a given context.

__vcpu_sys_reg() is rewritten to use this helper.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 85a529eeeae3..5b168226088e 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -405,12 +405,17 @@ struct kvm_vcpu_arch {
 #define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
 
 /*
- * Only use __vcpu_sys_reg if you know you want the memory backed version of a
- * register, and not the one most recently accessed by a running VCPU.  For
- * example, for userspace access or for system registers that are never context
- * switched, but only emulated.
+ * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the
+ * memory backed version of a register, and not the one most recently
+ * accessed by a running VCPU.  For example, for userspace access or
+ * for system registers that are never context switched, but only
+ * emulated.
  */
-#define __vcpu_sys_reg(v,r)	((v)->arch.ctxt.sys_regs[(r)])
+#define __ctxt_sys_reg(c,r)	(&(c)->sys_regs[(r)])
+
+#define ctxt_sys_reg(c,r)	(*__ctxt_sys_reg(c,r))
+
+#define __vcpu_sys_reg(v,r)	(ctxt_sys_reg(&(v)->arch.ctxt, (r)))
 
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
 void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);

From 71071acfd392c51d9c0b286067033534b59f6be4 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 12 Apr 2020 14:00:43 +0100
Subject: [PATCH 042/474] KVM: arm64: hyp: Use ctxt_sys_reg/__vcpu_sys_reg
 instead of raw sys_regs access

Switch the hypervisor code to using ctxt_sys_reg/__vcpu_sys_reg instead
of raw sys_regs accesses. No intended functionnal change.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h          |   2 +-
 arch/arm64/kvm/hyp/include/hyp/debug-sr.h  |   4 +-
 arch/arm64/kvm/hyp/include/hyp/switch.h    |   7 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 110 ++++++++++-----------
 arch/arm64/kvm/hyp/nvhe/switch.c           |   4 +-
 5 files changed, 62 insertions(+), 65 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 5b168226088e..d9360f91ef44 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -561,7 +561,7 @@ DECLARE_PER_CPU(kvm_host_data_t, kvm_host_data);
 static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
 {
 	/* The host's MPIDR is immutable, so let's set it up at boot time */
-	cpu_ctxt->sys_regs[MPIDR_EL1] = read_cpuid_mpidr();
+	ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr();
 }
 
 static inline bool kvm_arch_requires_vhe(void)
diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index 24e8acf9ec10..5499d6c1fd9f 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -104,7 +104,7 @@ static inline void __debug_save_state(struct kvm_vcpu *vcpu,
 	save_debug(dbg->dbg_wcr, dbgwcr, wrps);
 	save_debug(dbg->dbg_wvr, dbgwvr, wrps);
 
-	ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
+	ctxt_sys_reg(ctxt, MDCCINT_EL1) = read_sysreg(mdccint_el1);
 }
 
 static inline void __debug_restore_state(struct kvm_vcpu *vcpu,
@@ -124,7 +124,7 @@ static inline void __debug_restore_state(struct kvm_vcpu *vcpu,
 	restore_debug(dbg->dbg_wcr, dbgwcr, wrps);
 	restore_debug(dbg->dbg_wvr, dbgwvr, wrps);
 
-	write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, MDCCINT_EL1), mdccint_el1);
 }
 
 static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 5c03441b5b6c..7cf14e4f9f77 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -53,7 +53,7 @@ static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
+	__vcpu_sys_reg(vcpu, FPEXC32_EL2) = read_sysreg(fpexc32_el2);
 }
 
 static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
@@ -268,15 +268,14 @@ static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 		sve_load_state(vcpu_sve_pffr(vcpu),
 			       &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
 			       sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
-		write_sysreg_s(vcpu->arch.ctxt.sys_regs[ZCR_EL1], SYS_ZCR_EL12);
+		write_sysreg_s(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR_EL12);
 	} else {
 		__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
 	}
 
 	/* Skip restoring fpexc32 for AArch64 guests */
 	if (!(read_sysreg(hcr_el2) & HCR_RW))
-		write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2],
-			     fpexc32_el2);
+		write_sysreg(__vcpu_sys_reg(vcpu, FPEXC32_EL2), fpexc32_el2);
 
 	vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 6e04e061f762..37ef3e2cdbef 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -17,34 +17,34 @@
 
 static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
+	ctxt_sys_reg(ctxt, MDSCR_EL1)	= read_sysreg(mdscr_el1);
 }
 
 static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
-	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
+	ctxt_sys_reg(ctxt, TPIDR_EL0)	= read_sysreg(tpidr_el0);
+	ctxt_sys_reg(ctxt, TPIDRRO_EL0)	= read_sysreg(tpidrro_el0);
 }
 
 static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
-	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(SYS_SCTLR);
-	ctxt->sys_regs[CPACR_EL1]	= read_sysreg_el1(SYS_CPACR);
-	ctxt->sys_regs[TTBR0_EL1]	= read_sysreg_el1(SYS_TTBR0);
-	ctxt->sys_regs[TTBR1_EL1]	= read_sysreg_el1(SYS_TTBR1);
-	ctxt->sys_regs[TCR_EL1]		= read_sysreg_el1(SYS_TCR);
-	ctxt->sys_regs[ESR_EL1]		= read_sysreg_el1(SYS_ESR);
-	ctxt->sys_regs[AFSR0_EL1]	= read_sysreg_el1(SYS_AFSR0);
-	ctxt->sys_regs[AFSR1_EL1]	= read_sysreg_el1(SYS_AFSR1);
-	ctxt->sys_regs[FAR_EL1]		= read_sysreg_el1(SYS_FAR);
-	ctxt->sys_regs[MAIR_EL1]	= read_sysreg_el1(SYS_MAIR);
-	ctxt->sys_regs[VBAR_EL1]	= read_sysreg_el1(SYS_VBAR);
-	ctxt->sys_regs[CONTEXTIDR_EL1]	= read_sysreg_el1(SYS_CONTEXTIDR);
-	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg_el1(SYS_AMAIR);
-	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg_el1(SYS_CNTKCTL);
-	ctxt->sys_regs[PAR_EL1]		= read_sysreg(par_el1);
-	ctxt->sys_regs[TPIDR_EL1]	= read_sysreg(tpidr_el1);
+	ctxt_sys_reg(ctxt, CSSELR_EL1)	= read_sysreg(csselr_el1);
+	ctxt_sys_reg(ctxt, SCTLR_EL1)	= read_sysreg_el1(SYS_SCTLR);
+	ctxt_sys_reg(ctxt, CPACR_EL1)	= read_sysreg_el1(SYS_CPACR);
+	ctxt_sys_reg(ctxt, TTBR0_EL1)	= read_sysreg_el1(SYS_TTBR0);
+	ctxt_sys_reg(ctxt, TTBR1_EL1)	= read_sysreg_el1(SYS_TTBR1);
+	ctxt_sys_reg(ctxt, TCR_EL1)	= read_sysreg_el1(SYS_TCR);
+	ctxt_sys_reg(ctxt, ESR_EL1)	= read_sysreg_el1(SYS_ESR);
+	ctxt_sys_reg(ctxt, AFSR0_EL1)	= read_sysreg_el1(SYS_AFSR0);
+	ctxt_sys_reg(ctxt, AFSR1_EL1)	= read_sysreg_el1(SYS_AFSR1);
+	ctxt_sys_reg(ctxt, FAR_EL1)	= read_sysreg_el1(SYS_FAR);
+	ctxt_sys_reg(ctxt, MAIR_EL1)	= read_sysreg_el1(SYS_MAIR);
+	ctxt_sys_reg(ctxt, VBAR_EL1)	= read_sysreg_el1(SYS_VBAR);
+	ctxt_sys_reg(ctxt, CONTEXTIDR_EL1) = read_sysreg_el1(SYS_CONTEXTIDR);
+	ctxt_sys_reg(ctxt, AMAIR_EL1)	= read_sysreg_el1(SYS_AMAIR);
+	ctxt_sys_reg(ctxt, CNTKCTL_EL1)	= read_sysreg_el1(SYS_CNTKCTL);
+	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg(par_el1);
+	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
 
 	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
 	ctxt->gp_regs.elr_el1		= read_sysreg_el1(SYS_ELR);
@@ -57,55 +57,55 @@ static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(SYS_SPSR);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
-		ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
+		ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2);
 }
 
 static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
-	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, MDSCR_EL1),  mdscr_el1);
 }
 
 static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
 {
-	write_sysreg(ctxt->sys_regs[TPIDR_EL0],		tpidr_el0);
-	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0],	tpidrro_el0);
+	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL0),	tpidr_el0);
+	write_sysreg(ctxt_sys_reg(ctxt, TPIDRRO_EL0),	tpidrro_el0);
 }
 
 static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 {
-	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
-	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, MPIDR_EL1),	vmpidr_el2);
+	write_sysreg(ctxt_sys_reg(ctxt, CSSELR_EL1),	csselr_el1);
 
 	if (has_vhe() ||
 	    !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
-		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1),	SYS_SCTLR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
 	} else	if (!ctxt->__hyp_running_vcpu) {
 		/*
 		 * Must only be done for guest registers, hence the context
 		 * test. We're coming from the host, so SCTLR.M is already
 		 * set. Pairs with nVHE's __activate_traps().
 		 */
-		write_sysreg_el1((ctxt->sys_regs[TCR_EL1] |
+		write_sysreg_el1((ctxt_sys_reg(ctxt, TCR_EL1) |
 				  TCR_EPD1_MASK | TCR_EPD0_MASK),
 				 SYS_TCR);
 		isb();
 	}
 
-	write_sysreg_el1(ctxt->sys_regs[CPACR_EL1],	SYS_CPACR);
-	write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1],	SYS_TTBR0);
-	write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1],	SYS_TTBR1);
-	write_sysreg_el1(ctxt->sys_regs[ESR_EL1],	SYS_ESR);
-	write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1],	SYS_AFSR0);
-	write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1],	SYS_AFSR1);
-	write_sysreg_el1(ctxt->sys_regs[FAR_EL1],	SYS_FAR);
-	write_sysreg_el1(ctxt->sys_regs[MAIR_EL1],	SYS_MAIR);
-	write_sysreg_el1(ctxt->sys_regs[VBAR_EL1],	SYS_VBAR);
-	write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],SYS_CONTEXTIDR);
-	write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1],	SYS_AMAIR);
-	write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1],	SYS_CNTKCTL);
-	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
-	write_sysreg(ctxt->sys_regs[TPIDR_EL1],		tpidr_el1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, CPACR_EL1),	SYS_CPACR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR0_EL1),	SYS_TTBR0);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR1_EL1),	SYS_TTBR1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, ESR_EL1),	SYS_ESR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR0_EL1),	SYS_AFSR0);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR1_EL1),	SYS_AFSR1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, FAR_EL1),	SYS_FAR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, MAIR_EL1),	SYS_MAIR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, VBAR_EL1),	SYS_VBAR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, CONTEXTIDR_EL1), SYS_CONTEXTIDR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AMAIR_EL1),	SYS_AMAIR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, CNTKCTL_EL1), SYS_CNTKCTL);
+	write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1),	par_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1),	tpidr_el1);
 
 	if (!has_vhe() &&
 	    cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT) &&
@@ -120,9 +120,9 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 		 * deconfigured and disabled. We can now restore the host's
 		 * S1 configuration: SCTLR, and only then TCR.
 		 */
-		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1),	SYS_SCTLR);
 		isb();
-		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
 	}
 
 	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
@@ -153,51 +153,49 @@ static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctx
 	write_sysreg_el2(pstate,			SYS_SPSR);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
-		write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
+		write_sysreg_s(ctxt_sys_reg(ctxt, DISR_EL1), SYS_VDISR_EL2);
 }
 
 static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
 {
-	u64 *spsr, *sysreg;
+	u64 *spsr;
 
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
 	spsr = vcpu->arch.ctxt.gp_regs.spsr;
-	sysreg = vcpu->arch.ctxt.sys_regs;
 
 	spsr[KVM_SPSR_ABT] = read_sysreg(spsr_abt);
 	spsr[KVM_SPSR_UND] = read_sysreg(spsr_und);
 	spsr[KVM_SPSR_IRQ] = read_sysreg(spsr_irq);
 	spsr[KVM_SPSR_FIQ] = read_sysreg(spsr_fiq);
 
-	sysreg[DACR32_EL2] = read_sysreg(dacr32_el2);
-	sysreg[IFSR32_EL2] = read_sysreg(ifsr32_el2);
+	__vcpu_sys_reg(vcpu, DACR32_EL2) = read_sysreg(dacr32_el2);
+	__vcpu_sys_reg(vcpu, IFSR32_EL2) = read_sysreg(ifsr32_el2);
 
 	if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)
-		sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2);
+		__vcpu_sys_reg(vcpu, DBGVCR32_EL2) = read_sysreg(dbgvcr32_el2);
 }
 
 static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 {
-	u64 *spsr, *sysreg;
+	u64 *spsr;
 
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
 	spsr = vcpu->arch.ctxt.gp_regs.spsr;
-	sysreg = vcpu->arch.ctxt.sys_regs;
 
 	write_sysreg(spsr[KVM_SPSR_ABT], spsr_abt);
 	write_sysreg(spsr[KVM_SPSR_UND], spsr_und);
 	write_sysreg(spsr[KVM_SPSR_IRQ], spsr_irq);
 	write_sysreg(spsr[KVM_SPSR_FIQ], spsr_fiq);
 
-	write_sysreg(sysreg[DACR32_EL2], dacr32_el2);
-	write_sysreg(sysreg[IFSR32_EL2], ifsr32_el2);
+	write_sysreg(__vcpu_sys_reg(vcpu, DACR32_EL2), dacr32_el2);
+	write_sysreg(__vcpu_sys_reg(vcpu, IFSR32_EL2), ifsr32_el2);
 
 	if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)
-		write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2);
+		write_sysreg(__vcpu_sys_reg(vcpu, DBGVCR32_EL2), dbgvcr32_el2);
 }
 
 #endif /* __ARM64_KVM_HYP_SYSREG_SR_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 37321b2157d9..341be2f2f312 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -52,9 +52,9 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		 * configured and enabled. We can now restore the guest's S1
 		 * configuration: SCTLR, and only then TCR.
 		 */
-		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1),	SYS_SCTLR);
 		isb();
-		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
 	}
 }
 

From 308472c69213cea9b22a2156a19ea9ec06ea3bc1 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 4 Jul 2019 17:25:09 +0100
Subject: [PATCH 043/474] KVM: arm64: sve: Use __vcpu_sys_reg() instead of raw
 sys_regs access

Now that we have a wrapper for the sysreg accesses, let's use that
consistently.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/fpsimd.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index e329a36b2bee..e503caff14d1 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -109,12 +109,10 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 	local_irq_save(flags);
 
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
-		u64 *guest_zcr = &vcpu->arch.ctxt.sys_regs[ZCR_EL1];
-
 		fpsimd_save_and_flush_cpu_state();
 
 		if (guest_has_sve)
-			*guest_zcr = read_sysreg_s(SYS_ZCR_EL12);
+			__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_s(SYS_ZCR_EL12);
 	} else if (host_has_sve) {
 		/*
 		 * The FPSIMD/SVE state in the CPU has not been touched, and we

From 2c3db77c62b681af60757378219edcc93f658ba1 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 5 Jul 2019 11:21:27 +0100
Subject: [PATCH 044/474] KVM: arm64: pauth: Use ctxt_sys_reg() instead of raw
 sys_regs access

Now that we have a wrapper for the sysreg accesses, let's use that
consistently.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/switch.h | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 7cf14e4f9f77..70367699d69a 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -364,11 +364,14 @@ static inline bool esr_is_ptrauth_trap(u32 esr)
 	return false;
 }
 
-#define __ptrauth_save_key(regs, key)						\
-({										\
-	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
-	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
-})
+#define __ptrauth_save_key(ctxt, key)					\
+	do {								\
+	u64 __val;                                                      \
+	__val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);                \
+	ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val;                   \
+	__val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);                \
+	ctxt_sys_reg(ctxt, key ## KEYHI_EL1) = __val;                   \
+} while(0)
 
 static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 {
@@ -380,11 +383,11 @@ static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 		return false;
 
 	ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
-	__ptrauth_save_key(ctxt->sys_regs, APIA);
-	__ptrauth_save_key(ctxt->sys_regs, APIB);
-	__ptrauth_save_key(ctxt->sys_regs, APDA);
-	__ptrauth_save_key(ctxt->sys_regs, APDB);
-	__ptrauth_save_key(ctxt->sys_regs, APGA);
+	__ptrauth_save_key(ctxt, APIA);
+	__ptrauth_save_key(ctxt, APIB);
+	__ptrauth_save_key(ctxt, APDA);
+	__ptrauth_save_key(ctxt, APDB);
+	__ptrauth_save_key(ctxt, APGA);
 
 	vcpu_ptrauth_enable(vcpu);
 

From 5b78077a00f8109f7a4717b19309ef0a76d73372 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 5 Jul 2019 11:25:10 +0100
Subject: [PATCH 045/474] KVM: arm64: debug: Drop useless vpcu parameter

As part of the ongoing spring cleanup, remove the now useless
vcpu parameter that is passed around (host and guest contexts
give us everything we need).

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/debug-sr.h | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index 5499d6c1fd9f..0297dc63988c 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -88,9 +88,8 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
-static inline void __debug_save_state(struct kvm_vcpu *vcpu,
-				      struct kvm_guest_debug_arch *dbg,
-				      struct kvm_cpu_context *ctxt)
+static void __debug_save_state(struct kvm_guest_debug_arch *dbg,
+			       struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -107,9 +106,8 @@ static inline void __debug_save_state(struct kvm_vcpu *vcpu,
 	ctxt_sys_reg(ctxt, MDCCINT_EL1) = read_sysreg(mdccint_el1);
 }
 
-static inline void __debug_restore_state(struct kvm_vcpu *vcpu,
-					 struct kvm_guest_debug_arch *dbg,
-					 struct kvm_cpu_context *ctxt)
+static void __debug_restore_state(struct kvm_guest_debug_arch *dbg,
+				  struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -142,8 +140,8 @@ static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
 	host_dbg = &vcpu->arch.host_debug_state.regs;
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
 
-	__debug_save_state(vcpu, host_dbg, host_ctxt);
-	__debug_restore_state(vcpu, guest_dbg, guest_ctxt);
+	__debug_save_state(host_dbg, host_ctxt);
+	__debug_restore_state(guest_dbg, guest_ctxt);
 }
 
 static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
@@ -161,8 +159,8 @@ static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 	host_dbg = &vcpu->arch.host_debug_state.regs;
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
 
-	__debug_save_state(vcpu, guest_dbg, guest_ctxt);
-	__debug_restore_state(vcpu, host_dbg, host_ctxt);
+	__debug_save_state(guest_dbg, guest_ctxt);
+	__debug_restore_state(host_dbg, host_ctxt);
 
 	vcpu->arch.flags &= ~KVM_ARM64_DEBUG_DIRTY;
 }

From e47c2055c68e06977d7d8b7dbc2f7468a36d3658 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 28 Jun 2019 22:40:58 +0100
Subject: [PATCH 046/474] KVM: arm64: Make struct kvm_regs userspace-only

struct kvm_regs is used by userspace to indicate which register gets
accessed by the {GET,SET}_ONE_REG API. But as we're about to refactor
the layout of the in-kernel register structures, we need the kernel to
move away from it.

Let's make kvm_regs userspace only, and let the kernel map it to its own
internal representation.

Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h       | 18 +++---
 arch/arm64/include/asm/kvm_host.h          | 12 +++-
 arch/arm64/kernel/asm-offsets.c            |  3 +-
 arch/arm64/kvm/fpsimd.c                    |  2 +-
 arch/arm64/kvm/guest.c                     | 70 +++++++++++++++++-----
 arch/arm64/kvm/hyp/entry.S                 |  3 +-
 arch/arm64/kvm/hyp/include/hyp/switch.h    |  4 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 24 ++++----
 arch/arm64/kvm/regmap.c                    |  6 +-
 arch/arm64/kvm/reset.c                     |  2 +-
 10 files changed, 96 insertions(+), 48 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 269a76cd51ff..cd607999abc2 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -124,12 +124,12 @@ static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr)
 
 static __always_inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
 {
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;
+	return (unsigned long *)&vcpu_gp_regs(vcpu)->pc;
 }
 
 static inline unsigned long *__vcpu_elr_el1(const struct kvm_vcpu *vcpu)
 {
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->elr_el1;
+	return (unsigned long *)&vcpu->arch.ctxt.elr_el1;
 }
 
 static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu)
@@ -150,7 +150,7 @@ static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long
 
 static __always_inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu)
 {
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pstate;
+	return (unsigned long *)&vcpu_gp_regs(vcpu)->pstate;
 }
 
 static __always_inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu)
@@ -179,14 +179,14 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
 static __always_inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu,
 					 u8 reg_num)
 {
-	return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num];
+	return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs[reg_num];
 }
 
 static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
 				unsigned long val)
 {
 	if (reg_num != 31)
-		vcpu_gp_regs(vcpu)->regs.regs[reg_num] = val;
+		vcpu_gp_regs(vcpu)->regs[reg_num] = val;
 }
 
 static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
@@ -197,7 +197,7 @@ static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		return read_sysreg_el1(SYS_SPSR);
 	else
-		return vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1];
+		return vcpu->arch.ctxt.spsr[KVM_SPSR_EL1];
 }
 
 static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
@@ -210,7 +210,7 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		write_sysreg_el1(v, SYS_SPSR);
 	else
-		vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v;
+		vcpu->arch.ctxt.spsr[KVM_SPSR_EL1] = v;
 }
 
 /*
@@ -519,11 +519,11 @@ static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_i
 static __always_inline void __kvm_skip_instr(struct kvm_vcpu *vcpu)
 {
 	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
-	vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR);
+	vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR);
 
 	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 
-	write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, SYS_SPSR);
+	write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR);
 	write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
 }
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d9360f91ef44..bc1e91573d00 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -236,7 +236,15 @@ enum vcpu_sysreg {
 #define NR_COPRO_REGS	(NR_SYS_REGS * 2)
 
 struct kvm_cpu_context {
-	struct kvm_regs	gp_regs;
+	struct user_pt_regs regs;	/* sp = sp_el0 */
+
+	u64	sp_el1;
+	u64	elr_el1;
+
+	u64	spsr[KVM_NR_SPSR];
+
+	struct user_fpsimd_state fp_regs;
+
 	union {
 		u64 sys_regs[NR_SYS_REGS];
 		u32 copro[NR_COPRO_REGS];
@@ -402,7 +410,7 @@ struct kvm_vcpu_arch {
 				  system_supports_generic_auth()) && \
 				 ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_PTRAUTH))
 
-#define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
+#define vcpu_gp_regs(v)		(&(v)->arch.ctxt.regs)
 
 /*
  * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 0577e2142284..7d32fc959b1a 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -102,13 +102,12 @@ int main(void)
   DEFINE(VCPU_FAULT_DISR,	offsetof(struct kvm_vcpu, arch.fault.disr_el1));
   DEFINE(VCPU_WORKAROUND_FLAGS,	offsetof(struct kvm_vcpu, arch.workaround_flags));
   DEFINE(VCPU_HCR_EL2,		offsetof(struct kvm_vcpu, arch.hcr_el2));
-  DEFINE(CPU_GP_REGS,		offsetof(struct kvm_cpu_context, gp_regs));
+  DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_cpu_context, regs));
   DEFINE(CPU_APIAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIAKEYLO_EL1]));
   DEFINE(CPU_APIBKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIBKEYLO_EL1]));
   DEFINE(CPU_APDAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APDAKEYLO_EL1]));
   DEFINE(CPU_APDBKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APDBKEYLO_EL1]));
   DEFINE(CPU_APGAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APGAKEYLO_EL1]));
-  DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
   DEFINE(HOST_CONTEXT_VCPU,	offsetof(struct kvm_cpu_context, __hyp_running_vcpu));
   DEFINE(HOST_DATA_CONTEXT,	offsetof(struct kvm_host_data, host_ctxt));
 #endif
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index e503caff14d1..3e081d556e81 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -85,7 +85,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 	WARN_ON_ONCE(!irqs_disabled());
 
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
-		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.gp_regs.fp_regs,
+		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs,
 					 vcpu->arch.sve_state,
 					 vcpu->arch.sve_max_vl);
 
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index aea43ec60f37..9dd5bbeefae6 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -101,19 +101,60 @@ static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off)
 	return size;
 }
 
-static int validate_core_offset(const struct kvm_vcpu *vcpu,
-				const struct kvm_one_reg *reg)
+static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	u64 off = core_reg_offset_from_id(reg->id);
 	int size = core_reg_size_from_offset(vcpu, off);
 
 	if (size < 0)
-		return -EINVAL;
+		return NULL;
 
 	if (KVM_REG_SIZE(reg->id) != size)
-		return -EINVAL;
+		return NULL;
 
-	return 0;
+	switch (off) {
+	case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+	     KVM_REG_ARM_CORE_REG(regs.regs[30]):
+		off -= KVM_REG_ARM_CORE_REG(regs.regs[0]);
+		off /= 2;
+		return &vcpu->arch.ctxt.regs.regs[off];
+
+	case KVM_REG_ARM_CORE_REG(regs.sp):
+		return &vcpu->arch.ctxt.regs.sp;
+
+	case KVM_REG_ARM_CORE_REG(regs.pc):
+		return &vcpu->arch.ctxt.regs.pc;
+
+	case KVM_REG_ARM_CORE_REG(regs.pstate):
+		return &vcpu->arch.ctxt.regs.pstate;
+
+	case KVM_REG_ARM_CORE_REG(sp_el1):
+		return &vcpu->arch.ctxt.sp_el1;
+
+	case KVM_REG_ARM_CORE_REG(elr_el1):
+		return &vcpu->arch.ctxt.elr_el1;
+
+	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
+	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
+		off -= KVM_REG_ARM_CORE_REG(spsr[0]);
+		off /= 2;
+		return &vcpu->arch.ctxt.spsr[off];
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+		off -= KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]);
+		off /= 4;
+		return &vcpu->arch.ctxt.fp_regs.vregs[off];
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+		return &vcpu->arch.ctxt.fp_regs.fpsr;
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+		return &vcpu->arch.ctxt.fp_regs.fpcr;
+
+	default:
+		return NULL;
+	}
 }
 
 static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
@@ -125,8 +166,8 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	 * off the index in the "array".
 	 */
 	__u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr;
-	struct kvm_regs *regs = vcpu_gp_regs(vcpu);
-	int nr_regs = sizeof(*regs) / sizeof(__u32);
+	int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32);
+	void *addr;
 	u32 off;
 
 	/* Our ID is an index into the kvm_regs struct. */
@@ -135,10 +176,11 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
-	if (validate_core_offset(vcpu, reg))
+	addr = core_reg_addr(vcpu, reg);
+	if (!addr)
 		return -EINVAL;
 
-	if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
+	if (copy_to_user(uaddr, addr, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
 
 	return 0;
@@ -147,10 +189,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	__u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr;
-	struct kvm_regs *regs = vcpu_gp_regs(vcpu);
-	int nr_regs = sizeof(*regs) / sizeof(__u32);
+	int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32);
 	__uint128_t tmp;
-	void *valp = &tmp;
+	void *valp = &tmp, *addr;
 	u64 off;
 	int err = 0;
 
@@ -160,7 +201,8 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
-	if (validate_core_offset(vcpu, reg))
+	addr = core_reg_addr(vcpu, reg);
+	if (!addr)
 		return -EINVAL;
 
 	if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
@@ -198,7 +240,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		}
 	}
 
-	memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id));
+	memcpy(addr, valp, KVM_REG_SIZE(reg->id));
 
 	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
 		int i;
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index dfb4e6d359ab..ee32a7743389 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -16,8 +16,7 @@
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_ptrauth.h>
 
-#define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
-#define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
+#define CPU_XREG_OFFSET(x)	(CPU_USER_PT_REGS + 8*x)
 #define CPU_SP_EL0_OFFSET	(CPU_XREG_OFFSET(30) + 8)
 
 	.text
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 70367699d69a..784a581071fc 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -266,11 +266,11 @@ static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 
 	if (sve_guest) {
 		sve_load_state(vcpu_sve_pffr(vcpu),
-			       &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
+			       &vcpu->arch.ctxt.fp_regs.fpsr,
 			       sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
 		write_sysreg_s(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR_EL12);
 	} else {
-		__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
+		__fpsimd_restore_state(&vcpu->arch.ctxt.fp_regs);
 	}
 
 	/* Skip restoring fpexc32 for AArch64 guests */
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 37ef3e2cdbef..50938093cc5d 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -46,15 +46,15 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg(par_el1);
 	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
 
-	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
-	ctxt->gp_regs.elr_el1		= read_sysreg_el1(SYS_ELR);
-	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(SYS_SPSR);
+	ctxt->sp_el1			= read_sysreg(sp_el1);
+	ctxt->elr_el1			= read_sysreg_el1(SYS_ELR);
+	ctxt->spsr[KVM_SPSR_EL1]	= read_sysreg_el1(SYS_SPSR);
 }
 
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->gp_regs.regs.pc		= read_sysreg_el2(SYS_ELR);
-	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(SYS_SPSR);
+	ctxt->regs.pc			= read_sysreg_el2(SYS_ELR);
+	ctxt->regs.pstate		= read_sysreg_el2(SYS_SPSR);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
 		ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2);
@@ -125,14 +125,14 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
 	}
 
-	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
-	write_sysreg_el1(ctxt->gp_regs.elr_el1,		SYS_ELR);
-	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR);
+	write_sysreg(ctxt->sp_el1,			sp_el1);
+	write_sysreg_el1(ctxt->elr_el1,			SYS_ELR);
+	write_sysreg_el1(ctxt->spsr[KVM_SPSR_EL1],	SYS_SPSR);
 }
 
 static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
 {
-	u64 pstate = ctxt->gp_regs.regs.pstate;
+	u64 pstate = ctxt->regs.pstate;
 	u64 mode = pstate & PSR_AA32_MODE_MASK;
 
 	/*
@@ -149,7 +149,7 @@ static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctx
 	if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t)
 		pstate = PSR_MODE_EL2h | PSR_IL_BIT;
 
-	write_sysreg_el2(ctxt->gp_regs.regs.pc,		SYS_ELR);
+	write_sysreg_el2(ctxt->regs.pc,			SYS_ELR);
 	write_sysreg_el2(pstate,			SYS_SPSR);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
@@ -163,7 +163,7 @@ static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	spsr = vcpu->arch.ctxt.gp_regs.spsr;
+	spsr = vcpu->arch.ctxt.spsr;
 
 	spsr[KVM_SPSR_ABT] = read_sysreg(spsr_abt);
 	spsr[KVM_SPSR_UND] = read_sysreg(spsr_und);
@@ -184,7 +184,7 @@ static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	spsr = vcpu->arch.ctxt.gp_regs.spsr;
+	spsr = vcpu->arch.ctxt.spsr;
 
 	write_sysreg(spsr[KVM_SPSR_ABT], spsr_abt);
 	write_sysreg(spsr[KVM_SPSR_UND], spsr_und);
diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c
index a900181e3867..b1596f314087 100644
--- a/arch/arm64/kvm/regmap.c
+++ b/arch/arm64/kvm/regmap.c
@@ -100,7 +100,7 @@ static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][16] = {
  */
 unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num)
 {
-	unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs.regs;
+	unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.regs;
 	unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK;
 
 	switch (mode) {
@@ -148,7 +148,7 @@ unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu)
 	int spsr_idx = vcpu_spsr32_mode(vcpu);
 
 	if (!vcpu->arch.sysregs_loaded_on_cpu)
-		return vcpu_gp_regs(vcpu)->spsr[spsr_idx];
+		return vcpu->arch.ctxt.spsr[spsr_idx];
 
 	switch (spsr_idx) {
 	case KVM_SPSR_SVC:
@@ -171,7 +171,7 @@ void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v)
 	int spsr_idx = vcpu_spsr32_mode(vcpu);
 
 	if (!vcpu->arch.sysregs_loaded_on_cpu) {
-		vcpu_gp_regs(vcpu)->spsr[spsr_idx] = v;
+		vcpu->arch.ctxt.spsr[spsr_idx] = v;
 		return;
 	}
 
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index d3b209023727..8ca8607f5a9f 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -288,7 +288,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	/* Reset core registers */
 	memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu)));
-	vcpu_gp_regs(vcpu)->regs.pstate = pstate;
+	vcpu_gp_regs(vcpu)->pstate = pstate;
 
 	/* Reset system registers */
 	kvm_reset_sys_regs(vcpu);

From 98909e6d1c811b6368c9c84fa6b3f0817c32ac2f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 28 Jun 2019 23:05:38 +0100
Subject: [PATCH 047/474] KVM: arm64: Move ELR_EL1 to the system register array

As ELR-EL1 is a VNCR-capable register with ARMv8.4-NV, let's move it to
the sys_regs array and repaint the accessors. While we're at it, let's
kill the now useless accessors used only on the fault injection path.

Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h       | 21 ---------------------
 arch/arm64/include/asm/kvm_host.h          |  3 ++-
 arch/arm64/kvm/guest.c                     |  2 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h |  4 ++--
 arch/arm64/kvm/inject_fault.c              |  2 +-
 arch/arm64/kvm/sys_regs.c                  |  2 ++
 6 files changed, 8 insertions(+), 26 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index cd607999abc2..a12b5dc5db0d 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -127,27 +127,6 @@ static __always_inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->pc;
 }
 
-static inline unsigned long *__vcpu_elr_el1(const struct kvm_vcpu *vcpu)
-{
-	return (unsigned long *)&vcpu->arch.ctxt.elr_el1;
-}
-
-static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu)
-{
-	if (vcpu->arch.sysregs_loaded_on_cpu)
-		return read_sysreg_el1(SYS_ELR);
-	else
-		return *__vcpu_elr_el1(vcpu);
-}
-
-static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long v)
-{
-	if (vcpu->arch.sysregs_loaded_on_cpu)
-		write_sysreg_el1(v, SYS_ELR);
-	else
-		*__vcpu_elr_el1(vcpu) = v;
-}
-
 static __always_inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu)
 {
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->pstate;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index bc1e91573d00..f255507dd916 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -185,6 +185,8 @@ enum vcpu_sysreg {
 	APGAKEYLO_EL1,
 	APGAKEYHI_EL1,
 
+	ELR_EL1,
+
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
@@ -239,7 +241,6 @@ struct kvm_cpu_context {
 	struct user_pt_regs regs;	/* sp = sp_el0 */
 
 	u64	sp_el1;
-	u64	elr_el1;
 
 	u64	spsr[KVM_NR_SPSR];
 
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 9dd5bbeefae6..99ff09ad24e8 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -132,7 +132,7 @@ static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		return &vcpu->arch.ctxt.sp_el1;
 
 	case KVM_REG_ARM_CORE_REG(elr_el1):
-		return &vcpu->arch.ctxt.elr_el1;
+		return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1);
 
 	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
 	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 50938093cc5d..9ebbd626d4ab 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -47,7 +47,7 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
 
 	ctxt->sp_el1			= read_sysreg(sp_el1);
-	ctxt->elr_el1			= read_sysreg_el1(SYS_ELR);
+	ctxt_sys_reg(ctxt, ELR_EL1)	= read_sysreg_el1(SYS_ELR);
 	ctxt->spsr[KVM_SPSR_EL1]	= read_sysreg_el1(SYS_SPSR);
 }
 
@@ -126,7 +126,7 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	}
 
 	write_sysreg(ctxt->sp_el1,			sp_el1);
-	write_sysreg_el1(ctxt->elr_el1,			SYS_ELR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL1),	SYS_ELR);
 	write_sysreg_el1(ctxt->spsr[KVM_SPSR_EL1],	SYS_SPSR);
 }
 
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index e21fdd93027a..ebfdfc27b2bd 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -64,7 +64,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
 	case PSR_MODE_EL1h:
 		vbar = vcpu_read_sys_reg(vcpu, VBAR_EL1);
 		sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
-		vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
+		vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1);
 		break;
 	default:
 		/* Don't do that */
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index baf5ce9225ce..6657b83c0647 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -94,6 +94,7 @@ static bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
 	case TPIDR_EL1:		*val = read_sysreg_s(SYS_TPIDR_EL1);	break;
 	case AMAIR_EL1:		*val = read_sysreg_s(SYS_AMAIR_EL12);	break;
 	case CNTKCTL_EL1:	*val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
+	case ELR_EL1:		*val = read_sysreg_s(SYS_ELR_EL12);	break;
 	case PAR_EL1:		*val = read_sysreg_s(SYS_PAR_EL1);	break;
 	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
 	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
@@ -133,6 +134,7 @@ static bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
 	case TPIDR_EL1:		write_sysreg_s(val, SYS_TPIDR_EL1);	break;
 	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
 	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
+	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
 	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
 	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
 	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;

From 1bded23ea71cee2053fe1dd55c5d36d35bec56aa Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 28 Jun 2019 23:05:38 +0100
Subject: [PATCH 048/474] KVM: arm64: Move SP_EL1 to the system register array

SP_EL1 being a VNCR-capable register with ARMv8.4-NV, move it to the
system register array and update the accessors.

Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h          | 3 +--
 arch/arm64/kvm/guest.c                     | 2 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 4 ++--
 3 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f255507dd916..2bd6285eaf4c 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -186,6 +186,7 @@ enum vcpu_sysreg {
 	APGAKEYHI_EL1,
 
 	ELR_EL1,
+	SP_EL1,
 
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
@@ -240,8 +241,6 @@ enum vcpu_sysreg {
 struct kvm_cpu_context {
 	struct user_pt_regs regs;	/* sp = sp_el0 */
 
-	u64	sp_el1;
-
 	u64	spsr[KVM_NR_SPSR];
 
 	struct user_fpsimd_state fp_regs;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 99ff09ad24e8..d614716e073b 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -129,7 +129,7 @@ static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		return &vcpu->arch.ctxt.regs.pstate;
 
 	case KVM_REG_ARM_CORE_REG(sp_el1):
-		return &vcpu->arch.ctxt.sp_el1;
+		return __ctxt_sys_reg(&vcpu->arch.ctxt, SP_EL1);
 
 	case KVM_REG_ARM_CORE_REG(elr_el1):
 		return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1);
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 9ebbd626d4ab..4c26ba72120e 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -46,7 +46,7 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg(par_el1);
 	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
 
-	ctxt->sp_el1			= read_sysreg(sp_el1);
+	ctxt_sys_reg(ctxt, SP_EL1)	= read_sysreg(sp_el1);
 	ctxt_sys_reg(ctxt, ELR_EL1)	= read_sysreg_el1(SYS_ELR);
 	ctxt->spsr[KVM_SPSR_EL1]	= read_sysreg_el1(SYS_SPSR);
 }
@@ -125,7 +125,7 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
 	}
 
-	write_sysreg(ctxt->sp_el1,			sp_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, SP_EL1),	sp_el1);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL1),	SYS_ELR);
 	write_sysreg_el1(ctxt->spsr[KVM_SPSR_EL1],	SYS_SPSR);
 }

From fd85b66789aaa594a158f0a8aa4482c3ed0fed3d Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 28 Jun 2019 23:36:42 +0100
Subject: [PATCH 049/474] KVM: arm64: Disintegrate SPSR array

As we're about to move SPSR_EL1 into the VNCR page, we need to
disassociate it from the rest of the 32bit cruft. Let's break
the array into individual fields.

Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h       |  4 +--
 arch/arm64/include/asm/kvm_host.h          |  6 +++-
 arch/arm64/kvm/guest.c                     | 19 ++++++++----
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 28 +++++++----------
 arch/arm64/kvm/regmap.c                    | 35 ++++++++++++++++++++--
 5 files changed, 63 insertions(+), 29 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index a12b5dc5db0d..5f959fedff09 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -176,7 +176,7 @@ static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		return read_sysreg_el1(SYS_SPSR);
 	else
-		return vcpu->arch.ctxt.spsr[KVM_SPSR_EL1];
+		return vcpu->arch.ctxt.spsr_el1;
 }
 
 static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
@@ -189,7 +189,7 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		write_sysreg_el1(v, SYS_SPSR);
 	else
-		vcpu->arch.ctxt.spsr[KVM_SPSR_EL1] = v;
+		vcpu->arch.ctxt.spsr_el1 = v;
 }
 
 /*
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 2bd6285eaf4c..dfb97ed2f680 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -241,7 +241,11 @@ enum vcpu_sysreg {
 struct kvm_cpu_context {
 	struct user_pt_regs regs;	/* sp = sp_el0 */
 
-	u64	spsr[KVM_NR_SPSR];
+	u64	spsr_el1;		/* aka spsr_svc */
+	u64	spsr_abt;
+	u64	spsr_und;
+	u64	spsr_irq;
+	u64	spsr_fiq;
 
 	struct user_fpsimd_state fp_regs;
 
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index d614716e073b..70215f3a6f89 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -134,11 +134,20 @@ static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	case KVM_REG_ARM_CORE_REG(elr_el1):
 		return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1);
 
-	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
-	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
-		off -= KVM_REG_ARM_CORE_REG(spsr[0]);
-		off /= 2;
-		return &vcpu->arch.ctxt.spsr[off];
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_EL1]):
+		return &vcpu->arch.ctxt.spsr_el1;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_ABT]):
+		return &vcpu->arch.ctxt.spsr_abt;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_UND]):
+		return &vcpu->arch.ctxt.spsr_und;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_IRQ]):
+		return &vcpu->arch.ctxt.spsr_irq;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_FIQ]):
+		return &vcpu->arch.ctxt.spsr_fiq;
 
 	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
 	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 4c26ba72120e..fb4bc42e72c5 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -48,7 +48,7 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 
 	ctxt_sys_reg(ctxt, SP_EL1)	= read_sysreg(sp_el1);
 	ctxt_sys_reg(ctxt, ELR_EL1)	= read_sysreg_el1(SYS_ELR);
-	ctxt->spsr[KVM_SPSR_EL1]	= read_sysreg_el1(SYS_SPSR);
+	ctxt->spsr_el1			= read_sysreg_el1(SYS_SPSR);
 }
 
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
@@ -127,7 +127,7 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 
 	write_sysreg(ctxt_sys_reg(ctxt, SP_EL1),	sp_el1);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL1),	SYS_ELR);
-	write_sysreg_el1(ctxt->spsr[KVM_SPSR_EL1],	SYS_SPSR);
+	write_sysreg_el1(ctxt->spsr_el1,		SYS_SPSR);
 }
 
 static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
@@ -158,17 +158,13 @@ static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctx
 
 static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
 {
-	u64 *spsr;
-
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	spsr = vcpu->arch.ctxt.spsr;
-
-	spsr[KVM_SPSR_ABT] = read_sysreg(spsr_abt);
-	spsr[KVM_SPSR_UND] = read_sysreg(spsr_und);
-	spsr[KVM_SPSR_IRQ] = read_sysreg(spsr_irq);
-	spsr[KVM_SPSR_FIQ] = read_sysreg(spsr_fiq);
+	vcpu->arch.ctxt.spsr_abt = read_sysreg(spsr_abt);
+	vcpu->arch.ctxt.spsr_und = read_sysreg(spsr_und);
+	vcpu->arch.ctxt.spsr_irq = read_sysreg(spsr_irq);
+	vcpu->arch.ctxt.spsr_fiq = read_sysreg(spsr_fiq);
 
 	__vcpu_sys_reg(vcpu, DACR32_EL2) = read_sysreg(dacr32_el2);
 	__vcpu_sys_reg(vcpu, IFSR32_EL2) = read_sysreg(ifsr32_el2);
@@ -179,17 +175,13 @@ static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
 
 static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 {
-	u64 *spsr;
-
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	spsr = vcpu->arch.ctxt.spsr;
-
-	write_sysreg(spsr[KVM_SPSR_ABT], spsr_abt);
-	write_sysreg(spsr[KVM_SPSR_UND], spsr_und);
-	write_sysreg(spsr[KVM_SPSR_IRQ], spsr_irq);
-	write_sysreg(spsr[KVM_SPSR_FIQ], spsr_fiq);
+	write_sysreg(vcpu->arch.ctxt.spsr_abt, spsr_abt);
+	write_sysreg(vcpu->arch.ctxt.spsr_und, spsr_und);
+	write_sysreg(vcpu->arch.ctxt.spsr_irq, spsr_irq);
+	write_sysreg(vcpu->arch.ctxt.spsr_fiq, spsr_fiq);
 
 	write_sysreg(__vcpu_sys_reg(vcpu, DACR32_EL2), dacr32_el2);
 	write_sysreg(__vcpu_sys_reg(vcpu, IFSR32_EL2), ifsr32_el2);
diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c
index b1596f314087..97c110810527 100644
--- a/arch/arm64/kvm/regmap.c
+++ b/arch/arm64/kvm/regmap.c
@@ -147,8 +147,20 @@ unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu)
 {
 	int spsr_idx = vcpu_spsr32_mode(vcpu);
 
-	if (!vcpu->arch.sysregs_loaded_on_cpu)
-		return vcpu->arch.ctxt.spsr[spsr_idx];
+	if (!vcpu->arch.sysregs_loaded_on_cpu) {
+		switch (spsr_idx) {
+		case KVM_SPSR_SVC:
+			return vcpu->arch.ctxt.spsr_el1;
+		case KVM_SPSR_ABT:
+			return vcpu->arch.ctxt.spsr_abt;
+		case KVM_SPSR_UND:
+			return vcpu->arch.ctxt.spsr_und;
+		case KVM_SPSR_IRQ:
+			return vcpu->arch.ctxt.spsr_irq;
+		case KVM_SPSR_FIQ:
+			return vcpu->arch.ctxt.spsr_fiq;
+		}
+	}
 
 	switch (spsr_idx) {
 	case KVM_SPSR_SVC:
@@ -171,7 +183,24 @@ void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v)
 	int spsr_idx = vcpu_spsr32_mode(vcpu);
 
 	if (!vcpu->arch.sysregs_loaded_on_cpu) {
-		vcpu->arch.ctxt.spsr[spsr_idx] = v;
+		switch (spsr_idx) {
+		case KVM_SPSR_SVC:
+			vcpu->arch.ctxt.spsr_el1 = v;
+			break;
+		case KVM_SPSR_ABT:
+			vcpu->arch.ctxt.spsr_abt = v;
+			break;
+		case KVM_SPSR_UND:
+			vcpu->arch.ctxt.spsr_und = v;
+			break;
+		case KVM_SPSR_IRQ:
+			vcpu->arch.ctxt.spsr_irq = v;
+			break;
+		case KVM_SPSR_FIQ:
+			vcpu->arch.ctxt.spsr_fiq = v;
+			break;
+		}
+
 		return;
 	}
 

From 710f1982187afd3f25413d92a0804ccd780634f7 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 28 Jun 2019 23:05:38 +0100
Subject: [PATCH 050/474] KVM: arm64: Move SPSR_EL1 to the system register
 array

SPSR_EL1 being a VNCR-capable register with ARMv8.4-NV, move it to
the sysregs array and update the accessors.

Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h       | 4 ++--
 arch/arm64/include/asm/kvm_host.h          | 2 +-
 arch/arm64/kvm/guest.c                     | 2 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 4 ++--
 arch/arm64/kvm/regmap.c                    | 4 ++--
 5 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 5f959fedff09..57f9042e7270 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -176,7 +176,7 @@ static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		return read_sysreg_el1(SYS_SPSR);
 	else
-		return vcpu->arch.ctxt.spsr_el1;
+		return __vcpu_sys_reg(vcpu, SPSR_EL1);
 }
 
 static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
@@ -189,7 +189,7 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 	if (vcpu->arch.sysregs_loaded_on_cpu)
 		write_sysreg_el1(v, SYS_SPSR);
 	else
-		vcpu->arch.ctxt.spsr_el1 = v;
+		__vcpu_sys_reg(vcpu, SPSR_EL1) = v;
 }
 
 /*
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index dfb97ed2f680..91b1adb6789c 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -187,6 +187,7 @@ enum vcpu_sysreg {
 
 	ELR_EL1,
 	SP_EL1,
+	SPSR_EL1,
 
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
@@ -241,7 +242,6 @@ enum vcpu_sysreg {
 struct kvm_cpu_context {
 	struct user_pt_regs regs;	/* sp = sp_el0 */
 
-	u64	spsr_el1;		/* aka spsr_svc */
 	u64	spsr_abt;
 	u64	spsr_und;
 	u64	spsr_irq;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 70215f3a6f89..dfb5218137ca 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -135,7 +135,7 @@ static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1);
 
 	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_EL1]):
-		return &vcpu->arch.ctxt.spsr_el1;
+		return __ctxt_sys_reg(&vcpu->arch.ctxt, SPSR_EL1);
 
 	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_ABT]):
 		return &vcpu->arch.ctxt.spsr_abt;
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index fb4bc42e72c5..7a986030145f 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -48,7 +48,7 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 
 	ctxt_sys_reg(ctxt, SP_EL1)	= read_sysreg(sp_el1);
 	ctxt_sys_reg(ctxt, ELR_EL1)	= read_sysreg_el1(SYS_ELR);
-	ctxt->spsr_el1			= read_sysreg_el1(SYS_SPSR);
+	ctxt_sys_reg(ctxt, SPSR_EL1)	= read_sysreg_el1(SYS_SPSR);
 }
 
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
@@ -127,7 +127,7 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 
 	write_sysreg(ctxt_sys_reg(ctxt, SP_EL1),	sp_el1);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL1),	SYS_ELR);
-	write_sysreg_el1(ctxt->spsr_el1,		SYS_SPSR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, SPSR_EL1),	SYS_SPSR);
 }
 
 static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c
index 97c110810527..accc1d5fba61 100644
--- a/arch/arm64/kvm/regmap.c
+++ b/arch/arm64/kvm/regmap.c
@@ -150,7 +150,7 @@ unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu)
 	if (!vcpu->arch.sysregs_loaded_on_cpu) {
 		switch (spsr_idx) {
 		case KVM_SPSR_SVC:
-			return vcpu->arch.ctxt.spsr_el1;
+			return __vcpu_sys_reg(vcpu, SPSR_EL1);
 		case KVM_SPSR_ABT:
 			return vcpu->arch.ctxt.spsr_abt;
 		case KVM_SPSR_UND:
@@ -185,7 +185,7 @@ void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v)
 	if (!vcpu->arch.sysregs_loaded_on_cpu) {
 		switch (spsr_idx) {
 		case KVM_SPSR_SVC:
-			vcpu->arch.ctxt.spsr_el1 = v;
+			__vcpu_sys_reg(vcpu, SPSR_EL1) = v;
 			break;
 		case KVM_SPSR_ABT:
 			vcpu->arch.ctxt.spsr_abt = v;

From 3c5ff0c60f2febb170bc4096d4b8a8390ebb0bad Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 22 Apr 2020 08:58:22 +0100
Subject: [PATCH 051/474] KVM: arm64: timers: Rename kvm_timer_sync_hwstate to
 kvm_timer_sync_user

kvm_timer_sync_hwstate() has nothing to do with the timer HW state,
but more to do with the state of a userspace interrupt controller.
Change the suffix from _hwstate to_user, in keeping with the rest
of the code.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/arch_timer.c  | 2 +-
 arch/arm64/kvm/arm.c         | 4 ++--
 include/kvm/arm_arch_timer.h | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index a1fe0ea3254e..33d85a504720 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -615,7 +615,7 @@ static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu)
 	}
 }
 
-void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
+void kvm_timer_sync_user(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = vcpu_timer(vcpu);
 
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index beb0e68cccaa..e52f2b2305b5 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -723,7 +723,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			isb(); /* Ensure work in x_flush_hwstate is committed */
 			kvm_pmu_sync_hwstate(vcpu);
 			if (static_branch_unlikely(&userspace_irqchip_in_use))
-				kvm_timer_sync_hwstate(vcpu);
+				kvm_timer_sync_user(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			local_irq_enable();
 			preempt_enable();
@@ -768,7 +768,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * timer virtual interrupt state.
 		 */
 		if (static_branch_unlikely(&userspace_irqchip_in_use))
-			kvm_timer_sync_hwstate(vcpu);
+			kvm_timer_sync_user(vcpu);
 
 		kvm_arch_vcpu_ctxsync_fp(vcpu);
 
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index d120e6c323e7..a821dd1df0cf 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -71,7 +71,7 @@ int kvm_timer_hyp_init(bool);
 int kvm_timer_enable(struct kvm_vcpu *vcpu);
 int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
-void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu);
+void kvm_timer_sync_user(struct kvm_vcpu *vcpu);
 bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu);
 void kvm_timer_update_run(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu);

From 41ce82f63c0624556b94b90551e4f70a0c913879 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 28 Jun 2019 15:23:43 +0100
Subject: [PATCH 052/474] KVM: arm64: timers: Move timer registers to the
 sys_regs file

Move the timer gsisters to the sysreg file. This will further help when
they are directly changed by a nesting hypervisor in the VNCR page.

This requires moving the initialisation of the timer struct so that some
of the helpers (such as arch_timer_ctx_index) can work correctly at an
early stage.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h |   6 ++
 arch/arm64/kvm/arch_timer.c       | 155 +++++++++++++++++++++++-------
 arch/arm64/kvm/trace_arm.h        |   8 +-
 include/kvm/arm_arch_timer.h      |  11 +--
 4 files changed, 136 insertions(+), 44 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 91b1adb6789c..e1a32c0707bb 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -189,6 +189,12 @@ enum vcpu_sysreg {
 	SP_EL1,
 	SPSR_EL1,
 
+	CNTVOFF_EL2,
+	CNTV_CVAL_EL0,
+	CNTV_CTL_EL0,
+	CNTP_CVAL_EL0,
+	CNTP_CTL_EL0,
+
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 33d85a504720..32ba6fbc3814 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -51,6 +51,93 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 			      struct arch_timer_context *timer,
 			      enum kvm_arch_timer_regs treg);
 
+u32 timer_get_ctl(struct arch_timer_context *ctxt)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		return __vcpu_sys_reg(vcpu, CNTV_CTL_EL0);
+	case TIMER_PTIMER:
+		return __vcpu_sys_reg(vcpu, CNTP_CTL_EL0);
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+}
+
+u64 timer_get_cval(struct arch_timer_context *ctxt)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		return __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
+	case TIMER_PTIMER:
+		return __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+}
+
+static u64 timer_get_offset(struct arch_timer_context *ctxt)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		return __vcpu_sys_reg(vcpu, CNTVOFF_EL2);
+	default:
+		return 0;
+	}
+}
+
+static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		__vcpu_sys_reg(vcpu, CNTV_CTL_EL0) = ctl;
+		break;
+	case TIMER_PTIMER:
+		__vcpu_sys_reg(vcpu, CNTP_CTL_EL0) = ctl;
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
+static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0) = cval;
+		break;
+	case TIMER_PTIMER:
+		__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = cval;
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
+static void timer_set_offset(struct arch_timer_context *ctxt, u64 offset)
+{
+	struct kvm_vcpu *vcpu = ctxt->vcpu;
+
+	switch(arch_timer_ctx_index(ctxt)) {
+	case TIMER_VTIMER:
+		__vcpu_sys_reg(vcpu, CNTVOFF_EL2) = offset;
+		break;
+	default:
+		WARN(offset, "timer %ld\n", arch_timer_ctx_index(ctxt));
+	}
+}
+
 u64 kvm_phys_timer_read(void)
 {
 	return timecounter->cc->read(timecounter->cc);
@@ -124,8 +211,8 @@ static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx)
 {
 	u64 cval, now;
 
-	cval = timer_ctx->cnt_cval;
-	now = kvm_phys_timer_read() - timer_ctx->cntvoff;
+	cval = timer_get_cval(timer_ctx);
+	now = kvm_phys_timer_read() - timer_get_offset(timer_ctx);
 
 	if (now < cval) {
 		u64 ns;
@@ -144,8 +231,8 @@ static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx)
 {
 	WARN_ON(timer_ctx && timer_ctx->loaded);
 	return timer_ctx &&
-	       !(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_IT_MASK) &&
-		(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_ENABLE);
+		((timer_get_ctl(timer_ctx) &
+		  (ARCH_TIMER_CTRL_IT_MASK | ARCH_TIMER_CTRL_ENABLE)) == ARCH_TIMER_CTRL_ENABLE);
 }
 
 /*
@@ -256,8 +343,8 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx)
 	if (!kvm_timer_irq_can_fire(timer_ctx))
 		return false;
 
-	cval = timer_ctx->cnt_cval;
-	now = kvm_phys_timer_read() - timer_ctx->cntvoff;
+	cval = timer_get_cval(timer_ctx);
+	now = kvm_phys_timer_read() - timer_get_offset(timer_ctx);
 
 	return cval <= now;
 }
@@ -350,8 +437,8 @@ static void timer_save_state(struct arch_timer_context *ctx)
 
 	switch (index) {
 	case TIMER_VTIMER:
-		ctx->cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL);
-		ctx->cnt_cval = read_sysreg_el0(SYS_CNTV_CVAL);
+		timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTV_CTL));
+		timer_set_cval(ctx, read_sysreg_el0(SYS_CNTV_CVAL));
 
 		/* Disable the timer */
 		write_sysreg_el0(0, SYS_CNTV_CTL);
@@ -359,8 +446,8 @@ static void timer_save_state(struct arch_timer_context *ctx)
 
 		break;
 	case TIMER_PTIMER:
-		ctx->cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL);
-		ctx->cnt_cval = read_sysreg_el0(SYS_CNTP_CVAL);
+		timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL));
+		timer_set_cval(ctx, read_sysreg_el0(SYS_CNTP_CVAL));
 
 		/* Disable the timer */
 		write_sysreg_el0(0, SYS_CNTP_CTL);
@@ -429,14 +516,14 @@ static void timer_restore_state(struct arch_timer_context *ctx)
 
 	switch (index) {
 	case TIMER_VTIMER:
-		write_sysreg_el0(ctx->cnt_cval, SYS_CNTV_CVAL);
+		write_sysreg_el0(timer_get_cval(ctx), SYS_CNTV_CVAL);
 		isb();
-		write_sysreg_el0(ctx->cnt_ctl, SYS_CNTV_CTL);
+		write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL);
 		break;
 	case TIMER_PTIMER:
-		write_sysreg_el0(ctx->cnt_cval, SYS_CNTP_CVAL);
+		write_sysreg_el0(timer_get_cval(ctx), SYS_CNTP_CVAL);
 		isb();
-		write_sysreg_el0(ctx->cnt_ctl, SYS_CNTP_CTL);
+		write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL);
 		break;
 	case NR_KVM_TIMERS:
 		BUG();
@@ -528,7 +615,7 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu)
 		kvm_timer_vcpu_load_nogic(vcpu);
 	}
 
-	set_cntvoff(map.direct_vtimer->cntvoff);
+	set_cntvoff(timer_get_offset(map.direct_vtimer));
 
 	kvm_timer_unblocking(vcpu);
 
@@ -639,8 +726,8 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 	 * resets the timer to be disabled and unmasked and is compliant with
 	 * the ARMv7 architecture.
 	 */
-	vcpu_vtimer(vcpu)->cnt_ctl = 0;
-	vcpu_ptimer(vcpu)->cnt_ctl = 0;
+	timer_set_ctl(vcpu_vtimer(vcpu), 0);
+	timer_set_ctl(vcpu_ptimer(vcpu), 0);
 
 	if (timer->enabled) {
 		kvm_timer_update_irq(vcpu, false, vcpu_vtimer(vcpu));
@@ -668,13 +755,13 @@ static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff)
 
 	mutex_lock(&kvm->lock);
 	kvm_for_each_vcpu(i, tmp, kvm)
-		vcpu_vtimer(tmp)->cntvoff = cntvoff;
+		timer_set_offset(vcpu_vtimer(tmp), cntvoff);
 
 	/*
 	 * When called from the vcpu create path, the CPU being created is not
 	 * included in the loop above, so we just set it here as well.
 	 */
-	vcpu_vtimer(vcpu)->cntvoff = cntvoff;
+	timer_set_offset(vcpu_vtimer(vcpu), cntvoff);
 	mutex_unlock(&kvm->lock);
 }
 
@@ -684,9 +771,12 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 
+	vtimer->vcpu = vcpu;
+	ptimer->vcpu = vcpu;
+
 	/* Synchronize cntvoff across all vtimers of a VM. */
 	update_vtimer_cntvoff(vcpu, kvm_phys_timer_read());
-	ptimer->cntvoff = 0;
+	timer_set_offset(ptimer, 0);
 
 	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	timer->bg_timer.function = kvm_bg_timer_expire;
@@ -704,9 +794,6 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 
 	vtimer->host_timer_irq_flags = host_vtimer_irq_flags;
 	ptimer->host_timer_irq_flags = host_ptimer_irq_flags;
-
-	vtimer->vcpu = vcpu;
-	ptimer->vcpu = vcpu;
 }
 
 static void kvm_timer_init_interrupt(void *info)
@@ -756,10 +843,12 @@ static u64 read_timer_ctl(struct arch_timer_context *timer)
 	 * UNKNOWN when ENABLE bit is 0, so we chose to set ISTATUS bit
 	 * regardless of ENABLE bit for our implementation convenience.
 	 */
+	u32 ctl = timer_get_ctl(timer);
+
 	if (!kvm_timer_compute_delta(timer))
-		return timer->cnt_ctl | ARCH_TIMER_CTRL_IT_STAT;
-	else
-		return timer->cnt_ctl;
+		ctl |= ARCH_TIMER_CTRL_IT_STAT;
+
+	return ctl;
 }
 
 u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
@@ -795,8 +884,8 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 
 	switch (treg) {
 	case TIMER_REG_TVAL:
-		val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff;
-		val &= lower_32_bits(val);
+		val = timer_get_cval(timer) - kvm_phys_timer_read() + timer_get_offset(timer);
+		val = lower_32_bits(val);
 		break;
 
 	case TIMER_REG_CTL:
@@ -804,11 +893,11 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 		break;
 
 	case TIMER_REG_CVAL:
-		val = timer->cnt_cval;
+		val = timer_get_cval(timer);
 		break;
 
 	case TIMER_REG_CNT:
-		val = kvm_phys_timer_read() - timer->cntvoff;
+		val = kvm_phys_timer_read() - timer_get_offset(timer);
 		break;
 
 	default:
@@ -842,15 +931,15 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu,
 {
 	switch (treg) {
 	case TIMER_REG_TVAL:
-		timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + (s32)val;
+		timer_set_cval(timer, kvm_phys_timer_read() - timer_get_offset(timer) + (s32)val);
 		break;
 
 	case TIMER_REG_CTL:
-		timer->cnt_ctl = val & ~ARCH_TIMER_CTRL_IT_STAT;
+		timer_set_ctl(timer, val & ~ARCH_TIMER_CTRL_IT_STAT);
 		break;
 
 	case TIMER_REG_CVAL:
-		timer->cnt_cval = val;
+		timer_set_cval(timer, val);
 		break;
 
 	default:
diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
index 4c71270cc097..4691053c5ee4 100644
--- a/arch/arm64/kvm/trace_arm.h
+++ b/arch/arm64/kvm/trace_arm.h
@@ -301,8 +301,8 @@ TRACE_EVENT(kvm_timer_save_state,
 	),
 
 	TP_fast_assign(
-		__entry->ctl			= ctx->cnt_ctl;
-		__entry->cval			= ctx->cnt_cval;
+		__entry->ctl			= timer_get_ctl(ctx);
+		__entry->cval			= timer_get_cval(ctx);
 		__entry->timer_idx		= arch_timer_ctx_index(ctx);
 	),
 
@@ -323,8 +323,8 @@ TRACE_EVENT(kvm_timer_restore_state,
 	),
 
 	TP_fast_assign(
-		__entry->ctl			= ctx->cnt_ctl;
-		__entry->cval			= ctx->cnt_cval;
+		__entry->ctl			= timer_get_ctl(ctx);
+		__entry->cval			= timer_get_cval(ctx);
 		__entry->timer_idx		= arch_timer_ctx_index(ctx);
 	),
 
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index a821dd1df0cf..51c19381108c 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -26,16 +26,9 @@ enum kvm_arch_timer_regs {
 struct arch_timer_context {
 	struct kvm_vcpu			*vcpu;
 
-	/* Registers: control register, timer value */
-	u32				cnt_ctl;
-	u64				cnt_cval;
-
 	/* Timer IRQ */
 	struct kvm_irq_level		irq;
 
-	/* Virtual offset */
-	u64				cntvoff;
-
 	/* Emulated Timer (may be unused) */
 	struct hrtimer			hrtimer;
 
@@ -109,4 +102,8 @@ void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu,
 				enum kvm_arch_timer_regs treg,
 				u64 val);
 
+/* Needed for tracing */
+u32 timer_get_ctl(struct arch_timer_context *ctxt);
+u64 timer_get_cval(struct arch_timer_context *ctxt);
+
 #endif

From 6de7dd31ded078b31a3812a46d8874f871b4e82f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 7 Jul 2020 15:34:06 +0100
Subject: [PATCH 053/474] KVM: arm64: Don't use has_vhe() for CHOOSE_HYP_SYM()

The recently introduced CHOOSE_HYP_SYM() macro picks one symbol
or another, depending on whether the kernel run as a VHE
hypervisor or not. For that, it uses the has_vhe() helper, which
is itself implemented as a final capability.

Unfortunately, __copy_hyp_vect_bpi now indirectly uses CHOOSE_HYP_SYM
to get the __bp_harden_hyp_vecs symbol, using has_vhe() in the process.
At this stage, the capability isn't final and things explode:

[    0.000000] ACPI: SRAT not present
[    0.000000] percpu: Embedded 34 pages/cpu s101264 r8192 d29808 u139264
[    0.000000] Detected PIPT I-cache on CPU0
[    0.000000] ------------[ cut here ]------------
[    0.000000] kernel BUG at arch/arm64/include/asm/cpufeature.h:459!
[    0.000000] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
[    0.000000] Modules linked in:
[    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 5.8.0-rc4-00080-gd630681366e5 #1388
[    0.000000] pstate: 80000085 (Nzcv daIf -PAN -UAO BTYPE=--)
[    0.000000] pc : check_branch_predictor+0x3a4/0x408
[    0.000000] lr : check_branch_predictor+0x2a4/0x408
[    0.000000] sp : ffff800011693e90
[    0.000000] x29: ffff800011693e90 x28: ffff8000116a1530
[    0.000000] x27: ffff8000112c1008 x26: ffff800010ca6ff8
[    0.000000] x25: ffff8000112c1000 x24: ffff8000116a1320
[    0.000000] x23: 0000000000000000 x22: ffff8000112c1000
[    0.000000] x21: ffff800010177120 x20: ffff8000116ae108
[    0.000000] x19: 0000000000000000 x18: ffff800011965c90
[    0.000000] x17: 0000000000022000 x16: 0000000000000003
[    0.000000] x15: 00000000ffffffff x14: ffff8000118c3a38
[    0.000000] x13: 0000000000000021 x12: 0000000000000022
[    0.000000] x11: d37a6f4de9bd37a7 x10: 000000000000001d
[    0.000000] x9 : 0000000000000000 x8 : ffff800011f8dad8
[    0.000000] x7 : ffff800011965ad0 x6 : 0000000000000003
[    0.000000] x5 : 0000000000000000 x4 : 0000000000000000
[    0.000000] x3 : 0000000000000100 x2 : 0000000000000004
[    0.000000] x1 : ffff8000116ae148 x0 : 0000000000000000
[    0.000000] Call trace:
[    0.000000]  check_branch_predictor+0x3a4/0x408
[    0.000000]  update_cpu_capabilities+0x84/0x138
[    0.000000]  init_cpu_features+0x2c0/0x2d8
[    0.000000]  cpuinfo_store_boot_cpu+0x54/0x64
[    0.000000]  smp_prepare_boot_cpu+0x2c/0x60
[    0.000000]  start_kernel+0x16c/0x574
[    0.000000] Code: 17ffffc7 91010281 14000198 17ffffca (d4210000)

This is addressed using a two-fold process:
- Replace has_vhe() with is_kernel_in_hyp_mode(), which tests
  whether we are running at EL2.
- Make CHOOSE_HYP_SYM() return an *undefined* symbol when
  compiled in the nVHE hypervisor, as we really should never
  use this helper in the nVHE-specific code.

With this in place, we're back to a bootable kernel again.

Fixes: b877e9849d41 ("KVM: arm64: Build hyp-entry.S separately for VHE/nVHE")
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_asm.h | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 5a91aaae78d2..1a66815ea01b 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -62,8 +62,26 @@
 
 #define CHOOSE_VHE_SYM(sym)	sym
 #define CHOOSE_NVHE_SYM(sym)	kvm_nvhe_sym(sym)
-#define CHOOSE_HYP_SYM(sym)	(has_vhe() ? CHOOSE_VHE_SYM(sym) \
+
+#ifndef __KVM_NVHE_HYPERVISOR__
+/*
+ * BIG FAT WARNINGS:
+ *
+ * - Don't be tempted to change the following is_kernel_in_hyp_mode()
+ *   to has_vhe(). has_vhe() is implemented as a *final* capability,
+ *   while this is used early at boot time, when the capabilities are
+ *   not final yet....
+ *
+ * - Don't let the nVHE hypervisor have access to this, as it will
+ *   pick the *wrong* symbol (yes, it runs at EL2...).
+ */
+#define CHOOSE_HYP_SYM(sym)	(is_kernel_in_hyp_mode() ? CHOOSE_VHE_SYM(sym) \
 					   : CHOOSE_NVHE_SYM(sym))
+#else
+/* The nVHE hypervisor shouldn't even try to access anything */
+extern void *__nvhe_undefined_symbol;
+#define CHOOSE_HYP_SYM(sym)	__nvhe_undefined_symbol
+#endif
 
 /* Translate a kernel address @ptr into its equivalent linear mapping */
 #define kvm_ksym_ref(ptr)						\

From 465931e70881476a210d44705102ef8b6ee6cdb0 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Thu, 18 Jun 2020 18:56:29 +0100
Subject: [PATCH 054/474] clk: rockchip: Revert "fix wrong mmc sample phase
 shift for rk3328"

This reverts commit 82f4b67f018c88a7cc9337f0067ed3d6ec352648.

According to a subsequent revert in the vendor kernel, the original
change was based on unclear documentation and was in fact incorrect.

Emprically, my board's HS200 eMMC at 200MHZ apparently gets lucky with a
phase where this had no impact, but limiting max-frequency to 150MHz to
match the nominal capability of the I/O pins made it virtually unusable,
constantly throwing errors and retuning. With this revert, it starts
behaving perfectly at 150MHz too.

Fixes: 82f4b67f018c ("clk: rockchip: fix wrong mmc sample phase shift for rk3328")
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Shawn Lin <shawn.lin@rock-chips.com>
Link: https://lore.kernel.org/r/c80eb52e34c03f817586b6b7912fbd4e31be9079.1589475794.git.robin.murphy@arm.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 drivers/clk/rockchip/clk-rk3328.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/clk/rockchip/clk-rk3328.c b/drivers/clk/rockchip/clk-rk3328.c
index c186a1985bf4..2429b7c2a8b3 100644
--- a/drivers/clk/rockchip/clk-rk3328.c
+++ b/drivers/clk/rockchip/clk-rk3328.c
@@ -808,22 +808,22 @@ static struct rockchip_clk_branch rk3328_clk_branches[] __initdata = {
 	MMC(SCLK_SDMMC_DRV, "sdmmc_drv", "clk_sdmmc",
 	    RK3328_SDMMC_CON0, 1),
 	MMC(SCLK_SDMMC_SAMPLE, "sdmmc_sample", "clk_sdmmc",
-	    RK3328_SDMMC_CON1, 0),
+	    RK3328_SDMMC_CON1, 1),
 
 	MMC(SCLK_SDIO_DRV, "sdio_drv", "clk_sdio",
 	    RK3328_SDIO_CON0, 1),
 	MMC(SCLK_SDIO_SAMPLE, "sdio_sample", "clk_sdio",
-	    RK3328_SDIO_CON1, 0),
+	    RK3328_SDIO_CON1, 1),
 
 	MMC(SCLK_EMMC_DRV, "emmc_drv", "clk_emmc",
 	    RK3328_EMMC_CON0, 1),
 	MMC(SCLK_EMMC_SAMPLE, "emmc_sample", "clk_emmc",
-	    RK3328_EMMC_CON1, 0),
+	    RK3328_EMMC_CON1, 1),
 
 	MMC(SCLK_SDMMC_EXT_DRV, "sdmmc_ext_drv", "clk_sdmmc_ext",
 	    RK3328_SDMMC_EXT_CON0, 1),
 	MMC(SCLK_SDMMC_EXT_SAMPLE, "sdmmc_ext_sample", "clk_sdmmc_ext",
-	    RK3328_SDMMC_EXT_CON1, 0),
+	    RK3328_SDMMC_EXT_CON1, 1),
 };
 
 static const char *const rk3328_critical_clocks[] __initconst = {

From d8f090dbeafdcc3d30761aa0062f19d1adf9ef08 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 15 Jun 2020 18:14:55 +0200
Subject: [PATCH 055/474] rtc: max77686: Do not allow interrupt to fire before
 system resume

The rtc-max77686 device shares the main interrupt line with parent MFD
device (max77686 driver).  During the system suspend, the parent MFD
device disables this IRQ to prevent an early event happening before
resuming I2C bus controller.

The same should be done by rtc-max77686 driver because otherwise the
interrupt handler max77686_rtc_alarm_irq() will be called before its
resume function (max77686_rtc_resume()).  Such issue is not fatal but
disabling shared IRQ by all users ensures correct behavior.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20200615161455.4420-1-krzk@kernel.org
---
 drivers/rtc/rtc-max77686.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c
index 03ebcf1c0f3d..645de5af707b 100644
--- a/drivers/rtc/rtc-max77686.c
+++ b/drivers/rtc/rtc-max77686.c
@@ -805,17 +805,33 @@ static int max77686_rtc_remove(struct platform_device *pdev)
 #ifdef CONFIG_PM_SLEEP
 static int max77686_rtc_suspend(struct device *dev)
 {
+	struct max77686_rtc_info *info = dev_get_drvdata(dev);
+	int ret = 0;
+
 	if (device_may_wakeup(dev)) {
 		struct max77686_rtc_info *info = dev_get_drvdata(dev);
 
-		return enable_irq_wake(info->virq);
+		ret = enable_irq_wake(info->virq);
 	}
 
-	return 0;
+	/*
+	 * Main IRQ (not virtual) must be disabled during suspend because if it
+	 * happens while suspended it will be handled before resuming I2C.
+	 *
+	 * Since Main IRQ is shared, all its users should disable it to be sure
+	 * it won't fire while one of them is still suspended.
+	 */
+	disable_irq(info->rtc_irq);
+
+	return ret;
 }
 
 static int max77686_rtc_resume(struct device *dev)
 {
+	struct max77686_rtc_info *info = dev_get_drvdata(dev);
+
+	enable_irq(info->rtc_irq);
+
 	if (device_may_wakeup(dev)) {
 		struct max77686_rtc_info *info = dev_get_drvdata(dev);
 

From 22f8d5a1bf230cf8567a4121fc3789babb46336d Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Sat, 20 Jun 2020 20:04:43 +0800
Subject: [PATCH 056/474] rtc: goldfish: Enable interrupt in set_alarm() when
 necessary

When use goldfish rtc, the "hwclock" command fails with "select() to
/dev/rtc to wait for clock tick timed out". This is because "hwclock"
need the set_alarm() hook to enable interrupt when alrm->enabled is
true. This operation is missing in goldfish rtc (but other rtc drivers,
such as cmos rtc, enable interrupt here), so add it.

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/1592654683-31314-1-git-send-email-chenhc@lemote.com
---
 drivers/rtc/rtc-goldfish.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/rtc/rtc-goldfish.c b/drivers/rtc/rtc-goldfish.c
index 27797157fcb3..6349d2cd3680 100644
--- a/drivers/rtc/rtc-goldfish.c
+++ b/drivers/rtc/rtc-goldfish.c
@@ -73,6 +73,7 @@ static int goldfish_rtc_set_alarm(struct device *dev,
 		rtc_alarm64 = rtc_tm_to_time64(&alrm->time) * NSEC_PER_SEC;
 		writel((rtc_alarm64 >> 32), base + TIMER_ALARM_HIGH);
 		writel(rtc_alarm64, base + TIMER_ALARM_LOW);
+		writel(1, base + TIMER_IRQ_ENABLED);
 	} else {
 		/*
 		 * if this function was called with enabled=0

From 3567d3d1477289d2ee988ee007507fca69f97eb8 Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Mon, 6 Jul 2020 08:27:27 +0200
Subject: [PATCH 057/474] rtc: Replace HTTP links with HTTPS ones

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `\bxmlns\b`:
        For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
          If both the HTTP and HTTPS versions
          return 200 OK and serve the same content:
            Replace HTTP with HTTPS.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20200706062727.18481-1-grandmaster@al2klimov.de
---
 drivers/rtc/rtc-ab-b5ze-s3.c | 2 +-
 drivers/rtc/rtc-bq32k.c      | 2 +-
 drivers/rtc/rtc-mcp795.c     | 2 +-
 drivers/rtc/rtc-pcf85063.c   | 4 ++--
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/rtc/rtc-ab-b5ze-s3.c b/drivers/rtc/rtc-ab-b5ze-s3.c
index 811fe2005488..2370ac0cdb5f 100644
--- a/drivers/rtc/rtc-ab-b5ze-s3.c
+++ b/drivers/rtc/rtc-ab-b5ze-s3.c
@@ -7,7 +7,7 @@
  *
  * Detailed datasheet of the chip is available here:
  *
- *  http://www.abracon.com/realtimeclock/AB-RTCMC-32.768kHz-B5ZE-S3-Application-Manual.pdf
+ *  https://www.abracon.com/realtimeclock/AB-RTCMC-32.768kHz-B5ZE-S3-Application-Manual.pdf
  *
  * This work is based on ISL12057 driver (drivers/rtc/rtc-isl12057.c).
  *
diff --git a/drivers/rtc/rtc-bq32k.c b/drivers/rtc/rtc-bq32k.c
index 4a63f0cd2321..933e4237237d 100644
--- a/drivers/rtc/rtc-bq32k.c
+++ b/drivers/rtc/rtc-bq32k.c
@@ -6,7 +6,7 @@
  * Copyright (C) 2014 Pavel Machek <pavel@denx.de>
  *
  * You can get hardware description at
- * http://www.ti.com/lit/ds/symlink/bq32000.pdf
+ * https://www.ti.com/lit/ds/symlink/bq32000.pdf
  */
 
 #include <linux/module.h>
diff --git a/drivers/rtc/rtc-mcp795.c b/drivers/rtc/rtc-mcp795.c
index 1660d5e79582..21cbf7f892e8 100644
--- a/drivers/rtc/rtc-mcp795.c
+++ b/drivers/rtc/rtc-mcp795.c
@@ -7,7 +7,7 @@
  * based on other Linux RTC drivers
  *
  * Device datasheet:
- * http://ww1.microchip.com/downloads/en/DeviceDoc/22280A.pdf
+ * https://ww1.microchip.com/downloads/en/DeviceDoc/22280A.pdf
  */
 
 #include <linux/module.h>
diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index 7a87f461bec8..ca55ba975aeb 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -21,8 +21,8 @@
 /*
  * Information for this driver was pulled from the following datasheets.
  *
- *  http://www.nxp.com/documents/data_sheet/PCF85063A.pdf
- *  http://www.nxp.com/documents/data_sheet/PCF85063TP.pdf
+ *  https://www.nxp.com/documents/data_sheet/PCF85063A.pdf
+ *  https://www.nxp.com/documents/data_sheet/PCF85063TP.pdf
  *
  *  PCF85063A -- Rev. 6 — 18 November 2015
  *  PCF85063TP -- Rev. 4 — 6 May 2015

From d3de4beb14a887754b83843bf23b6dbe8d022764 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johnson=20CH=20Chen=20=28=E9=99=B3=E6=98=AD=E5=8B=B3=29?=
 <JohnsonCH.Chen@moxa.com>
Date: Thu, 9 Jul 2020 06:34:06 +0000
Subject: [PATCH 058/474] rtc: ds1374: wdt: Use watchdog core for watchdog part

Let ds1374 watchdog use watchdog core functions. It also includes
improving watchdog timer setting and nowayout, and just uses ioctl()
of watchdog core.

Signed-off-by: Johnson Chen <johnsonch.chen@moxa.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/HK2PR01MB328182D5A54BFAA8A22E448AFA640@HK2PR01MB3281.apcprd01.prod.exchangelabs.com
---
 drivers/rtc/Kconfig      |   1 +
 drivers/rtc/rtc-ds1374.c | 258 +++++++++------------------------------
 2 files changed, 62 insertions(+), 197 deletions(-)

diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index b54d87d45c89..c25d51f35f0c 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -282,6 +282,7 @@ config RTC_DRV_DS1374
 config RTC_DRV_DS1374_WDT
 	bool "Dallas/Maxim DS1374 watchdog timer"
 	depends on RTC_DRV_DS1374
+	select WATCHDOG_CORE if WATCHDOG
 	help
 	  If you say Y here you will get support for the
 	  watchdog timer in the Dallas Semiconductor DS1374
diff --git a/drivers/rtc/rtc-ds1374.c b/drivers/rtc/rtc-ds1374.c
index 9c51a12cf70f..c71065d26cd2 100644
--- a/drivers/rtc/rtc-ds1374.c
+++ b/drivers/rtc/rtc-ds1374.c
@@ -46,6 +46,7 @@
 #define DS1374_REG_WDALM2	0x06
 #define DS1374_REG_CR		0x07 /* Control */
 #define DS1374_REG_CR_AIE	0x01 /* Alarm Int. Enable */
+#define DS1374_REG_CR_WDSTR	0x08 /* 1=INT, 0=RST */
 #define DS1374_REG_CR_WDALM	0x20 /* 1=Watchdog, 0=Alarm */
 #define DS1374_REG_CR_WACE	0x40 /* WD/Alarm counter enable */
 #define DS1374_REG_SR		0x08 /* Status */
@@ -71,7 +72,9 @@ struct ds1374 {
 	struct i2c_client *client;
 	struct rtc_device *rtc;
 	struct work_struct work;
-
+#ifdef CONFIG_RTC_DRV_DS1374_WDT
+	struct watchdog_device wdt;
+#endif
 	/* The mutex protects alarm operations, and prevents a race
 	 * between the enable_irq() in the workqueue and the free_irq()
 	 * in the remove function.
@@ -369,238 +372,98 @@ static const struct rtc_class_ops ds1374_rtc_ops = {
  *
  *****************************************************************************
  */
-static struct i2c_client *save_client;
 /* Default margin */
-#define WD_TIMO 131762
+#define TIMER_MARGIN_DEFAULT	32
+#define TIMER_MARGIN_MIN	1
+#define TIMER_MARGIN_MAX	4095 /* 24-bit value */
 
 #define DRV_NAME "DS1374 Watchdog"
 
-static int wdt_margin = WD_TIMO;
-static unsigned long wdt_is_open;
+static int wdt_margin;
 module_param(wdt_margin, int, 0);
 MODULE_PARM_DESC(wdt_margin, "Watchdog timeout in seconds (default 32s)");
 
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default ="
+		__MODULE_STRING(WATCHDOG_NOWAYOUT)")");
+
 static const struct watchdog_info ds1374_wdt_info = {
 	.identity       = "DS1374 WTD",
 	.options        = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING |
 						WDIOF_MAGICCLOSE,
 };
 
-static int ds1374_wdt_settimeout(unsigned int timeout)
+static int ds1374_wdt_settimeout(struct watchdog_device *wdt, unsigned int timeout)
 {
-	int ret = -ENOIOCTLCMD;
-	int cr;
+	struct ds1374 *ds1374 = watchdog_get_drvdata(wdt);
+	struct i2c_client *client = ds1374->client;
+	int ret, cr;
 
-	ret = cr = i2c_smbus_read_byte_data(save_client, DS1374_REG_CR);
-	if (ret < 0)
-		goto out;
+	wdt->timeout = timeout;
+
+	cr = i2c_smbus_read_byte_data(client, DS1374_REG_CR);
+	if (cr < 0)
+		return cr;
 
 	/* Disable any existing watchdog/alarm before setting the new one */
 	cr &= ~DS1374_REG_CR_WACE;
 
-	ret = i2c_smbus_write_byte_data(save_client, DS1374_REG_CR, cr);
+	ret = i2c_smbus_write_byte_data(client, DS1374_REG_CR, cr);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	/* Set new watchdog time */
-	ret = ds1374_write_rtc(save_client, timeout, DS1374_REG_WDALM0, 3);
-	if (ret) {
-		pr_info("couldn't set new watchdog time\n");
-		goto out;
-	}
+	timeout = timeout * 4096;
+	ret = ds1374_write_rtc(client, timeout, DS1374_REG_WDALM0, 3);
+	if (ret)
+		return ret;
 
 	/* Enable watchdog timer */
 	cr |= DS1374_REG_CR_WACE | DS1374_REG_CR_WDALM;
+	cr &= ~DS1374_REG_CR_WDSTR;/* for RST PIN */
 	cr &= ~DS1374_REG_CR_AIE;
 
-	ret = i2c_smbus_write_byte_data(save_client, DS1374_REG_CR, cr);
+	ret = i2c_smbus_write_byte_data(client, DS1374_REG_CR, cr);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	return 0;
-out:
-	return ret;
 }
 
-
 /*
  * Reload the watchdog timer.  (ie, pat the watchdog)
  */
-static void ds1374_wdt_ping(void)
+static int ds1374_wdt_start(struct watchdog_device *wdt)
 {
+	struct ds1374 *ds1374 = watchdog_get_drvdata(wdt);
 	u32 val;
-	int ret = 0;
 
-	ret = ds1374_read_rtc(save_client, &val, DS1374_REG_WDALM0, 3);
-	if (ret)
-		pr_info("WD TICK FAIL!!!!!!!!!! %i\n", ret);
+	return ds1374_read_rtc(ds1374->client, &val, DS1374_REG_WDALM0, 3);
 }
 
-static void ds1374_wdt_disable(void)
+static int ds1374_wdt_stop(struct watchdog_device *wdt)
 {
+	struct ds1374 *ds1374 = watchdog_get_drvdata(wdt);
+	struct i2c_client *client = ds1374->client;
 	int cr;
 
-	cr = i2c_smbus_read_byte_data(save_client, DS1374_REG_CR);
+	cr = i2c_smbus_read_byte_data(client, DS1374_REG_CR);
+	if (cr < 0)
+		return cr;
+
 	/* Disable watchdog timer */
 	cr &= ~DS1374_REG_CR_WACE;
 
-	i2c_smbus_write_byte_data(save_client, DS1374_REG_CR, cr);
+	return i2c_smbus_write_byte_data(client, DS1374_REG_CR, cr);
 }
 
-/*
- * Watchdog device is opened, and watchdog starts running.
- */
-static int ds1374_wdt_open(struct inode *inode, struct file *file)
-{
-	struct ds1374 *ds1374 = i2c_get_clientdata(save_client);
-
-	if (MINOR(inode->i_rdev) == WATCHDOG_MINOR) {
-		mutex_lock(&ds1374->mutex);
-		if (test_and_set_bit(0, &wdt_is_open)) {
-			mutex_unlock(&ds1374->mutex);
-			return -EBUSY;
-		}
-		/*
-		 *      Activate
-		 */
-		wdt_is_open = 1;
-		mutex_unlock(&ds1374->mutex);
-		return stream_open(inode, file);
-	}
-	return -ENODEV;
-}
-
-/*
- * Close the watchdog device.
- */
-static int ds1374_wdt_release(struct inode *inode, struct file *file)
-{
-	if (MINOR(inode->i_rdev) == WATCHDOG_MINOR)
-		clear_bit(0, &wdt_is_open);
-
-	return 0;
-}
-
-/*
- * Pat the watchdog whenever device is written to.
- */
-static ssize_t ds1374_wdt_write(struct file *file, const char __user *data,
-				size_t len, loff_t *ppos)
-{
-	if (len) {
-		ds1374_wdt_ping();
-		return 1;
-	}
-	return 0;
-}
-
-static ssize_t ds1374_wdt_read(struct file *file, char __user *data,
-				size_t len, loff_t *ppos)
-{
-	return 0;
-}
-
-/*
- * Handle commands from user-space.
- */
-static long ds1374_wdt_ioctl(struct file *file, unsigned int cmd,
-							unsigned long arg)
-{
-	int new_margin, options;
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		return copy_to_user((struct watchdog_info __user *)arg,
-		&ds1374_wdt_info, sizeof(ds1374_wdt_info)) ? -EFAULT : 0;
-
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		return put_user(0, (int __user *)arg);
-	case WDIOC_KEEPALIVE:
-		ds1374_wdt_ping();
-		return 0;
-	case WDIOC_SETTIMEOUT:
-		if (get_user(new_margin, (int __user *)arg))
-			return -EFAULT;
-
-		/* the hardware's tick rate is 4096 Hz, so
-		 * the counter value needs to be scaled accordingly
-		 */
-		new_margin <<= 12;
-		if (new_margin < 1 || new_margin > 16777216)
-			return -EINVAL;
-
-		wdt_margin = new_margin;
-		ds1374_wdt_settimeout(new_margin);
-		ds1374_wdt_ping();
-		/* fallthrough */
-	case WDIOC_GETTIMEOUT:
-		/* when returning ... inverse is true */
-		return put_user((wdt_margin >> 12), (int __user *)arg);
-	case WDIOC_SETOPTIONS:
-		if (copy_from_user(&options, (int __user *)arg, sizeof(int)))
-			return -EFAULT;
-
-		if (options & WDIOS_DISABLECARD) {
-			pr_info("disable watchdog\n");
-			ds1374_wdt_disable();
-			return 0;
-		}
-
-		if (options & WDIOS_ENABLECARD) {
-			pr_info("enable watchdog\n");
-			ds1374_wdt_settimeout(wdt_margin);
-			ds1374_wdt_ping();
-			return 0;
-		}
-		return -EINVAL;
-	}
-	return -ENOTTY;
-}
-
-static long ds1374_wdt_unlocked_ioctl(struct file *file, unsigned int cmd,
-			unsigned long arg)
-{
-	int ret;
-	struct ds1374 *ds1374 = i2c_get_clientdata(save_client);
-
-	mutex_lock(&ds1374->mutex);
-	ret = ds1374_wdt_ioctl(file, cmd, arg);
-	mutex_unlock(&ds1374->mutex);
-
-	return ret;
-}
-
-static int ds1374_wdt_notify_sys(struct notifier_block *this,
-			unsigned long code, void *unused)
-{
-	if (code == SYS_DOWN || code == SYS_HALT)
-		/* Disable Watchdog */
-		ds1374_wdt_disable();
-	return NOTIFY_DONE;
-}
-
-static const struct file_operations ds1374_wdt_fops = {
-	.owner			= THIS_MODULE,
-	.read			= ds1374_wdt_read,
-	.unlocked_ioctl		= ds1374_wdt_unlocked_ioctl,
-	.compat_ioctl		= compat_ptr_ioctl,
-	.write			= ds1374_wdt_write,
-	.open                   = ds1374_wdt_open,
-	.release                = ds1374_wdt_release,
-	.llseek			= no_llseek,
+static const struct watchdog_ops ds1374_wdt_ops = {
+	.owner          = THIS_MODULE,
+	.start          = ds1374_wdt_start,
+	.stop           = ds1374_wdt_stop,
+	.set_timeout    = ds1374_wdt_settimeout,
 };
-
-static struct miscdevice ds1374_miscdev = {
-	.minor          = WATCHDOG_MINOR,
-	.name           = "watchdog",
-	.fops           = &ds1374_wdt_fops,
-};
-
-static struct notifier_block ds1374_wdt_notifier = {
-	.notifier_call = ds1374_wdt_notify_sys,
-};
-
 #endif /*CONFIG_RTC_DRV_DS1374_WDT*/
 /*
  *****************************************************************************
@@ -652,16 +515,22 @@ static int ds1374_probe(struct i2c_client *client,
 		return ret;
 
 #ifdef CONFIG_RTC_DRV_DS1374_WDT
-	save_client = client;
-	ret = misc_register(&ds1374_miscdev);
+	ds1374->wdt.info = &ds1374_wdt_info;
+	ds1374->wdt.ops = &ds1374_wdt_ops;
+	ds1374->wdt.timeout = TIMER_MARGIN_DEFAULT;
+	ds1374->wdt.min_timeout = TIMER_MARGIN_MIN;
+	ds1374->wdt.max_timeout = TIMER_MARGIN_MAX;
+
+	watchdog_init_timeout(&ds1374->wdt, wdt_margin, &client->dev);
+	watchdog_set_nowayout(&ds1374->wdt, nowayout);
+	watchdog_stop_on_reboot(&ds1374->wdt);
+	watchdog_stop_on_unregister(&ds1374->wdt);
+	watchdog_set_drvdata(&ds1374->wdt, ds1374);
+	ds1374_wdt_settimeout(&ds1374->wdt, ds1374->wdt.timeout);
+
+	ret = devm_watchdog_register_device(&client->dev, &ds1374->wdt);
 	if (ret)
 		return ret;
-	ret = register_reboot_notifier(&ds1374_wdt_notifier);
-	if (ret) {
-		misc_deregister(&ds1374_miscdev);
-		return ret;
-	}
-	ds1374_wdt_settimeout(131072);
 #endif
 
 	return 0;
@@ -670,11 +539,6 @@ static int ds1374_probe(struct i2c_client *client,
 static int ds1374_remove(struct i2c_client *client)
 {
 	struct ds1374 *ds1374 = i2c_get_clientdata(client);
-#ifdef CONFIG_RTC_DRV_DS1374_WDT
-	misc_deregister(&ds1374_miscdev);
-	ds1374_miscdev.parent = NULL;
-	unregister_reboot_notifier(&ds1374_wdt_notifier);
-#endif
 
 	if (client->irq > 0) {
 		mutex_lock(&ds1374->mutex);

From 4df2ef85f0efe44505f511ca5e4455585f53a2da Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Tue, 14 Jul 2020 13:45:56 +0100
Subject: [PATCH 059/474] rtc: pl031: fix set_alarm by adding back call to
 alarm_irq_enable

Commit c8ff5841a90b ("rtc: pl031: switch to rtc_time64_to_tm/rtc_tm_to_time64")
seemed to have accidentally removed the call to pl031_alarm_irq_enable
from pl031_set_alarm while switching to 64-bit apis.

Let us add back the same to get the set alarm functionality back.

Fixes: c8ff5841a90b ("rtc: pl031: switch to rtc_time64_to_tm/rtc_tm_to_time64")
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Tested-by: Valentin Schneider <valentin.schneider@arm.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20200714124556.20294-1-sudeep.holla@arm.com
---
 drivers/rtc/rtc-pl031.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c
index 40d7450a1ce4..c6b89273feba 100644
--- a/drivers/rtc/rtc-pl031.c
+++ b/drivers/rtc/rtc-pl031.c
@@ -275,6 +275,7 @@ static int pl031_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 	struct pl031_local *ldata = dev_get_drvdata(dev);
 
 	writel(rtc_tm_to_time64(&alarm->time), ldata->base + RTC_MR);
+	pl031_alarm_irq_enable(dev, alarm->enabled);
 
 	return 0;
 }

From a5e6f964bb2c613933de58a35ddfa306128ba004 Mon Sep 17 00:00:00 2001
From: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Date: Fri, 10 Jul 2020 17:00:03 +0900
Subject: [PATCH 060/474] rtc: cleanup obsolete comment about struct
 rtc_class_ops

Commit ea369ea6d828 ("rtc: remove .open() and .release()") removes
open/release callback from struct rtc_class_ops.

Also commit 80d4bb515b78 ("RTC: Cleanup rtc_class_ops->irq_set_state")
and commit 696160fec162 ("RTC: Cleanup rtc_class_ops->irq_set_freq()")
removes irq callbacks.

So, just remove related comments so that readers will not be confused.

Signed-off-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20200710080003.7986-1-misono.tomohiro@jp.fujitsu.com
---
 include/linux/rtc.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index bba3db3f7efa..22d1575e4991 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -55,10 +55,6 @@ extern struct class *rtc_class;
  *
  * The (current) exceptions are mostly filesystem hooks:
  *   - the proc() hook for procfs
- *   - non-ioctl() chardev hooks:  open(), release()
- *
- * REVISIT those periodic irq calls *do* have ops_lock when they're
- * issued through ioctl() ...
  */
 struct rtc_class_ops {
 	int (*ioctl)(struct device *, unsigned int, unsigned long);

From 4cb4ade19b4219af8f5cda9313dd99b0004c8b3c Mon Sep 17 00:00:00 2001
From: Alistair Popple <alistair@popple.id.au>
Date: Tue, 2 Jun 2020 15:53:25 +1000
Subject: [PATCH 061/474] KVM: PPC: Book3SHV: Enable support for ISA v3.1
 guests

Adds support for emulating ISAv3.1 guests by adding the appropriate PCR
and FSCR bits.

Signed-off-by: Alistair Popple <alistair@popple.id.au>
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/include/asm/reg.h |  1 +
 arch/powerpc/kvm/book3s_hv.c   | 12 ++++++++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 88e6c78100d9..28311e52d7e8 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1354,6 +1354,7 @@
 #define PVR_ARCH_206p	0x0f100003
 #define PVR_ARCH_207	0x0f000004
 #define PVR_ARCH_300	0x0f000005
+#define PVR_ARCH_31	0x0f000006
 
 /* Macros for setting and retrieving special purpose registers */
 #ifndef __ASSEMBLY__
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6bf66649ab92..d64a2dc1ccca 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -342,13 +342,18 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
 	vcpu->arch.pvr = pvr;
 }
 
+/* Dummy value used in computing PCR value below */
+#define PCR_ARCH_31    (PCR_ARCH_300 << 1)
+
 static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 {
 	unsigned long host_pcr_bit = 0, guest_pcr_bit = 0;
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
 	/* We can (emulate) our own architecture version and anything older */
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
+	if (cpu_has_feature(CPU_FTR_ARCH_31))
+		host_pcr_bit = PCR_ARCH_31;
+	else if (cpu_has_feature(CPU_FTR_ARCH_300))
 		host_pcr_bit = PCR_ARCH_300;
 	else if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		host_pcr_bit = PCR_ARCH_207;
@@ -374,6 +379,9 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 		case PVR_ARCH_300:
 			guest_pcr_bit = PCR_ARCH_300;
 			break;
+		case PVR_ARCH_31:
+			guest_pcr_bit = PCR_ARCH_31;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -2318,7 +2326,7 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 	 * to trap and then we emulate them.
 	 */
 	vcpu->arch.hfscr = HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB |
-		HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP;
+		HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP | HFSCR_PREFIX;
 	if (cpu_has_feature(CPU_FTR_HVMODE)) {
 		vcpu->arch.hfscr &= mfspr(SPRN_HFSCR);
 		if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))

From e55f4d5898a9855350834535037f62732bbd320a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@kaod.org>
Date: Mon, 8 Jun 2020 13:57:14 +0200
Subject: [PATCH 062/474] KVM: PPC: Book3S HV: Increase KVMPPC_NR_LPIDS on
 POWER8 and POWER9
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

POWER8 and POWER9 have 12-bit LPIDs. Change LPID_RSVD to support up to
(4096 - 2) guests on these processors. POWER7 is kept the same with a
limitation of (1024 - 2), but it might be time to drop KVM support for
POWER7.

Tested with 2048 guests * 4 vCPUs on a witherspoon system with 512G
RAM and a bit of swap.

Signed-off-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/include/asm/reg.h      | 3 ++-
 arch/powerpc/kvm/book3s_64_mmu_hv.c | 8 ++++++--
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 28311e52d7e8..caef0483e9bb 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -473,7 +473,8 @@
 #ifndef SPRN_LPID
 #define SPRN_LPID	0x13F	/* Logical Partition Identifier */
 #endif
-#define   LPID_RSVD	0x3ff		/* Reserved LPID for partn switching */
+#define   LPID_RSVD_POWER7	0x3ff	/* Reserved LPID for partn switching */
+#define   LPID_RSVD		0xfff	/* Reserved LPID for partn switching */
 #define	SPRN_HMER	0x150	/* Hypervisor maintenance exception reg */
 #define   HMER_DEBUG_TRIG	(1ul << (63 - 17)) /* Debug trigger */
 #define	SPRN_HMEER	0x151	/* Hyp maintenance exception enable reg */
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 7c5a1812a1c3..38ea396a23d6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -260,11 +260,15 @@ int kvmppc_mmu_hv_init(void)
 	if (!mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE))
 		return -EINVAL;
 
-	/* POWER7 has 10-bit LPIDs (12-bit in POWER8) */
 	host_lpid = 0;
 	if (cpu_has_feature(CPU_FTR_HVMODE))
 		host_lpid = mfspr(SPRN_LPID);
-	rsvd_lpid = LPID_RSVD;
+
+	/* POWER8 and above have 12-bit LPIDs (10-bit in POWER7) */
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		rsvd_lpid = LPID_RSVD;
+	else
+		rsvd_lpid = LPID_RSVD_POWER7;
 
 	kvmppc_init_lpid(rsvd_lpid + 1);
 

From 1508c22f112ce11944cea84efb128a623e8ff03b Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Tue, 9 Jun 2020 12:12:29 +1000
Subject: [PATCH 063/474] KVM: PPC: Protect kvm_vcpu_read_guest with srcu locks

The kvm_vcpu_read_guest/kvm_vcpu_write_guest used for nested guests
eventually call srcu_dereference_check to dereference a memslot and
lockdep produces a warning as neither kvm->slots_lock nor
kvm->srcu lock is held and kvm->users_count is above zero (>100 in fact).

This wraps mentioned VCPU read/write helpers in srcu read lock/unlock as
it is done in other places. This uses vcpu->srcu_idx when possible.

These helpers are only used for nested KVM so this may explain why
we did not see these before.

Here is an example of a warning:

=============================
WARNING: suspicious RCU usage
5.7.0-rc3-le_dma-bypass.3.2_a+fstn1 #897 Not tainted
-----------------------------
include/linux/kvm_host.h:633 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
1 lock held by qemu-system-ppc/2752:
 #0: c000200359016be0 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x144/0xd80 [kvm]

stack backtrace:
CPU: 80 PID: 2752 Comm: qemu-system-ppc Not tainted 5.7.0-rc3-le_dma-bypass.3.2_a+fstn1 #897
Call Trace:
[c0002003591ab240] [c000000000b23ab4] dump_stack+0x190/0x25c (unreliable)
[c0002003591ab2b0] [c00000000023f954] lockdep_rcu_suspicious+0x140/0x164
[c0002003591ab330] [c008000004a445f8] kvm_vcpu_gfn_to_memslot+0x4c0/0x510 [kvm]
[c0002003591ab3a0] [c008000004a44c18] kvm_vcpu_read_guest+0xa0/0x180 [kvm]
[c0002003591ab410] [c008000004ff9bd8] kvmhv_enter_nested_guest+0x90/0xb80 [kvm_hv]
[c0002003591ab980] [c008000004fe07bc] kvmppc_pseries_do_hcall+0x7b4/0x1c30 [kvm_hv]
[c0002003591aba10] [c008000004fe5d30] kvmppc_vcpu_run_hv+0x10a8/0x1a30 [kvm_hv]
[c0002003591abae0] [c008000004a5d954] kvmppc_vcpu_run+0x4c/0x70 [kvm]
[c0002003591abb10] [c008000004a56e54] kvm_arch_vcpu_ioctl_run+0x56c/0x7c0 [kvm]
[c0002003591abba0] [c008000004a3ddc4] kvm_vcpu_ioctl+0x4ac/0xd80 [kvm]
[c0002003591abd20] [c0000000006ebb58] ksys_ioctl+0x188/0x210
[c0002003591abd70] [c0000000006ebc28] sys_ioctl+0x48/0xb0
[c0002003591abdb0] [c000000000042764] system_call_exception+0x1d4/0x2e0
[c0002003591abe20] [c00000000000cce8] system_call_common+0xe8/0x214

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/kvm/book3s_64_mmu_radix.c |  4 ++++
 arch/powerpc/kvm/book3s_hv_nested.c    | 30 ++++++++++++++++----------
 arch/powerpc/kvm/book3s_rtas.c         |  2 ++
 arch/powerpc/kvm/powerpc.c             |  5 ++++-
 4 files changed, 29 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 3cb0c9843d01..c6b3390e0de6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -160,7 +160,9 @@ int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr,
 			return -EINVAL;
 		/* Read the entry from guest memory */
 		addr = base + (index * sizeof(rpte));
+		vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
 		ret = kvm_read_guest(kvm, addr, &rpte, sizeof(rpte));
+		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 		if (ret) {
 			if (pte_ret_p)
 				*pte_ret_p = addr;
@@ -236,7 +238,9 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 	/* Read the table to find the root of the radix tree */
 	ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry));
+	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
 	ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry));
+	srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 	if (ret)
 		return ret;
 
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 2c849a65db77..6822d23a2da4 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -233,20 +233,21 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 
 	/* copy parameters in */
 	hv_ptr = kvmppc_get_gpr(vcpu, 4);
+	regs_ptr = kvmppc_get_gpr(vcpu, 5);
+	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	err = kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv,
-				  sizeof(struct hv_guest_state));
+				  sizeof(struct hv_guest_state)) ||
+		kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs,
+				    sizeof(struct pt_regs));
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	if (err)
 		return H_PARAMETER;
+
 	if (kvmppc_need_byteswap(vcpu))
 		byteswap_hv_regs(&l2_hv);
 	if (l2_hv.version != HV_GUEST_STATE_VERSION)
 		return H_P2;
 
-	regs_ptr = kvmppc_get_gpr(vcpu, 5);
-	err = kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs,
-				  sizeof(struct pt_regs));
-	if (err)
-		return H_PARAMETER;
 	if (kvmppc_need_byteswap(vcpu))
 		byteswap_pt_regs(&l2_regs);
 	if (l2_hv.vcpu_token >= NR_CPUS)
@@ -323,12 +324,12 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 		byteswap_hv_regs(&l2_hv);
 		byteswap_pt_regs(&l2_regs);
 	}
+	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	err = kvm_vcpu_write_guest(vcpu, hv_ptr, &l2_hv,
-				   sizeof(struct hv_guest_state));
-	if (err)
-		return H_AUTHORITY;
-	err = kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs,
+				   sizeof(struct hv_guest_state)) ||
+		kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs,
 				   sizeof(struct pt_regs));
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	if (err)
 		return H_AUTHORITY;
 
@@ -508,12 +509,16 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu)
 			goto not_found;
 
 		/* Write what was loaded into our buffer back to the L1 guest */
+		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		rc = kvm_vcpu_write_guest(vcpu, gp_to, buf, n);
+		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 		if (rc)
 			goto not_found;
 	} else {
 		/* Load the data to be stored from the L1 guest into our buf */
+		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		rc = kvm_vcpu_read_guest(vcpu, gp_from, buf, n);
+		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 		if (rc)
 			goto not_found;
 
@@ -548,9 +553,12 @@ static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp)
 
 	ret = -EFAULT;
 	ptbl_addr = (kvm->arch.l1_ptcr & PRTB_MASK) + (gp->l1_lpid << 4);
-	if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8)))
+	if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8))) {
+		int srcu_idx = srcu_read_lock(&kvm->srcu);
 		ret = kvm_read_guest(kvm, ptbl_addr,
 				     &ptbl_entry, sizeof(ptbl_entry));
+		srcu_read_unlock(&kvm->srcu, srcu_idx);
+	}
 	if (ret) {
 		gp->l1_gr_to_hr = 0;
 		gp->process_table = 0;
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index 26b25994c969..c5e677508d3b 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -229,7 +229,9 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 	 */
 	args_phys = kvmppc_get_gpr(vcpu, 4) & KVM_PAM;
 
+	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	rc = kvm_read_guest(vcpu->kvm, args_phys, &args, sizeof(args));
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	if (rc)
 		goto fail;
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index dd7d141e33e8..d7b69784bb7e 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -403,7 +403,10 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 		return EMULATE_DONE;
 	}
 
-	if (kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size))
+	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+	rc = kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size);
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	if (rc)
 		return EMULATE_DO_MMIO;
 
 	return EMULATE_DONE;

From c7f3be4c94d3686ec67b7e7b4fb47e4c225a2789 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Mon, 20 Jul 2020 09:52:49 +0200
Subject: [PATCH 064/474] rtc: ds1374: fix RTC_DRV_DS1374_WDT dependencies

It is not enough to select WATCHDOG_CORE, the watchdog part of the driver
now also depends on WATCHDOG. This is currently the best we can do because
alarm support and watchdog support are mutually exclusive.

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Link: https://lore.kernel.org/r/20200720075250.1019172-1-alexandre.belloni@bootlin.com
---
 drivers/rtc/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index c25d51f35f0c..2753e0f54cc3 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -281,8 +281,8 @@ config RTC_DRV_DS1374
 
 config RTC_DRV_DS1374_WDT
 	bool "Dallas/Maxim DS1374 watchdog timer"
-	depends on RTC_DRV_DS1374
-	select WATCHDOG_CORE if WATCHDOG
+	depends on RTC_DRV_DS1374 && WATCHDOG
+	select WATCHDOG_CORE
 	help
 	  If you say Y here you will get support for the
 	  watchdog timer in the Dallas Semiconductor DS1374

From 3d6cfb36ed719e5efdc2a6a8e8ee07f185c88da1 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Mon, 20 Jul 2020 09:52:50 +0200
Subject: [PATCH 065/474] rtc: ds1374: remove unused define

Remove unused define and fix typo where it should have been used.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20200720075250.1019172-2-alexandre.belloni@bootlin.com
---
 drivers/rtc/rtc-ds1374.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/rtc/rtc-ds1374.c b/drivers/rtc/rtc-ds1374.c
index c71065d26cd2..177d870bda0d 100644
--- a/drivers/rtc/rtc-ds1374.c
+++ b/drivers/rtc/rtc-ds1374.c
@@ -377,8 +377,6 @@ static const struct rtc_class_ops ds1374_rtc_ops = {
 #define TIMER_MARGIN_MIN	1
 #define TIMER_MARGIN_MAX	4095 /* 24-bit value */
 
-#define DRV_NAME "DS1374 Watchdog"
-
 static int wdt_margin;
 module_param(wdt_margin, int, 0);
 MODULE_PARM_DESC(wdt_margin, "Watchdog timeout in seconds (default 32s)");
@@ -389,7 +387,7 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default ="
 		__MODULE_STRING(WATCHDOG_NOWAYOUT)")");
 
 static const struct watchdog_info ds1374_wdt_info = {
-	.identity       = "DS1374 WTD",
+	.identity       = "DS1374 Watchdog",
 	.options        = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING |
 						WDIOF_MAGICCLOSE,
 };

From f47ee279d25fb0e010cae5d6e758e39b40eb6378 Mon Sep 17 00:00:00 2001
From: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
Date: Fri, 3 Jul 2020 20:05:07 +0300
Subject: [PATCH 066/474] clk: actions: Fix h_clk for Actions S500 SoC

The h_clk clock in the Actions Semi S500 SoC clock driver has an
invalid parent. Replace with the correct one.

Fixes: ed6b4795ece4 ("clk: actions: Add clock driver for S500 SoC")
Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/c57e7ebabfa970014f073b92fe95b47d3e5a70b1.1593788312.git.cristian.ciocaltea@gmail.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/actions/owl-s500.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/actions/owl-s500.c b/drivers/clk/actions/owl-s500.c
index e2007ac4d235..0eb83a0b70bc 100644
--- a/drivers/clk/actions/owl-s500.c
+++ b/drivers/clk/actions/owl-s500.c
@@ -183,7 +183,7 @@ static OWL_GATE(timer_clk, "timer_clk", "hosc", CMU_DEVCLKEN1, 27, 0, 0);
 static OWL_GATE(hdmi_clk, "hdmi_clk", "hosc", CMU_DEVCLKEN1, 3, 0, 0);
 
 /* divider clocks */
-static OWL_DIVIDER(h_clk, "h_clk", "ahbprevdiv_clk", CMU_BUSCLK1, 12, 2, NULL, 0, 0);
+static OWL_DIVIDER(h_clk, "h_clk", "ahbprediv_clk", CMU_BUSCLK1, 12, 2, NULL, 0, 0);
 static OWL_DIVIDER(rmii_ref_clk, "rmii_ref_clk", "ethernet_pll_clk", CMU_ETHERNETPLL, 1, 1, rmii_ref_div_table, 0, 0);
 
 /* factor clocks */

From 1a4ae4138f386600fc539747bb978873299017f8 Mon Sep 17 00:00:00 2001
From: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
Date: Fri, 3 Jul 2020 20:05:08 +0300
Subject: [PATCH 067/474] dt-bindings: clock: Add APB, DMAC, GPIO bindings for
 Actions S500 SoC

Add the missing APB, DMAC and GPIO clock bindings constants for
Actions Semi S500 SoC.

Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
Link: https://lore.kernel.org/r/67112af4f5bc0cc5e70ce8410feb369cc72972b8.1593788312.git.cristian.ciocaltea@gmail.com
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 include/dt-bindings/clock/actions,s500-cmu.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/include/dt-bindings/clock/actions,s500-cmu.h b/include/dt-bindings/clock/actions,s500-cmu.h
index 030981cd2d56..a250a52a6192 100644
--- a/include/dt-bindings/clock/actions,s500-cmu.h
+++ b/include/dt-bindings/clock/actions,s500-cmu.h
@@ -72,7 +72,12 @@
 #define CLK_NAND		52
 #define CLK_ECC			53
 #define CLK_RMII_REF		54
+#define CLK_GPIO		55
 
-#define CLK_NR_CLKS	       (CLK_RMII_REF + 1)
+/* system clock (part 2) */
+#define CLK_APB			56
+#define CLK_DMAC		57
+
+#define CLK_NR_CLKS		(CLK_DMAC + 1)
 
 #endif /* __DT_BINDINGS_CLOCK_S500_CMU_H */

From b81e88dead64b4d3725b02bf275d5594943c125a Mon Sep 17 00:00:00 2001
From: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
Date: Fri, 3 Jul 2020 20:05:09 +0300
Subject: [PATCH 068/474] clk: actions: Add APB, DMAC, GPIO clock support for
 Actions S500 SoC

Add support for the missing APB, DMAC and GPIO clocks in the Actions
Semi S500 SoC clock driver.

Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
Link: https://lore.kernel.org/r/87964ae012e513597b8b4c7be2e7ac332a70087a.1593788312.git.cristian.ciocaltea@gmail.com
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/actions/owl-s500.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/clk/actions/owl-s500.c b/drivers/clk/actions/owl-s500.c
index 0eb83a0b70bc..025a8f6d6482 100644
--- a/drivers/clk/actions/owl-s500.c
+++ b/drivers/clk/actions/owl-s500.c
@@ -175,6 +175,8 @@ static OWL_MUX(dev_clk, "dev_clk", dev_clk_mux_p, CMU_DEVPLL, 12, 1, CLK_SET_RAT
 static OWL_MUX(ahbprediv_clk, "ahbprediv_clk", ahbprediv_clk_mux_p, CMU_BUSCLK1, 8, 3, CLK_SET_RATE_PARENT);
 
 /* gate clocks */
+static OWL_GATE(gpio_clk, "gpio_clk", "apb_clk", CMU_DEVCLKEN0, 18, 0, 0);
+static OWL_GATE(dmac_clk, "dmac_clk", "h_clk", CMU_DEVCLKEN0, 1, 0, 0);
 static OWL_GATE(spi0_clk, "spi0_clk", "ahb_clk", CMU_DEVCLKEN1, 10, 0, CLK_IGNORE_UNUSED);
 static OWL_GATE(spi1_clk, "spi1_clk", "ahb_clk", CMU_DEVCLKEN1, 11, 0, CLK_IGNORE_UNUSED);
 static OWL_GATE(spi2_clk, "spi2_clk", "ahb_clk", CMU_DEVCLKEN1, 12, 0, CLK_IGNORE_UNUSED);
@@ -184,6 +186,7 @@ static OWL_GATE(hdmi_clk, "hdmi_clk", "hosc", CMU_DEVCLKEN1, 3, 0, 0);
 
 /* divider clocks */
 static OWL_DIVIDER(h_clk, "h_clk", "ahbprediv_clk", CMU_BUSCLK1, 12, 2, NULL, 0, 0);
+static OWL_DIVIDER(apb_clk, "apb_clk", "ahb_clk", CMU_BUSCLK1, 14, 2, NULL, 0, 0);
 static OWL_DIVIDER(rmii_ref_clk, "rmii_ref_clk", "ethernet_pll_clk", CMU_ETHERNETPLL, 1, 1, rmii_ref_div_table, 0, 0);
 
 /* factor clocks */
@@ -428,6 +431,9 @@ static struct owl_clk_common *s500_clks[] = {
 	&spdif_clk.common,
 	&nand_clk.common,
 	&ecc_clk.common,
+	&apb_clk.common,
+	&dmac_clk.common,
+	&gpio_clk.common,
 };
 
 static struct clk_hw_onecell_data s500_hw_clks = {
@@ -484,6 +490,9 @@ static struct clk_hw_onecell_data s500_hw_clks = {
 		[CLK_SPDIF]		= &spdif_clk.common.hw,
 		[CLK_NAND]		= &nand_clk.common.hw,
 		[CLK_ECC]		= &ecc_clk.common.hw,
+		[CLK_APB]		= &apb_clk.common.hw,
+		[CLK_DMAC]		= &dmac_clk.common.hw,
+		[CLK_GPIO]		= &gpio_clk.common.hw,
 	},
 	.num = CLK_NR_CLKS,
 };

From fac1d443a2b73dfb5b277d4e3c202609f0927eb5 Mon Sep 17 00:00:00 2001
From: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
Date: Fri, 3 Jul 2020 20:05:10 +0300
Subject: [PATCH 069/474] dt-bindings: reset: Add binding constants for Actions
 S500 RMU

Add device tree binding constants for Actions Semi S500 SoC Reset
Management Unit (RMU).

Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
Acked-by: Philipp Zabel <p.zabel@pengutronix.de>
Link: https://lore.kernel.org/r/daf615160b3be9f38dcf7926cc82128c9c2d73e3.1593788312.git.cristian.ciocaltea@gmail.com
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../dt-bindings/reset/actions,s500-reset.h    | 67 +++++++++++++++++++
 1 file changed, 67 insertions(+)
 create mode 100644 include/dt-bindings/reset/actions,s500-reset.h

diff --git a/include/dt-bindings/reset/actions,s500-reset.h b/include/dt-bindings/reset/actions,s500-reset.h
new file mode 100644
index 000000000000..f5d94176d10b
--- /dev/null
+++ b/include/dt-bindings/reset/actions,s500-reset.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Device Tree binding constants for Actions Semi S500 Reset Management Unit
+ *
+ * Copyright (c) 2014 Actions Semi Inc.
+ * Copyright (c) 2020 Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
+ */
+
+#ifndef __DT_BINDINGS_ACTIONS_S500_RESET_H
+#define __DT_BINDINGS_ACTIONS_S500_RESET_H
+
+#define RESET_DMAC				0
+#define RESET_NORIF				1
+#define RESET_DDR				2
+#define RESET_NANDC				3
+#define RESET_SD0				4
+#define RESET_SD1				5
+#define RESET_PCM1				6
+#define RESET_DE				7
+#define RESET_LCD				8
+#define RESET_SD2				9
+#define RESET_DSI				10
+#define RESET_CSI				11
+#define RESET_BISP				12
+#define RESET_KEY				13
+#define RESET_GPIO				14
+#define RESET_AUDIO				15
+#define RESET_PCM0				16
+#define RESET_VDE				17
+#define RESET_VCE				18
+#define RESET_GPU3D				19
+#define RESET_NIC301				20
+#define RESET_LENS				21
+#define RESET_PERIPHRESET			22
+#define RESET_USB2_0				23
+#define RESET_TVOUT				24
+#define RESET_HDMI				25
+#define RESET_HDCP2TX				26
+#define RESET_UART6				27
+#define RESET_UART0				28
+#define RESET_UART1				29
+#define RESET_UART2				30
+#define RESET_SPI0				31
+#define RESET_SPI1				32
+#define RESET_SPI2				33
+#define RESET_SPI3				34
+#define RESET_I2C0				35
+#define RESET_I2C1				36
+#define RESET_USB3				37
+#define RESET_UART3				38
+#define RESET_UART4				39
+#define RESET_UART5				40
+#define RESET_I2C2				41
+#define RESET_I2C3				42
+#define RESET_ETHERNET				43
+#define RESET_CHIPID				44
+#define RESET_USB2_1				45
+#define RESET_WD0RESET				46
+#define RESET_WD1RESET				47
+#define RESET_WD2RESET				48
+#define RESET_WD3RESET				49
+#define RESET_DBG0RESET				50
+#define RESET_DBG1RESET				51
+#define RESET_DBG2RESET				52
+#define RESET_DBG3RESET				53
+
+#endif /* __DT_BINDINGS_ACTIONS_S500_RESET_H */

From 9fb961da91393e33b09a87582ee526e6328869a1 Mon Sep 17 00:00:00 2001
From: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
Date: Fri, 3 Jul 2020 20:05:11 +0300
Subject: [PATCH 070/474] clk: actions: Add Actions S500 SoC Reset Management
 Unit support

Add Reset Management Unit (RMU) support for Actions Semi S500 SoC.

Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/3fba2e6f0edfac97cb8c6ce60f95c24852578eac.1593788312.git.cristian.ciocaltea@gmail.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/actions/owl-s500.c | 78 ++++++++++++++++++++++++++++++++++
 1 file changed, 78 insertions(+)

diff --git a/drivers/clk/actions/owl-s500.c b/drivers/clk/actions/owl-s500.c
index 025a8f6d6482..61bb224f6330 100644
--- a/drivers/clk/actions/owl-s500.c
+++ b/drivers/clk/actions/owl-s500.c
@@ -23,8 +23,10 @@
 #include "owl-gate.h"
 #include "owl-mux.h"
 #include "owl-pll.h"
+#include "owl-reset.h"
 
 #include <dt-bindings/clock/actions,s500-cmu.h>
+#include <dt-bindings/reset/actions,s500-reset.h>
 
 #define CMU_COREPLL			(0x0000)
 #define CMU_DEVPLL			(0x0004)
@@ -497,20 +499,96 @@ static struct clk_hw_onecell_data s500_hw_clks = {
 	.num = CLK_NR_CLKS,
 };
 
+static const struct owl_reset_map s500_resets[] = {
+	[RESET_DMAC]	= { CMU_DEVRST0, BIT(0) },
+	[RESET_NORIF]	= { CMU_DEVRST0, BIT(1) },
+	[RESET_DDR]	= { CMU_DEVRST0, BIT(2) },
+	[RESET_NANDC]	= { CMU_DEVRST0, BIT(3) },
+	[RESET_SD0]	= { CMU_DEVRST0, BIT(4) },
+	[RESET_SD1]	= { CMU_DEVRST0, BIT(5) },
+	[RESET_PCM1]	= { CMU_DEVRST0, BIT(6) },
+	[RESET_DE]	= { CMU_DEVRST0, BIT(7) },
+	[RESET_LCD]	= { CMU_DEVRST0, BIT(8) },
+	[RESET_SD2]	= { CMU_DEVRST0, BIT(9) },
+	[RESET_DSI]	= { CMU_DEVRST0, BIT(10) },
+	[RESET_CSI]	= { CMU_DEVRST0, BIT(11) },
+	[RESET_BISP]	= { CMU_DEVRST0, BIT(12) },
+	[RESET_KEY]	= { CMU_DEVRST0, BIT(14) },
+	[RESET_GPIO]	= { CMU_DEVRST0, BIT(15) },
+	[RESET_AUDIO]	= { CMU_DEVRST0, BIT(17) },
+	[RESET_PCM0]	= { CMU_DEVRST0, BIT(18) },
+	[RESET_VDE]	= { CMU_DEVRST0, BIT(19) },
+	[RESET_VCE]	= { CMU_DEVRST0, BIT(20) },
+	[RESET_GPU3D]	= { CMU_DEVRST0, BIT(22) },
+	[RESET_NIC301]	= { CMU_DEVRST0, BIT(23) },
+	[RESET_LENS]	= { CMU_DEVRST0, BIT(26) },
+	[RESET_PERIPHRESET] = { CMU_DEVRST0, BIT(27) },
+	[RESET_USB2_0]	= { CMU_DEVRST1, BIT(0) },
+	[RESET_TVOUT]	= { CMU_DEVRST1, BIT(1) },
+	[RESET_HDMI]	= { CMU_DEVRST1, BIT(2) },
+	[RESET_HDCP2TX]	= { CMU_DEVRST1, BIT(3) },
+	[RESET_UART6]	= { CMU_DEVRST1, BIT(4) },
+	[RESET_UART0]	= { CMU_DEVRST1, BIT(5) },
+	[RESET_UART1]	= { CMU_DEVRST1, BIT(6) },
+	[RESET_UART2]	= { CMU_DEVRST1, BIT(7) },
+	[RESET_SPI0]	= { CMU_DEVRST1, BIT(8) },
+	[RESET_SPI1]	= { CMU_DEVRST1, BIT(9) },
+	[RESET_SPI2]	= { CMU_DEVRST1, BIT(10) },
+	[RESET_SPI3]	= { CMU_DEVRST1, BIT(11) },
+	[RESET_I2C0]	= { CMU_DEVRST1, BIT(12) },
+	[RESET_I2C1]	= { CMU_DEVRST1, BIT(13) },
+	[RESET_USB3]	= { CMU_DEVRST1, BIT(14) },
+	[RESET_UART3]	= { CMU_DEVRST1, BIT(15) },
+	[RESET_UART4]	= { CMU_DEVRST1, BIT(16) },
+	[RESET_UART5]	= { CMU_DEVRST1, BIT(17) },
+	[RESET_I2C2]	= { CMU_DEVRST1, BIT(18) },
+	[RESET_I2C3]	= { CMU_DEVRST1, BIT(19) },
+	[RESET_ETHERNET] = { CMU_DEVRST1, BIT(20) },
+	[RESET_CHIPID]	= { CMU_DEVRST1, BIT(21) },
+	[RESET_USB2_1]	= { CMU_DEVRST1, BIT(22) },
+	[RESET_WD0RESET] = { CMU_DEVRST1, BIT(24) },
+	[RESET_WD1RESET] = { CMU_DEVRST1, BIT(25) },
+	[RESET_WD2RESET] = { CMU_DEVRST1, BIT(26) },
+	[RESET_WD3RESET] = { CMU_DEVRST1, BIT(27) },
+	[RESET_DBG0RESET] = { CMU_DEVRST1, BIT(28) },
+	[RESET_DBG1RESET] = { CMU_DEVRST1, BIT(29) },
+	[RESET_DBG2RESET] = { CMU_DEVRST1, BIT(30) },
+	[RESET_DBG3RESET] = { CMU_DEVRST1, BIT(31) },
+};
+
 static struct owl_clk_desc s500_clk_desc = {
 	.clks	    = s500_clks,
 	.num_clks   = ARRAY_SIZE(s500_clks),
 
 	.hw_clks    = &s500_hw_clks,
+
+	.resets     = s500_resets,
+	.num_resets = ARRAY_SIZE(s500_resets),
 };
 
 static int s500_clk_probe(struct platform_device *pdev)
 {
 	struct owl_clk_desc *desc;
+	struct owl_reset *reset;
+	int ret;
 
 	desc = &s500_clk_desc;
 	owl_clk_regmap_init(pdev, desc);
 
+	reset = devm_kzalloc(&pdev->dev, sizeof(*reset), GFP_KERNEL);
+	if (!reset)
+		return -ENOMEM;
+
+	reset->rcdev.of_node = pdev->dev.of_node;
+	reset->rcdev.ops = &owl_reset_ops;
+	reset->rcdev.nr_resets = desc->num_resets;
+	reset->reset_map = desc->resets;
+	reset->regmap = desc->regmap;
+
+	ret = devm_reset_controller_register(&pdev->dev, &reset->rcdev);
+	if (ret)
+		dev_err(&pdev->dev, "Failed to register reset controller\n");
+
 	return owl_clk_probe(&pdev->dev, desc->hw_clks);
 }
 

From cb7c6677bfb5c92526df73b20760d65bd9189344 Mon Sep 17 00:00:00 2001
From: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
Date: Fri, 3 Jul 2020 20:05:12 +0300
Subject: [PATCH 071/474] MAINTAINERS: Add reset binding entry for Actions Semi
 Owl SoCs

Add a reset binding entry to match all members of Actions Semi Owl SoCs.

Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
Link: https://lore.kernel.org/r/78d63d97e3a8a8f7a9048b6eec74a9d158578833.1593788312.git.cristian.ciocaltea@gmail.com
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 68f21d46614c..931c78a5e035 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1533,6 +1533,7 @@ F:	drivers/mmc/host/owl-mmc.c
 F:	drivers/pinctrl/actions/*
 F:	drivers/soc/actions/
 F:	include/dt-bindings/power/owl-*
+F:	include/dt-bindings/reset/actions,*
 F:	include/linux/soc/actions/
 N:	owl
 

From ef990bcad58cf1d13c5a49191a2c2342eb8d6709 Mon Sep 17 00:00:00 2001
From: Alex Bee <knaerzche@gmail.com>
Date: Wed, 22 Jul 2020 18:18:20 +0200
Subject: [PATCH 072/474] clk: rockchip: add sclk_mac_lbtest to
 rk3188_critical_clocks

Since the loopbacktest clock is not exported and is not touched in the
driver, it has to be added to rk3188_critical_clocks to be protected from
being disabled and in order to get the emac working.

Signed-off-by: Alex Bee <knaerzche@gmail.com>
Link: https://lore.kernel.org/r/20200722161820.5316-1-knaerzche@gmail.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 drivers/clk/rockchip/clk-rk3188.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/rockchip/clk-rk3188.c b/drivers/clk/rockchip/clk-rk3188.c
index 77aebfb1d6d5..730020fcc7fe 100644
--- a/drivers/clk/rockchip/clk-rk3188.c
+++ b/drivers/clk/rockchip/clk-rk3188.c
@@ -751,6 +751,7 @@ static const char *const rk3188_critical_clocks[] __initconst = {
 	"pclk_peri",
 	"hclk_cpubus",
 	"hclk_vio_bus",
+	"sclk_mac_lbtest",
 };
 
 static struct rockchip_clk_provider *__init rk3188_common_clk_init(struct device_node *np)

From ba937f51090d04bde3c2b9bf1213dabac706461d Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Tue, 21 Jul 2020 12:18:34 +0200
Subject: [PATCH 073/474] dt-bindings: clock: Fix qcom,msm8996-apcc yaml syntax

Fix errors reported by dt_binding_check.
- Fix literal block scalar for dts example
- Fix schema identifier URI

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Link: https://lore.kernel.org/r/1595326714-20485-1-git-send-email-loic.poulain@linaro.org
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../devicetree/bindings/clock/qcom,msm8996-apcc.yaml        | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/clock/qcom,msm8996-apcc.yaml b/Documentation/devicetree/bindings/clock/qcom,msm8996-apcc.yaml
index d673edeed98d..a20cb10636dd 100644
--- a/Documentation/devicetree/bindings/clock/qcom,msm8996-apcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,msm8996-apcc.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/clock/qcom,kryocc.yaml#
+$id: http://devicetree.org/schemas/clock/qcom,msm8996-apcc.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Qualcomm clock controller for MSM8996 CPUs
@@ -46,11 +46,9 @@ required:
 additionalProperties: false
 
 examples:
-  # Example for msm8996
   - |
     kryocc: clock-controller@6400000 {
         compatible = "qcom,msm8996-apcc";
         reg = <0x6400000 0x90000>;
         #clock-cells = <1>;
-  };
-...
+    };

From 8200597fb16651e5b2280b694dd86352b738657b Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 25 Jun 2020 14:27:36 +0100
Subject: [PATCH 074/474] clk: vc5: fix use of memory after it has been kfree'd

There are a several places where printing an error message of
init.name occurs after init.name has been kfree'd. Also the failure
message is duplicated each time in the code. Fix this by adding
a registration error failure path for these cases, moving the
duplicated error messages to one common point and kfree'ing init.name
only after it has been used.

Changes also shrink the object code size by 171 bytes (x86-64, gcc 9.3):

Before:
   text	   data	    bss	    dec	    hex	filename
  21057	   3960	     64	  25081	   61f9	drivers/clk/clk-versaclock5.o

After:
   text	   data	    bss	    dec	    hex	filename
  20886	   3960	     64	  24910	   614e	drivers/clk/clk-versaclock5.o

Addresses-Coverity: ("Use after free")
Fixes: f491276a5168 ("clk: vc5: Allow Versaclock driver to support multiple instances")

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Link: https://lore.kernel.org/r/20200625132736.88832-1-colin.king@canonical.com
Reviewed-by: Luca Ceresoli <luca@lucaceresoli.net>
[sboyd@kernel.org: Drop stray newline]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-versaclock5.c | 50 +++++++++++++----------------------
 1 file changed, 18 insertions(+), 32 deletions(-)

diff --git a/drivers/clk/clk-versaclock5.c b/drivers/clk/clk-versaclock5.c
index 9a5fb3834b9a..d6fa15b6f37f 100644
--- a/drivers/clk/clk-versaclock5.c
+++ b/drivers/clk/clk-versaclock5.c
@@ -882,11 +882,9 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	init.parent_names = parent_names;
 	vc5->clk_mux.init = &init;
 	ret = devm_clk_hw_register(&client->dev, &vc5->clk_mux);
+	if (ret)
+		goto err_clk_register;
 	kfree(init.name);	/* clock framework made a copy of the name */
-	if (ret) {
-		dev_err(&client->dev, "unable to register %s\n", init.name);
-		goto err_clk;
-	}
 
 	if (vc5->chip_info->flags & VC5_HAS_PFD_FREQ_DBL) {
 		/* Register frequency doubler */
@@ -900,12 +898,9 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		init.num_parents = 1;
 		vc5->clk_mul.init = &init;
 		ret = devm_clk_hw_register(&client->dev, &vc5->clk_mul);
+		if (ret)
+			goto err_clk_register;
 		kfree(init.name); /* clock framework made a copy of the name */
-		if (ret) {
-			dev_err(&client->dev, "unable to register %s\n",
-				init.name);
-			goto err_clk;
-		}
 	}
 
 	/* Register PFD */
@@ -921,11 +916,9 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	init.num_parents = 1;
 	vc5->clk_pfd.init = &init;
 	ret = devm_clk_hw_register(&client->dev, &vc5->clk_pfd);
+	if (ret)
+		goto err_clk_register;
 	kfree(init.name);	/* clock framework made a copy of the name */
-	if (ret) {
-		dev_err(&client->dev, "unable to register %s\n", init.name);
-		goto err_clk;
-	}
 
 	/* Register PLL */
 	memset(&init, 0, sizeof(init));
@@ -939,11 +932,9 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	vc5->clk_pll.vc5 = vc5;
 	vc5->clk_pll.hw.init = &init;
 	ret = devm_clk_hw_register(&client->dev, &vc5->clk_pll.hw);
+	if (ret)
+		goto err_clk_register;
 	kfree(init.name); /* clock framework made a copy of the name */
-	if (ret) {
-		dev_err(&client->dev, "unable to register %s\n", init.name);
-		goto err_clk;
-	}
 
 	/* Register FODs */
 	for (n = 0; n < vc5->chip_info->clk_fod_cnt; n++) {
@@ -960,12 +951,9 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		vc5->clk_fod[n].vc5 = vc5;
 		vc5->clk_fod[n].hw.init = &init;
 		ret = devm_clk_hw_register(&client->dev, &vc5->clk_fod[n].hw);
+		if (ret)
+			goto err_clk_register;
 		kfree(init.name); /* clock framework made a copy of the name */
-		if (ret) {
-			dev_err(&client->dev, "unable to register %s\n",
-				init.name);
-			goto err_clk;
-		}
 	}
 
 	/* Register MUX-connected OUT0_I2C_SELB output */
@@ -981,11 +969,9 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	vc5->clk_out[0].vc5 = vc5;
 	vc5->clk_out[0].hw.init = &init;
 	ret = devm_clk_hw_register(&client->dev, &vc5->clk_out[0].hw);
-	kfree(init.name);	/* clock framework made a copy of the name */
-	if (ret) {
-		dev_err(&client->dev, "unable to register %s\n", init.name);
-		goto err_clk;
-	}
+	if (ret)
+		goto err_clk_register;
+	kfree(init.name); /* clock framework made a copy of the name */
 
 	/* Register FOD-connected OUTx outputs */
 	for (n = 1; n < vc5->chip_info->clk_out_cnt; n++) {
@@ -1008,12 +994,9 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		vc5->clk_out[n].vc5 = vc5;
 		vc5->clk_out[n].hw.init = &init;
 		ret = devm_clk_hw_register(&client->dev, &vc5->clk_out[n].hw);
+		if (ret)
+			goto err_clk_register;
 		kfree(init.name); /* clock framework made a copy of the name */
-		if (ret) {
-			dev_err(&client->dev, "unable to register %s\n",
-				init.name);
-			goto err_clk;
-		}
 
 		/* Fetch Clock Output configuration from DT (if specified) */
 		ret = vc5_get_output_config(client, &vc5->clk_out[n]);
@@ -1029,6 +1012,9 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id)
 
 	return 0;
 
+err_clk_register:
+	dev_err(&client->dev, "unable to register %s\n", init.name);
+	kfree(init.name); /* clock framework made a copy of the name */
 err_clk:
 	if (vc5->chip_info->flags & VC5_HAS_INTERNAL_XTAL)
 		clk_unregister_fixed_rate(vc5->pin_xin);

From faf29338f3cb6ebcbff7297471b0fa56639a98bc Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Thu, 16 Jul 2020 07:26:20 -0500
Subject: [PATCH 075/474] clk: vc5: Add memory check to prevent oops

When getting the names of the child nodes, kasprintf is used to
allocate memory which is used to create the string for the node
name.  Unfortunately, there is no memory check to determine
if this allocation fails, it may cause an error when trying
to get child node name.

This patch will check if the memory allocation fails, and returns
and -ENOMEM error instead of blindly moving on.

Fixes: 260249f929e8 ("clk: vc5: Enable addition output configurations of the Versaclock")

Suggested-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Adam Ford <aford173@gmail.com>
Reviewed-by: Luca Ceresoli <luca@lucaceresoli.net>
Link: https://lore.kernel.org/r/20200716122620.4538-1-aford173@gmail.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-versaclock5.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/clk/clk-versaclock5.c b/drivers/clk/clk-versaclock5.c
index d6fa15b6f37f..32f0aa64f062 100644
--- a/drivers/clk/clk-versaclock5.c
+++ b/drivers/clk/clk-versaclock5.c
@@ -789,10 +789,13 @@ static int vc5_get_output_config(struct i2c_client *client,
 	int ret = 0;
 
 	child_name = kasprintf(GFP_KERNEL, "OUT%d", clk_out->num + 1);
+	if (!child_name)
+		return -ENOMEM;
+
 	np_output = of_get_child_by_name(client->dev.of_node, child_name);
 	kfree(child_name);
 	if (!np_output)
-		goto output_done;
+		return 0;
 
 	ret = vc5_update_mode(np_output, clk_out);
 	if (ret)
@@ -813,7 +816,6 @@ static int vc5_get_output_config(struct i2c_client *client,
 
 	of_node_put(np_output);
 
-output_done:
 	return ret;
 }
 
@@ -828,7 +830,7 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	int ret;
 
 	vc5 = devm_kzalloc(&client->dev, sizeof(*vc5), GFP_KERNEL);
-	if (vc5 == NULL)
+	if (!vc5)
 		return -ENOMEM;
 
 	i2c_set_clientdata(client, vc5);

From 7ec21d9da57e1ea770fae48e8fabb06c579487a7 Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Date: Tue, 23 Jun 2020 21:14:16 +0800
Subject: [PATCH 076/474] KVM: PPC: Clean up redundant kvm_run parameters in
 assembly

In the current kvm version, 'kvm_run' has been included in the 'kvm_vcpu'
structure. For historical reasons, many kvm-related function parameters
retain the 'kvm_run' and 'kvm_vcpu' parameters at the same time. This
patch does a unified cleanup of these remaining redundant parameters.

[paulus@ozlabs.org - Fixed places that were missed in book3s_interrupts.S]

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/include/asm/kvm_ppc.h    |  2 +-
 arch/powerpc/kvm/book3s_interrupts.S  | 56 +++++++++++++--------------
 arch/powerpc/kvm/book3s_pr.c          |  9 ++---
 arch/powerpc/kvm/booke.c              |  9 ++---
 arch/powerpc/kvm/booke_interrupts.S   |  9 ++---
 arch/powerpc/kvm/bookehv_interrupts.S | 10 ++---
 6 files changed, 45 insertions(+), 50 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index ccf66b3a4c1d..0a056c64c317 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -59,7 +59,7 @@ enum xlate_readwrite {
 };
 
 extern int kvmppc_vcpu_run(struct kvm_vcpu *vcpu);
-extern int __kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu);
+extern int __kvmppc_vcpu_run(struct kvm_vcpu *vcpu);
 extern void kvmppc_handler_highmem(void);
 
 extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu);
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index f7ad99d972ce..17371e197994 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -55,8 +55,7 @@
  ****************************************************************************/
 
 /* Registers:
- *  r3: kvm_run pointer
- *  r4: vcpu pointer
+ *  r3: vcpu pointer
  */
 _GLOBAL(__kvmppc_vcpu_run)
 
@@ -68,8 +67,8 @@ kvm_start_entry:
 	/* Save host state to the stack */
 	PPC_STLU r1, -SWITCH_FRAME_SIZE(r1)
 
-	/* Save r3 (kvm_run) and r4 (vcpu) */
-	SAVE_2GPRS(3, r1)
+	/* Save r3 (vcpu) */
+	SAVE_GPR(3, r1)
 
 	/* Save non-volatile registers (r14 - r31) */
 	SAVE_NVGPRS(r1)
@@ -82,47 +81,46 @@ kvm_start_entry:
 	PPC_STL	r0, _LINK(r1)
 
 	/* Load non-volatile guest state from the vcpu */
-	VCPU_LOAD_NVGPRS(r4)
+	VCPU_LOAD_NVGPRS(r3)
 
 kvm_start_lightweight:
 	/* Copy registers into shadow vcpu so we can access them in real mode */
-	mr	r3, r4
 	bl	FUNC(kvmppc_copy_to_svcpu)
 	nop
-	REST_GPR(4, r1)
+	REST_GPR(3, r1)
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	/* Get the dcbz32 flag */
-	PPC_LL	r3, VCPU_HFLAGS(r4)
-	rldicl	r3, r3, 0, 63		/* r3 &= 1 */
-	stb	r3, HSTATE_RESTORE_HID5(r13)
+	PPC_LL	r0, VCPU_HFLAGS(r3)
+	rldicl	r0, r0, 0, 63		/* r3 &= 1 */
+	stb	r0, HSTATE_RESTORE_HID5(r13)
 
 	/* Load up guest SPRG3 value, since it's user readable */
-	lwz	r3, VCPU_SHAREDBE(r4)
-	cmpwi	r3, 0
-	ld	r5, VCPU_SHARED(r4)
+	lbz	r4, VCPU_SHAREDBE(r3)
+	cmpwi	r4, 0
+	ld	r5, VCPU_SHARED(r3)
 	beq	sprg3_little_endian
 sprg3_big_endian:
 #ifdef __BIG_ENDIAN__
-	ld	r3, VCPU_SHARED_SPRG3(r5)
+	ld	r4, VCPU_SHARED_SPRG3(r5)
 #else
 	addi	r5, r5, VCPU_SHARED_SPRG3
-	ldbrx	r3, 0, r5
+	ldbrx	r4, 0, r5
 #endif
 	b	after_sprg3_load
 sprg3_little_endian:
 #ifdef __LITTLE_ENDIAN__
-	ld	r3, VCPU_SHARED_SPRG3(r5)
+	ld	r4, VCPU_SHARED_SPRG3(r5)
 #else
 	addi	r5, r5, VCPU_SHARED_SPRG3
-	ldbrx	r3, 0, r5
+	ldbrx	r4, 0, r5
 #endif
 
 after_sprg3_load:
-	mtspr	SPRN_SPRG3, r3
+	mtspr	SPRN_SPRG3, r4
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
-	PPC_LL	r4, VCPU_SHADOW_MSR(r4)	/* get shadow_msr */
+	PPC_LL	r4, VCPU_SHADOW_MSR(r3)	/* get shadow_msr */
 
 	/* Jump to segment patching handler and into our guest */
 	bl	FUNC(kvmppc_entry_trampoline)
@@ -146,7 +144,7 @@ after_sprg3_load:
 	 *
 	 */
 
-	PPC_LL	r3, GPR4(r1)		/* vcpu pointer */
+	PPC_LL	r3, GPR3(r1)		/* vcpu pointer */
 
 	/*
 	 * kvmppc_copy_from_svcpu can clobber volatile registers, save
@@ -169,7 +167,7 @@ after_sprg3_load:
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 	/* R7 = vcpu */
-	PPC_LL	r7, GPR4(r1)
+	PPC_LL	r7, GPR3(r1)
 
 	PPC_STL	r14, VCPU_GPR(R14)(r7)
 	PPC_STL	r15, VCPU_GPR(R15)(r7)
@@ -190,11 +188,11 @@ after_sprg3_load:
 	PPC_STL	r30, VCPU_GPR(R30)(r7)
 	PPC_STL	r31, VCPU_GPR(R31)(r7)
 
-	/* Pass the exit number as 3rd argument to kvmppc_handle_exit */
-	lwz	r5, VCPU_TRAP(r7)
+	/* Pass the exit number as 2nd argument to kvmppc_handle_exit */
+	lwz	r4, VCPU_TRAP(r7)
 
-	/* Restore r3 (kvm_run) and r4 (vcpu) */
-	REST_2GPRS(3, r1)
+	/* Restore r3 (vcpu) */
+	REST_GPR(3, r1)
 	bl	FUNC(kvmppc_handle_exit_pr)
 
 	/* If RESUME_GUEST, get back in the loop */
@@ -223,11 +221,11 @@ kvm_loop_heavyweight:
 	PPC_LL	r4, _LINK(r1)
 	PPC_STL r4, (PPC_LR_STKOFF + SWITCH_FRAME_SIZE)(r1)
 
-	/* Load vcpu and cpu_run */
-	REST_2GPRS(3, r1)
+	/* Load vcpu */
+	REST_GPR(3, r1)
 
 	/* Load non-volatile guest state from the vcpu */
-	VCPU_LOAD_NVGPRS(r4)
+	VCPU_LOAD_NVGPRS(r3)
 
 	/* Jump back into the beginning of this function */
 	b	kvm_start_lightweight
@@ -235,7 +233,7 @@ kvm_loop_heavyweight:
 kvm_loop_lightweight:
 
 	/* We'll need the vcpu pointer */
-	REST_GPR(4, r1)
+	REST_GPR(3, r1)
 
 	/* Jump back into the beginning of this function */
 	b	kvm_start_lightweight
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index ef54f917bdaf..01c8fe5abe0d 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1151,9 +1151,9 @@ static int kvmppc_exit_pr_progint(struct kvm_vcpu *vcpu, unsigned int exit_nr)
 	return r;
 }
 
-int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
-			  unsigned int exit_nr)
+int kvmppc_handle_exit_pr(struct kvm_vcpu *vcpu, unsigned int exit_nr)
 {
+	struct kvm_run *run = vcpu->run;
 	int r = RESUME_HOST;
 	int s;
 
@@ -1826,7 +1826,6 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu)
 
 static int kvmppc_vcpu_run_pr(struct kvm_vcpu *vcpu)
 {
-	struct kvm_run *run = vcpu->run;
 	int ret;
 #ifdef CONFIG_ALTIVEC
 	unsigned long uninitialized_var(vrsave);
@@ -1834,7 +1833,7 @@ static int kvmppc_vcpu_run_pr(struct kvm_vcpu *vcpu)
 
 	/* Check if we can run the vcpu at all */
 	if (!vcpu->arch.sane) {
-		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1861,7 +1860,7 @@ static int kvmppc_vcpu_run_pr(struct kvm_vcpu *vcpu)
 
 	kvmppc_fix_ee_before_entry();
 
-	ret = __kvmppc_vcpu_run(run, vcpu);
+	ret = __kvmppc_vcpu_run(vcpu);
 
 	kvmppc_clear_debug(vcpu);
 
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index c0d62a917e20..3e1c9f08e302 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -731,12 +731,11 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 
 int kvmppc_vcpu_run(struct kvm_vcpu *vcpu)
 {
-	struct kvm_run *run = vcpu->run;
 	int ret, s;
 	struct debug_reg debug;
 
 	if (!vcpu->arch.sane) {
-		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		return -EINVAL;
 	}
 
@@ -778,7 +777,7 @@ int kvmppc_vcpu_run(struct kvm_vcpu *vcpu)
 	vcpu->arch.pgdir = vcpu->kvm->mm->pgd;
 	kvmppc_fix_ee_before_entry();
 
-	ret = __kvmppc_vcpu_run(run, vcpu);
+	ret = __kvmppc_vcpu_run(vcpu);
 
 	/* No need for guest_exit. It's done in handle_exit.
 	   We also get here with interrupts enabled. */
@@ -982,9 +981,9 @@ static int kvmppc_resume_inst_load(struct kvm_vcpu *vcpu,
  *
  * Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV)
  */
-int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                       unsigned int exit_nr)
+int kvmppc_handle_exit(struct kvm_vcpu *vcpu, unsigned int exit_nr)
 {
+	struct kvm_run *run = vcpu->run;
 	int r = RESUME_HOST;
 	int s;
 	int idx;
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index 2e56ab5a5f55..6fa82efe833b 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -237,7 +237,7 @@ _GLOBAL(kvmppc_resume_host)
 	/* Switch to kernel stack and jump to handler. */
 	LOAD_REG_ADDR(r3, kvmppc_handle_exit)
 	mtctr	r3
-	lwz	r3, HOST_RUN(r1)
+	mr	r3, r4
 	lwz	r2, HOST_R2(r1)
 	mr	r14, r4 /* Save vcpu pointer. */
 
@@ -337,15 +337,14 @@ heavyweight_exit:
 
 
 /* Registers:
- *  r3: kvm_run pointer
- *  r4: vcpu pointer
+ *  r3: vcpu pointer
  */
 _GLOBAL(__kvmppc_vcpu_run)
 	stwu	r1, -HOST_STACK_SIZE(r1)
-	stw	r1, VCPU_HOST_STACK(r4)	/* Save stack pointer to vcpu. */
+	stw	r1, VCPU_HOST_STACK(r3)	/* Save stack pointer to vcpu. */
 
 	/* Save host state to stack. */
-	stw	r3, HOST_RUN(r1)
+	mr	r4, r3
 	mflr	r3
 	stw	r3, HOST_STACK_LR(r1)
 	mfcr	r5
diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
index c577ba4b3169..8262c14fc9e6 100644
--- a/arch/powerpc/kvm/bookehv_interrupts.S
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -434,9 +434,10 @@ _GLOBAL(kvmppc_resume_host)
 #endif
 
 	/* Switch to kernel stack and jump to handler. */
-	PPC_LL	r3, HOST_RUN(r1)
+	mr	r3, r4
 	mr	r5, r14 /* intno */
 	mr	r14, r4 /* Save vcpu pointer. */
+	mr	r4, r5
 	bl	kvmppc_handle_exit
 
 	/* Restore vcpu pointer and the nonvolatiles we used. */
@@ -525,15 +526,14 @@ heavyweight_exit:
 	blr
 
 /* Registers:
- *  r3: kvm_run pointer
- *  r4: vcpu pointer
+ *  r3: vcpu pointer
  */
 _GLOBAL(__kvmppc_vcpu_run)
 	stwu	r1, -HOST_STACK_SIZE(r1)
-	PPC_STL	r1, VCPU_HOST_STACK(r4)	/* Save stack pointer to vcpu. */
+	PPC_STL	r1, VCPU_HOST_STACK(r3)	/* Save stack pointer to vcpu. */
 
 	/* Save host state to stack. */
-	PPC_STL	r3, HOST_RUN(r1)
+	mr	r4, r3
 	mflr	r3
 	mfcr	r5
 	PPC_STL	r3, HOST_STACK_LR(r1)

From 2a08a9232ba2e6103843870e68edae8e381eb02a Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime@cerno.tech>
Date: Fri, 26 Jun 2020 13:54:33 +0200
Subject: [PATCH 077/474] dt-bindings: arm: bcm: Add a select to the RPI
 Firmware binding

The RaspberryPi firmware binding uses two compatible, include simple-bus.
The select statement generated by default will thus select any node that
has simple-bus, not all of them being the raspberrypi firmware node.

This results in warnings being wrongfully reported. Let's add a custom
select statement to fix that.

Fixes: d4c708c032df ("dt-bindings: arm: bcm: Convert BCM2835 firmware binding to YAML")
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Link: https://lore.kernel.org/r/20200626115433.125735-1-maxime@cerno.tech
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml   | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml b/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml
index b48ed875eb8e..17e4f20c8d39 100644
--- a/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml
@@ -10,6 +10,15 @@ maintainers:
   - Eric Anholt <eric@anholt.net>
   - Stefan Wahren <wahrenst@gmx.net>
 
+select:
+  properties:
+    compatible:
+      contains:
+        const: raspberrypi,bcm2835-firmware
+
+  required:
+    - compatible
+
 properties:
   compatible:
     items:

From 3ba72c35cf1c79cb95eebd7fa20f416c4fa952eb Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Thu, 23 Jul 2020 09:41:10 +0200
Subject: [PATCH 078/474] dt-bindings: clk: versaclock5: fix 'idt' prefix typos

'idt' is misspelled 'itd' in a few places, fix it.

Fixes: 34662f6e3084 ("dt: Add additional option bindings for IDT VersaClock")
Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20200723074112.3159-2-luca@lucaceresoli.net
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 Documentation/devicetree/bindings/clock/idt,versaclock5.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/clock/idt,versaclock5.txt b/Documentation/devicetree/bindings/clock/idt,versaclock5.txt
index 6165b6ddb1a9..9656d4cf221c 100644
--- a/Documentation/devicetree/bindings/clock/idt,versaclock5.txt
+++ b/Documentation/devicetree/bindings/clock/idt,versaclock5.txt
@@ -35,7 +35,7 @@ For all output ports, a corresponding, optional child node named OUT1,
 OUT2, etc. can represent a each output, and the node can be used to
 specify the following:
 
-- itd,mode: can be one of the following:
+- idt,mode: can be one of the following:
                  - VC5_LVPECL
                  - VC5_CMOS
                  - VC5_HCSL33
@@ -106,7 +106,7 @@ i2c-master-node {
 		clock-names = "xin";
 
 		OUT1 {
-			itd,mode = <VC5_CMOS>;
+			idt,mode = <VC5_CMOS>;
 			idt,voltage-microvolts = <1800000>;
 			idt,slew-percent = <80>;
 		};

From db136ac978ffbcc9a07b69906d7f6d2c49e033c0 Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Thu, 23 Jul 2020 09:41:11 +0200
Subject: [PATCH 079/474] MAINTAINERS: take over IDT VersaClock 5 clock driver

Marek has been the primary developer of this driver (thanks!). Now as
he is not working on it anymore he suggested I take over maintainership.

Cc: Marek Vasut <marek.vasut@gmail.com>
Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Link: https://lore.kernel.org/r/20200723074112.3159-3-luca@lucaceresoli.net
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 68f21d46614c..5aa16c245c63 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8324,7 +8324,7 @@ W:	https://github.com/o2genum/ideapad-slidebar
 F:	drivers/input/misc/ideapad_slidebar.c
 
 IDT VersaClock 5 CLOCK DRIVER
-M:	Marek Vasut <marek.vasut@gmail.com>
+M:	Luca Ceresoli <luca@lucaceresoli.net>
 S:	Maintained
 F:	drivers/clk/clk-versaclock5.c
 

From 45c940184b501fc65592432a269b7a34cf2237b6 Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Thu, 23 Jul 2020 09:41:12 +0200
Subject: [PATCH 080/474] dt-bindings: clk: versaclock5: convert to yaml

Convert to yaml the VersaClock bindings document. The mapping between
clock specifier and physical pins cannot be described formally in yaml
schema, then keep it verbatim in the description field.

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Link: https://lore.kernel.org/r/20200723074112.3159-4-luca@lucaceresoli.net
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../bindings/clock/idt,versaclock5.txt        | 125 --------------
 .../bindings/clock/idt,versaclock5.yaml       | 154 ++++++++++++++++++
 MAINTAINERS                                   |   1 +
 3 files changed, 155 insertions(+), 125 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/clock/idt,versaclock5.txt
 create mode 100644 Documentation/devicetree/bindings/clock/idt,versaclock5.yaml

diff --git a/Documentation/devicetree/bindings/clock/idt,versaclock5.txt b/Documentation/devicetree/bindings/clock/idt,versaclock5.txt
deleted file mode 100644
index 9656d4cf221c..000000000000
--- a/Documentation/devicetree/bindings/clock/idt,versaclock5.txt
+++ /dev/null
@@ -1,125 +0,0 @@
-Binding for IDT VersaClock 5,6 programmable i2c clock generators.
-
-The IDT VersaClock 5 and VersaClock 6 are programmable i2c clock
-generators providing from 3 to 12 output clocks.
-
-==I2C device node==
-
-Required properties:
-- compatible:	shall be one of
-		"idt,5p49v5923"
-		"idt,5p49v5925"
-		"idt,5p49v5933"
-		"idt,5p49v5935"
-		"idt,5p49v6901"
-		"idt,5p49v6965"
-- reg:		i2c device address, shall be 0x68 or 0x6a.
-- #clock-cells:	from common clock binding; shall be set to 1.
-- clocks:	from common clock binding; list of parent clock handles,
-		- 5p49v5923 and
-		  5p49v5925 and
-		  5p49v6901: (required) either or both of XTAL or CLKIN
-					reference clock.
-		- 5p49v5933 and
-		- 5p49v5935: (optional) property not present (internal
-					Xtal used) or CLKIN reference
-					clock.
-- clock-names:	from common clock binding; clock input names, can be
-		- 5p49v5923 and
-		  5p49v5925 and
-		  5p49v6901: (required) either or both of "xin", "clkin".
-		- 5p49v5933 and
-		- 5p49v5935: (optional) property not present or "clkin".
-
-For all output ports, a corresponding, optional child node named OUT1,
-OUT2, etc. can represent a each output, and the node can be used to
-specify the following:
-
-- idt,mode: can be one of the following:
-                 - VC5_LVPECL
-                 - VC5_CMOS
-                 - VC5_HCSL33
-                 - VC5_LVDS
-                 - VC5_CMOS2
-                 - VC5_CMOSD
-                 - VC5_HCSL25
-
-- idt,voltage-microvolts:  can be one of the following
-                 - 1800000
-                 - 2500000
-                 - 3300000
--  idt,slew-percent: Percent of normal, can be one of
-                 - 80
-                 - 85
-                 - 90
-                 - 100
-
-==Mapping between clock specifier and physical pins==
-
-When referencing the provided clock in the DT using phandle and
-clock specifier, the following mapping applies:
-
-5P49V5923:
-	0 -- OUT0_SEL_I2CB
-	1 -- OUT1
-	2 -- OUT2
-
-5P49V5933:
-	0 -- OUT0_SEL_I2CB
-	1 -- OUT1
-	2 -- OUT4
-
-5P49V5925 and
-5P49V5935:
-	0 -- OUT0_SEL_I2CB
-	1 -- OUT1
-	2 -- OUT2
-	3 -- OUT3
-	4 -- OUT4
-
-5P49V6901:
-	0 -- OUT0_SEL_I2CB
-	1 -- OUT1
-	2 -- OUT2
-	3 -- OUT3
-	4 -- OUT4
-
-==Example==
-
-/* 25MHz reference crystal */
-ref25: ref25m {
-	compatible = "fixed-clock";
-	#clock-cells = <0>;
-	clock-frequency = <25000000>;
-};
-
-i2c-master-node {
-
-	/* IDT 5P49V5923 i2c clock generator */
-	vc5: clock-generator@6a {
-		compatible = "idt,5p49v5923";
-		reg = <0x6a>;
-		#clock-cells = <1>;
-
-		/* Connect XIN input to 25MHz reference */
-		clocks = <&ref25m>;
-		clock-names = "xin";
-
-		OUT1 {
-			idt,mode = <VC5_CMOS>;
-			idt,voltage-microvolts = <1800000>;
-			idt,slew-percent = <80>;
-		};
-		OUT2 {
-			...
-		};
-		...
-	};
-};
-
-/* Consumer referencing the 5P49V5923 pin OUT1 */
-consumer {
-	...
-	clocks = <&vc5 1>;
-	...
-}
diff --git a/Documentation/devicetree/bindings/clock/idt,versaclock5.yaml b/Documentation/devicetree/bindings/clock/idt,versaclock5.yaml
new file mode 100644
index 000000000000..3d4e1685cc55
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/idt,versaclock5.yaml
@@ -0,0 +1,154 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/idt,versaclock5.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Binding for IDT VersaClock 5 and 6 programmable I2C clock generators
+
+description: |
+  The IDT VersaClock 5 and VersaClock 6 are programmable I2C
+  clock generators providing from 3 to 12 output clocks.
+
+  When referencing the provided clock in the DT using phandle and clock
+  specifier, the following mapping applies:
+
+  - 5P49V5923:
+    0 -- OUT0_SEL_I2CB
+    1 -- OUT1
+    2 -- OUT2
+
+  - 5P49V5933:
+    0 -- OUT0_SEL_I2CB
+    1 -- OUT1
+    2 -- OUT4
+
+  - other parts:
+    0 -- OUT0_SEL_I2CB
+    1 -- OUT1
+    2 -- OUT2
+    3 -- OUT3
+    4 -- OUT4
+
+maintainers:
+  - Luca Ceresoli <luca@lucaceresoli.net>
+
+properties:
+  compatible:
+    enum:
+      - idt,5p49v5923
+      - idt,5p49v5925
+      - idt,5p49v5933
+      - idt,5p49v5935
+      - idt,5p49v6901
+      - idt,5p49v6965
+
+  reg:
+    description: I2C device address
+    enum: [ 0x68, 0x6a ]
+
+  '#clock-cells':
+    const: 1
+
+patternProperties:
+  "^OUT[1-4]$":
+    type: object
+    description:
+      Description of one of the outputs (OUT1..OUT4). See "Clock1 Output
+      Configuration" in the Versaclock 5/6/6E Family Register Description
+      and Programming Guide.
+    properties:
+      idt,mode:
+        description:
+          The output drive mode. Values defined in dt-bindings/clk/versaclock.h
+        $ref: /schemas/types.yaml#/definitions/uint32
+        minimum: 0
+        maximum: 6
+      idt,voltage-microvolt:
+        description: The output drive voltage.
+        enum: [ 1800000, 2500000, 3300000 ]
+      idt,slew-percent:
+        description: The Slew rate control for CMOS single-ended.
+        $ref: /schemas/types.yaml#/definitions/uint32
+        enum: [ 80, 85, 90, 100 ]
+
+required:
+  - compatible
+  - reg
+  - '#clock-cells'
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          enum:
+            - idt,5p49v5933
+            - idt,5p49v5935
+    then:
+      # Devices with builtin crystal + optional external input
+      properties:
+        clock-names:
+          const: clkin
+        clocks:
+          maxItems: 1
+    else:
+      # Devices without builtin crystal
+      properties:
+        clock-names:
+            minItems: 1
+            maxItems: 2
+            items:
+              enum: [ xin, clkin ]
+        clocks:
+          minItems: 1
+          maxItems: 2
+      required:
+        - clock-names
+        - clocks
+
+examples:
+  - |
+    #include <dt-bindings/clk/versaclock.h>
+
+    /* 25MHz reference crystal */
+    ref25: ref25m {
+        compatible = "fixed-clock";
+        #clock-cells = <0>;
+        clock-frequency = <25000000>;
+    };
+
+    i2c@0 {
+        reg = <0x0 0x100>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        /* IDT 5P49V5923 I2C clock generator */
+        vc5: clock-generator@6a {
+            compatible = "idt,5p49v5923";
+            reg = <0x6a>;
+            #clock-cells = <1>;
+
+            /* Connect XIN input to 25MHz reference */
+            clocks = <&ref25m>;
+            clock-names = "xin";
+
+            OUT1 {
+                idt,drive-mode = <VC5_CMOSD>;
+                idt,voltage-microvolts = <1800000>;
+                idt,slew-percent = <80>;
+            };
+
+            OUT4 {
+                idt,drive-mode = <VC5_LVDS>;
+            };
+        };
+    };
+
+    /* Consumer referencing the 5P49V5923 pin OUT1 */
+    consumer {
+        /* ... */
+        clocks = <&vc5 1>;
+        /* ... */
+    };
+
+...
diff --git a/MAINTAINERS b/MAINTAINERS
index 5aa16c245c63..09d6efd1d0d0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8326,6 +8326,7 @@ F:	drivers/input/misc/ideapad_slidebar.c
 IDT VersaClock 5 CLOCK DRIVER
 M:	Luca Ceresoli <luca@lucaceresoli.net>
 S:	Maintained
+F:	Documentation/devicetree/bindings/clock/idt,versaclock5.yaml
 F:	drivers/clk/clk-versaclock5.c
 
 IEEE 802.15.4 SUBSYSTEM

From 3bca66b08ec833c4506e97371f2c74e7de00792a Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Thu, 23 Jul 2020 09:26:03 +0200
Subject: [PATCH 081/474] clk: vc5: use a dedicated struct to describe the
 output drivers

Reusing the generic struct vc5_hw_data for all blocks is handy. However it
implies we allocate space the div_int and div_frc fields even for the
output drivers where they are unused, and the clk_output_cfg0 and
clk_output_cfg0_mask fields for all components even though they are used
only for the output drivers.

Use a dedicated struct for the output drivers so that each block uses
exactly the fields it needs, not more.

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Link: https://lore.kernel.org/r/20200723072603.1795-1-luca@lucaceresoli.net
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-versaclock5.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/clk/clk-versaclock5.c b/drivers/clk/clk-versaclock5.c
index 32f0aa64f062..c90460e7ef21 100644
--- a/drivers/clk/clk-versaclock5.c
+++ b/drivers/clk/clk-versaclock5.c
@@ -167,6 +167,12 @@ struct vc5_hw_data {
 	u32			div_int;
 	u32			div_frc;
 	unsigned int		num;
+};
+
+struct vc5_out_data {
+	struct clk_hw		hw;
+	struct vc5_driver_data	*vc5;
+	unsigned int		num;
 	unsigned int		clk_output_cfg0;
 	unsigned int		clk_output_cfg0_mask;
 };
@@ -184,7 +190,7 @@ struct vc5_driver_data {
 	struct clk_hw		clk_pfd;
 	struct vc5_hw_data	clk_pll;
 	struct vc5_hw_data	clk_fod[VC5_MAX_FOD_NUM];
-	struct vc5_hw_data	clk_out[VC5_MAX_CLK_OUT_NUM];
+	struct vc5_out_data	clk_out[VC5_MAX_CLK_OUT_NUM];
 };
 
 /*
@@ -567,7 +573,7 @@ static const struct clk_ops vc5_fod_ops = {
 
 static int vc5_clk_out_prepare(struct clk_hw *hw)
 {
-	struct vc5_hw_data *hwdata = container_of(hw, struct vc5_hw_data, hw);
+	struct vc5_out_data *hwdata = container_of(hw, struct vc5_out_data, hw);
 	struct vc5_driver_data *vc5 = hwdata->vc5;
 	const u8 mask = VC5_OUT_DIV_CONTROL_SELB_NORM |
 			VC5_OUT_DIV_CONTROL_SEL_EXT |
@@ -609,7 +615,7 @@ static int vc5_clk_out_prepare(struct clk_hw *hw)
 
 static void vc5_clk_out_unprepare(struct clk_hw *hw)
 {
-	struct vc5_hw_data *hwdata = container_of(hw, struct vc5_hw_data, hw);
+	struct vc5_out_data *hwdata = container_of(hw, struct vc5_out_data, hw);
 	struct vc5_driver_data *vc5 = hwdata->vc5;
 
 	/* Disable the clock buffer */
@@ -619,7 +625,7 @@ static void vc5_clk_out_unprepare(struct clk_hw *hw)
 
 static unsigned char vc5_clk_out_get_parent(struct clk_hw *hw)
 {
-	struct vc5_hw_data *hwdata = container_of(hw, struct vc5_hw_data, hw);
+	struct vc5_out_data *hwdata = container_of(hw, struct vc5_out_data, hw);
 	struct vc5_driver_data *vc5 = hwdata->vc5;
 	const u8 mask = VC5_OUT_DIV_CONTROL_SELB_NORM |
 			VC5_OUT_DIV_CONTROL_SEL_EXT |
@@ -649,7 +655,7 @@ static unsigned char vc5_clk_out_get_parent(struct clk_hw *hw)
 
 static int vc5_clk_out_set_parent(struct clk_hw *hw, u8 index)
 {
-	struct vc5_hw_data *hwdata = container_of(hw, struct vc5_hw_data, hw);
+	struct vc5_out_data *hwdata = container_of(hw, struct vc5_out_data, hw);
 	struct vc5_driver_data *vc5 = hwdata->vc5;
 	const u8 mask = VC5_OUT_DIV_CONTROL_RESET |
 			VC5_OUT_DIV_CONTROL_SELB_NORM |
@@ -704,7 +710,7 @@ static int vc5_map_index_to_output(const enum vc5_model model,
 }
 
 static int vc5_update_mode(struct device_node *np_output,
-			   struct vc5_hw_data *clk_out)
+			   struct vc5_out_data *clk_out)
 {
 	u32 value;
 
@@ -729,7 +735,7 @@ static int vc5_update_mode(struct device_node *np_output,
 }
 
 static int vc5_update_power(struct device_node *np_output,
-			    struct vc5_hw_data *clk_out)
+			    struct vc5_out_data *clk_out)
 {
 	u32 value;
 
@@ -754,7 +760,7 @@ static int vc5_update_power(struct device_node *np_output,
 }
 
 static int vc5_update_slew(struct device_node *np_output,
-			   struct vc5_hw_data *clk_out)
+			   struct vc5_out_data *clk_out)
 {
 	u32 value;
 
@@ -782,7 +788,7 @@ static int vc5_update_slew(struct device_node *np_output,
 }
 
 static int vc5_get_output_config(struct i2c_client *client,
-				 struct vc5_hw_data *clk_out)
+				 struct vc5_out_data *clk_out)
 {
 	struct device_node *np_output;
 	char *child_name;

From 667f39b59b494d96ae70f4217637db2ebbee3df0 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 9 Jul 2020 09:52:32 -0400
Subject: [PATCH 082/474] clk: qcom: gcc: fix sm8150 GPU and NPU clocks

Fix the parents and set BRANCH_HALT_SKIP. From the downstream driver it
should be a 500us delay and not skip, however this matches what was done
for other clocks that had 500us delay in downstream.

Fixes: f73a4230d5bb ("clk: qcom: gcc: Add GPU and NPU clocks for SM8150")
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20200709135251.643-2-jonathan@marek.ca
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/gcc-sm8150.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/qcom/gcc-sm8150.c b/drivers/clk/qcom/gcc-sm8150.c
index 72524cf11048..55e9d6d75a0c 100644
--- a/drivers/clk/qcom/gcc-sm8150.c
+++ b/drivers/clk/qcom/gcc-sm8150.c
@@ -1617,6 +1617,7 @@ static struct clk_branch gcc_gpu_cfg_ahb_clk = {
 };
 
 static struct clk_branch gcc_gpu_gpll0_clk_src = {
+	.halt_check = BRANCH_HALT_SKIP,
 	.clkr = {
 		.enable_reg = 0x52004,
 		.enable_mask = BIT(15),
@@ -1632,13 +1633,14 @@ static struct clk_branch gcc_gpu_gpll0_clk_src = {
 };
 
 static struct clk_branch gcc_gpu_gpll0_div_clk_src = {
+	.halt_check = BRANCH_HALT_SKIP,
 	.clkr = {
 		.enable_reg = 0x52004,
 		.enable_mask = BIT(16),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_gpu_gpll0_div_clk_src",
 			.parent_hws = (const struct clk_hw *[]){
-				&gcc_gpu_gpll0_clk_src.clkr.hw },
+				&gpll0_out_even.clkr.hw },
 			.num_parents = 1,
 			.flags = CLK_SET_RATE_PARENT,
 			.ops = &clk_branch2_ops,
@@ -1729,6 +1731,7 @@ static struct clk_branch gcc_npu_cfg_ahb_clk = {
 };
 
 static struct clk_branch gcc_npu_gpll0_clk_src = {
+	.halt_check = BRANCH_HALT_SKIP,
 	.clkr = {
 		.enable_reg = 0x52004,
 		.enable_mask = BIT(18),
@@ -1744,13 +1747,14 @@ static struct clk_branch gcc_npu_gpll0_clk_src = {
 };
 
 static struct clk_branch gcc_npu_gpll0_div_clk_src = {
+	.halt_check = BRANCH_HALT_SKIP,
 	.clkr = {
 		.enable_reg = 0x52004,
 		.enable_mask = BIT(19),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_npu_gpll0_div_clk_src",
 			.parent_hws = (const struct clk_hw *[]){
-				&gcc_npu_gpll0_clk_src.clkr.hw },
+				&gpll0_out_even.clkr.hw },
 			.num_parents = 1,
 			.flags = CLK_SET_RATE_PARENT,
 			.ops = &clk_branch2_ops,

From c8b9002f44e4a1d2771b2f59f6de900864b1f9d7 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 9 Jul 2020 09:52:33 -0400
Subject: [PATCH 083/474] clk: qcom: clk-alpha-pll: remove unused/incorrect
 PLL_CAL_VAL

0x44 isn't a register offset, it is the value that goes into CAL_L_VAL.

Fixes: 548a909597d5 ("clk: qcom: clk-alpha-pll: Add support for Trion PLLs")
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20200709135251.643-3-jonathan@marek.ca
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/clk-alpha-pll.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index 9b2dfa08acb2..1325139173c9 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -56,7 +56,6 @@
 #define PLL_STATUS(p)		((p)->offset + (p)->regs[PLL_OFF_STATUS])
 #define PLL_OPMODE(p)		((p)->offset + (p)->regs[PLL_OFF_OPMODE])
 #define PLL_FRAC(p)		((p)->offset + (p)->regs[PLL_OFF_FRAC])
-#define PLL_CAL_VAL(p)		((p)->offset + (p)->regs[PLL_OFF_CAL_VAL])
 
 const u8 clk_alpha_pll_regs[][PLL_OFF_MAX_REGS] = {
 	[CLK_ALPHA_PLL_TYPE_DEFAULT] =  {
@@ -115,7 +114,6 @@ const u8 clk_alpha_pll_regs[][PLL_OFF_MAX_REGS] = {
 		[PLL_OFF_STATUS] = 0x30,
 		[PLL_OFF_OPMODE] = 0x38,
 		[PLL_OFF_ALPHA_VAL] = 0x40,
-		[PLL_OFF_CAL_VAL] = 0x44,
 	},
 	[CLK_ALPHA_PLL_TYPE_LUCID] =  {
 		[PLL_OFF_L_VAL] = 0x04,

From 0b01489475c655f8ccce8fa13cc4088954ac5503 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 9 Jul 2020 09:52:34 -0400
Subject: [PATCH 084/474] clk: qcom: clk-alpha-pll: same regs and ops for trion
 and lucid

Fixed ops were already identical, this adds support for non-fixed ops by
sharing between trion and lucid.

This also changes the names for trion ops to be consistent with the rest.

Note LUCID_PCAL_DONE is renamed to TRION_PCAL_DONE because it is wrong for
lucid, LUCID_PCAL_DONE should be BIT(27). Next patch will address this.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20200709135251.643-4-jonathan@marek.ca
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/clk-alpha-pll.c | 58 ++++++++++----------------------
 drivers/clk/qcom/clk-alpha-pll.h | 17 ++++++----
 drivers/clk/qcom/gcc-sm8150.c    |  8 ++---
 3 files changed, 32 insertions(+), 51 deletions(-)

diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index 1325139173c9..be7ffeae21b1 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -101,21 +101,6 @@ const u8 clk_alpha_pll_regs[][PLL_OFF_MAX_REGS] = {
 		[PLL_OFF_FRAC] = 0x38,
 	},
 	[CLK_ALPHA_PLL_TYPE_TRION] = {
-		[PLL_OFF_L_VAL] = 0x04,
-		[PLL_OFF_CAL_L_VAL] = 0x08,
-		[PLL_OFF_USER_CTL] = 0x0c,
-		[PLL_OFF_USER_CTL_U] = 0x10,
-		[PLL_OFF_USER_CTL_U1] = 0x14,
-		[PLL_OFF_CONFIG_CTL] = 0x18,
-		[PLL_OFF_CONFIG_CTL_U] = 0x1c,
-		[PLL_OFF_CONFIG_CTL_U1] = 0x20,
-		[PLL_OFF_TEST_CTL] = 0x24,
-		[PLL_OFF_TEST_CTL_U] = 0x28,
-		[PLL_OFF_STATUS] = 0x30,
-		[PLL_OFF_OPMODE] = 0x38,
-		[PLL_OFF_ALPHA_VAL] = 0x40,
-	},
-	[CLK_ALPHA_PLL_TYPE_LUCID] =  {
 		[PLL_OFF_L_VAL] = 0x04,
 		[PLL_OFF_CAL_L_VAL] = 0x08,
 		[PLL_OFF_USER_CTL] = 0x0c,
@@ -154,9 +139,9 @@ EXPORT_SYMBOL_GPL(clk_alpha_pll_regs);
 #define PLL_OUT_MASK		0x7
 #define PLL_RATE_MARGIN		500
 
-/* LUCID PLL specific settings and offsets */
-#define LUCID_PLL_CAL_VAL	0x44
-#define LUCID_PCAL_DONE		BIT(26)
+/* TRION PLL specific settings and offsets */
+#define TRION_PLL_CAL_VAL	0x44
+#define TRION_PCAL_DONE		BIT(26)
 
 #define pll_alpha_width(p)					\
 		((PLL_ALPHA_VAL_U(p) - PLL_ALPHA_VAL(p) == 4) ?	\
@@ -910,14 +895,14 @@ const struct clk_ops clk_alpha_pll_hwfsm_ops = {
 };
 EXPORT_SYMBOL_GPL(clk_alpha_pll_hwfsm_ops);
 
-const struct clk_ops clk_trion_fixed_pll_ops = {
+const struct clk_ops clk_alpha_pll_fixed_trion_ops = {
 	.enable = clk_trion_pll_enable,
 	.disable = clk_trion_pll_disable,
 	.is_enabled = clk_trion_pll_is_enabled,
 	.recalc_rate = clk_trion_pll_recalc_rate,
 	.round_rate = clk_alpha_pll_round_rate,
 };
-EXPORT_SYMBOL_GPL(clk_trion_fixed_pll_ops);
+EXPORT_SYMBOL_GPL(clk_alpha_pll_fixed_trion_ops);
 
 static unsigned long
 clk_alpha_pll_postdiv_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
@@ -1337,12 +1322,12 @@ clk_trion_pll_postdiv_set_rate(struct clk_hw *hw, unsigned long rate,
 				  val << PLL_POST_DIV_SHIFT);
 }
 
-const struct clk_ops clk_trion_pll_postdiv_ops = {
+const struct clk_ops clk_alpha_pll_postdiv_trion_ops = {
 	.recalc_rate = clk_trion_pll_postdiv_recalc_rate,
 	.round_rate = clk_trion_pll_postdiv_round_rate,
 	.set_rate = clk_trion_pll_postdiv_set_rate,
 };
-EXPORT_SYMBOL_GPL(clk_trion_pll_postdiv_ops);
+EXPORT_SYMBOL_GPL(clk_alpha_pll_postdiv_trion_ops);
 
 static long clk_alpha_pll_postdiv_fabia_round_rate(struct clk_hw *hw,
 				unsigned long rate, unsigned long *prate)
@@ -1397,13 +1382,13 @@ EXPORT_SYMBOL_GPL(clk_alpha_pll_postdiv_fabia_ops);
  * @regmap: register map
  * @config: configuration to apply for pll
  */
-void clk_lucid_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
+void clk_trion_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 			     const struct alpha_pll_config *config)
 {
 	if (config->l)
 		regmap_write(regmap, PLL_L_VAL(pll), config->l);
 
-	regmap_write(regmap, PLL_CAL_L_VAL(pll), LUCID_PLL_CAL_VAL);
+	regmap_write(regmap, PLL_CAL_L_VAL(pll), TRION_PLL_CAL_VAL);
 
 	if (config->alpha)
 		regmap_write(regmap, PLL_ALPHA_VAL(pll), config->alpha);
@@ -1456,13 +1441,13 @@ void clk_lucid_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 	/* Place the PLL in STANDBY mode */
 	regmap_update_bits(regmap, PLL_MODE(pll), PLL_RESET_N, PLL_RESET_N);
 }
-EXPORT_SYMBOL_GPL(clk_lucid_pll_configure);
+EXPORT_SYMBOL_GPL(clk_trion_pll_configure);
 
 /*
- * The Lucid PLL requires a power-on self-calibration which happens when the
+ * The TRION PLL requires a power-on self-calibration which happens when the
  * PLL comes out of reset. Calibrate in case it is not completed.
  */
-static int alpha_pll_lucid_prepare(struct clk_hw *hw)
+static int alpha_pll_trion_prepare(struct clk_hw *hw)
 {
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
 	u32 regval;
@@ -1470,7 +1455,7 @@ static int alpha_pll_lucid_prepare(struct clk_hw *hw)
 
 	/* Return early if calibration is not needed. */
 	regmap_read(pll->clkr.regmap, PLL_STATUS(pll), &regval);
-	if (regval & LUCID_PCAL_DONE)
+	if (regval & TRION_PCAL_DONE)
 		return 0;
 
 	/* On/off to calibrate */
@@ -1481,7 +1466,7 @@ static int alpha_pll_lucid_prepare(struct clk_hw *hw)
 	return ret;
 }
 
-static int alpha_pll_lucid_set_rate(struct clk_hw *hw, unsigned long rate,
+static int alpha_pll_trion_set_rate(struct clk_hw *hw, unsigned long rate,
 				    unsigned long prate)
 {
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
@@ -1535,26 +1520,17 @@ static int alpha_pll_lucid_set_rate(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
-const struct clk_ops clk_alpha_pll_lucid_ops = {
-	.prepare = alpha_pll_lucid_prepare,
+const struct clk_ops clk_alpha_pll_trion_ops = {
+	.prepare = alpha_pll_trion_prepare,
 	.enable = clk_trion_pll_enable,
 	.disable = clk_trion_pll_disable,
 	.is_enabled = clk_trion_pll_is_enabled,
 	.recalc_rate = clk_trion_pll_recalc_rate,
 	.round_rate = clk_alpha_pll_round_rate,
-	.set_rate = alpha_pll_lucid_set_rate,
+	.set_rate = alpha_pll_trion_set_rate,
 };
 EXPORT_SYMBOL_GPL(clk_alpha_pll_lucid_ops);
 
-const struct clk_ops clk_alpha_pll_fixed_lucid_ops = {
-	.enable = clk_trion_pll_enable,
-	.disable = clk_trion_pll_disable,
-	.is_enabled = clk_trion_pll_is_enabled,
-	.recalc_rate = clk_trion_pll_recalc_rate,
-	.round_rate = clk_alpha_pll_round_rate,
-};
-EXPORT_SYMBOL_GPL(clk_alpha_pll_fixed_lucid_ops);
-
 const struct clk_ops clk_alpha_pll_postdiv_lucid_ops = {
 	.recalc_rate = clk_alpha_pll_postdiv_fabia_recalc_rate,
 	.round_rate = clk_alpha_pll_postdiv_fabia_round_rate,
diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h
index 1ba82be93dd5..d283ba739057 100644
--- a/drivers/clk/qcom/clk-alpha-pll.h
+++ b/drivers/clk/qcom/clk-alpha-pll.h
@@ -14,7 +14,7 @@ enum {
 	CLK_ALPHA_PLL_TYPE_BRAMMO,
 	CLK_ALPHA_PLL_TYPE_FABIA,
 	CLK_ALPHA_PLL_TYPE_TRION,
-	CLK_ALPHA_PLL_TYPE_LUCID,
+	CLK_ALPHA_PLL_TYPE_LUCID = CLK_ALPHA_PLL_TYPE_TRION,
 	CLK_ALPHA_PLL_TYPE_MAX,
 };
 
@@ -134,18 +134,23 @@ extern const struct clk_ops clk_alpha_pll_fabia_ops;
 extern const struct clk_ops clk_alpha_pll_fixed_fabia_ops;
 extern const struct clk_ops clk_alpha_pll_postdiv_fabia_ops;
 
-extern const struct clk_ops clk_alpha_pll_lucid_ops;
-extern const struct clk_ops clk_alpha_pll_fixed_lucid_ops;
+extern const struct clk_ops clk_alpha_pll_trion_ops;
+extern const struct clk_ops clk_alpha_pll_fixed_trion_ops;
+extern const struct clk_ops clk_alpha_pll_postdiv_trion_ops;
+
+#define clk_alpha_pll_lucid_ops clk_alpha_pll_trion_ops
+#define clk_alpha_pll_fixed_lucid_ops clk_alpha_pll_fixed_trion_ops
 extern const struct clk_ops clk_alpha_pll_postdiv_lucid_ops;
 
 void clk_alpha_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 			     const struct alpha_pll_config *config);
 void clk_fabia_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 				const struct alpha_pll_config *config);
-void clk_lucid_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
+void clk_trion_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 			     const struct alpha_pll_config *config);
+#define clk_lucid_pll_configure(pll, regmap, config) \
+	clk_trion_pll_configure(pll, regmap, config)
+
 
-extern const struct clk_ops clk_trion_fixed_pll_ops;
-extern const struct clk_ops clk_trion_pll_postdiv_ops;
 
 #endif
diff --git a/drivers/clk/qcom/gcc-sm8150.c b/drivers/clk/qcom/gcc-sm8150.c
index 55e9d6d75a0c..d7778def37da 100644
--- a/drivers/clk/qcom/gcc-sm8150.c
+++ b/drivers/clk/qcom/gcc-sm8150.c
@@ -53,7 +53,7 @@ static struct clk_alpha_pll gpll0 = {
 				.name = "bi_tcxo",
 			},
 			.num_parents = 1,
-			.ops = &clk_trion_fixed_pll_ops,
+			.ops = &clk_alpha_pll_fixed_trion_ops,
 		},
 	},
 };
@@ -79,7 +79,7 @@ static struct clk_alpha_pll_postdiv gpll0_out_even = {
 			.hw = &gpll0.clkr.hw,
 		},
 		.num_parents = 1,
-		.ops = &clk_trion_pll_postdiv_ops,
+		.ops = &clk_alpha_pll_postdiv_trion_ops,
 	},
 };
 
@@ -98,7 +98,7 @@ static struct clk_alpha_pll gpll7 = {
 				.name = "bi_tcxo",
 			},
 			.num_parents = 1,
-			.ops = &clk_trion_fixed_pll_ops,
+			.ops = &clk_alpha_pll_fixed_trion_ops,
 		},
 	},
 };
@@ -118,7 +118,7 @@ static struct clk_alpha_pll gpll9 = {
 				.name = "bi_tcxo",
 			},
 			.num_parents = 1,
-			.ops = &clk_trion_fixed_pll_ops,
+			.ops = &clk_alpha_pll_fixed_trion_ops,
 		},
 	},
 };

From d28b503c248df8a3b4c73b504a043bdf7e2d5207 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 9 Jul 2020 09:52:35 -0400
Subject: [PATCH 085/474] clk: qcom: clk-alpha-pll: use the right PCAL_DONE
 value for lucid pll

Lucid PCAL_DONE is different from trion.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20200709135251.643-5-jonathan@marek.ca
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/clk-alpha-pll.c | 28 ++++++++++++++++++++++++++--
 drivers/clk/qcom/clk-alpha-pll.h |  2 +-
 2 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index be7ffeae21b1..26139ef005e4 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -143,6 +143,9 @@ EXPORT_SYMBOL_GPL(clk_alpha_pll_regs);
 #define TRION_PLL_CAL_VAL	0x44
 #define TRION_PCAL_DONE		BIT(26)
 
+/* LUCID PLL specific settings and offsets */
+#define LUCID_PCAL_DONE		BIT(27)
+
 #define pll_alpha_width(p)					\
 		((PLL_ALPHA_VAL_U(p) - PLL_ALPHA_VAL(p) == 4) ?	\
 				 ALPHA_REG_BITWIDTH : ALPHA_REG_16BIT_WIDTH)
@@ -1447,7 +1450,7 @@ EXPORT_SYMBOL_GPL(clk_trion_pll_configure);
  * The TRION PLL requires a power-on self-calibration which happens when the
  * PLL comes out of reset. Calibrate in case it is not completed.
  */
-static int alpha_pll_trion_prepare(struct clk_hw *hw)
+static int __alpha_pll_trion_prepare(struct clk_hw *hw, u32 pcal_done)
 {
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
 	u32 regval;
@@ -1455,7 +1458,7 @@ static int alpha_pll_trion_prepare(struct clk_hw *hw)
 
 	/* Return early if calibration is not needed. */
 	regmap_read(pll->clkr.regmap, PLL_STATUS(pll), &regval);
-	if (regval & TRION_PCAL_DONE)
+	if (regval & pcal_done)
 		return 0;
 
 	/* On/off to calibrate */
@@ -1466,6 +1469,16 @@ static int alpha_pll_trion_prepare(struct clk_hw *hw)
 	return ret;
 }
 
+static int alpha_pll_trion_prepare(struct clk_hw *hw)
+{
+	return __alpha_pll_trion_prepare(hw, TRION_PCAL_DONE);
+}
+
+static int alpha_pll_lucid_prepare(struct clk_hw *hw)
+{
+	return __alpha_pll_trion_prepare(hw, LUCID_PCAL_DONE);
+}
+
 static int alpha_pll_trion_set_rate(struct clk_hw *hw, unsigned long rate,
 				    unsigned long prate)
 {
@@ -1529,6 +1542,17 @@ const struct clk_ops clk_alpha_pll_trion_ops = {
 	.round_rate = clk_alpha_pll_round_rate,
 	.set_rate = alpha_pll_trion_set_rate,
 };
+EXPORT_SYMBOL_GPL(clk_alpha_pll_trion_ops);
+
+const struct clk_ops clk_alpha_pll_lucid_ops = {
+	.prepare = alpha_pll_lucid_prepare,
+	.enable = clk_trion_pll_enable,
+	.disable = clk_trion_pll_disable,
+	.is_enabled = clk_trion_pll_is_enabled,
+	.recalc_rate = clk_trion_pll_recalc_rate,
+	.round_rate = clk_alpha_pll_round_rate,
+	.set_rate = alpha_pll_trion_set_rate,
+};
 EXPORT_SYMBOL_GPL(clk_alpha_pll_lucid_ops);
 
 const struct clk_ops clk_alpha_pll_postdiv_lucid_ops = {
diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h
index d283ba739057..d3201b87c0cd 100644
--- a/drivers/clk/qcom/clk-alpha-pll.h
+++ b/drivers/clk/qcom/clk-alpha-pll.h
@@ -138,7 +138,7 @@ extern const struct clk_ops clk_alpha_pll_trion_ops;
 extern const struct clk_ops clk_alpha_pll_fixed_trion_ops;
 extern const struct clk_ops clk_alpha_pll_postdiv_trion_ops;
 
-#define clk_alpha_pll_lucid_ops clk_alpha_pll_trion_ops
+extern const struct clk_ops clk_alpha_pll_lucid_ops;
 #define clk_alpha_pll_fixed_lucid_ops clk_alpha_pll_fixed_trion_ops
 extern const struct clk_ops clk_alpha_pll_postdiv_lucid_ops;
 

From 3f6b25062587cd18ef01bf67ca67e601e6abde94 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 9 Jul 2020 09:52:36 -0400
Subject: [PATCH 086/474] clk: qcom: gcc: remove unnecessary vco_table from
 SM8150

The fixed alpha pll ops only use it for clamping in round_rate, which is
unnecessary. This is consistent with SM8250 GCC not using vco_table.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20200709135251.643-6-jonathan@marek.ca
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/gcc-sm8150.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/clk/qcom/gcc-sm8150.c b/drivers/clk/qcom/gcc-sm8150.c
index d7778def37da..8e9b5b3cceaf 100644
--- a/drivers/clk/qcom/gcc-sm8150.c
+++ b/drivers/clk/qcom/gcc-sm8150.c
@@ -34,14 +34,8 @@ enum {
 	P_SLEEP_CLK,
 };
 
-static const struct pll_vco trion_vco[] = {
-	{ 249600000, 2000000000, 0 },
-};
-
 static struct clk_alpha_pll gpll0 = {
 	.offset = 0x0,
-	.vco_table = trion_vco,
-	.num_vco = ARRAY_SIZE(trion_vco),
 	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TRION],
 	.clkr = {
 		.enable_reg = 0x52000,
@@ -85,8 +79,6 @@ static struct clk_alpha_pll_postdiv gpll0_out_even = {
 
 static struct clk_alpha_pll gpll7 = {
 	.offset = 0x1a000,
-	.vco_table = trion_vco,
-	.num_vco = ARRAY_SIZE(trion_vco),
 	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TRION],
 	.clkr = {
 		.enable_reg = 0x52000,
@@ -105,8 +97,6 @@ static struct clk_alpha_pll gpll7 = {
 
 static struct clk_alpha_pll gpll9 = {
 	.offset = 0x1c000,
-	.vco_table = trion_vco,
-	.num_vco = ARRAY_SIZE(trion_vco),
 	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TRION],
 	.clkr = {
 		.enable_reg = 0x52000,

From 23e2653ee649125d1fddd1b16c2d2ca95c684631 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 9 Jul 2020 09:52:37 -0400
Subject: [PATCH 087/474] dt-bindings: clock: combine qcom,sdm845-gpucc and
 qcom,sc7180-gpucc

These two bindings are almost identical, so combine them into one. This
will make it easier to add the sm8150 and sm8250 gpucc bindings.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20200709135251.643-7-jonathan@marek.ca
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 ...qcom,sdm845-gpucc.yaml => qcom,gpucc.yaml} | 14 ++--
 .../bindings/clock/qcom,sc7180-gpucc.yaml     | 74 -------------------
 2 files changed, 9 insertions(+), 79 deletions(-)
 rename Documentation/devicetree/bindings/clock/{qcom,sdm845-gpucc.yaml => qcom,gpucc.yaml} (82%)
 delete mode 100644 Documentation/devicetree/bindings/clock/qcom,sc7180-gpucc.yaml

diff --git a/Documentation/devicetree/bindings/clock/qcom,sdm845-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml
similarity index 82%
rename from Documentation/devicetree/bindings/clock/qcom,sdm845-gpucc.yaml
rename to Documentation/devicetree/bindings/clock/qcom,gpucc.yaml
index 8a0c576ba8b3..aab6bef79771 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sdm845-gpucc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml
@@ -1,23 +1,27 @@
 # SPDX-License-Identifier: GPL-2.0-only
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/clock/qcom,sdm845-gpucc.yaml#
+$id: http://devicetree.org/schemas/clock/qcom,gpucc.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Qualcomm Graphics Clock & Reset Controller Binding for SDM845
+title: Qualcomm Graphics Clock & Reset Controller Binding
 
 maintainers:
   - Taniya Das <tdas@codeaurora.org>
 
 description: |
   Qualcomm graphics clock control module which supports the clocks, resets and
-  power domains on SDM845.
+  power domains on SDM845/SC7180.
 
-  See also dt-bindings/clock/qcom,gpucc-sdm845.h.
+  See also:
+    dt-bindings/clock/qcom,gpucc-sdm845.h
+    dt-bindings/clock/qcom,gpucc-sc7180.h
 
 properties:
   compatible:
-    const: qcom,sdm845-gpucc
+    enum:
+      - qcom,sdm845-gpucc
+      - qcom,sc7180-gpucc
 
   clocks:
     items:
diff --git a/Documentation/devicetree/bindings/clock/qcom,sc7180-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sc7180-gpucc.yaml
deleted file mode 100644
index fe08461fce05..000000000000
--- a/Documentation/devicetree/bindings/clock/qcom,sc7180-gpucc.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-%YAML 1.2
----
-$id: http://devicetree.org/schemas/clock/qcom,sc7180-gpucc.yaml#
-$schema: http://devicetree.org/meta-schemas/core.yaml#
-
-title: Qualcomm Graphics Clock & Reset Controller Binding for SC7180
-
-maintainers:
-  - Taniya Das <tdas@codeaurora.org>
-
-description: |
-  Qualcomm graphics clock control module which supports the clocks, resets and
-  power domains on SC7180.
-
-  See also dt-bindings/clock/qcom,gpucc-sc7180.h.
-
-properties:
-  compatible:
-    const: qcom,sc7180-gpucc
-
-  clocks:
-    items:
-      - description: Board XO source
-      - description: GPLL0 main branch source
-      - description: GPLL0 div branch source
-
-  clock-names:
-    items:
-      - const: bi_tcxo
-      - const: gcc_gpu_gpll0_clk_src
-      - const: gcc_gpu_gpll0_div_clk_src
-
-  '#clock-cells':
-    const: 1
-
-  '#reset-cells':
-    const: 1
-
-  '#power-domain-cells':
-    const: 1
-
-  reg:
-    maxItems: 1
-
-required:
-  - compatible
-  - reg
-  - clocks
-  - clock-names
-  - '#clock-cells'
-  - '#reset-cells'
-  - '#power-domain-cells'
-
-additionalProperties: false
-
-examples:
-  - |
-    #include <dt-bindings/clock/qcom,gcc-sc7180.h>
-    #include <dt-bindings/clock/qcom,rpmh.h>
-    clock-controller@5090000 {
-      compatible = "qcom,sc7180-gpucc";
-      reg = <0x05090000 0x9000>;
-      clocks = <&rpmhcc RPMH_CXO_CLK>,
-               <&gcc GCC_GPU_GPLL0_CLK_SRC>,
-               <&gcc GCC_GPU_GPLL0_DIV_CLK_SRC>;
-      clock-names = "bi_tcxo",
-                    "gcc_gpu_gpll0_clk_src",
-                    "gcc_gpu_gpll0_div_clk_src";
-      #clock-cells = <1>;
-      #reset-cells = <1>;
-      #power-domain-cells = <1>;
-    };
-...

From f793e45494586f742410f17539f1ea4156ea7bf9 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 9 Jul 2020 09:52:38 -0400
Subject: [PATCH 088/474] dt-bindings: clock: add SM8150 QCOM Graphics clock
 bindings

Add device tree bindings for graphics clock controller for
Qualcomm Technology Inc's SM8150 SoCs.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20200709135251.643-8-jonathan@marek.ca
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../devicetree/bindings/clock/qcom,gpucc.yaml |  4 ++-
 include/dt-bindings/clock/qcom,gpucc-sm8150.h | 33 +++++++++++++++++++
 2 files changed, 36 insertions(+), 1 deletion(-)
 create mode 100644 include/dt-bindings/clock/qcom,gpucc-sm8150.h

diff --git a/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml
index aab6bef79771..3e064ed0e0ea 100644
--- a/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml
@@ -11,17 +11,19 @@ maintainers:
 
 description: |
   Qualcomm graphics clock control module which supports the clocks, resets and
-  power domains on SDM845/SC7180.
+  power domains on SDM845/SC7180/SM8150.
 
   See also:
     dt-bindings/clock/qcom,gpucc-sdm845.h
     dt-bindings/clock/qcom,gpucc-sc7180.h
+    dt-bindings/clock/qcom,gpucc-sm8150.h
 
 properties:
   compatible:
     enum:
       - qcom,sdm845-gpucc
       - qcom,sc7180-gpucc
+      - qcom,sm8150-gpucc
 
   clocks:
     items:
diff --git a/include/dt-bindings/clock/qcom,gpucc-sm8150.h b/include/dt-bindings/clock/qcom,gpucc-sm8150.h
new file mode 100644
index 000000000000..c5b70aad7770
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,gpucc-sm8150.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_GPU_CC_SM8150_H
+#define _DT_BINDINGS_CLK_QCOM_GPU_CC_SM8150_H
+
+/* GPU_CC clock registers */
+#define GPU_CC_AHB_CLK				0
+#define GPU_CC_CRC_AHB_CLK			1
+#define GPU_CC_CX_APB_CLK			2
+#define GPU_CC_CX_GMU_CLK			3
+#define GPU_CC_CX_SNOC_DVM_CLK			4
+#define GPU_CC_CXO_AON_CLK			5
+#define GPU_CC_CXO_CLK				6
+#define GPU_CC_GMU_CLK_SRC			7
+#define GPU_CC_GX_GMU_CLK			8
+#define GPU_CC_PLL1				9
+
+/* GPU_CC Resets */
+#define GPUCC_GPU_CC_CX_BCR			0
+#define GPUCC_GPU_CC_GFX3D_AON_BCR		1
+#define GPUCC_GPU_CC_GMU_BCR			2
+#define GPUCC_GPU_CC_GX_BCR			3
+#define GPUCC_GPU_CC_SPDM_BCR			4
+#define GPUCC_GPU_CC_XO_BCR			5
+
+/* GPU_CC GDSCRs */
+#define GPU_CX_GDSC				0
+#define GPU_GX_GDSC				1
+
+#endif

From 324e0bfcfb005f161bbb31ea21ddad0f1bc8f400 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 9 Jul 2020 09:52:39 -0400
Subject: [PATCH 089/474] dt-bindings: clock: add SM8250 QCOM Graphics clock
 bindings

Add device tree bindings for graphics clock controller for
Qualcomm Technology Inc's SM8250 SoCs.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20200709135251.643-9-jonathan@marek.ca
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../devicetree/bindings/clock/qcom,gpucc.yaml |  4 ++-
 include/dt-bindings/clock/qcom,gpucc-sm8250.h | 34 +++++++++++++++++++
 2 files changed, 37 insertions(+), 1 deletion(-)
 create mode 100644 include/dt-bindings/clock/qcom,gpucc-sm8250.h

diff --git a/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml
index 3e064ed0e0ea..df943c4c3234 100644
--- a/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml
@@ -11,12 +11,13 @@ maintainers:
 
 description: |
   Qualcomm graphics clock control module which supports the clocks, resets and
-  power domains on SDM845/SC7180/SM8150.
+  power domains on SDM845/SC7180/SM8150/SM8250.
 
   See also:
     dt-bindings/clock/qcom,gpucc-sdm845.h
     dt-bindings/clock/qcom,gpucc-sc7180.h
     dt-bindings/clock/qcom,gpucc-sm8150.h
+    dt-bindings/clock/qcom,gpucc-sm8250.h
 
 properties:
   compatible:
@@ -24,6 +25,7 @@ properties:
       - qcom,sdm845-gpucc
       - qcom,sc7180-gpucc
       - qcom,sm8150-gpucc
+      - qcom,sm8250-gpucc
 
   clocks:
     items:
diff --git a/include/dt-bindings/clock/qcom,gpucc-sm8250.h b/include/dt-bindings/clock/qcom,gpucc-sm8250.h
new file mode 100644
index 000000000000..dc8e387c48ad
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,gpucc-sm8250.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_GPU_CC_SM8250_H
+#define _DT_BINDINGS_CLK_QCOM_GPU_CC_SM8250_H
+
+/* GPU_CC clock registers */
+#define GPU_CC_AHB_CLK				0
+#define GPU_CC_CRC_AHB_CLK			1
+#define GPU_CC_CX_APB_CLK			2
+#define GPU_CC_CX_GMU_CLK			3
+#define GPU_CC_CX_SNOC_DVM_CLK			4
+#define GPU_CC_CXO_AON_CLK			5
+#define GPU_CC_CXO_CLK				6
+#define GPU_CC_GMU_CLK_SRC			7
+#define GPU_CC_GX_GMU_CLK			8
+#define GPU_CC_PLL1				9
+#define GPU_CC_HLOS1_VOTE_GPU_SMMU_CLK		10
+
+/* GPU_CC Resets */
+#define GPUCC_GPU_CC_ACD_BCR			0
+#define GPUCC_GPU_CC_CX_BCR			1
+#define GPUCC_GPU_CC_GFX3D_AON_BCR		2
+#define GPUCC_GPU_CC_GMU_BCR			3
+#define GPUCC_GPU_CC_GX_BCR			4
+#define GPUCC_GPU_CC_XO_BCR			5
+
+/* GPU_CC GDSCRs */
+#define GPU_CX_GDSC				0
+#define GPU_GX_GDSC				1
+
+#endif

From 0638226dd0953c0c34f8df203b6c32d6066ceb65 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 9 Jul 2020 09:52:40 -0400
Subject: [PATCH 090/474] clk: qcom: add common gdsc_gx_do_nothing_enable for
 gpucc drivers

All gpucc drivers need this, so move it to common code instead of
duplicating it in every gpucc driver.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20200709135251.643-10-jonathan@marek.ca
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/gdsc.c         | 25 +++++++++++++++++++++++++
 drivers/clk/qcom/gdsc.h         |  1 +
 drivers/clk/qcom/gpucc-sc7180.c | 27 +--------------------------
 drivers/clk/qcom/gpucc-sdm845.c | 27 +--------------------------
 4 files changed, 28 insertions(+), 52 deletions(-)

diff --git a/drivers/clk/qcom/gdsc.c b/drivers/clk/qcom/gdsc.c
index 04944f11659b..628397703717 100644
--- a/drivers/clk/qcom/gdsc.c
+++ b/drivers/clk/qcom/gdsc.c
@@ -433,3 +433,28 @@ void gdsc_unregister(struct gdsc_desc *desc)
 	}
 	of_genpd_del_provider(dev->of_node);
 }
+
+/*
+ * On SDM845+ the GPU GX domain is *almost* entirely controlled by the GMU
+ * running in the CX domain so the CPU doesn't need to know anything about the
+ * GX domain EXCEPT....
+ *
+ * Hardware constraints dictate that the GX be powered down before the CX. If
+ * the GMU crashes it could leave the GX on. In order to successfully bring back
+ * the device the CPU needs to disable the GX headswitch. There being no sane
+ * way to reach in and touch that register from deep inside the GPU driver we
+ * need to set up the infrastructure to be able to ensure that the GPU can
+ * ensure that the GX is off during this super special case. We do this by
+ * defining a GX gdsc with a dummy enable function and a "default" disable
+ * function.
+ *
+ * This allows us to attach with genpd_dev_pm_attach_by_name() in the GPU
+ * driver. During power up, nothing will happen from the CPU (and the GMU will
+ * power up normally but during power down this will ensure that the GX domain
+ * is *really* off - this gives us a semi standard way of doing what we need.
+ */
+int gdsc_gx_do_nothing_enable(struct generic_pm_domain *domain)
+{
+	/* Do nothing but give genpd the impression that we were successful */
+	return 0;
+}
diff --git a/drivers/clk/qcom/gdsc.h b/drivers/clk/qcom/gdsc.h
index c36fc26dcdff..1896bfb2bbd1 100644
--- a/drivers/clk/qcom/gdsc.h
+++ b/drivers/clk/qcom/gdsc.h
@@ -68,6 +68,7 @@ struct gdsc_desc {
 int gdsc_register(struct gdsc_desc *desc, struct reset_controller_dev *,
 		  struct regmap *);
 void gdsc_unregister(struct gdsc_desc *desc);
+int gdsc_gx_do_nothing_enable(struct generic_pm_domain *domain);
 #else
 static inline int gdsc_register(struct gdsc_desc *desc,
 				struct reset_controller_dev *rcdev,
diff --git a/drivers/clk/qcom/gpucc-sc7180.c b/drivers/clk/qcom/gpucc-sc7180.c
index 7b656b6aeced..88a739b6fec3 100644
--- a/drivers/clk/qcom/gpucc-sc7180.c
+++ b/drivers/clk/qcom/gpucc-sc7180.c
@@ -170,37 +170,12 @@ static struct gdsc cx_gdsc = {
 	.flags = VOTABLE,
 };
 
-/*
- * On SC7180 the GPU GX domain is *almost* entirely controlled by the GMU
- * running in the CX domain so the CPU doesn't need to know anything about the
- * GX domain EXCEPT....
- *
- * Hardware constraints dictate that the GX be powered down before the CX. If
- * the GMU crashes it could leave the GX on. In order to successfully bring back
- * the device the CPU needs to disable the GX headswitch. There being no sane
- * way to reach in and touch that register from deep inside the GPU driver we
- * need to set up the infrastructure to be able to ensure that the GPU can
- * ensure that the GX is off during this super special case. We do this by
- * defining a GX gdsc with a dummy enable function and a "default" disable
- * function.
- *
- * This allows us to attach with genpd_dev_pm_attach_by_name() in the GPU
- * driver. During power up, nothing will happen from the CPU (and the GMU will
- * power up normally but during power down this will ensure that the GX domain
- * is *really* off - this gives us a semi standard way of doing what we need.
- */
-static int gx_gdsc_enable(struct generic_pm_domain *domain)
-{
-	/* Do nothing but give genpd the impression that we were successful */
-	return 0;
-}
-
 static struct gdsc gx_gdsc = {
 	.gdscr = 0x100c,
 	.clamp_io_ctrl = 0x1508,
 	.pd = {
 		.name = "gx_gdsc",
-		.power_on = gx_gdsc_enable,
+		.power_on = gdsc_gx_do_nothing_enable,
 	},
 	.pwrsts = PWRSTS_OFF_ON,
 	.flags = CLAMP_IO,
diff --git a/drivers/clk/qcom/gpucc-sdm845.c b/drivers/clk/qcom/gpucc-sdm845.c
index e40efba1bf7d..5663698b306b 100644
--- a/drivers/clk/qcom/gpucc-sdm845.c
+++ b/drivers/clk/qcom/gpucc-sdm845.c
@@ -131,37 +131,12 @@ static struct gdsc gpu_cx_gdsc = {
 	.flags = VOTABLE,
 };
 
-/*
- * On SDM845 the GPU GX domain is *almost* entirely controlled by the GMU
- * running in the CX domain so the CPU doesn't need to know anything about the
- * GX domain EXCEPT....
- *
- * Hardware constraints dictate that the GX be powered down before the CX. If
- * the GMU crashes it could leave the GX on. In order to successfully bring back
- * the device the CPU needs to disable the GX headswitch. There being no sane
- * way to reach in and touch that register from deep inside the GPU driver we
- * need to set up the infrastructure to be able to ensure that the GPU can
- * ensure that the GX is off during this super special case. We do this by
- * defining a GX gdsc with a dummy enable function and a "default" disable
- * function.
- *
- * This allows us to attach with genpd_dev_pm_attach_by_name() in the GPU
- * driver. During power up, nothing will happen from the CPU (and the GMU will
- * power up normally but during power down this will ensure that the GX domain
- * is *really* off - this gives us a semi standard way of doing what we need.
- */
-static int gx_gdsc_enable(struct generic_pm_domain *domain)
-{
-	/* Do nothing but give genpd the impression that we were successful */
-	return 0;
-}
-
 static struct gdsc gpu_gx_gdsc = {
 	.gdscr = 0x100c,
 	.clamp_io_ctrl = 0x1508,
 	.pd = {
 		.name = "gpu_gx_gdsc",
-		.power_on = gx_gdsc_enable,
+		.power_on = gdsc_gx_do_nothing_enable,
 	},
 	.pwrsts = PWRSTS_OFF_ON,
 	.flags = CLAMP_IO | AON_RESET | POLL_CFG_GDSCR,

From 0cef71f2ccc84dd85a60b312343f1973f149e2d3 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 9 Jul 2020 09:52:41 -0400
Subject: [PATCH 091/474] clk: qcom: Add graphics clock controller driver for
 SM8150

Add support for the graphics clock controller found on SM8150
based devices.

This is initially copied from the downstream kernel, but has
been modified to more closely match the upstream sc7180 driver.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20200709135251.643-11-jonathan@marek.ca
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/Kconfig        |   8 +
 drivers/clk/qcom/Makefile       |   1 +
 drivers/clk/qcom/gpucc-sm8150.c | 320 ++++++++++++++++++++++++++++++++
 3 files changed, 329 insertions(+)
 create mode 100644 drivers/clk/qcom/gpucc-sm8150.c

diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index 318c0adfaae1..9643de4465dc 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -419,6 +419,14 @@ config SM_GCC_8250
 	  Say Y if you want to use peripheral devices such as UART,
 	  SPI, I2C, USB, SD/UFS, PCIe etc.
 
+config SM_GPUCC_8150
+	tristate "SM8150 Graphics Clock Controller"
+	select SM_GCC_8150
+	help
+	  Support for the graphics clock controller on SM8150 devices.
+	  Say Y if you want to support graphics controller devices and
+	  functionality such as 3D graphics.
+
 config SPMI_PMIC_CLKDIV
 	tristate "SPMI PMIC clkdiv Support"
 	depends on SPMI || COMPILE_TEST
diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile
index ae0979bebe18..02c87943f9fd 100644
--- a/drivers/clk/qcom/Makefile
+++ b/drivers/clk/qcom/Makefile
@@ -65,6 +65,7 @@ obj-$(CONFIG_SDM_LPASSCC_845) += lpasscc-sdm845.o
 obj-$(CONFIG_SDM_VIDEOCC_845) += videocc-sdm845.o
 obj-$(CONFIG_SM_GCC_8150) += gcc-sm8150.o
 obj-$(CONFIG_SM_GCC_8250) += gcc-sm8250.o
+obj-$(CONFIG_SM_GPUCC_8150) += gpucc-sm8150.o
 obj-$(CONFIG_SPMI_PMIC_CLKDIV) += clk-spmi-pmic-div.o
 obj-$(CONFIG_KPSS_XCC) += kpss-xcc.o
 obj-$(CONFIG_QCOM_HFPLL) += hfpll.o
diff --git a/drivers/clk/qcom/gpucc-sm8150.c b/drivers/clk/qcom/gpucc-sm8150.c
new file mode 100644
index 000000000000..27c40754b2c7
--- /dev/null
+++ b/drivers/clk/qcom/gpucc-sm8150.c
@@ -0,0 +1,320 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include <dt-bindings/clock/qcom,gpucc-sm8150.h>
+
+#include "common.h"
+#include "clk-alpha-pll.h"
+#include "clk-branch.h"
+#include "clk-pll.h"
+#include "clk-rcg.h"
+#include "clk-regmap.h"
+#include "reset.h"
+#include "gdsc.h"
+
+enum {
+	P_BI_TCXO,
+	P_CORE_BI_PLL_TEST_SE,
+	P_GPLL0_OUT_MAIN,
+	P_GPLL0_OUT_MAIN_DIV,
+	P_GPU_CC_PLL1_OUT_MAIN,
+};
+
+static const struct pll_vco trion_vco[] = {
+	{ 249600000, 2000000000, 0 },
+};
+
+static struct alpha_pll_config gpu_cc_pll1_config = {
+	.l = 0x1a,
+	.alpha = 0xaaa,
+	.config_ctl_val = 0x20485699,
+	.config_ctl_hi_val = 0x00002267,
+	.config_ctl_hi1_val = 0x00000024,
+	.test_ctl_val = 0x00000000,
+	.test_ctl_hi_val = 0x00000002,
+	.test_ctl_hi1_val = 0x00000000,
+	.user_ctl_val = 0x00000000,
+	.user_ctl_hi_val = 0x00000805,
+	.user_ctl_hi1_val = 0x000000d0,
+};
+
+static struct clk_alpha_pll gpu_cc_pll1 = {
+	.offset = 0x100,
+	.vco_table = trion_vco,
+	.num_vco = ARRAY_SIZE(trion_vco),
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TRION],
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_pll1",
+			.parent_data =  &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_trion_ops,
+		},
+	},
+};
+
+static const struct parent_map gpu_cc_parent_map_0[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_GPU_CC_PLL1_OUT_MAIN, 3 },
+	{ P_GPLL0_OUT_MAIN, 5 },
+	{ P_GPLL0_OUT_MAIN_DIV, 6 },
+};
+
+static const struct clk_parent_data gpu_cc_parent_data_0[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &gpu_cc_pll1.clkr.hw },
+	{ .fw_name = "gcc_gpu_gpll0_clk_src" },
+	{ .fw_name = "gcc_gpu_gpll0_div_clk_src" },
+};
+
+static const struct freq_tbl ftbl_gpu_cc_gmu_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(200000000, P_GPLL0_OUT_MAIN_DIV, 1.5, 0, 0),
+	F(500000000, P_GPU_CC_PLL1_OUT_MAIN, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gpu_cc_gmu_clk_src = {
+	.cmd_rcgr = 0x1120,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = gpu_cc_parent_map_0,
+	.freq_tbl = ftbl_gpu_cc_gmu_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpu_cc_gmu_clk_src",
+		.parent_data = gpu_cc_parent_data_0,
+		.num_parents = ARRAY_SIZE(gpu_cc_parent_data_0),
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch gpu_cc_ahb_clk = {
+	.halt_reg = 0x1078,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x1078,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_crc_ahb_clk = {
+	.halt_reg = 0x107c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x107c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_crc_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cx_apb_clk = {
+	.halt_reg = 0x1088,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x1088,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cx_apb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cx_gmu_clk = {
+	.halt_reg = 0x1098,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x1098,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cx_gmu_clk",
+			.parent_data =  &(const struct clk_parent_data){
+				.hw = &gpu_cc_gmu_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cx_snoc_dvm_clk = {
+	.halt_reg = 0x108c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x108c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cx_snoc_dvm_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cxo_aon_clk = {
+	.halt_reg = 0x1004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x1004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cxo_aon_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cxo_clk = {
+	.halt_reg = 0x109c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x109c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cxo_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_gx_gmu_clk = {
+	.halt_reg = 0x1064,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x1064,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_gx_gmu_clk",
+			.parent_data =  &(const struct clk_parent_data){
+				.hw = &gpu_cc_gmu_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct gdsc gpu_cx_gdsc = {
+	.gdscr = 0x106c,
+	.gds_hw_ctrl = 0x1540,
+	.pd = {
+		.name = "gpu_cx_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = VOTABLE,
+};
+
+static struct gdsc gpu_gx_gdsc = {
+	.gdscr = 0x100c,
+	.clamp_io_ctrl = 0x1508,
+	.pd = {
+		.name = "gpu_gx_gdsc",
+		.power_on = gdsc_gx_do_nothing_enable,
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = CLAMP_IO | AON_RESET | POLL_CFG_GDSCR,
+};
+
+static struct clk_regmap *gpu_cc_sm8150_clocks[] = {
+	[GPU_CC_AHB_CLK] = &gpu_cc_ahb_clk.clkr,
+	[GPU_CC_CRC_AHB_CLK] = &gpu_cc_crc_ahb_clk.clkr,
+	[GPU_CC_CX_APB_CLK] = &gpu_cc_cx_apb_clk.clkr,
+	[GPU_CC_CX_GMU_CLK] = &gpu_cc_cx_gmu_clk.clkr,
+	[GPU_CC_CX_SNOC_DVM_CLK] = &gpu_cc_cx_snoc_dvm_clk.clkr,
+	[GPU_CC_CXO_AON_CLK] = &gpu_cc_cxo_aon_clk.clkr,
+	[GPU_CC_CXO_CLK] = &gpu_cc_cxo_clk.clkr,
+	[GPU_CC_GMU_CLK_SRC] = &gpu_cc_gmu_clk_src.clkr,
+	[GPU_CC_GX_GMU_CLK] = &gpu_cc_gx_gmu_clk.clkr,
+	[GPU_CC_PLL1] = &gpu_cc_pll1.clkr,
+};
+
+static const struct qcom_reset_map gpu_cc_sm8150_resets[] = {
+	[GPUCC_GPU_CC_CX_BCR] = { 0x1068 },
+	[GPUCC_GPU_CC_GMU_BCR] = { 0x111c },
+	[GPUCC_GPU_CC_GX_BCR] = { 0x1008 },
+	[GPUCC_GPU_CC_SPDM_BCR] = { 0x1110 },
+	[GPUCC_GPU_CC_XO_BCR] = { 0x1000 },
+};
+
+static struct gdsc *gpu_cc_sm8150_gdscs[] = {
+	[GPU_CX_GDSC] = &gpu_cx_gdsc,
+	[GPU_GX_GDSC] = &gpu_gx_gdsc,
+};
+
+static const struct regmap_config gpu_cc_sm8150_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x8008,
+	.fast_io	= true,
+};
+
+static const struct qcom_cc_desc gpu_cc_sm8150_desc = {
+	.config = &gpu_cc_sm8150_regmap_config,
+	.clks = gpu_cc_sm8150_clocks,
+	.num_clks = ARRAY_SIZE(gpu_cc_sm8150_clocks),
+	.resets = gpu_cc_sm8150_resets,
+	.num_resets = ARRAY_SIZE(gpu_cc_sm8150_resets),
+	.gdscs = gpu_cc_sm8150_gdscs,
+	.num_gdscs = ARRAY_SIZE(gpu_cc_sm8150_gdscs),
+};
+
+static const struct of_device_id gpu_cc_sm8150_match_table[] = {
+	{ .compatible = "qcom,sm8150-gpucc" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, gpu_cc_sm8150_match_table);
+
+static int gpu_cc_sm8150_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+
+	regmap = qcom_cc_map(pdev, &gpu_cc_sm8150_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	clk_trion_pll_configure(&gpu_cc_pll1, regmap, &gpu_cc_pll1_config);
+
+	return qcom_cc_really_probe(pdev, &gpu_cc_sm8150_desc, regmap);
+}
+
+static struct platform_driver gpu_cc_sm8150_driver = {
+	.probe = gpu_cc_sm8150_probe,
+	.driver = {
+		.name = "sm8150-gpucc",
+		.of_match_table = gpu_cc_sm8150_match_table,
+	},
+};
+
+static int __init gpu_cc_sm8150_init(void)
+{
+	return platform_driver_register(&gpu_cc_sm8150_driver);
+}
+subsys_initcall(gpu_cc_sm8150_init);
+
+static void __exit gpu_cc_sm8150_exit(void)
+{
+	platform_driver_unregister(&gpu_cc_sm8150_driver);
+}
+module_exit(gpu_cc_sm8150_exit);
+
+MODULE_DESCRIPTION("QTI GPUCC SM8150 Driver");
+MODULE_LICENSE("GPL v2");

From 28f0769c772bb0c431e2833978474d4dfe3754a7 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Thu, 9 Jul 2020 09:52:42 -0400
Subject: [PATCH 092/474] clk: qcom: Add graphics clock controller driver for
 SM8250

Add support for the graphics clock controller found on SM8250
based devices.

This is initially copied from the downstream kernel, but has
been modified to more closely match the upstream sc7180 driver.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://lore.kernel.org/r/20200709135251.643-12-jonathan@marek.ca
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/Kconfig        |   8 +
 drivers/clk/qcom/Makefile       |   1 +
 drivers/clk/qcom/gpucc-sm8250.c | 348 ++++++++++++++++++++++++++++++++
 3 files changed, 357 insertions(+)
 create mode 100644 drivers/clk/qcom/gpucc-sm8250.c

diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index 9643de4465dc..cd0f01136039 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -427,6 +427,14 @@ config SM_GPUCC_8150
 	  Say Y if you want to support graphics controller devices and
 	  functionality such as 3D graphics.
 
+config SM_GPUCC_8250
+	tristate "SM8250 Graphics Clock Controller"
+	select SM_GCC_8250
+	help
+	  Support for the graphics clock controller on SM8250 devices.
+	  Say Y if you want to support graphics controller devices and
+	  functionality such as 3D graphics.
+
 config SPMI_PMIC_CLKDIV
 	tristate "SPMI PMIC clkdiv Support"
 	depends on SPMI || COMPILE_TEST
diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile
index 02c87943f9fd..1e9a21882ed5 100644
--- a/drivers/clk/qcom/Makefile
+++ b/drivers/clk/qcom/Makefile
@@ -66,6 +66,7 @@ obj-$(CONFIG_SDM_VIDEOCC_845) += videocc-sdm845.o
 obj-$(CONFIG_SM_GCC_8150) += gcc-sm8150.o
 obj-$(CONFIG_SM_GCC_8250) += gcc-sm8250.o
 obj-$(CONFIG_SM_GPUCC_8150) += gpucc-sm8150.o
+obj-$(CONFIG_SM_GPUCC_8250) += gpucc-sm8250.o
 obj-$(CONFIG_SPMI_PMIC_CLKDIV) += clk-spmi-pmic-div.o
 obj-$(CONFIG_KPSS_XCC) += kpss-xcc.o
 obj-$(CONFIG_QCOM_HFPLL) += hfpll.o
diff --git a/drivers/clk/qcom/gpucc-sm8250.c b/drivers/clk/qcom/gpucc-sm8250.c
new file mode 100644
index 000000000000..3fa7d1f9ff98
--- /dev/null
+++ b/drivers/clk/qcom/gpucc-sm8250.c
@@ -0,0 +1,348 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018-2020, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include <dt-bindings/clock/qcom,gpucc-sm8250.h>
+
+#include "common.h"
+#include "clk-alpha-pll.h"
+#include "clk-branch.h"
+#include "clk-pll.h"
+#include "clk-rcg.h"
+#include "clk-regmap.h"
+#include "reset.h"
+#include "gdsc.h"
+
+#define CX_GMU_CBCR_SLEEP_MASK		0xf
+#define CX_GMU_CBCR_SLEEP_SHIFT		4
+#define CX_GMU_CBCR_WAKE_MASK		0xf
+#define CX_GMU_CBCR_WAKE_SHIFT		8
+
+enum {
+	P_BI_TCXO,
+	P_CORE_BI_PLL_TEST_SE,
+	P_GPLL0_OUT_MAIN,
+	P_GPLL0_OUT_MAIN_DIV,
+	P_GPU_CC_PLL0_OUT_MAIN,
+	P_GPU_CC_PLL1_OUT_MAIN,
+};
+
+static struct pll_vco lucid_vco[] = {
+	{ 249600000, 2000000000, 0 },
+};
+
+static const struct alpha_pll_config gpu_cc_pll1_config = {
+	.l = 0x1a,
+	.alpha = 0xaaa,
+	.config_ctl_val = 0x20485699,
+	.config_ctl_hi_val = 0x00002261,
+	.config_ctl_hi1_val = 0x029a699c,
+	.user_ctl_val = 0x00000000,
+	.user_ctl_hi_val = 0x00000805,
+	.user_ctl_hi1_val = 0x00000000,
+};
+
+static struct clk_alpha_pll gpu_cc_pll1 = {
+	.offset = 0x100,
+	.vco_table = lucid_vco,
+	.num_vco = ARRAY_SIZE(lucid_vco),
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_LUCID],
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_pll1",
+			.parent_data =  &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_lucid_ops,
+		},
+	},
+};
+
+static const struct parent_map gpu_cc_parent_map_0[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_GPU_CC_PLL1_OUT_MAIN, 3 },
+	{ P_GPLL0_OUT_MAIN, 5 },
+	{ P_GPLL0_OUT_MAIN_DIV, 6 },
+};
+
+static const struct clk_parent_data gpu_cc_parent_data_0[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &gpu_cc_pll1.clkr.hw },
+	{ .fw_name = "gcc_gpu_gpll0_clk_src" },
+	{ .fw_name = "gcc_gpu_gpll0_div_clk_src" },
+};
+
+static const struct freq_tbl ftbl_gpu_cc_gmu_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(200000000, P_GPLL0_OUT_MAIN_DIV, 1.5, 0, 0),
+	F(500000000, P_GPU_CC_PLL1_OUT_MAIN, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gpu_cc_gmu_clk_src = {
+	.cmd_rcgr = 0x1120,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = gpu_cc_parent_map_0,
+	.freq_tbl = ftbl_gpu_cc_gmu_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpu_cc_gmu_clk_src",
+		.parent_data = gpu_cc_parent_data_0,
+		.num_parents = ARRAY_SIZE(gpu_cc_parent_data_0),
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch gpu_cc_ahb_clk = {
+	.halt_reg = 0x1078,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x1078,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_crc_ahb_clk = {
+	.halt_reg = 0x107c,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x107c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_crc_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cx_apb_clk = {
+	.halt_reg = 0x1088,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1088,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cx_apb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cx_gmu_clk = {
+	.halt_reg = 0x1098,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x1098,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cx_gmu_clk",
+			.parent_data =  &(const struct clk_parent_data){
+				.hw = &gpu_cc_gmu_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cx_snoc_dvm_clk = {
+	.halt_reg = 0x108c,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x108c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cx_snoc_dvm_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cxo_aon_clk = {
+	.halt_reg = 0x1004,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cxo_aon_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cxo_clk = {
+	.halt_reg = 0x109c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x109c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cxo_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_gx_gmu_clk = {
+	.halt_reg = 0x1064,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x1064,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_gx_gmu_clk",
+			.parent_data =  &(const struct clk_parent_data){
+				.hw = &gpu_cc_gmu_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_hlos1_vote_gpu_smmu_clk = {
+	.halt_reg = 0x5000,
+	.halt_check = BRANCH_VOTED,
+	.clkr = {
+		.enable_reg = 0x5000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			 .name = "gpu_cc_hlos1_vote_gpu_smmu_clk",
+			 .ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct gdsc gpu_cx_gdsc = {
+	.gdscr = 0x106c,
+	.gds_hw_ctrl = 0x1540,
+	.pd = {
+		.name = "gpu_cx_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = VOTABLE,
+};
+
+static struct gdsc gpu_gx_gdsc = {
+	.gdscr = 0x100c,
+	.clamp_io_ctrl = 0x1508,
+	.pd = {
+		.name = "gpu_gx_gdsc",
+		.power_on = gdsc_gx_do_nothing_enable,
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = CLAMP_IO | AON_RESET | POLL_CFG_GDSCR,
+};
+
+static struct clk_regmap *gpu_cc_sm8250_clocks[] = {
+	[GPU_CC_AHB_CLK] = &gpu_cc_ahb_clk.clkr,
+	[GPU_CC_CRC_AHB_CLK] = &gpu_cc_crc_ahb_clk.clkr,
+	[GPU_CC_CX_APB_CLK] = &gpu_cc_cx_apb_clk.clkr,
+	[GPU_CC_CX_GMU_CLK] = &gpu_cc_cx_gmu_clk.clkr,
+	[GPU_CC_CX_SNOC_DVM_CLK] = &gpu_cc_cx_snoc_dvm_clk.clkr,
+	[GPU_CC_CXO_AON_CLK] = &gpu_cc_cxo_aon_clk.clkr,
+	[GPU_CC_CXO_CLK] = &gpu_cc_cxo_clk.clkr,
+	[GPU_CC_GMU_CLK_SRC] = &gpu_cc_gmu_clk_src.clkr,
+	[GPU_CC_GX_GMU_CLK] = &gpu_cc_gx_gmu_clk.clkr,
+	[GPU_CC_PLL1] = &gpu_cc_pll1.clkr,
+	[GPU_CC_HLOS1_VOTE_GPU_SMMU_CLK] = &gpu_cc_hlos1_vote_gpu_smmu_clk.clkr,
+};
+
+static const struct qcom_reset_map gpu_cc_sm8250_resets[] = {
+	[GPUCC_GPU_CC_ACD_BCR] = { 0x1160 },
+	[GPUCC_GPU_CC_CX_BCR] = { 0x1068 },
+	[GPUCC_GPU_CC_GFX3D_AON_BCR] = { 0x10a0 },
+	[GPUCC_GPU_CC_GMU_BCR] = { 0x111c },
+	[GPUCC_GPU_CC_GX_BCR] = { 0x1008 },
+	[GPUCC_GPU_CC_XO_BCR] = { 0x1000 },
+};
+
+static struct gdsc *gpu_cc_sm8250_gdscs[] = {
+	[GPU_CX_GDSC] = &gpu_cx_gdsc,
+	[GPU_GX_GDSC] = &gpu_gx_gdsc,
+};
+
+static const struct regmap_config gpu_cc_sm8250_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.max_register = 0x8008,
+	.fast_io = true,
+};
+
+static const struct qcom_cc_desc gpu_cc_sm8250_desc = {
+	.config = &gpu_cc_sm8250_regmap_config,
+	.clks = gpu_cc_sm8250_clocks,
+	.num_clks = ARRAY_SIZE(gpu_cc_sm8250_clocks),
+	.resets = gpu_cc_sm8250_resets,
+	.num_resets = ARRAY_SIZE(gpu_cc_sm8250_resets),
+	.gdscs = gpu_cc_sm8250_gdscs,
+	.num_gdscs = ARRAY_SIZE(gpu_cc_sm8250_gdscs),
+};
+
+static const struct of_device_id gpu_cc_sm8250_match_table[] = {
+	{ .compatible = "qcom,sm8250-gpucc" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, gpu_cc_sm8250_match_table);
+
+static int gpu_cc_sm8250_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+	unsigned int value, mask;
+
+	regmap = qcom_cc_map(pdev, &gpu_cc_sm8250_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	clk_lucid_pll_configure(&gpu_cc_pll1, regmap, &gpu_cc_pll1_config);
+
+	/*
+	 * Configure gpu_cc_cx_gmu_clk with recommended
+	 * wakeup/sleep settings
+	 */
+	mask = CX_GMU_CBCR_WAKE_MASK << CX_GMU_CBCR_WAKE_SHIFT;
+	mask |= CX_GMU_CBCR_SLEEP_MASK << CX_GMU_CBCR_SLEEP_SHIFT;
+	value = 0xf << CX_GMU_CBCR_WAKE_SHIFT | 0xf << CX_GMU_CBCR_SLEEP_SHIFT;
+	regmap_update_bits(regmap, 0x1098, mask, value);
+
+	return qcom_cc_really_probe(pdev, &gpu_cc_sm8250_desc, regmap);
+}
+
+static struct platform_driver gpu_cc_sm8250_driver = {
+	.probe = gpu_cc_sm8250_probe,
+	.driver = {
+		.name = "sm8250-gpucc",
+		.of_match_table = gpu_cc_sm8250_match_table,
+	},
+};
+
+static int __init gpu_cc_sm8250_init(void)
+{
+	return platform_driver_register(&gpu_cc_sm8250_driver);
+}
+subsys_initcall(gpu_cc_sm8250_init);
+
+static void __exit gpu_cc_sm8250_exit(void)
+{
+	platform_driver_unregister(&gpu_cc_sm8250_driver);
+}
+module_exit(gpu_cc_sm8250_exit);
+
+MODULE_DESCRIPTION("QTI GPU_CC SM8250 Driver");
+MODULE_LICENSE("GPL v2");

From 9f7d5042a64160e20c73d734f9ed5dd8c6bba205 Mon Sep 17 00:00:00 2001
From: Lori Hikichi <lhikichi@broadcom.com>
Date: Fri, 12 Jun 2020 15:52:12 -0700
Subject: [PATCH 093/474] clk: iproc: round clock rate to the closest

Change from 'DIV_ROUND_UP' to 'DIV_ROUND_CLOSEST' when calculating the
clock divisor in the iProc ASIU clock driver to allow to get to the
closest clock rate.

Fixes: 5fe225c105fd ("clk: iproc: add initial common clock support")
Signed-off-by: Lori Hikichi <lhikichi@broadcom.com>
Signed-off-by: Ray Jui <ray.jui@broadcom.com>
Link: https://lore.kernel.org/r/20200612225212.124301-1-ray.jui@broadcom.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/bcm/clk-iproc-asiu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/bcm/clk-iproc-asiu.c b/drivers/clk/bcm/clk-iproc-asiu.c
index 6fb8af506777..e062dd4992ea 100644
--- a/drivers/clk/bcm/clk-iproc-asiu.c
+++ b/drivers/clk/bcm/clk-iproc-asiu.c
@@ -119,7 +119,7 @@ static long iproc_asiu_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 	if (rate == *parent_rate)
 		return *parent_rate;
 
-	div = DIV_ROUND_UP(*parent_rate, rate);
+	div = DIV_ROUND_CLOSEST(*parent_rate, rate);
 	if (div < 2)
 		return *parent_rate;
 
@@ -145,7 +145,7 @@ static int iproc_asiu_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 		return 0;
 	}
 
-	div = DIV_ROUND_UP(parent_rate, rate);
+	div = DIV_ROUND_CLOSEST(parent_rate, rate);
 	if (div < 2)
 		return -EINVAL;
 

From 8529fc0aaa704c6618e69e8d35834aa977b6ece9 Mon Sep 17 00:00:00 2001
From: Rahul Tanwar <rahul.tanwar@linux.intel.com>
Date: Thu, 16 Jul 2020 14:30:30 +0800
Subject: [PATCH 094/474] clk: intel: Use devm_clk_hw_register() instead of
 clk_hw_register()

To ensure that clks are unregistered in case of any failure, use
devm_clk_hw_register() instead of clk_hw_register().

Signed-off-by: Rahul Tanwar <rahul.tanwar@linux.intel.com>
Link: https://lore.kernel.org/r/7ef7009b4e9f986fd6dfbf487c0e85de68a4ba9b.1594880946.git.rahul.tanwar@linux.intel.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/x86/clk-cgu-pll.c | 2 +-
 drivers/clk/x86/clk-cgu.c     | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/clk/x86/clk-cgu-pll.c b/drivers/clk/x86/clk-cgu-pll.c
index c03cc6b85b9f..3179557b5f78 100644
--- a/drivers/clk/x86/clk-cgu-pll.c
+++ b/drivers/clk/x86/clk-cgu-pll.c
@@ -128,7 +128,7 @@ lgm_clk_register_pll(struct lgm_clk_provider *ctx,
 	pll->hw.init = &init;
 
 	hw = &pll->hw;
-	ret = clk_hw_register(dev, hw);
+	ret = devm_clk_hw_register(dev, hw);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/drivers/clk/x86/clk-cgu.c b/drivers/clk/x86/clk-cgu.c
index 56af0e04ec1e..88ebeb53b109 100644
--- a/drivers/clk/x86/clk-cgu.c
+++ b/drivers/clk/x86/clk-cgu.c
@@ -119,7 +119,7 @@ lgm_clk_register_mux(struct lgm_clk_provider *ctx,
 	mux->hw.init = &init;
 
 	hw = &mux->hw;
-	ret = clk_hw_register(dev, hw);
+	ret = devm_clk_hw_register(dev, hw);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -247,7 +247,7 @@ lgm_clk_register_divider(struct lgm_clk_provider *ctx,
 	div->hw.init = &init;
 
 	hw = &div->hw;
-	ret = clk_hw_register(dev, hw);
+	ret = devm_clk_hw_register(dev, hw);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -361,7 +361,7 @@ lgm_clk_register_gate(struct lgm_clk_provider *ctx,
 	gate->hw.init = &init;
 
 	hw = &gate->hw;
-	ret = clk_hw_register(dev, hw);
+	ret = devm_clk_hw_register(dev, hw);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -624,7 +624,7 @@ int lgm_clk_register_ddiv(struct lgm_clk_provider *ctx,
 		ddiv->hw.init = &init;
 
 		hw = &ddiv->hw;
-		ret = clk_hw_register(dev, hw);
+		ret = devm_clk_hw_register(dev, hw);
 		if (ret) {
 			dev_err(dev, "register clk: %s failed!\n", list->name);
 			return ret;

From c9e28fe649f76ee13a9bcc09f89ae0189f85801b Mon Sep 17 00:00:00 2001
From: Rahul Tanwar <rahul.tanwar@linux.intel.com>
Date: Thu, 16 Jul 2020 14:30:31 +0800
Subject: [PATCH 095/474] clk: intel: Improve locking in the driver

Remove/reduce unnecessary spin locking of the code.

Signed-off-by: Rahul Tanwar <rahul.tanwar@linux.intel.com>
Link: https://lore.kernel.org/r/79c0f5f9f5bc512a7e2b5f3c91f6341f28b5854c.1594880946.git.rahul.tanwar@linux.intel.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/x86/clk-cgu.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

diff --git a/drivers/clk/x86/clk-cgu.c b/drivers/clk/x86/clk-cgu.c
index 88ebeb53b109..c379fedfb9f2 100644
--- a/drivers/clk/x86/clk-cgu.c
+++ b/drivers/clk/x86/clk-cgu.c
@@ -420,18 +420,14 @@ lgm_clk_ddiv_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 {
 	struct lgm_clk_ddiv *ddiv = to_lgm_clk_ddiv(hw);
 	unsigned int div0, div1, exdiv;
-	unsigned long flags;
 	u64 prate;
 
-	spin_lock_irqsave(&ddiv->lock, flags);
 	div0 = lgm_get_clk_val(ddiv->membase, ddiv->reg,
 			       ddiv->shift0, ddiv->width0) + 1;
 	div1 = lgm_get_clk_val(ddiv->membase, ddiv->reg,
 			       ddiv->shift1, ddiv->width1) + 1;
 	exdiv = lgm_get_clk_val(ddiv->membase, ddiv->reg,
 				ddiv->shift2, ddiv->width2);
-	spin_unlock_irqrestore(&ddiv->lock, flags);
-
 	prate = (u64)parent_rate;
 	do_div(prate, div0);
 	do_div(prate, div1);
@@ -548,24 +544,21 @@ lgm_clk_ddiv_round_rate(struct clk_hw *hw, unsigned long rate,
 		div = div * 2;
 		div = DIV_ROUND_CLOSEST_ULL((u64)div, 5);
 	}
+	spin_unlock_irqrestore(&ddiv->lock, flags);
 
-	if (div <= 0) {
-		spin_unlock_irqrestore(&ddiv->lock, flags);
+	if (div <= 0)
 		return *prate;
-	}
 
-	if (lgm_clk_get_ddiv_val(div, &ddiv1, &ddiv2) != 0) {
-		if (lgm_clk_get_ddiv_val(div + 1, &ddiv1, &ddiv2) != 0) {
-			spin_unlock_irqrestore(&ddiv->lock, flags);
+	if (lgm_clk_get_ddiv_val(div, &ddiv1, &ddiv2) != 0)
+		if (lgm_clk_get_ddiv_val(div + 1, &ddiv1, &ddiv2) != 0)
 			return -EINVAL;
-		}
-	}
 
 	rate64 = *prate;
 	do_div(rate64, ddiv1);
 	do_div(rate64, ddiv2);
 
 	/* if predivide bit is enabled, modify rounded rate by factor of 2.5 */
+	spin_lock_irqsave(&ddiv->lock, flags);
 	if (lgm_get_clk_val(ddiv->membase, ddiv->reg, ddiv->shift2, 1)) {
 		rate64 = rate64 * 2;
 		rate64 = DIV_ROUND_CLOSEST_ULL(rate64, 5);

From d310124cd99df5e5011d79f36a6d16d3452de348 Mon Sep 17 00:00:00 2001
From: Rahul Tanwar <rahul.tanwar@linux.intel.com>
Date: Thu, 16 Jul 2020 14:30:32 +0800
Subject: [PATCH 096/474] clk: intel: Avoid unnecessary memset by improving
 code

memset can be avoided in a loop if the variables used are declared
inside the loop. Move such variables declaration inside the loop
to avoid memset.

Signed-off-by: Rahul Tanwar <rahul.tanwar@linux.intel.com>
Link: https://lore.kernel.org/r/26624b65d0e6b958c4765a406b9929d1a9ce1c2c.1594880946.git.rahul.tanwar@linux.intel.com
[sboyd@kernel.org: Drop NULL assignment that is overwritten]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/x86/clk-cgu.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/clk/x86/clk-cgu.c b/drivers/clk/x86/clk-cgu.c
index c379fedfb9f2..33de600e0c38 100644
--- a/drivers/clk/x86/clk-cgu.c
+++ b/drivers/clk/x86/clk-cgu.c
@@ -581,19 +581,18 @@ int lgm_clk_register_ddiv(struct lgm_clk_provider *ctx,
 			  unsigned int nr_clk)
 {
 	struct device *dev = ctx->dev;
-	struct clk_init_data init = {};
-	struct lgm_clk_ddiv *ddiv;
 	struct clk_hw *hw;
 	unsigned int idx;
 	int ret;
 
 	for (idx = 0; idx < nr_clk; idx++, list++) {
-		ddiv = NULL;
+		struct clk_init_data init = {};
+		struct lgm_clk_ddiv *ddiv;
+
 		ddiv = devm_kzalloc(dev, sizeof(*ddiv), GFP_KERNEL);
 		if (!ddiv)
 			return -ENOMEM;
 
-		memset(&init, 0, sizeof(init));
 		init.name = list->name;
 		init.ops = &lgm_clk_ddiv_ops;
 		init.flags = list->flags;

From 03111b1088f18f93d38e888c41e8a1e6aba9f8bb Mon Sep 17 00:00:00 2001
From: Mike Tipton <mdtipton@codeaurora.org>
Date: Mon, 29 Jun 2020 17:30:24 -0700
Subject: [PATCH 097/474] clk: Add support for enabling/disabling clocks from
 debugfs

For test and debug purposes, it's simple enough to enable or disable
clocks from shell. Add a new debugfs file 'clk_prepare_enable' that
calls clk_prepare_enable() when writing "1" and clk_disable_unprepare()
when writing "0".

This can have security implications, so only support it when the code
has been modified to #define CLOCK_ALLOW_WRITE_DEBUGFS.

Signed-off-by: Mike Tipton <mdtipton@codeaurora.org>
Link: https://lore.kernel.org/r/20200630003024.6282-1-mdtipton@codeaurora.org
[sboyd@kernel.org: Reword commit text and remove comment update]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 3f588ed06ce3..4d455a657b01 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -3039,6 +3039,31 @@ static int clk_rate_set(void *data, u64 val)
 }
 
 #define clk_rate_mode	0644
+
+static int clk_prepare_enable_set(void *data, u64 val)
+{
+	struct clk_core *core = data;
+	int ret = 0;
+
+	if (val)
+		ret = clk_prepare_enable(core->hw->clk);
+	else
+		clk_disable_unprepare(core->hw->clk);
+
+	return ret;
+}
+
+static int clk_prepare_enable_get(void *data, u64 *val)
+{
+	struct clk_core *core = data;
+
+	*val = core->enable_count && core->prepare_count;
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(clk_prepare_enable_fops, clk_prepare_enable_get,
+			 clk_prepare_enable_set, "%llu\n");
+
 #else
 #define clk_rate_set	NULL
 #define clk_rate_mode	0444
@@ -3216,6 +3241,10 @@ static void clk_debug_create_one(struct clk_core *core, struct dentry *pdentry)
 	debugfs_create_u32("clk_notifier_count", 0444, root, &core->notifier_count);
 	debugfs_create_file("clk_duty_cycle", 0444, root, core,
 			    &clk_duty_cycle_fops);
+#ifdef CLOCK_ALLOW_WRITE_DEBUGFS
+	debugfs_create_file("clk_prepare_enable", 0644, root, core,
+			    &clk_prepare_enable_fops);
+#endif
 
 	if (core->num_parents > 0)
 		debugfs_create_file("clk_parent", 0444, root, core,

From 153bc1c66a8814e621ca0483098ac722be860aaf Mon Sep 17 00:00:00 2001
From: Ahmad Fatoum <a.fatoum@pengutronix.de>
Date: Fri, 3 Jul 2020 09:32:35 +0200
Subject: [PATCH 098/474] clk: at91: fix possible dead lock in new drivers

syscon_node_to_regmap() will make the created regmap get and enable the
first clock it can parse from the device tree. This clock is not needed to
access the registers and should not be enabled at that time.

Use device_node_to_regmap to resolve this as it looks up the regmap in
the same list but doesn't care about the clocks. This issue is detected
by lockdep when booting the sama5d3 with a device tree containing the
new clk bindings.

This fix already happened in 6956eb33abb5 ("clk: at91: fix possible
deadlock") for the drivers that had been migrated to the new clk binding
back then. This does the same for the new drivers as well.

Fixes: 01e2113de9a5 ("clk: at91: add sam9x60 pmc driver")
Signed-off-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Link: https://lore.kernel.org/r/20200703073236.23923-1-a.fatoum@pengutronix.de
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/at91sam9g45.c | 2 +-
 drivers/clk/at91/at91sam9n12.c | 2 +-
 drivers/clk/at91/sam9x60.c     | 2 +-
 drivers/clk/at91/sama5d3.c     | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/clk/at91/at91sam9g45.c b/drivers/clk/at91/at91sam9g45.c
index 9873b583c260..fe9d391adeba 100644
--- a/drivers/clk/at91/at91sam9g45.c
+++ b/drivers/clk/at91/at91sam9g45.c
@@ -111,7 +111,7 @@ static void __init at91sam9g45_pmc_setup(struct device_node *np)
 		return;
 	mainxtal_name = of_clk_get_parent_name(np, i);
 
-	regmap = syscon_node_to_regmap(np);
+	regmap = device_node_to_regmap(np);
 	if (IS_ERR(regmap))
 		return;
 
diff --git a/drivers/clk/at91/at91sam9n12.c b/drivers/clk/at91/at91sam9n12.c
index 630dc5d87171..4aa97e672bd6 100644
--- a/drivers/clk/at91/at91sam9n12.c
+++ b/drivers/clk/at91/at91sam9n12.c
@@ -124,7 +124,7 @@ static void __init at91sam9n12_pmc_setup(struct device_node *np)
 		return;
 	mainxtal_name = of_clk_get_parent_name(np, i);
 
-	regmap = syscon_node_to_regmap(np);
+	regmap = device_node_to_regmap(np);
 	if (IS_ERR(regmap))
 		return;
 
diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index 3e20aa68259f..2b4c67485eee 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -178,7 +178,7 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 		return;
 	mainxtal_name = of_clk_get_parent_name(np, i);
 
-	regmap = syscon_node_to_regmap(np);
+	regmap = device_node_to_regmap(np);
 	if (IS_ERR(regmap))
 		return;
 
diff --git a/drivers/clk/at91/sama5d3.c b/drivers/clk/at91/sama5d3.c
index 5e4e44dd4c37..5609b04e6565 100644
--- a/drivers/clk/at91/sama5d3.c
+++ b/drivers/clk/at91/sama5d3.c
@@ -121,7 +121,7 @@ static void __init sama5d3_pmc_setup(struct device_node *np)
 		return;
 	mainxtal_name = of_clk_get_parent_name(np, i);
 
-	regmap = syscon_node_to_regmap(np);
+	regmap = device_node_to_regmap(np);
 	if (IS_ERR(regmap))
 		return;
 

From 3a5c42b18a6ddc0de77dde017baf45262fbf1ced Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:09 +0300
Subject: [PATCH 099/474] clk: at91: clk-generated: continue if
 __clk_determine_rate() returns error

__clk_determine_rate() may return error. Skip the current step
in case of error.

Fixes: 1a1a36d72e3d3 ("clk: at91: clk-generated: make gclk determine audio_pll rate")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Reviewed-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/1595403506-8209-2-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-generated.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c
index 44a46dcc0518..995a13133cfb 100644
--- a/drivers/clk/at91/clk-generated.c
+++ b/drivers/clk/at91/clk-generated.c
@@ -170,7 +170,8 @@ static int clk_generated_determine_rate(struct clk_hw *hw,
 
 	for (div = 1; div < GENERATED_MAX_DIV + 2; div++) {
 		req_parent.rate = req->rate * div;
-		__clk_determine_rate(parent, &req_parent);
+		if (__clk_determine_rate(parent, &req_parent))
+			continue;
 		clk_generated_best_diff(req, parent, req_parent.rate, div,
 					&best_diff, &best_rate);
 

From 83331bfcc021a24da79f38a2452e86182c7ae94b Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:10 +0300
Subject: [PATCH 100/474] clk: at91: clk-generated: check best_rate against
 ranges

Check best_rate against available clock ranges.

Fixes: df70aeef6083 ("clk: at91: add generated clock driver")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Reviewed-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/1595403506-8209-3-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-generated.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c
index 995a13133cfb..f8e557e0e1b8 100644
--- a/drivers/clk/at91/clk-generated.c
+++ b/drivers/clk/at91/clk-generated.c
@@ -185,8 +185,8 @@ static int clk_generated_determine_rate(struct clk_hw *hw,
 		 __clk_get_name((req->best_parent_hw)->clk),
 		 req->best_parent_rate);
 
-	if (best_rate < 0)
-		return best_rate;
+	if (best_rate < 0 || (gck->range.max && best_rate > gck->range.max))
+		return -EINVAL;
 
 	req->rate = best_rate;
 	return 0;

From 3bf639a611a8deca7e4daa57a4df9ba4c6025249 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:11 +0300
Subject: [PATCH 101/474] clk: at91: clk-sam9x60-pll: fix mul mask

According to datasheet mul mask is on bits 31..24.

Fixes: a436c2a447e59 ("clk: at91: add sam9x60 PLL driver")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Reviewed-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/1595403506-8209-4-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-sam9x60-pll.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/at91/clk-sam9x60-pll.c b/drivers/clk/at91/clk-sam9x60-pll.c
index e699803986e5..3522eae2edd6 100644
--- a/drivers/clk/at91/clk-sam9x60-pll.c
+++ b/drivers/clk/at91/clk-sam9x60-pll.c
@@ -15,7 +15,7 @@
 #include "pmc.h"
 
 #define	PMC_PLL_CTRL0_DIV_MSK	GENMASK(7, 0)
-#define	PMC_PLL_CTRL1_MUL_MSK	GENMASK(30, 24)
+#define	PMC_PLL_CTRL1_MUL_MSK	GENMASK(31, 24)
 
 #define PLL_DIV_MAX		(FIELD_GET(PMC_PLL_CTRL0_DIV_MSK, UINT_MAX) + 1)
 #define UPLL_DIV		2

From 1bef0986b125942d65d39c10cbfa75b20c3b94b3 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:12 +0300
Subject: [PATCH 102/474] clk: at91: sam9x60-pll: use logical or for range
 check

Use logical or for range check. In case bestrate is not in
characteristics->output[0].min..characteristics->output[0].max
range we should return -ERANGE.

Fixes: a436c2a447e59 ("clk: at91: add sam9x60 PLL driver")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Reviewed-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/1595403506-8209-5-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-sam9x60-pll.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/at91/clk-sam9x60-pll.c b/drivers/clk/at91/clk-sam9x60-pll.c
index 3522eae2edd6..4b7b6c435d4e 100644
--- a/drivers/clk/at91/clk-sam9x60-pll.c
+++ b/drivers/clk/at91/clk-sam9x60-pll.c
@@ -231,7 +231,7 @@ static long sam9x60_pll_get_best_div_mul(struct sam9x60_pll *pll,
 	}
 
 	/* Check if bestrate is a valid output rate  */
-	if (bestrate < characteristics->output[0].min &&
+	if (bestrate < characteristics->output[0].min ||
 	    bestrate > characteristics->output[0].max)
 		return -ERANGE;
 

From 390227dca870cd0b8b0961da9e293551015c0007 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:13 +0300
Subject: [PATCH 103/474] clk: at91: sam9x60-pll: check fcore against ranges

According to datasheet the range of 600-1200MHz is for the
frequency generated by the fractional part of the PLL (namely
Fcorepllck according to datasheet). With this in mind the output
range of the PLL itself (fractional + div), taking into account
that the divider is 8 bits wide, is 600/256-1200Hz=2.3-1200MHz.

Fixes: a436c2a447e59 ("clk: at91: add sam9x60 PLL driver")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-6-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-sam9x60-pll.c | 12 +++++++++++-
 drivers/clk/at91/sam9x60.c         |  2 +-
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/at91/clk-sam9x60-pll.c b/drivers/clk/at91/clk-sam9x60-pll.c
index 4b7b6c435d4e..a933abebfbaf 100644
--- a/drivers/clk/at91/clk-sam9x60-pll.c
+++ b/drivers/clk/at91/clk-sam9x60-pll.c
@@ -21,6 +21,9 @@
 #define UPLL_DIV		2
 #define PLL_MUL_MAX		(FIELD_GET(PMC_PLL_CTRL1_MUL_MSK, UINT_MAX) + 1)
 
+#define FCORE_MIN		(600000000)
+#define FCORE_MAX		(1200000000)
+
 #define PLL_MAX_ID		1
 
 struct sam9x60_pll {
@@ -168,6 +171,7 @@ static long sam9x60_pll_get_best_div_mul(struct sam9x60_pll *pll,
 	unsigned long bestdiv = 0;
 	unsigned long bestmul = 0;
 	unsigned long bestfrac = 0;
+	u64 fcore = 0;
 
 	if (rate < characteristics->output[0].min ||
 	    rate > characteristics->output[0].max)
@@ -212,6 +216,11 @@ static long sam9x60_pll_get_best_div_mul(struct sam9x60_pll *pll,
 				remainder = rate - tmprate;
 		}
 
+		fcore = parent_rate * (tmpmul + 1) +
+			((u64)parent_rate * tmpfrac >> 22);
+		if (fcore < FCORE_MIN || fcore > FCORE_MAX)
+			continue;
+
 		/*
 		 * Compare the remainder with the best remainder found until
 		 * now and elect a new best multiplier/divider pair if the
@@ -231,7 +240,8 @@ static long sam9x60_pll_get_best_div_mul(struct sam9x60_pll *pll,
 	}
 
 	/* Check if bestrate is a valid output rate  */
-	if (bestrate < characteristics->output[0].min ||
+	if (fcore < FCORE_MIN || fcore > FCORE_MAX ||
+	    bestrate < characteristics->output[0].min ||
 	    bestrate > characteristics->output[0].max)
 		return -ERANGE;
 
diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index 2b4c67485eee..19945138123b 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -22,7 +22,7 @@ static const struct clk_master_layout sam9x60_master_layout = {
 };
 
 static const struct clk_range plla_outputs[] = {
-	{ .min = 300000000, .max = 600000000 },
+	{ .min = 2343750, .max = 1200000000 },
 };
 
 static const struct clk_pll_characteristics plla_characteristics = {

From 35d06f74785cc8d108dcb1e3324b2404fb39df0b Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:14 +0300
Subject: [PATCH 104/474] clk: at91: sam9x60-pll: use frac when setting
 frequency

In commit a436c2a447e59 ("clk: at91: add sam9x60 PLL driver")
the fractional part of PLL wasn't set on registers but it was
calculated and taken into account for determining div and mul
(see sam9x60_pll_get_best_div_mul()).

Fixes: a436c2a447e59 ("clk: at91: add sam9x60 PLL driver")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-7-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-sam9x60-pll.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/clk/at91/clk-sam9x60-pll.c b/drivers/clk/at91/clk-sam9x60-pll.c
index a933abebfbaf..1f0bcc6b4fea 100644
--- a/drivers/clk/at91/clk-sam9x60-pll.c
+++ b/drivers/clk/at91/clk-sam9x60-pll.c
@@ -16,6 +16,7 @@
 
 #define	PMC_PLL_CTRL0_DIV_MSK	GENMASK(7, 0)
 #define	PMC_PLL_CTRL1_MUL_MSK	GENMASK(31, 24)
+#define	PMC_PLL_CTRL1_FRACR_MSK	GENMASK(21, 0)
 
 #define PLL_DIV_MAX		(FIELD_GET(PMC_PLL_CTRL0_DIV_MSK, UINT_MAX) + 1)
 #define UPLL_DIV		2
@@ -55,7 +56,7 @@ static int sam9x60_pll_prepare(struct clk_hw *hw)
 	unsigned long flags;
 	u8 div;
 	u16 mul;
-	u32 val;
+	u32 val, frac;
 
 	spin_lock_irqsave(pll->lock, flags);
 	regmap_write(regmap, AT91_PMC_PLL_UPDT, pll->id);
@@ -65,9 +66,10 @@ static int sam9x60_pll_prepare(struct clk_hw *hw)
 
 	regmap_read(regmap, AT91_PMC_PLL_CTRL1, &val);
 	mul = FIELD_GET(PMC_PLL_CTRL1_MUL_MSK, val);
+	frac = FIELD_GET(PMC_PLL_CTRL1_FRACR_MSK, val);
 
 	if (sam9x60_pll_ready(regmap, pll->id) &&
-	    (div == pll->div && mul == pll->mul)) {
+	    (div == pll->div && mul == pll->mul && frac == pll->frac)) {
 		spin_unlock_irqrestore(pll->lock, flags);
 		return 0;
 	}
@@ -80,7 +82,8 @@ static int sam9x60_pll_prepare(struct clk_hw *hw)
 	regmap_write(regmap, AT91_PMC_PLL_ACR, val);
 
 	regmap_write(regmap, AT91_PMC_PLL_CTRL1,
-		     FIELD_PREP(PMC_PLL_CTRL1_MUL_MSK, pll->mul));
+		     FIELD_PREP(PMC_PLL_CTRL1_MUL_MSK, pll->mul) |
+		     FIELD_PREP(PMC_PLL_CTRL1_FRACR_MSK, pll->frac));
 
 	if (pll->characteristics->upll) {
 		/* Enable the UTMI internal bandgap */
@@ -155,7 +158,8 @@ static unsigned long sam9x60_pll_recalc_rate(struct clk_hw *hw,
 {
 	struct sam9x60_pll *pll = to_sam9x60_pll(hw);
 
-	return (parent_rate * (pll->mul + 1)) / (pll->div + 1);
+	return DIV_ROUND_CLOSEST_ULL((parent_rate * (pll->mul + 1) +
+		((u64)parent_rate * pll->frac >> 22)), (pll->div + 1));
 }
 
 static long sam9x60_pll_get_best_div_mul(struct sam9x60_pll *pll,

From 172e7ddeeafd95caa809b7b1a140bfd7f20597d9 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:15 +0300
Subject: [PATCH 105/474] clk: at91: sam9x60: fix main rc oscillator frequency

Main RC oscillator frequency is 12MHz according to datasheet
(chapter 27.2).

Fixes: 01e2113de9a52 ("clk: at91: add sam9x60 pmc driver")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Reviewed-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/1595403506-8209-8-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/sam9x60.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index 19945138123b..d9f6d9ba1eca 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -189,7 +189,7 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 	if (!sam9x60_pmc)
 		return;
 
-	hw = at91_clk_register_main_rc_osc(regmap, "main_rc_osc", 24000000,
+	hw = at91_clk_register_main_rc_osc(regmap, "main_rc_osc", 12000000,
 					   50000000);
 	if (IS_ERR(hw))
 		goto err_free;

From e1e3e7008a90f9ffe0161191bd64a4c06f0d417a Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:16 +0300
Subject: [PATCH 106/474] clk: at91: sckc: register slow_rc with accuracy
 option

Chapter 57.7.5 of SAM9X60 datasheet specifies that the maximum drift of
this oscillator is +- 3KHz. Use that value and the formula at [1]
or the calculator at [2] to compute the PPB value.

[1] https://www.everythingrf.com/rf-calculators/ppm-to-hz-calculator
[2] https://www.changpuak.ch/electronics/ppm_to_Hz_converter.php

Fixes: 04bcc4275e601 ("clk: at91: sckc: add support for SAM9X60")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-9-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/sckc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/at91/sckc.c b/drivers/clk/at91/sckc.c
index 15dc4cd86d76..2d65770d8665 100644
--- a/drivers/clk/at91/sckc.c
+++ b/drivers/clk/at91/sckc.c
@@ -471,8 +471,9 @@ static void __init of_sam9x60_sckc_setup(struct device_node *np)
 	if (!regbase)
 		return;
 
-	slow_rc = clk_hw_register_fixed_rate(NULL, parent_names[0], NULL, 0,
-					     32768);
+	slow_rc = clk_hw_register_fixed_rate_with_accuracy(NULL, parent_names[0],
+							   NULL, 0, 32768,
+							   93750000);
 	if (IS_ERR(slow_rc))
 		return;
 

From 42324d953b38e74cf5cb05a02c81d4922a2ddcd5 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:17 +0300
Subject: [PATCH 107/474] clk: at91: replace conditional operator with double
 logical not

Replace conditional operator with double logical not as code
may be simpler to read.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-10-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-generated.c  | 2 +-
 drivers/clk/at91/clk-main.c       | 6 +++---
 drivers/clk/at91/clk-master.c     | 2 +-
 drivers/clk/at91/clk-peripheral.c | 2 +-
 drivers/clk/at91/clk-system.c     | 4 ++--
 5 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c
index f8e557e0e1b8..2448bdc63425 100644
--- a/drivers/clk/at91/clk-generated.c
+++ b/drivers/clk/at91/clk-generated.c
@@ -83,7 +83,7 @@ static int clk_generated_is_enabled(struct clk_hw *hw)
 	regmap_read(gck->regmap, gck->layout->offset, &status);
 	spin_unlock_irqrestore(gck->lock, flags);
 
-	return status & AT91_PMC_PCR_GCKEN ? 1 : 0;
+	return !!(status & AT91_PMC_PCR_GCKEN);
 }
 
 static unsigned long
diff --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c
index 37c22667e831..5c83e899084f 100644
--- a/drivers/clk/at91/clk-main.c
+++ b/drivers/clk/at91/clk-main.c
@@ -175,7 +175,7 @@ static bool clk_main_rc_osc_ready(struct regmap *regmap)
 
 	regmap_read(regmap, AT91_PMC_SR, &status);
 
-	return status & AT91_PMC_MOSCRCS;
+	return !!(status & AT91_PMC_MOSCRCS);
 }
 
 static int clk_main_rc_osc_prepare(struct clk_hw *hw)
@@ -336,7 +336,7 @@ static int clk_rm9200_main_is_prepared(struct clk_hw *hw)
 
 	regmap_read(clkmain->regmap, AT91_CKGR_MCFR, &status);
 
-	return status & AT91_PMC_MAINRDY ? 1 : 0;
+	return !!(status & AT91_PMC_MAINRDY);
 }
 
 static unsigned long clk_rm9200_main_recalc_rate(struct clk_hw *hw,
@@ -398,7 +398,7 @@ static inline bool clk_sam9x5_main_ready(struct regmap *regmap)
 
 	regmap_read(regmap, AT91_PMC_SR, &status);
 
-	return status & AT91_PMC_MOSCSELS ? 1 : 0;
+	return !!(status & AT91_PMC_MOSCSELS);
 }
 
 static int clk_sam9x5_main_prepare(struct clk_hw *hw)
diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
index e7e0ba652de1..88d545b1698c 100644
--- a/drivers/clk/at91/clk-master.c
+++ b/drivers/clk/at91/clk-master.c
@@ -33,7 +33,7 @@ static inline bool clk_master_ready(struct regmap *regmap)
 
 	regmap_read(regmap, AT91_PMC_SR, &status);
 
-	return status & AT91_PMC_MCKRDY ? 1 : 0;
+	return !!(status & AT91_PMC_MCKRDY);
 }
 
 static int clk_master_prepare(struct clk_hw *hw)
diff --git a/drivers/clk/at91/clk-peripheral.c b/drivers/clk/at91/clk-peripheral.c
index c2ab4860a2bf..4c9a4147dfe5 100644
--- a/drivers/clk/at91/clk-peripheral.c
+++ b/drivers/clk/at91/clk-peripheral.c
@@ -208,7 +208,7 @@ static int clk_sam9x5_peripheral_is_enabled(struct clk_hw *hw)
 	regmap_read(periph->regmap, periph->layout->offset, &status);
 	spin_unlock_irqrestore(periph->lock, flags);
 
-	return status & AT91_PMC_PCR_EN ? 1 : 0;
+	return !!(status & AT91_PMC_PCR_EN);
 }
 
 static unsigned long
diff --git a/drivers/clk/at91/clk-system.c b/drivers/clk/at91/clk-system.c
index c4b3877aa445..f83ec0de86c3 100644
--- a/drivers/clk/at91/clk-system.c
+++ b/drivers/clk/at91/clk-system.c
@@ -34,7 +34,7 @@ static inline bool clk_system_ready(struct regmap *regmap, int id)
 
 	regmap_read(regmap, AT91_PMC_SR, &status);
 
-	return status & (1 << id) ? 1 : 0;
+	return !!(status & (1 << id));
 }
 
 static int clk_system_prepare(struct clk_hw *hw)
@@ -74,7 +74,7 @@ static int clk_system_is_prepared(struct clk_hw *hw)
 
 	regmap_read(sys->regmap, AT91_PMC_SR, &status);
 
-	return status & (1 << sys->id) ? 1 : 0;
+	return !!(status & (1 << sys->id));
 }
 
 static const struct clk_ops system_ops = {

From 64c9247b9e87e96e41cea545eb64727cee10c55c Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:18 +0300
Subject: [PATCH 108/474] clk: at91: clk-generated: pass the id of changeable
 parent at registration

Pass the ID of changeable parent at registration. This will allow
the scalability of this clock driver with regards to the changeable
parent ID for versions of this IP where changeable parent is not the
last one in the parents list (e.g. SAMA7G5). With this the clock flags
are set to zero in case we have no changeable parent. Also in
clk_generated_best_diff() the *best_diff variable is check against
tmp_diff variable using ">=" operator instead of ">" so that in case
the requested frequency could be obtained using fix parents + gck
dividers but the clock also supports changeable parent to be able
to force the usage of the changeable parent.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-11-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-generated.c | 26 ++++++++++++++------------
 drivers/clk/at91/dt-compat.c     |  8 +++++---
 drivers/clk/at91/pmc.h           |  4 ++--
 drivers/clk/at91/sam9x60.c       |  3 +--
 drivers/clk/at91/sama5d2.c       | 31 +++++++++++++++----------------
 5 files changed, 37 insertions(+), 35 deletions(-)

diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c
index 2448bdc63425..f9ca04c97128 100644
--- a/drivers/clk/at91/clk-generated.c
+++ b/drivers/clk/at91/clk-generated.c
@@ -18,8 +18,6 @@
 
 #define GENERATED_MAX_DIV	255
 
-#define GCK_INDEX_DT_AUDIO_PLL	5
-
 struct clk_generated {
 	struct clk_hw hw;
 	struct regmap *regmap;
@@ -29,7 +27,7 @@ struct clk_generated {
 	u32 gckdiv;
 	const struct clk_pcr_layout *layout;
 	u8 parent_id;
-	bool audio_pll_allowed;
+	int chg_pid;
 };
 
 #define to_clk_generated(hw) \
@@ -109,7 +107,7 @@ static void clk_generated_best_diff(struct clk_rate_request *req,
 		tmp_rate = parent_rate / div;
 	tmp_diff = abs(req->rate - tmp_rate);
 
-	if (*best_diff < 0 || *best_diff > tmp_diff) {
+	if (*best_diff < 0 || *best_diff >= tmp_diff) {
 		*best_rate = tmp_rate;
 		*best_diff = tmp_diff;
 		req->best_parent_rate = parent_rate;
@@ -129,7 +127,10 @@ static int clk_generated_determine_rate(struct clk_hw *hw,
 	int i;
 	u32 div;
 
-	for (i = 0; i < clk_hw_get_num_parents(hw) - 1; i++) {
+	for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
+		if (gck->chg_pid == i)
+			continue;
+
 		parent = clk_hw_get_parent_by_index(hw, i);
 		if (!parent)
 			continue;
@@ -161,10 +162,10 @@ static int clk_generated_determine_rate(struct clk_hw *hw,
 	 * that the only clks able to modify gck rate are those of audio IPs.
 	 */
 
-	if (!gck->audio_pll_allowed)
+	if (gck->chg_pid < 0)
 		goto end;
 
-	parent = clk_hw_get_parent_by_index(hw, GCK_INDEX_DT_AUDIO_PLL);
+	parent = clk_hw_get_parent_by_index(hw, gck->chg_pid);
 	if (!parent)
 		goto end;
 
@@ -272,8 +273,8 @@ struct clk_hw * __init
 at91_clk_register_generated(struct regmap *regmap, spinlock_t *lock,
 			    const struct clk_pcr_layout *layout,
 			    const char *name, const char **parent_names,
-			    u8 num_parents, u8 id, bool pll_audio,
-			    const struct clk_range *range)
+			    u8 num_parents, u8 id,
+			    const struct clk_range *range, int chg_pid)
 {
 	struct clk_generated *gck;
 	struct clk_init_data init;
@@ -288,15 +289,16 @@ at91_clk_register_generated(struct regmap *regmap, spinlock_t *lock,
 	init.ops = &generated_ops;
 	init.parent_names = parent_names;
 	init.num_parents = num_parents;
-	init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE |
-		CLK_SET_RATE_PARENT;
+	init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE;
+	if (chg_pid >= 0)
+		init.flags |= CLK_SET_RATE_PARENT;
 
 	gck->id = id;
 	gck->hw.init = &init;
 	gck->regmap = regmap;
 	gck->lock = lock;
 	gck->range = *range;
-	gck->audio_pll_allowed = pll_audio;
+	gck->chg_pid = chg_pid;
 	gck->layout = layout;
 
 	clk_generated_startup(gck);
diff --git a/drivers/clk/at91/dt-compat.c b/drivers/clk/at91/dt-compat.c
index aa1754eac59f..8a652c44c25a 100644
--- a/drivers/clk/at91/dt-compat.c
+++ b/drivers/clk/at91/dt-compat.c
@@ -22,6 +22,8 @@
 
 #define SYSTEM_MAX_ID		31
 
+#define GCK_INDEX_DT_AUDIO_PLL	5
+
 #ifdef CONFIG_HAVE_AT91_AUDIO_PLL
 static void __init of_sama5d2_clk_audio_pll_frac_setup(struct device_node *np)
 {
@@ -135,7 +137,7 @@ static void __init of_sama5d2_clk_generated_setup(struct device_node *np)
 		return;
 
 	for_each_child_of_node(np, gcknp) {
-		bool pll_audio = false;
+		int chg_pid = INT_MIN;
 
 		if (of_property_read_u32(gcknp, "reg", &id))
 			continue;
@@ -152,12 +154,12 @@ static void __init of_sama5d2_clk_generated_setup(struct device_node *np)
 		if (of_device_is_compatible(np, "atmel,sama5d2-clk-generated") &&
 		    (id == GCK_ID_I2S0 || id == GCK_ID_I2S1 ||
 		     id == GCK_ID_CLASSD))
-			pll_audio = true;
+			chg_pid = GCK_INDEX_DT_AUDIO_PLL;
 
 		hw = at91_clk_register_generated(regmap, &pmc_pcr_lock,
 						 &dt_pcr_layout, name,
 						 parent_names, num_parents,
-						 id, pll_audio, &range);
+						 id, &range, chg_pid);
 		if (IS_ERR(hw))
 			continue;
 
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index df616f2937e7..949b1a7b91e5 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -122,8 +122,8 @@ struct clk_hw * __init
 at91_clk_register_generated(struct regmap *regmap, spinlock_t *lock,
 			    const struct clk_pcr_layout *layout,
 			    const char *name, const char **parent_names,
-			    u8 num_parents, u8 id, bool pll_audio,
-			    const struct clk_range *range);
+			    u8 num_parents, u8 id,
+			    const struct clk_range *range, int chg_pid);
 
 struct clk_hw * __init
 at91_clk_register_h32mx(struct regmap *regmap, const char *name,
diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index d9f6d9ba1eca..58661b6f6eaa 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -290,8 +290,7 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 						 sam9x60_gck[i].n,
 						 parent_names, 6,
 						 sam9x60_gck[i].id,
-						 false,
-						 &sam9x60_gck[i].r);
+						 &sam9x60_gck[i].r, INT_MIN);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/sama5d2.c b/drivers/clk/at91/sama5d2.c
index d69421d71daf..42637d9531d3 100644
--- a/drivers/clk/at91/sama5d2.c
+++ b/drivers/clk/at91/sama5d2.c
@@ -116,21 +116,20 @@ static const struct {
 	char *n;
 	u8 id;
 	struct clk_range r;
-	bool pll;
+	int chg_pid;
 } sama5d2_gck[] = {
-	{ .n = "sdmmc0_gclk", .id = 31, },
-	{ .n = "sdmmc1_gclk", .id = 32, },
-	{ .n = "tcb0_gclk",   .id = 35, .r = { .min = 0, .max = 83000000 }, },
-	{ .n = "tcb1_gclk",   .id = 36, .r = { .min = 0, .max = 83000000 }, },
-	{ .n = "pwm_gclk",    .id = 38, .r = { .min = 0, .max = 83000000 }, },
-	{ .n = "isc_gclk",    .id = 46, },
-	{ .n = "pdmic_gclk",  .id = 48, },
-	{ .n = "i2s0_gclk",   .id = 54, .pll = true },
-	{ .n = "i2s1_gclk",   .id = 55, .pll = true },
-	{ .n = "can0_gclk",   .id = 56, .r = { .min = 0, .max = 80000000 }, },
-	{ .n = "can1_gclk",   .id = 57, .r = { .min = 0, .max = 80000000 }, },
-	{ .n = "classd_gclk", .id = 59, .r = { .min = 0, .max = 100000000 },
-	  .pll = true },
+	{ .n = "sdmmc0_gclk", .id = 31, .chg_pid = INT_MIN, },
+	{ .n = "sdmmc1_gclk", .id = 32, .chg_pid = INT_MIN, },
+	{ .n = "tcb0_gclk",   .id = 35, .chg_pid = INT_MIN, .r = { .min = 0, .max = 83000000 }, },
+	{ .n = "tcb1_gclk",   .id = 36, .chg_pid = INT_MIN, .r = { .min = 0, .max = 83000000 }, },
+	{ .n = "pwm_gclk",    .id = 38, .chg_pid = INT_MIN, .r = { .min = 0, .max = 83000000 }, },
+	{ .n = "isc_gclk",    .id = 46, .chg_pid = INT_MIN, },
+	{ .n = "pdmic_gclk",  .id = 48, .chg_pid = INT_MIN, },
+	{ .n = "i2s0_gclk",   .id = 54, .chg_pid = 5, },
+	{ .n = "i2s1_gclk",   .id = 55, .chg_pid = 5, },
+	{ .n = "can0_gclk",   .id = 56, .chg_pid = INT_MIN, .r = { .min = 0, .max = 80000000 }, },
+	{ .n = "can1_gclk",   .id = 57, .chg_pid = INT_MIN, .r = { .min = 0, .max = 80000000 }, },
+	{ .n = "classd_gclk", .id = 59, .chg_pid = 5, .r = { .min = 0, .max = 100000000 }, },
 };
 
 static const struct clk_programmable_layout sama5d2_programmable_layout = {
@@ -324,8 +323,8 @@ static void __init sama5d2_pmc_setup(struct device_node *np)
 						 sama5d2_gck[i].n,
 						 parent_names, 6,
 						 sama5d2_gck[i].id,
-						 sama5d2_gck[i].pll,
-						 &sama5d2_gck[i].r);
+						 &sama5d2_gck[i].r,
+						 sama5d2_gck[i].chg_pid);
 		if (IS_ERR(hw))
 			goto err_free;
 

From 22a1dfe93bf496d03cb1d76b1fbd23a7ff4a062c Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:19 +0300
Subject: [PATCH 109/474] clk: at91: clk-generated: add mux_table option

Add mux table option. This is necessary for IP versions that has
gaps in the range of available clock sources (e.g. SAMA7G5).

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-12-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-generated.c | 13 ++++++++++---
 drivers/clk/at91/dt-compat.c     |  5 +++--
 drivers/clk/at91/pmc.h           |  2 +-
 drivers/clk/at91/sam9x60.c       |  2 +-
 drivers/clk/at91/sama5d2.c       |  2 +-
 5 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c
index f9ca04c97128..b4fc8d71daf2 100644
--- a/drivers/clk/at91/clk-generated.c
+++ b/drivers/clk/at91/clk-generated.c
@@ -23,6 +23,7 @@ struct clk_generated {
 	struct regmap *regmap;
 	struct clk_range range;
 	spinlock_t *lock;
+	u32 *mux_table;
 	u32 id;
 	u32 gckdiv;
 	const struct clk_pcr_layout *layout;
@@ -201,7 +202,11 @@ static int clk_generated_set_parent(struct clk_hw *hw, u8 index)
 	if (index >= clk_hw_get_num_parents(hw))
 		return -EINVAL;
 
-	gck->parent_id = index;
+	if (gck->mux_table)
+		gck->parent_id = clk_mux_index_to_val(gck->mux_table, 0, index);
+	else
+		gck->parent_id = index;
+
 	return 0;
 }
 
@@ -273,8 +278,9 @@ struct clk_hw * __init
 at91_clk_register_generated(struct regmap *regmap, spinlock_t *lock,
 			    const struct clk_pcr_layout *layout,
 			    const char *name, const char **parent_names,
-			    u8 num_parents, u8 id,
-			    const struct clk_range *range, int chg_pid)
+			    u32 *mux_table, u8 num_parents, u8 id,
+			    const struct clk_range *range,
+			    int chg_pid)
 {
 	struct clk_generated *gck;
 	struct clk_init_data init;
@@ -300,6 +306,7 @@ at91_clk_register_generated(struct regmap *regmap, spinlock_t *lock,
 	gck->range = *range;
 	gck->chg_pid = chg_pid;
 	gck->layout = layout;
+	gck->mux_table = mux_table;
 
 	clk_generated_startup(gck);
 	hw = &gck->hw;
diff --git a/drivers/clk/at91/dt-compat.c b/drivers/clk/at91/dt-compat.c
index 8a652c44c25a..cc95d42f4d53 100644
--- a/drivers/clk/at91/dt-compat.c
+++ b/drivers/clk/at91/dt-compat.c
@@ -158,8 +158,9 @@ static void __init of_sama5d2_clk_generated_setup(struct device_node *np)
 
 		hw = at91_clk_register_generated(regmap, &pmc_pcr_lock,
 						 &dt_pcr_layout, name,
-						 parent_names, num_parents,
-						 id, &range, chg_pid);
+						 parent_names, NULL,
+						 num_parents, id, &range,
+						 chg_pid);
 		if (IS_ERR(hw))
 			continue;
 
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 949b1a7b91e5..2bfe1405f9f8 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -122,7 +122,7 @@ struct clk_hw * __init
 at91_clk_register_generated(struct regmap *regmap, spinlock_t *lock,
 			    const struct clk_pcr_layout *layout,
 			    const char *name, const char **parent_names,
-			    u8 num_parents, u8 id,
+			    u32 *mux_table, u8 num_parents, u8 id,
 			    const struct clk_range *range, int chg_pid);
 
 struct clk_hw * __init
diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index 58661b6f6eaa..197ffc70305a 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -288,7 +288,7 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 		hw = at91_clk_register_generated(regmap, &pmc_pcr_lock,
 						 &sam9x60_pcr_layout,
 						 sam9x60_gck[i].n,
-						 parent_names, 6,
+						 parent_names, NULL, 6,
 						 sam9x60_gck[i].id,
 						 &sam9x60_gck[i].r, INT_MIN);
 		if (IS_ERR(hw))
diff --git a/drivers/clk/at91/sama5d2.c b/drivers/clk/at91/sama5d2.c
index 42637d9531d3..6a685d00f16d 100644
--- a/drivers/clk/at91/sama5d2.c
+++ b/drivers/clk/at91/sama5d2.c
@@ -321,7 +321,7 @@ static void __init sama5d2_pmc_setup(struct device_node *np)
 		hw = at91_clk_register_generated(regmap, &pmc_pcr_lock,
 						 &sama5d2_pcr_layout,
 						 sama5d2_gck[i].n,
-						 parent_names, 6,
+						 parent_names, NULL, 6,
 						 sama5d2_gck[i].id,
 						 &sama5d2_gck[i].r,
 						 sama5d2_gck[i].chg_pid);

From 75c88143f3b879664cc5bf68b91854c1a98f5e5b Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:20 +0300
Subject: [PATCH 110/474] clk: at91: clk-master: add master clock support for
 SAMA7G5

Add master clock support (MCK1..4) for SAMA7G5. SAMA7G5's PMC has
multiple master clocks feeding different subsystems. One of them
feeds image subsystem and is changeable based on image subsystem
needs.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-13-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-master.c | 310 +++++++++++++++++++++++++++++++++-
 drivers/clk/at91/pmc.h        |   7 +
 include/linux/clk/at91_pmc.h  |   1 +
 3 files changed, 313 insertions(+), 5 deletions(-)

diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
index 88d545b1698c..bd0d8a69a2cf 100644
--- a/drivers/clk/at91/clk-master.c
+++ b/drivers/clk/at91/clk-master.c
@@ -17,30 +17,49 @@
 #define MASTER_DIV_SHIFT	8
 #define MASTER_DIV_MASK		0x3
 
+#define PMC_MCR			0x30
+#define PMC_MCR_ID_MSK		GENMASK(3, 0)
+#define PMC_MCR_CMD		BIT(7)
+#define PMC_MCR_DIV		GENMASK(10, 8)
+#define PMC_MCR_CSS		GENMASK(20, 16)
+#define PMC_MCR_CSS_SHIFT	(16)
+#define PMC_MCR_EN		BIT(28)
+
+#define PMC_MCR_ID(x)		((x) & PMC_MCR_ID_MSK)
+
+#define MASTER_MAX_ID		4
+
 #define to_clk_master(hw) container_of(hw, struct clk_master, hw)
 
 struct clk_master {
 	struct clk_hw hw;
 	struct regmap *regmap;
+	spinlock_t *lock;
 	const struct clk_master_layout *layout;
 	const struct clk_master_characteristics *characteristics;
+	u32 *mux_table;
 	u32 mckr;
+	int chg_pid;
+	u8 id;
+	u8 parent;
+	u8 div;
 };
 
-static inline bool clk_master_ready(struct regmap *regmap)
+static inline bool clk_master_ready(struct clk_master *master)
 {
+	unsigned int bit = master->id ? AT91_PMC_MCKXRDY : AT91_PMC_MCKRDY;
 	unsigned int status;
 
-	regmap_read(regmap, AT91_PMC_SR, &status);
+	regmap_read(master->regmap, AT91_PMC_SR, &status);
 
-	return !!(status & AT91_PMC_MCKRDY);
+	return !!(status & bit);
 }
 
 static int clk_master_prepare(struct clk_hw *hw)
 {
 	struct clk_master *master = to_clk_master(hw);
 
-	while (!clk_master_ready(master->regmap))
+	while (!clk_master_ready(master))
 		cpu_relax();
 
 	return 0;
@@ -50,7 +69,7 @@ static int clk_master_is_prepared(struct clk_hw *hw)
 {
 	struct clk_master *master = to_clk_master(hw);
 
-	return clk_master_ready(master->regmap);
+	return clk_master_ready(master);
 }
 
 static unsigned long clk_master_recalc_rate(struct clk_hw *hw,
@@ -143,6 +162,287 @@ at91_clk_register_master(struct regmap *regmap,
 	return hw;
 }
 
+static unsigned long
+clk_sama7g5_master_recalc_rate(struct clk_hw *hw,
+			       unsigned long parent_rate)
+{
+	struct clk_master *master = to_clk_master(hw);
+
+	return DIV_ROUND_CLOSEST_ULL(parent_rate, (1 << master->div));
+}
+
+static void clk_sama7g5_master_best_diff(struct clk_rate_request *req,
+					 struct clk_hw *parent,
+					 unsigned long parent_rate,
+					 long *best_rate,
+					 long *best_diff,
+					 u32 div)
+{
+	unsigned long tmp_rate, tmp_diff;
+
+	if (div == MASTER_PRES_MAX)
+		tmp_rate = parent_rate / 3;
+	else
+		tmp_rate = parent_rate >> div;
+
+	tmp_diff = abs(req->rate - tmp_rate);
+
+	if (*best_diff < 0 || *best_diff >= tmp_diff) {
+		*best_rate = tmp_rate;
+		*best_diff = tmp_diff;
+		req->best_parent_rate = parent_rate;
+		req->best_parent_hw = parent;
+	}
+}
+
+static int clk_sama7g5_master_determine_rate(struct clk_hw *hw,
+					     struct clk_rate_request *req)
+{
+	struct clk_master *master = to_clk_master(hw);
+	struct clk_rate_request req_parent = *req;
+	struct clk_hw *parent;
+	long best_rate = LONG_MIN, best_diff = LONG_MIN;
+	unsigned long parent_rate;
+	unsigned int div, i;
+
+	/* First: check the dividers of MCR. */
+	for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
+		parent = clk_hw_get_parent_by_index(hw, i);
+		if (!parent)
+			continue;
+
+		parent_rate = clk_hw_get_rate(parent);
+		if (!parent_rate)
+			continue;
+
+		for (div = 0; div < MASTER_PRES_MAX + 1; div++) {
+			clk_sama7g5_master_best_diff(req, parent, parent_rate,
+						     &best_rate, &best_diff,
+						     div);
+			if (!best_diff)
+				break;
+		}
+
+		if (!best_diff)
+			break;
+	}
+
+	/* Second: try to request rate form changeable parent. */
+	if (master->chg_pid < 0)
+		goto end;
+
+	parent = clk_hw_get_parent_by_index(hw, master->chg_pid);
+	if (!parent)
+		goto end;
+
+	for (div = 0; div < MASTER_PRES_MAX + 1; div++) {
+		if (div == MASTER_PRES_MAX)
+			req_parent.rate = req->rate * 3;
+		else
+			req_parent.rate = req->rate << div;
+
+		if (__clk_determine_rate(parent, &req_parent))
+			continue;
+
+		clk_sama7g5_master_best_diff(req, parent, req_parent.rate,
+					     &best_rate, &best_diff, div);
+
+		if (!best_diff)
+			break;
+	}
+
+end:
+	pr_debug("MCK: %s, best_rate = %ld, parent clk: %s @ %ld\n",
+		 __func__, best_rate,
+		 __clk_get_name((req->best_parent_hw)->clk),
+		req->best_parent_rate);
+
+	if (best_rate < 0)
+		return -EINVAL;
+
+	req->rate = best_rate;
+
+	return 0;
+}
+
+static u8 clk_sama7g5_master_get_parent(struct clk_hw *hw)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+	u8 index;
+
+	spin_lock_irqsave(master->lock, flags);
+	index = clk_mux_val_to_index(&master->hw, master->mux_table, 0,
+				     master->parent);
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return index;
+}
+
+static int clk_sama7g5_master_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+
+	if (index >= clk_hw_get_num_parents(hw))
+		return -EINVAL;
+
+	spin_lock_irqsave(master->lock, flags);
+	master->parent = clk_mux_index_to_val(master->mux_table, 0, index);
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return 0;
+}
+
+static int clk_sama7g5_master_enable(struct clk_hw *hw)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+	unsigned int val, cparent;
+
+	spin_lock_irqsave(master->lock, flags);
+
+	regmap_write(master->regmap, PMC_MCR, PMC_MCR_ID(master->id));
+	regmap_read(master->regmap, PMC_MCR, &val);
+	regmap_update_bits(master->regmap, PMC_MCR,
+			   PMC_MCR_EN | PMC_MCR_CSS | PMC_MCR_DIV |
+			   PMC_MCR_CMD | PMC_MCR_ID_MSK,
+			   PMC_MCR_EN | (master->parent << PMC_MCR_CSS_SHIFT) |
+			   (master->div << MASTER_DIV_SHIFT) |
+			   PMC_MCR_CMD | PMC_MCR_ID(master->id));
+
+	cparent = (val & PMC_MCR_CSS) >> PMC_MCR_CSS_SHIFT;
+
+	/* Wait here only if parent is being changed. */
+	while ((cparent != master->parent) && !clk_master_ready(master))
+		cpu_relax();
+
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return 0;
+}
+
+static void clk_sama7g5_master_disable(struct clk_hw *hw)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+
+	spin_lock_irqsave(master->lock, flags);
+
+	regmap_write(master->regmap, PMC_MCR, master->id);
+	regmap_update_bits(master->regmap, PMC_MCR,
+			   PMC_MCR_EN | PMC_MCR_CMD | PMC_MCR_ID_MSK,
+			   PMC_MCR_CMD | PMC_MCR_ID(master->id));
+
+	spin_unlock_irqrestore(master->lock, flags);
+}
+
+static int clk_sama7g5_master_is_enabled(struct clk_hw *hw)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+	unsigned int val;
+
+	spin_lock_irqsave(master->lock, flags);
+
+	regmap_write(master->regmap, PMC_MCR, master->id);
+	regmap_read(master->regmap, PMC_MCR, &val);
+
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return !!(val & PMC_MCR_EN);
+}
+
+static int clk_sama7g5_master_set_rate(struct clk_hw *hw, unsigned long rate,
+				       unsigned long parent_rate)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long div, flags;
+
+	div = DIV_ROUND_CLOSEST(parent_rate, rate);
+	if ((div > (1 << (MASTER_PRES_MAX - 1))) || (div & (div - 1)))
+		return -EINVAL;
+
+	if (div == 3)
+		div = MASTER_PRES_MAX;
+	else
+		div = ffs(div) - 1;
+
+	spin_lock_irqsave(master->lock, flags);
+	master->div = div;
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return 0;
+}
+
+static const struct clk_ops sama7g5_master_ops = {
+	.enable = clk_sama7g5_master_enable,
+	.disable = clk_sama7g5_master_disable,
+	.is_enabled = clk_sama7g5_master_is_enabled,
+	.recalc_rate = clk_sama7g5_master_recalc_rate,
+	.determine_rate = clk_sama7g5_master_determine_rate,
+	.set_rate = clk_sama7g5_master_set_rate,
+	.get_parent = clk_sama7g5_master_get_parent,
+	.set_parent = clk_sama7g5_master_set_parent,
+};
+
+struct clk_hw * __init
+at91_clk_sama7g5_register_master(struct regmap *regmap,
+				 const char *name, int num_parents,
+				 const char **parent_names,
+				 u32 *mux_table,
+				 spinlock_t *lock, u8 id,
+				 bool critical, int chg_pid)
+{
+	struct clk_master *master;
+	struct clk_hw *hw;
+	struct clk_init_data init;
+	unsigned long flags;
+	unsigned int val;
+	int ret;
+
+	if (!name || !num_parents || !parent_names || !mux_table ||
+	    !lock || id > MASTER_MAX_ID)
+		return ERR_PTR(-EINVAL);
+
+	master = kzalloc(sizeof(*master), GFP_KERNEL);
+	if (!master)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.ops = &sama7g5_master_ops;
+	init.parent_names = parent_names;
+	init.num_parents = num_parents;
+	init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE;
+	if (chg_pid >= 0)
+		init.flags |= CLK_SET_RATE_PARENT;
+	if (critical)
+		init.flags |= CLK_IS_CRITICAL;
+
+	master->hw.init = &init;
+	master->regmap = regmap;
+	master->id = id;
+	master->chg_pid = chg_pid;
+	master->lock = lock;
+	master->mux_table = mux_table;
+
+	spin_lock_irqsave(master->lock, flags);
+	regmap_write(master->regmap, PMC_MCR, master->id);
+	regmap_read(master->regmap, PMC_MCR, &val);
+	master->parent = (val & PMC_MCR_CSS) >> PMC_MCR_CSS_SHIFT;
+	master->div = (val & PMC_MCR_DIV) >> MASTER_DIV_SHIFT;
+	spin_unlock_irqrestore(master->lock, flags);
+
+	hw = &master->hw;
+	ret = clk_hw_register(NULL, &master->hw);
+	if (ret) {
+		kfree(master);
+		hw = ERR_PTR(ret);
+	}
+
+	return hw;
+}
+
 const struct clk_master_layout at91rm9200_master_layout = {
 	.mask = 0x31F,
 	.pres_shift = 2,
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 2bfe1405f9f8..29d150feaa46 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -154,6 +154,13 @@ at91_clk_register_master(struct regmap *regmap, const char *name,
 			 const struct clk_master_layout *layout,
 			 const struct clk_master_characteristics *characteristics);
 
+struct clk_hw * __init
+at91_clk_sama7g5_register_master(struct regmap *regmap,
+				 const char *name, int num_parents,
+				 const char **parent_names, u32 *mux_table,
+				 spinlock_t *lock, u8 id, bool critical,
+				 int chg_pid);
+
 struct clk_hw * __init
 at91_clk_register_peripheral(struct regmap *regmap, const char *name,
 			     const char *parent_name, u32 id);
diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h
index 49a53a137610..77d6dabc4c3c 100644
--- a/include/linux/clk/at91_pmc.h
+++ b/include/linux/clk/at91_pmc.h
@@ -174,6 +174,7 @@
 #define		AT91_PMC_MOSCRCS	(1 << 17)		/* Main On-Chip RC [some SAM9] */
 #define		AT91_PMC_CFDEV		(1 << 18)		/* Clock Failure Detector Event [some SAM9] */
 #define		AT91_PMC_GCKRDY		(1 << 24)		/* Generated Clocks */
+#define		AT91_PMC_MCKXRDY	(1 << 26)		/* Master Clock x [x=1..4] Ready Status */
 #define	AT91_PMC_IMR		0x6c			/* Interrupt Mask Register */
 
 #define AT91_PMC_FSMR		0x70		/* Fast Startup Mode Register */

From b4c115c76184f2c56a295579161652fd5eb2dcc1 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:21 +0300
Subject: [PATCH 111/474] clk: at91: clk-peripheral: add support for changeable
 parent rate

Some peripheral clocks on SAMA7G5 supports requesting parent to change
its rate (image related clocks: csi, csi2dc, isc). Add support
so that if registered with this option the clock rate to be
requested from parent.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-14-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/at91sam9n12.c    |   2 +-
 drivers/clk/at91/at91sam9x5.c     |   4 +-
 drivers/clk/at91/clk-peripheral.c | 109 ++++++++++++++++++++++++++++--
 drivers/clk/at91/dt-compat.c      |   3 +-
 drivers/clk/at91/pmc.h            |   3 +-
 drivers/clk/at91/sam9x60.c        |   2 +-
 drivers/clk/at91/sama5d2.c        |   5 +-
 drivers/clk/at91/sama5d3.c        |   3 +-
 drivers/clk/at91/sama5d4.c        |   4 +-
 9 files changed, 119 insertions(+), 16 deletions(-)

diff --git a/drivers/clk/at91/at91sam9n12.c b/drivers/clk/at91/at91sam9n12.c
index 4aa97e672bd6..aaf4da30584e 100644
--- a/drivers/clk/at91/at91sam9n12.c
+++ b/drivers/clk/at91/at91sam9n12.c
@@ -222,7 +222,7 @@ static void __init at91sam9n12_pmc_setup(struct device_node *np)
 							 at91sam9n12_periphck[i].n,
 							 "masterck",
 							 at91sam9n12_periphck[i].id,
-							 &range);
+							 &range, INT_MIN);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/at91sam9x5.c b/drivers/clk/at91/at91sam9x5.c
index 0ce3da080287..52a9d2f7ec83 100644
--- a/drivers/clk/at91/at91sam9x5.c
+++ b/drivers/clk/at91/at91sam9x5.c
@@ -257,7 +257,7 @@ static void __init at91sam9x5_pmc_setup(struct device_node *np,
 							 at91sam9x5_periphck[i].n,
 							 "masterck",
 							 at91sam9x5_periphck[i].id,
-							 &range);
+							 &range, INT_MIN);
 		if (IS_ERR(hw))
 			goto err_free;
 
@@ -270,7 +270,7 @@ static void __init at91sam9x5_pmc_setup(struct device_node *np,
 							 extra_pcks[i].n,
 							 "masterck",
 							 extra_pcks[i].id,
-							 &range);
+							 &range, INT_MIN);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/clk-peripheral.c b/drivers/clk/at91/clk-peripheral.c
index 4c9a4147dfe5..7867eaf0447f 100644
--- a/drivers/clk/at91/clk-peripheral.c
+++ b/drivers/clk/at91/clk-peripheral.c
@@ -38,6 +38,7 @@ struct clk_sam9x5_peripheral {
 	u32 div;
 	const struct clk_pcr_layout *layout;
 	bool auto_div;
+	int chg_pid;
 };
 
 #define to_clk_sam9x5_peripheral(hw) \
@@ -238,6 +239,87 @@ clk_sam9x5_peripheral_recalc_rate(struct clk_hw *hw,
 	return parent_rate >> periph->div;
 }
 
+static void clk_sam9x5_peripheral_best_diff(struct clk_rate_request *req,
+					    struct clk_hw *parent,
+					    unsigned long parent_rate,
+					    u32 shift, long *best_diff,
+					    long *best_rate)
+{
+	unsigned long tmp_rate = parent_rate >> shift;
+	unsigned long tmp_diff = abs(req->rate - tmp_rate);
+
+	if (*best_diff < 0 || *best_diff >= tmp_diff) {
+		*best_rate = tmp_rate;
+		*best_diff = tmp_diff;
+		req->best_parent_rate = parent_rate;
+		req->best_parent_hw = parent;
+	}
+}
+
+static int clk_sam9x5_peripheral_determine_rate(struct clk_hw *hw,
+						struct clk_rate_request *req)
+{
+	struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw);
+	struct clk_hw *parent = clk_hw_get_parent(hw);
+	struct clk_rate_request req_parent = *req;
+	unsigned long parent_rate = clk_hw_get_rate(parent);
+	unsigned long tmp_rate;
+	long best_rate = LONG_MIN;
+	long best_diff = LONG_MIN;
+	u32 shift;
+
+	if (periph->id < PERIPHERAL_ID_MIN || !periph->range.max)
+		return parent_rate;
+
+	/* Fist step: check the available dividers. */
+	for (shift = 0; shift <= PERIPHERAL_MAX_SHIFT; shift++) {
+		tmp_rate = parent_rate >> shift;
+
+		if (periph->range.max && tmp_rate > periph->range.max)
+			continue;
+
+		clk_sam9x5_peripheral_best_diff(req, parent, parent_rate,
+						shift, &best_diff, &best_rate);
+
+		if (!best_diff || best_rate <= req->rate)
+			break;
+	}
+
+	if (periph->chg_pid < 0)
+		goto end;
+
+	/* Step two: try to request rate from parent. */
+	parent = clk_hw_get_parent_by_index(hw, periph->chg_pid);
+	if (!parent)
+		goto end;
+
+	for (shift = 0; shift <= PERIPHERAL_MAX_SHIFT; shift++) {
+		req_parent.rate = req->rate << shift;
+
+		if (__clk_determine_rate(parent, &req_parent))
+			continue;
+
+		clk_sam9x5_peripheral_best_diff(req, parent, req_parent.rate,
+						shift, &best_diff, &best_rate);
+
+		if (!best_diff)
+			break;
+	}
+end:
+	if (best_rate < 0 ||
+	    (periph->range.max && best_rate > periph->range.max))
+		return -EINVAL;
+
+	pr_debug("PCK: %s, best_rate = %ld, parent clk: %s @ %ld\n",
+		 __func__, best_rate,
+		 __clk_get_name((req->best_parent_hw)->clk),
+		 req->best_parent_rate);
+
+	req->rate = best_rate;
+
+	return 0;
+}
+
 static long clk_sam9x5_peripheral_round_rate(struct clk_hw *hw,
 					     unsigned long rate,
 					     unsigned long *parent_rate)
@@ -320,11 +402,21 @@ static const struct clk_ops sam9x5_peripheral_ops = {
 	.set_rate = clk_sam9x5_peripheral_set_rate,
 };
 
+static const struct clk_ops sam9x5_peripheral_chg_ops = {
+	.enable = clk_sam9x5_peripheral_enable,
+	.disable = clk_sam9x5_peripheral_disable,
+	.is_enabled = clk_sam9x5_peripheral_is_enabled,
+	.recalc_rate = clk_sam9x5_peripheral_recalc_rate,
+	.determine_rate = clk_sam9x5_peripheral_determine_rate,
+	.set_rate = clk_sam9x5_peripheral_set_rate,
+};
+
 struct clk_hw * __init
 at91_clk_register_sam9x5_peripheral(struct regmap *regmap, spinlock_t *lock,
 				    const struct clk_pcr_layout *layout,
 				    const char *name, const char *parent_name,
-				    u32 id, const struct clk_range *range)
+				    u32 id, const struct clk_range *range,
+				    int chg_pid)
 {
 	struct clk_sam9x5_peripheral *periph;
 	struct clk_init_data init;
@@ -339,10 +431,16 @@ at91_clk_register_sam9x5_peripheral(struct regmap *regmap, spinlock_t *lock,
 		return ERR_PTR(-ENOMEM);
 
 	init.name = name;
-	init.ops = &sam9x5_peripheral_ops;
-	init.parent_names = (parent_name ? &parent_name : NULL);
-	init.num_parents = (parent_name ? 1 : 0);
-	init.flags = 0;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+	if (chg_pid < 0) {
+		init.flags = 0;
+		init.ops = &sam9x5_peripheral_ops;
+	} else {
+		init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE |
+			     CLK_SET_RATE_PARENT;
+		init.ops = &sam9x5_peripheral_chg_ops;
+	}
 
 	periph->id = id;
 	periph->hw.init = &init;
@@ -353,6 +451,7 @@ at91_clk_register_sam9x5_peripheral(struct regmap *regmap, spinlock_t *lock,
 		periph->auto_div = true;
 	periph->layout = layout;
 	periph->range = *range;
+	periph->chg_pid = chg_pid;
 
 	hw = &periph->hw;
 	ret = clk_hw_register(NULL, &periph->hw);
diff --git a/drivers/clk/at91/dt-compat.c b/drivers/clk/at91/dt-compat.c
index cc95d42f4d53..1b90c4f7b1d1 100644
--- a/drivers/clk/at91/dt-compat.c
+++ b/drivers/clk/at91/dt-compat.c
@@ -463,7 +463,8 @@ of_at91_clk_periph_setup(struct device_node *np, u8 type)
 								 &dt_pcr_layout,
 								 name,
 								 parent_name,
-								 id, &range);
+								 id, &range,
+								 INT_MIN);
 		}
 
 		if (IS_ERR(hw))
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 29d150feaa46..34c9506e6275 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -168,7 +168,8 @@ struct clk_hw * __init
 at91_clk_register_sam9x5_peripheral(struct regmap *regmap, spinlock_t *lock,
 				    const struct clk_pcr_layout *layout,
 				    const char *name, const char *parent_name,
-				    u32 id, const struct clk_range *range);
+				    u32 id, const struct clk_range *range,
+				    int chg_pid);
 
 struct clk_hw * __init
 at91_clk_register_pll(struct regmap *regmap, const char *name,
diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index 197ffc70305a..f090518d24a7 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -277,7 +277,7 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 							 sam9x60_periphck[i].n,
 							 "masterck",
 							 sam9x60_periphck[i].id,
-							 &range);
+							 &range, INT_MIN);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/sama5d2.c b/drivers/clk/at91/sama5d2.c
index 6a685d00f16d..c7765b664940 100644
--- a/drivers/clk/at91/sama5d2.c
+++ b/drivers/clk/at91/sama5d2.c
@@ -291,7 +291,7 @@ static void __init sama5d2_pmc_setup(struct device_node *np)
 							 sama5d2_periphck[i].n,
 							 "masterck",
 							 sama5d2_periphck[i].id,
-							 &range);
+							 &range, INT_MIN);
 		if (IS_ERR(hw))
 			goto err_free;
 
@@ -304,7 +304,8 @@ static void __init sama5d2_pmc_setup(struct device_node *np)
 							 sama5d2_periph32ck[i].n,
 							 "h32mxck",
 							 sama5d2_periph32ck[i].id,
-							 &sama5d2_periph32ck[i].r);
+							 &sama5d2_periph32ck[i].r,
+							 INT_MIN);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/sama5d3.c b/drivers/clk/at91/sama5d3.c
index 5609b04e6565..49ec5964bcb3 100644
--- a/drivers/clk/at91/sama5d3.c
+++ b/drivers/clk/at91/sama5d3.c
@@ -223,7 +223,8 @@ static void __init sama5d3_pmc_setup(struct device_node *np)
 							 sama5d3_periphck[i].n,
 							 "masterck",
 							 sama5d3_periphck[i].id,
-							 &sama5d3_periphck[i].r);
+							 &sama5d3_periphck[i].r,
+							 INT_MIN);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/sama5d4.c b/drivers/clk/at91/sama5d4.c
index 662ff5fa6e98..fa121897d95d 100644
--- a/drivers/clk/at91/sama5d4.c
+++ b/drivers/clk/at91/sama5d4.c
@@ -246,7 +246,7 @@ static void __init sama5d4_pmc_setup(struct device_node *np)
 							 sama5d4_periphck[i].n,
 							 "masterck",
 							 sama5d4_periphck[i].id,
-							 &range);
+							 &range, INT_MIN);
 		if (IS_ERR(hw))
 			goto err_free;
 
@@ -259,7 +259,7 @@ static void __init sama5d4_pmc_setup(struct device_node *np)
 							 sama5d4_periph32ck[i].n,
 							 "h32mxck",
 							 sama5d4_periph32ck[i].id,
-							 &range);
+							 &range, INT_MIN);
 		if (IS_ERR(hw))
 			goto err_free;
 

From c57aaaa28cf1a123c0029a36361a809eae2b1960 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:22 +0300
Subject: [PATCH 112/474] clk: at91: clk-programmable: add mux_table option

Add mux table option. This is necessary for IP versions that has
gaps in the range of available clock sources (e.g. SAMA7G5).

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-15-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/at91rm9200.c       |  3 ++-
 drivers/clk/at91/at91sam9260.c      |  3 ++-
 drivers/clk/at91/at91sam9g45.c      |  3 ++-
 drivers/clk/at91/at91sam9n12.c      |  3 ++-
 drivers/clk/at91/at91sam9rl.c       |  3 ++-
 drivers/clk/at91/at91sam9x5.c       |  3 ++-
 drivers/clk/at91/clk-programmable.c | 11 ++++++++++-
 drivers/clk/at91/dt-compat.c        | 11 ++++++-----
 drivers/clk/at91/pmc.h              |  3 ++-
 drivers/clk/at91/sam9x60.c          |  3 ++-
 drivers/clk/at91/sama5d2.c          |  3 ++-
 drivers/clk/at91/sama5d3.c          |  3 ++-
 drivers/clk/at91/sama5d4.c          |  3 ++-
 13 files changed, 38 insertions(+), 17 deletions(-)

diff --git a/drivers/clk/at91/at91rm9200.c b/drivers/clk/at91/at91rm9200.c
index 38bdb4981315..2c3d8e6ca63c 100644
--- a/drivers/clk/at91/at91rm9200.c
+++ b/drivers/clk/at91/at91rm9200.c
@@ -160,7 +160,8 @@ static void __init at91rm9200_pmc_setup(struct device_node *np)
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, 4, i,
-						    &at91rm9200_programmable_layout);
+						    &at91rm9200_programmable_layout,
+						    NULL);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/at91sam9260.c b/drivers/clk/at91/at91sam9260.c
index 6d0723aa8b13..bb81ff731ad8 100644
--- a/drivers/clk/at91/at91sam9260.c
+++ b/drivers/clk/at91/at91sam9260.c
@@ -436,7 +436,8 @@ static void __init at91sam926x_pmc_setup(struct device_node *np,
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, 4, i,
-						    &at91rm9200_programmable_layout);
+						    &at91rm9200_programmable_layout,
+						    NULL);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/at91sam9g45.c b/drivers/clk/at91/at91sam9g45.c
index fe9d391adeba..c88ee20bee31 100644
--- a/drivers/clk/at91/at91sam9g45.c
+++ b/drivers/clk/at91/at91sam9g45.c
@@ -181,7 +181,8 @@ static void __init at91sam9g45_pmc_setup(struct device_node *np)
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, 5, i,
-						    &at91sam9g45_programmable_layout);
+						    &at91sam9g45_programmable_layout,
+						    NULL);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/at91sam9n12.c b/drivers/clk/at91/at91sam9n12.c
index aaf4da30584e..93f7eb216122 100644
--- a/drivers/clk/at91/at91sam9n12.c
+++ b/drivers/clk/at91/at91sam9n12.c
@@ -199,7 +199,8 @@ static void __init at91sam9n12_pmc_setup(struct device_node *np)
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, 5, i,
-						    &at91sam9x5_programmable_layout);
+						    &at91sam9x5_programmable_layout,
+						    NULL);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/at91sam9rl.c b/drivers/clk/at91/at91sam9rl.c
index 0d1cc44b056f..a343eb69bb35 100644
--- a/drivers/clk/at91/at91sam9rl.c
+++ b/drivers/clk/at91/at91sam9rl.c
@@ -137,7 +137,8 @@ static void __init at91sam9rl_pmc_setup(struct device_node *np)
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, 5, i,
-						    &at91rm9200_programmable_layout);
+						    &at91rm9200_programmable_layout,
+						    NULL);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/at91sam9x5.c b/drivers/clk/at91/at91sam9x5.c
index 52a9d2f7ec83..22b9aad9efb8 100644
--- a/drivers/clk/at91/at91sam9x5.c
+++ b/drivers/clk/at91/at91sam9x5.c
@@ -226,7 +226,8 @@ static void __init at91sam9x5_pmc_setup(struct device_node *np,
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, 5, i,
-						    &at91sam9x5_programmable_layout);
+						    &at91sam9x5_programmable_layout,
+						    NULL);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c
index 8ee66fbee3d9..fcf8f6a1c2c6 100644
--- a/drivers/clk/at91/clk-programmable.c
+++ b/drivers/clk/at91/clk-programmable.c
@@ -21,6 +21,7 @@
 struct clk_programmable {
 	struct clk_hw hw;
 	struct regmap *regmap;
+	u32 *mux_table;
 	u8 id;
 	const struct clk_programmable_layout *layout;
 };
@@ -108,6 +109,9 @@ static int clk_programmable_set_parent(struct clk_hw *hw, u8 index)
 	if (layout->have_slck_mck)
 		mask |= AT91_PMC_CSSMCK_MCK;
 
+	if (prog->mux_table)
+		pckr = clk_mux_index_to_val(prog->mux_table, 0, index);
+
 	if (index > layout->css_mask) {
 		if (index > PROG_MAX_RM9200_CSS && !layout->have_slck_mck)
 			return -EINVAL;
@@ -134,6 +138,9 @@ static u8 clk_programmable_get_parent(struct clk_hw *hw)
 	if (layout->have_slck_mck && (pckr & AT91_PMC_CSSMCK_MCK) && !ret)
 		ret = PROG_MAX_RM9200_CSS + 1;
 
+	if (prog->mux_table)
+		ret = clk_mux_val_to_index(&prog->hw, prog->mux_table, 0, ret);
+
 	return ret;
 }
 
@@ -182,7 +189,8 @@ struct clk_hw * __init
 at91_clk_register_programmable(struct regmap *regmap,
 			       const char *name, const char **parent_names,
 			       u8 num_parents, u8 id,
-			       const struct clk_programmable_layout *layout)
+			       const struct clk_programmable_layout *layout,
+			       u32 *mux_table)
 {
 	struct clk_programmable *prog;
 	struct clk_hw *hw;
@@ -206,6 +214,7 @@ at91_clk_register_programmable(struct regmap *regmap,
 	prog->layout = layout;
 	prog->hw.init = &init;
 	prog->regmap = regmap;
+	prog->mux_table = mux_table;
 
 	hw = &prog->hw;
 	ret = clk_hw_register(NULL, &prog->hw);
diff --git a/drivers/clk/at91/dt-compat.c b/drivers/clk/at91/dt-compat.c
index 1b90c4f7b1d1..a50084de97d4 100644
--- a/drivers/clk/at91/dt-compat.c
+++ b/drivers/clk/at91/dt-compat.c
@@ -677,7 +677,8 @@ CLK_OF_DECLARE(at91sam9x5_clk_plldiv, "atmel,at91sam9x5-clk-plldiv",
 
 static void __init
 of_at91_clk_prog_setup(struct device_node *np,
-		       const struct clk_programmable_layout *layout)
+		       const struct clk_programmable_layout *layout,
+		       u32 *mux_table)
 {
 	int num;
 	u32 id;
@@ -711,7 +712,7 @@ of_at91_clk_prog_setup(struct device_node *np,
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, num_parents,
-						    id, layout);
+						    id, layout, mux_table);
 		if (IS_ERR(hw))
 			continue;
 
@@ -721,21 +722,21 @@ of_at91_clk_prog_setup(struct device_node *np,
 
 static void __init of_at91rm9200_clk_prog_setup(struct device_node *np)
 {
-	of_at91_clk_prog_setup(np, &at91rm9200_programmable_layout);
+	of_at91_clk_prog_setup(np, &at91rm9200_programmable_layout, NULL);
 }
 CLK_OF_DECLARE(at91rm9200_clk_prog, "atmel,at91rm9200-clk-programmable",
 	       of_at91rm9200_clk_prog_setup);
 
 static void __init of_at91sam9g45_clk_prog_setup(struct device_node *np)
 {
-	of_at91_clk_prog_setup(np, &at91sam9g45_programmable_layout);
+	of_at91_clk_prog_setup(np, &at91sam9g45_programmable_layout, NULL);
 }
 CLK_OF_DECLARE(at91sam9g45_clk_prog, "atmel,at91sam9g45-clk-programmable",
 	       of_at91sam9g45_clk_prog_setup);
 
 static void __init of_at91sam9x5_clk_prog_setup(struct device_node *np)
 {
-	of_at91_clk_prog_setup(np, &at91sam9x5_programmable_layout);
+	of_at91_clk_prog_setup(np, &at91sam9x5_programmable_layout, NULL);
 }
 CLK_OF_DECLARE(at91sam9x5_clk_prog, "atmel,at91sam9x5-clk-programmable",
 	       of_at91sam9x5_clk_prog_setup);
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 34c9506e6275..8d3e22f566cf 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -188,7 +188,8 @@ sam9x60_clk_register_pll(struct regmap *regmap, spinlock_t *lock,
 struct clk_hw * __init
 at91_clk_register_programmable(struct regmap *regmap, const char *name,
 			       const char **parent_names, u8 num_parents, u8 id,
-			       const struct clk_programmable_layout *layout);
+			       const struct clk_programmable_layout *layout,
+			       u32 *mux_table);
 
 struct clk_hw * __init
 at91_clk_register_sam9260_slow(struct regmap *regmap,
diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index f090518d24a7..d8d4b28ec4cb 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -254,7 +254,8 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, 6, i,
-						    &sam9x60_programmable_layout);
+						    &sam9x60_programmable_layout,
+						    NULL);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/sama5d2.c b/drivers/clk/at91/sama5d2.c
index c7765b664940..8b220762941a 100644
--- a/drivers/clk/at91/sama5d2.c
+++ b/drivers/clk/at91/sama5d2.c
@@ -268,7 +268,8 @@ static void __init sama5d2_pmc_setup(struct device_node *np)
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, 6, i,
-						    &sama5d2_programmable_layout);
+						    &sama5d2_programmable_layout,
+						    NULL);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/sama5d3.c b/drivers/clk/at91/sama5d3.c
index 49ec5964bcb3..7c6e0a5b9dc8 100644
--- a/drivers/clk/at91/sama5d3.c
+++ b/drivers/clk/at91/sama5d3.c
@@ -200,7 +200,8 @@ static void __init sama5d3_pmc_setup(struct device_node *np)
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, 5, i,
-						    &at91sam9x5_programmable_layout);
+						    &at91sam9x5_programmable_layout,
+						    NULL);
 		if (IS_ERR(hw))
 			goto err_free;
 
diff --git a/drivers/clk/at91/sama5d4.c b/drivers/clk/at91/sama5d4.c
index fa121897d95d..92d8d4141b43 100644
--- a/drivers/clk/at91/sama5d4.c
+++ b/drivers/clk/at91/sama5d4.c
@@ -223,7 +223,8 @@ static void __init sama5d4_pmc_setup(struct device_node *np)
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, 5, i,
-						    &at91sam9x5_programmable_layout);
+						    &at91sam9x5_programmable_layout,
+						    NULL);
 		if (IS_ERR(hw))
 			goto err_free;
 

From 0416824edca1cdcb6e00e6f909423bf0fc529eef Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:23 +0300
Subject: [PATCH 113/474] clk: at91: add macro for pll ids mask

Add macro for PLL IDs mask.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-16-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 include/linux/clk/at91_pmc.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h
index 77d6dabc4c3c..dc5e85f124e0 100644
--- a/include/linux/clk/at91_pmc.h
+++ b/include/linux/clk/at91_pmc.h
@@ -59,6 +59,7 @@
 #define AT91_PMC_PLL_UPDT		0x1C		/* PMC PLL update register [for SAM9X60] */
 #define		AT91_PMC_PLL_UPDT_UPDATE	(1 << 8)	/* Update PLL settings */
 #define		AT91_PMC_PLL_UPDT_ID		(1 << 0)	/* PLL ID */
+#define		AT91_PMC_PLL_UPDT_ID_MSK	(0xf)		/* PLL ID mask */
 #define		AT91_PMC_PLL_UPDT_STUPTIM	(0xff << 16)	/* Startup time */
 
 #define	AT91_CKGR_MOR		0x20			/* Main Oscillator Register [not on SAM9RL] */

From 43b1bb4a9b3e183af12225f56c27164c10d06223 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:24 +0300
Subject: [PATCH 114/474] clk: at91: clk-sam9x60-pll: re-factor to support plls
 with multiple outputs

Some of the SAMA7G5 PLLs support multiple outputs (e.g. AUDIO PLL).
For these, split the PLL clock in two: fractional clock and
divider clock. In case PLLs supports multiple outputs (since these
outputs are dividers (with different settings) sharing the same
fractional part), it will register one fractional clock and multiple
divider clocks (dividers sharing the fractional clock).

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-17-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-sam9x60-pll.c | 563 +++++++++++++++++++----------
 drivers/clk/at91/pmc.h             |  22 +-
 drivers/clk/at91/sam9x60.c         |  50 ++-
 3 files changed, 441 insertions(+), 194 deletions(-)

diff --git a/drivers/clk/at91/clk-sam9x60-pll.c b/drivers/clk/at91/clk-sam9x60-pll.c
index 1f0bcc6b4fea..b473298ef7e6 100644
--- a/drivers/clk/at91/clk-sam9x60-pll.c
+++ b/drivers/clk/at91/clk-sam9x60-pll.c
@@ -25,20 +25,31 @@
 #define FCORE_MIN		(600000000)
 #define FCORE_MAX		(1200000000)
 
-#define PLL_MAX_ID		1
+#define PLL_MAX_ID		7
 
-struct sam9x60_pll {
-	struct clk_hw hw;
+struct sam9x60_pll_core {
 	struct regmap *regmap;
 	spinlock_t *lock;
 	const struct clk_pll_characteristics *characteristics;
-	u32 frac;
+	const struct clk_pll_layout *layout;
+	struct clk_hw hw;
 	u8 id;
-	u8 div;
+};
+
+struct sam9x60_frac {
+	struct sam9x60_pll_core core;
+	u32 frac;
 	u16 mul;
 };
 
-#define to_sam9x60_pll(hw) container_of(hw, struct sam9x60_pll, hw)
+struct sam9x60_div {
+	struct sam9x60_pll_core core;
+	u8 div;
+};
+
+#define to_sam9x60_pll_core(hw)	container_of(hw, struct sam9x60_pll_core, hw)
+#define to_sam9x60_frac(core)	container_of(core, struct sam9x60_frac, core)
+#define to_sam9x60_div(core)	container_of(core, struct sam9x60_div, core)
 
 static inline bool sam9x60_pll_ready(struct regmap *regmap, int id)
 {
@@ -49,43 +60,53 @@ static inline bool sam9x60_pll_ready(struct regmap *regmap, int id)
 	return !!(status & BIT(id));
 }
 
-static int sam9x60_pll_prepare(struct clk_hw *hw)
+static bool sam9x60_frac_pll_ready(struct regmap *regmap, u8 id)
 {
-	struct sam9x60_pll *pll = to_sam9x60_pll(hw);
-	struct regmap *regmap = pll->regmap;
+	return sam9x60_pll_ready(regmap, id);
+}
+
+static unsigned long sam9x60_frac_pll_recalc_rate(struct clk_hw *hw,
+						  unsigned long parent_rate)
+{
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
+	struct sam9x60_frac *frac = to_sam9x60_frac(core);
+
+	return (parent_rate * (frac->mul + 1) +
+		((u64)parent_rate * frac->frac >> 22));
+}
+
+static int sam9x60_frac_pll_prepare(struct clk_hw *hw)
+{
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
+	struct sam9x60_frac *frac = to_sam9x60_frac(core);
+	struct regmap *regmap = core->regmap;
+	unsigned int val, cfrac, cmul;
 	unsigned long flags;
-	u8 div;
-	u16 mul;
-	u32 val, frac;
 
-	spin_lock_irqsave(pll->lock, flags);
-	regmap_write(regmap, AT91_PMC_PLL_UPDT, pll->id);
-
-	regmap_read(regmap, AT91_PMC_PLL_CTRL0, &val);
-	div = FIELD_GET(PMC_PLL_CTRL0_DIV_MSK, val);
+	spin_lock_irqsave(core->lock, flags);
 
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+			   AT91_PMC_PLL_UPDT_ID_MSK, core->id);
 	regmap_read(regmap, AT91_PMC_PLL_CTRL1, &val);
-	mul = FIELD_GET(PMC_PLL_CTRL1_MUL_MSK, val);
-	frac = FIELD_GET(PMC_PLL_CTRL1_FRACR_MSK, val);
+	cmul = (val & core->layout->mul_mask) >> core->layout->mul_shift;
+	cfrac = (val & core->layout->frac_mask) >> core->layout->frac_shift;
 
-	if (sam9x60_pll_ready(regmap, pll->id) &&
-	    (div == pll->div && mul == pll->mul && frac == pll->frac)) {
-		spin_unlock_irqrestore(pll->lock, flags);
-		return 0;
-	}
+	if (sam9x60_frac_pll_ready(regmap, core->id) &&
+	    (cmul == frac->mul && cfrac == frac->frac))
+		goto unlock;
 
-	/* Recommended value for AT91_PMC_PLL_ACR */
-	if (pll->characteristics->upll)
+	/* Recommended value for PMC_PLL_ACR */
+	if (core->characteristics->upll)
 		val = AT91_PMC_PLL_ACR_DEFAULT_UPLL;
 	else
 		val = AT91_PMC_PLL_ACR_DEFAULT_PLLA;
 	regmap_write(regmap, AT91_PMC_PLL_ACR, val);
 
 	regmap_write(regmap, AT91_PMC_PLL_CTRL1,
-		     FIELD_PREP(PMC_PLL_CTRL1_MUL_MSK, pll->mul) |
-		     FIELD_PREP(PMC_PLL_CTRL1_FRACR_MSK, pll->frac));
+		     (frac->mul << core->layout->mul_shift) |
+		     (frac->frac << core->layout->frac_shift));
 
-	if (pll->characteristics->upll) {
+	if (core->characteristics->upll) {
 		/* Enable the UTMI internal bandgap */
 		val |= AT91_PMC_PLL_ACR_UTMIBG;
 		regmap_write(regmap, AT91_PMC_PLL_ACR, val);
@@ -100,229 +121,409 @@ static int sam9x60_pll_prepare(struct clk_hw *hw)
 	}
 
 	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
-			   AT91_PMC_PLL_UPDT_UPDATE, AT91_PMC_PLL_UPDT_UPDATE);
+			   AT91_PMC_PLL_UPDT_UPDATE | AT91_PMC_PLL_UPDT_ID_MSK,
+			   AT91_PMC_PLL_UPDT_UPDATE | core->id);
 
-	regmap_write(regmap, AT91_PMC_PLL_CTRL0,
-		     AT91_PMC_PLL_CTRL0_ENLOCK | AT91_PMC_PLL_CTRL0_ENPLL |
-		     AT91_PMC_PLL_CTRL0_ENPLLCK | pll->div);
+	regmap_update_bits(regmap, AT91_PMC_PLL_CTRL0,
+			   AT91_PMC_PLL_CTRL0_ENLOCK | AT91_PMC_PLL_CTRL0_ENPLL,
+			   AT91_PMC_PLL_CTRL0_ENLOCK | AT91_PMC_PLL_CTRL0_ENPLL);
 
 	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
-			   AT91_PMC_PLL_UPDT_UPDATE, AT91_PMC_PLL_UPDT_UPDATE);
+			   AT91_PMC_PLL_UPDT_UPDATE | AT91_PMC_PLL_UPDT_ID_MSK,
+			   AT91_PMC_PLL_UPDT_UPDATE | core->id);
 
-	while (!sam9x60_pll_ready(regmap, pll->id))
+	while (!sam9x60_pll_ready(regmap, core->id))
 		cpu_relax();
 
-	spin_unlock_irqrestore(pll->lock, flags);
+unlock:
+	spin_unlock_irqrestore(core->lock, flags);
 
 	return 0;
 }
 
-static int sam9x60_pll_is_prepared(struct clk_hw *hw)
+static void sam9x60_frac_pll_unprepare(struct clk_hw *hw)
 {
-	struct sam9x60_pll *pll = to_sam9x60_pll(hw);
-
-	return sam9x60_pll_ready(pll->regmap, pll->id);
-}
-
-static void sam9x60_pll_unprepare(struct clk_hw *hw)
-{
-	struct sam9x60_pll *pll = to_sam9x60_pll(hw);
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
+	struct regmap *regmap = core->regmap;
 	unsigned long flags;
 
-	spin_lock_irqsave(pll->lock, flags);
+	spin_lock_irqsave(core->lock, flags);
 
-	regmap_write(pll->regmap, AT91_PMC_PLL_UPDT, pll->id);
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+			   AT91_PMC_PLL_UPDT_ID_MSK, core->id);
 
-	regmap_update_bits(pll->regmap, AT91_PMC_PLL_CTRL0,
-			   AT91_PMC_PLL_CTRL0_ENPLLCK, 0);
+	regmap_update_bits(regmap, AT91_PMC_PLL_CTRL0, AT91_PMC_PLL_CTRL0_ENPLL, 0);
 
-	regmap_update_bits(pll->regmap, AT91_PMC_PLL_UPDT,
-			   AT91_PMC_PLL_UPDT_UPDATE, AT91_PMC_PLL_UPDT_UPDATE);
+	if (core->characteristics->upll)
+		regmap_update_bits(regmap, AT91_PMC_PLL_ACR,
+				   AT91_PMC_PLL_ACR_UTMIBG | AT91_PMC_PLL_ACR_UTMIVR, 0);
 
-	regmap_update_bits(pll->regmap, AT91_PMC_PLL_CTRL0,
-			   AT91_PMC_PLL_CTRL0_ENPLL, 0);
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+			   AT91_PMC_PLL_UPDT_UPDATE | AT91_PMC_PLL_UPDT_ID_MSK,
+			   AT91_PMC_PLL_UPDT_UPDATE | core->id);
 
-	if (pll->characteristics->upll)
-		regmap_update_bits(pll->regmap, AT91_PMC_PLL_ACR,
-				   AT91_PMC_PLL_ACR_UTMIBG |
-				   AT91_PMC_PLL_ACR_UTMIVR, 0);
-
-	regmap_update_bits(pll->regmap, AT91_PMC_PLL_UPDT,
-			   AT91_PMC_PLL_UPDT_UPDATE, AT91_PMC_PLL_UPDT_UPDATE);
-
-	spin_unlock_irqrestore(pll->lock, flags);
+	spin_unlock_irqrestore(core->lock, flags);
 }
 
-static unsigned long sam9x60_pll_recalc_rate(struct clk_hw *hw,
-					     unsigned long parent_rate)
+static int sam9x60_frac_pll_is_prepared(struct clk_hw *hw)
 {
-	struct sam9x60_pll *pll = to_sam9x60_pll(hw);
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
 
-	return DIV_ROUND_CLOSEST_ULL((parent_rate * (pll->mul + 1) +
-		((u64)parent_rate * pll->frac >> 22)), (pll->div + 1));
+	return sam9x60_pll_ready(core->regmap, core->id);
 }
 
-static long sam9x60_pll_get_best_div_mul(struct sam9x60_pll *pll,
-					 unsigned long rate,
-					 unsigned long parent_rate,
-					 bool update)
+static long sam9x60_frac_pll_compute_mul_frac(struct sam9x60_pll_core *core,
+					      unsigned long rate,
+					      unsigned long parent_rate,
+					      bool update)
+{
+	struct sam9x60_frac *frac = to_sam9x60_frac(core);
+	unsigned long tmprate, remainder;
+	unsigned long nmul = 0;
+	unsigned long nfrac = 0;
+
+	if (rate < FCORE_MIN || rate > FCORE_MAX)
+		return -ERANGE;
+
+	/*
+	 * Calculate the multiplier associated with the current
+	 * divider that provide the closest rate to the requested one.
+	 */
+	nmul = mult_frac(rate, 1, parent_rate);
+	tmprate = mult_frac(parent_rate, nmul, 1);
+	remainder = rate - tmprate;
+
+	if (remainder) {
+		nfrac = DIV_ROUND_CLOSEST_ULL((u64)remainder * (1 << 22),
+					      parent_rate);
+
+		tmprate += DIV_ROUND_CLOSEST_ULL((u64)nfrac * parent_rate,
+						 (1 << 22));
+	}
+
+	/* Check if resulted rate is a valid.  */
+	if (tmprate < FCORE_MIN || tmprate > FCORE_MAX)
+		return -ERANGE;
+
+	if (update) {
+		frac->mul = nmul - 1;
+		frac->frac = nfrac;
+	}
+
+	return tmprate;
+}
+
+static long sam9x60_frac_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long *parent_rate)
+{
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
+
+	return sam9x60_frac_pll_compute_mul_frac(core, rate, *parent_rate, false);
+}
+
+static int sam9x60_frac_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long parent_rate)
+{
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
+
+	return sam9x60_frac_pll_compute_mul_frac(core, rate, parent_rate, true);
+}
+
+static const struct clk_ops sam9x60_frac_pll_ops = {
+	.prepare = sam9x60_frac_pll_prepare,
+	.unprepare = sam9x60_frac_pll_unprepare,
+	.is_prepared = sam9x60_frac_pll_is_prepared,
+	.recalc_rate = sam9x60_frac_pll_recalc_rate,
+	.round_rate = sam9x60_frac_pll_round_rate,
+	.set_rate = sam9x60_frac_pll_set_rate,
+};
+
+static int sam9x60_div_pll_prepare(struct clk_hw *hw)
+{
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
+	struct sam9x60_div *div = to_sam9x60_div(core);
+	struct regmap *regmap = core->regmap;
+	unsigned long flags;
+	unsigned int val, cdiv;
+
+	spin_lock_irqsave(core->lock, flags);
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+			   AT91_PMC_PLL_UPDT_ID_MSK, core->id);
+	regmap_read(regmap, AT91_PMC_PLL_CTRL0, &val);
+	cdiv = (val & core->layout->div_mask) >> core->layout->div_shift;
+
+	/* Stop if enabled an nothing changed. */
+	if (!!(val & core->layout->endiv_mask) && cdiv == div->div)
+		goto unlock;
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_CTRL0,
+			   core->layout->div_mask | core->layout->endiv_mask,
+			   (div->div << core->layout->div_shift) |
+			   (1 << core->layout->endiv_shift));
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+			   AT91_PMC_PLL_UPDT_UPDATE | AT91_PMC_PLL_UPDT_ID_MSK,
+			   AT91_PMC_PLL_UPDT_UPDATE | core->id);
+
+	while (!sam9x60_pll_ready(regmap, core->id))
+		cpu_relax();
+
+unlock:
+	spin_unlock_irqrestore(core->lock, flags);
+
+	return 0;
+}
+
+static void sam9x60_div_pll_unprepare(struct clk_hw *hw)
+{
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
+	struct regmap *regmap = core->regmap;
+	unsigned long flags;
+
+	spin_lock_irqsave(core->lock, flags);
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+			   AT91_PMC_PLL_UPDT_ID_MSK, core->id);
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_CTRL0,
+			   core->layout->endiv_mask, 0);
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+			   AT91_PMC_PLL_UPDT_UPDATE | AT91_PMC_PLL_UPDT_ID_MSK,
+			   AT91_PMC_PLL_UPDT_UPDATE | core->id);
+
+	spin_unlock_irqrestore(core->lock, flags);
+}
+
+static int sam9x60_div_pll_is_prepared(struct clk_hw *hw)
+{
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
+	struct regmap *regmap = core->regmap;
+	unsigned long flags;
+	unsigned int val;
+
+	spin_lock_irqsave(core->lock, flags);
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+			   AT91_PMC_PLL_UPDT_ID_MSK, core->id);
+	regmap_read(regmap, AT91_PMC_PLL_CTRL0, &val);
+
+	spin_unlock_irqrestore(core->lock, flags);
+
+	return !!(val & core->layout->endiv_mask);
+}
+
+static unsigned long sam9x60_div_pll_recalc_rate(struct clk_hw *hw,
+						 unsigned long parent_rate)
+{
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
+	struct sam9x60_div *div = to_sam9x60_div(core);
+
+	return DIV_ROUND_CLOSEST_ULL(parent_rate, (div->div + 1));
+}
+
+static long sam9x60_div_pll_compute_div(struct sam9x60_pll_core *core,
+					unsigned long *parent_rate,
+					unsigned long rate)
 {
 	const struct clk_pll_characteristics *characteristics =
-							pll->characteristics;
-	unsigned long bestremainder = ULONG_MAX;
-	unsigned long maxdiv, mindiv, tmpdiv;
-	long bestrate = -ERANGE;
-	unsigned long bestdiv = 0;
-	unsigned long bestmul = 0;
-	unsigned long bestfrac = 0;
-	u64 fcore = 0;
+							core->characteristics;
+	struct clk_hw *parent = clk_hw_get_parent(&core->hw);
+	unsigned long tmp_rate, tmp_parent_rate, tmp_diff;
+	long best_diff = -1, best_rate = -EINVAL;
+	u32 divid, best_div;
+
+	if (!rate)
+		return 0;
 
 	if (rate < characteristics->output[0].min ||
 	    rate > characteristics->output[0].max)
 		return -ERANGE;
 
-	if (!pll->characteristics->upll) {
-		mindiv = parent_rate / rate;
-		if (mindiv < 2)
-			mindiv = 2;
-
-		maxdiv = DIV_ROUND_UP(parent_rate * PLL_MUL_MAX, rate);
-		if (maxdiv > PLL_DIV_MAX)
-			maxdiv = PLL_DIV_MAX;
-	} else {
-		mindiv = maxdiv = UPLL_DIV;
-	}
-
-	for (tmpdiv = mindiv; tmpdiv <= maxdiv; tmpdiv++) {
-		unsigned long remainder;
-		unsigned long tmprate;
-		unsigned long tmpmul;
-		unsigned long tmpfrac = 0;
-
-		/*
-		 * Calculate the multiplier associated with the current
-		 * divider that provide the closest rate to the requested one.
-		 */
-		tmpmul = mult_frac(rate, tmpdiv, parent_rate);
-		tmprate = mult_frac(parent_rate, tmpmul, tmpdiv);
-		remainder = rate - tmprate;
-
-		if (remainder) {
-			tmpfrac = DIV_ROUND_CLOSEST_ULL((u64)remainder * tmpdiv * (1 << 22),
-							parent_rate);
-
-			tmprate += DIV_ROUND_CLOSEST_ULL((u64)tmpfrac * parent_rate,
-							 tmpdiv * (1 << 22));
-
-			if (tmprate > rate)
-				remainder = tmprate - rate;
-			else
-				remainder = rate - tmprate;
-		}
-
-		fcore = parent_rate * (tmpmul + 1) +
-			((u64)parent_rate * tmpfrac >> 22);
-		if (fcore < FCORE_MIN || fcore > FCORE_MAX)
+	for (divid = 1; divid < core->layout->div_mask; divid++) {
+		tmp_parent_rate = clk_hw_round_rate(parent, rate * divid);
+		if (!tmp_parent_rate)
 			continue;
 
-		/*
-		 * Compare the remainder with the best remainder found until
-		 * now and elect a new best multiplier/divider pair if the
-		 * current remainder is smaller than the best one.
-		 */
-		if (remainder < bestremainder) {
-			bestremainder = remainder;
-			bestdiv = tmpdiv;
-			bestmul = tmpmul;
-			bestrate = tmprate;
-			bestfrac = tmpfrac;
+		tmp_rate = DIV_ROUND_CLOSEST_ULL(tmp_parent_rate, divid);
+		tmp_diff = abs(rate - tmp_rate);
+
+		if (best_diff < 0 || best_diff > tmp_diff) {
+			*parent_rate = tmp_parent_rate;
+			best_rate = tmp_rate;
+			best_diff = tmp_diff;
+			best_div = divid;
 		}
 
-		/* We've found a perfect match!  */
-		if (!remainder)
+		if (!best_diff)
 			break;
 	}
 
-	/* Check if bestrate is a valid output rate  */
-	if (fcore < FCORE_MIN || fcore > FCORE_MAX ||
-	    bestrate < characteristics->output[0].min ||
-	    bestrate > characteristics->output[0].max)
+	if (best_rate < characteristics->output[0].min ||
+	    best_rate > characteristics->output[0].max)
 		return -ERANGE;
 
-	if (update) {
-		pll->div = bestdiv - 1;
-		pll->mul = bestmul - 1;
-		pll->frac = bestfrac;
-	}
-
-	return bestrate;
+	return best_rate;
 }
 
-static long sam9x60_pll_round_rate(struct clk_hw *hw, unsigned long rate,
-				   unsigned long *parent_rate)
+static long sam9x60_div_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+				       unsigned long *parent_rate)
 {
-	struct sam9x60_pll *pll = to_sam9x60_pll(hw);
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
 
-	return sam9x60_pll_get_best_div_mul(pll, rate, *parent_rate, false);
+	return sam9x60_div_pll_compute_div(core, parent_rate, rate);
 }
 
-static int sam9x60_pll_set_rate(struct clk_hw *hw, unsigned long rate,
-				unsigned long parent_rate)
+static int sam9x60_div_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long parent_rate)
 {
-	struct sam9x60_pll *pll = to_sam9x60_pll(hw);
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
+	struct sam9x60_div *div = to_sam9x60_div(core);
 
-	return sam9x60_pll_get_best_div_mul(pll, rate, parent_rate, true);
+	div->div = DIV_ROUND_CLOSEST(parent_rate, rate) - 1;
+
+	return 0;
 }
 
-static const struct clk_ops pll_ops = {
-	.prepare = sam9x60_pll_prepare,
-	.unprepare = sam9x60_pll_unprepare,
-	.is_prepared = sam9x60_pll_is_prepared,
-	.recalc_rate = sam9x60_pll_recalc_rate,
-	.round_rate = sam9x60_pll_round_rate,
-	.set_rate = sam9x60_pll_set_rate,
+static const struct clk_ops sam9x60_div_pll_ops = {
+	.prepare = sam9x60_div_pll_prepare,
+	.unprepare = sam9x60_div_pll_unprepare,
+	.is_prepared = sam9x60_div_pll_is_prepared,
+	.recalc_rate = sam9x60_div_pll_recalc_rate,
+	.round_rate = sam9x60_div_pll_round_rate,
+	.set_rate = sam9x60_div_pll_set_rate,
 };
 
 struct clk_hw * __init
-sam9x60_clk_register_pll(struct regmap *regmap, spinlock_t *lock,
-			 const char *name, const char *parent_name, u8 id,
-			 const struct clk_pll_characteristics *characteristics)
+sam9x60_clk_register_frac_pll(struct regmap *regmap, spinlock_t *lock,
+			      const char *name, const char *parent_name,
+			      struct clk_hw *parent_hw, u8 id,
+			      const struct clk_pll_characteristics *characteristics,
+			      const struct clk_pll_layout *layout, bool critical)
 {
-	struct sam9x60_pll *pll;
+	struct sam9x60_frac *frac;
 	struct clk_hw *hw;
 	struct clk_init_data init;
-	unsigned int pllr;
+	unsigned long parent_rate, flags;
+	unsigned int val;
 	int ret;
 
-	if (id > PLL_MAX_ID)
+	if (id > PLL_MAX_ID || !lock || !parent_hw)
 		return ERR_PTR(-EINVAL);
 
-	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
-	if (!pll)
+	frac = kzalloc(sizeof(*frac), GFP_KERNEL);
+	if (!frac)
 		return ERR_PTR(-ENOMEM);
 
 	init.name = name;
-	init.ops = &pll_ops;
 	init.parent_names = &parent_name;
 	init.num_parents = 1;
+	init.ops = &sam9x60_frac_pll_ops;
 	init.flags = CLK_SET_RATE_GATE;
+	if (critical)
+		init.flags |= CLK_IS_CRITICAL;
 
-	pll->id = id;
-	pll->hw.init = &init;
-	pll->characteristics = characteristics;
-	pll->regmap = regmap;
-	pll->lock = lock;
+	frac->core.id = id;
+	frac->core.hw.init = &init;
+	frac->core.characteristics = characteristics;
+	frac->core.layout = layout;
+	frac->core.regmap = regmap;
+	frac->core.lock = lock;
 
-	regmap_write(regmap, AT91_PMC_PLL_UPDT, id);
-	regmap_read(regmap, AT91_PMC_PLL_CTRL0, &pllr);
-	pll->div = FIELD_GET(PMC_PLL_CTRL0_DIV_MSK, pllr);
-	regmap_read(regmap, AT91_PMC_PLL_CTRL1, &pllr);
-	pll->mul = FIELD_GET(PMC_PLL_CTRL1_MUL_MSK, pllr);
+	spin_lock_irqsave(frac->core.lock, flags);
+	if (sam9x60_pll_ready(regmap, id)) {
+		regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+				   AT91_PMC_PLL_UPDT_ID_MSK, id);
+		regmap_read(regmap, AT91_PMC_PLL_CTRL1, &val);
+		frac->mul = FIELD_GET(PMC_PLL_CTRL1_MUL_MSK, val);
+		frac->frac = FIELD_GET(PMC_PLL_CTRL1_FRACR_MSK, val);
+	} else {
+		/*
+		 * This means the PLL is not setup by bootloaders. In this
+		 * case we need to set the minimum rate for it. Otherwise
+		 * a clock child of this PLL may be enabled before setting
+		 * its rate leading to enabling this PLL with unsupported
+		 * rate. This will lead to PLL not being locked at all.
+		 */
+		parent_rate = clk_hw_get_rate(parent_hw);
+		if (!parent_rate) {
+			hw = ERR_PTR(-EINVAL);
+			goto free;
+		}
 
-	hw = &pll->hw;
+		ret = sam9x60_frac_pll_compute_mul_frac(&frac->core, FCORE_MIN,
+							parent_rate, true);
+		if (ret <= 0) {
+			hw = ERR_PTR(ret);
+			goto free;
+		}
+	}
+	spin_unlock_irqrestore(frac->core.lock, flags);
+
+	hw = &frac->core.hw;
 	ret = clk_hw_register(NULL, hw);
 	if (ret) {
-		kfree(pll);
+		kfree(frac);
+		hw = ERR_PTR(ret);
+	}
+
+	return hw;
+
+free:
+	spin_unlock_irqrestore(frac->core.lock, flags);
+	kfree(frac);
+	return hw;
+}
+
+struct clk_hw * __init
+sam9x60_clk_register_div_pll(struct regmap *regmap, spinlock_t *lock,
+			     const char *name, const char *parent_name, u8 id,
+			     const struct clk_pll_characteristics *characteristics,
+			     const struct clk_pll_layout *layout, bool critical)
+{
+	struct sam9x60_div *div;
+	struct clk_hw *hw;
+	struct clk_init_data init;
+	unsigned long flags;
+	unsigned int val;
+	int ret;
+
+	if (id > PLL_MAX_ID || !lock)
+		return ERR_PTR(-EINVAL);
+
+	div = kzalloc(sizeof(*div), GFP_KERNEL);
+	if (!div)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+	init.ops = &sam9x60_div_pll_ops;
+	init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE |
+		     CLK_SET_RATE_PARENT;
+	if (critical)
+		init.flags |= CLK_IS_CRITICAL;
+
+	div->core.id = id;
+	div->core.hw.init = &init;
+	div->core.characteristics = characteristics;
+	div->core.layout = layout;
+	div->core.regmap = regmap;
+	div->core.lock = lock;
+
+	spin_lock_irqsave(div->core.lock, flags);
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+			   AT91_PMC_PLL_UPDT_ID_MSK, id);
+	regmap_read(regmap, AT91_PMC_PLL_CTRL0, &val);
+	div->div = FIELD_GET(PMC_PLL_CTRL0_DIV_MSK, val);
+
+	spin_unlock_irqrestore(div->core.lock, flags);
+
+	hw = &div->core.hw;
+	ret = clk_hw_register(NULL, hw);
+	if (ret) {
+		kfree(div);
 		hw = ERR_PTR(ret);
 	}
 
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 8d3e22f566cf..6340b9be8205 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -54,8 +54,14 @@ struct clk_master_characteristics {
 
 struct clk_pll_layout {
 	u32 pllr_mask;
-	u16 mul_mask;
+	u32 mul_mask;
+	u32 frac_mask;
+	u32 div_mask;
+	u32 endiv_mask;
 	u8 mul_shift;
+	u8 frac_shift;
+	u8 div_shift;
+	u8 endiv_shift;
 };
 
 extern const struct clk_pll_layout at91rm9200_pll_layout;
@@ -181,9 +187,17 @@ at91_clk_register_plldiv(struct regmap *regmap, const char *name,
 			 const char *parent_name);
 
 struct clk_hw * __init
-sam9x60_clk_register_pll(struct regmap *regmap, spinlock_t *lock,
-			 const char *name, const char *parent_name, u8 id,
-			 const struct clk_pll_characteristics *characteristics);
+sam9x60_clk_register_div_pll(struct regmap *regmap, spinlock_t *lock,
+			     const char *name, const char *parent_name, u8 id,
+			     const struct clk_pll_characteristics *characteristics,
+			     const struct clk_pll_layout *layout, bool critical);
+
+struct clk_hw * __init
+sam9x60_clk_register_frac_pll(struct regmap *regmap, spinlock_t *lock,
+			      const char *name, const char *parent_name,
+			      struct clk_hw *parent_hw, u8 id,
+			      const struct clk_pll_characteristics *characteristics,
+			      const struct clk_pll_layout *layout, bool critical);
 
 struct clk_hw * __init
 at91_clk_register_programmable(struct regmap *regmap, const char *name,
diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index d8d4b28ec4cb..ab6318c0589e 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -42,6 +42,20 @@ static const struct clk_pll_characteristics upll_characteristics = {
 	.upll = true,
 };
 
+static const struct clk_pll_layout pll_frac_layout = {
+	.mul_mask = GENMASK(31, 24),
+	.frac_mask = GENMASK(21, 0),
+	.mul_shift = 24,
+	.frac_shift = 0,
+};
+
+static const struct clk_pll_layout pll_div_layout = {
+	.div_mask = GENMASK(7, 0),
+	.endiv_mask = BIT(29),
+	.div_shift = 0,
+	.endiv_shift = 29,
+};
+
 static const struct clk_programmable_layout sam9x60_programmable_layout = {
 	.pres_mask = 0xff,
 	.pres_shift = 8,
@@ -156,6 +170,7 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 	const char *td_slck_name, *md_slck_name, *mainxtal_name;
 	struct pmc_data *sam9x60_pmc;
 	const char *parent_names[6];
+	struct clk_hw *main_osc_hw;
 	struct regmap *regmap;
 	struct clk_hw *hw;
 	int i;
@@ -200,6 +215,7 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 					bypass);
 	if (IS_ERR(hw))
 		goto err_free;
+	main_osc_hw = hw;
 
 	parent_names[0] = "main_rc_osc";
 	parent_names[1] = "main_osc";
@@ -209,15 +225,31 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 
 	sam9x60_pmc->chws[PMC_MAIN] = hw;
 
-	hw = sam9x60_clk_register_pll(regmap, &pmc_pll_lock, "pllack",
-				      "mainck", 0, &plla_characteristics);
+	hw = sam9x60_clk_register_frac_pll(regmap, &pmc_pll_lock, "pllack_fracck",
+					   "mainck", sam9x60_pmc->chws[PMC_MAIN],
+					   0, &plla_characteristics,
+					   &pll_frac_layout, true);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	hw = sam9x60_clk_register_div_pll(regmap, &pmc_pll_lock, "pllack_divck",
+					  "pllack_fracck", 0, &plla_characteristics,
+					  &pll_div_layout, true);
 	if (IS_ERR(hw))
 		goto err_free;
 
 	sam9x60_pmc->chws[PMC_PLLACK] = hw;
 
-	hw = sam9x60_clk_register_pll(regmap, &pmc_pll_lock, "upllck",
-				      "main_osc", 1, &upll_characteristics);
+	hw = sam9x60_clk_register_frac_pll(regmap, &pmc_pll_lock, "upllck_fracck",
+					   "main_osc", main_osc_hw, 1,
+					   &upll_characteristics,
+					   &pll_frac_layout, false);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	hw = sam9x60_clk_register_div_pll(regmap, &pmc_pll_lock, "upllck_divck",
+					  "upllck_fracck", 1, &upll_characteristics,
+					  &pll_div_layout, false);
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -225,7 +257,7 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 
 	parent_names[0] = md_slck_name;
 	parent_names[1] = "mainck";
-	parent_names[2] = "pllack";
+	parent_names[2] = "pllack_divck";
 	hw = at91_clk_register_master(regmap, "masterck", 3, parent_names,
 				      &sam9x60_master_layout,
 				      &mck_characteristics);
@@ -234,8 +266,8 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 
 	sam9x60_pmc->chws[PMC_MCK] = hw;
 
-	parent_names[0] = "pllack";
-	parent_names[1] = "upllck";
+	parent_names[0] = "pllack_divck";
+	parent_names[1] = "upllck_divck";
 	parent_names[2] = "main_osc";
 	hw = sam9x60_clk_register_usb(regmap, "usbck", parent_names, 3);
 	if (IS_ERR(hw))
@@ -245,8 +277,8 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 	parent_names[1] = td_slck_name;
 	parent_names[2] = "mainck";
 	parent_names[3] = "masterck";
-	parent_names[4] = "pllack";
-	parent_names[5] = "upllck";
+	parent_names[4] = "pllack_divck";
+	parent_names[5] = "upllck_divck";
 	for (i = 0; i < 8; i++) {
 		char name[6];
 

From ef396df99251b848596c717b63ff4fe74a941193 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:25 +0300
Subject: [PATCH 115/474] clk: at91: clk-utmi: add utmi support for sama7g5

Add UTMI support for SAMA7G5. SAMA7G5's UTMI control is done via
XTALF register. Values written at bits 2..0 in this register
correspond to the on board crystal oscillator frequency.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-18-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/clk-utmi.c  | 103 +++++++++++++++++++++++++++++++++--
 drivers/clk/at91/pmc.h       |   4 ++
 include/linux/clk/at91_pmc.h |   2 +
 3 files changed, 104 insertions(+), 5 deletions(-)

diff --git a/drivers/clk/at91/clk-utmi.c b/drivers/clk/at91/clk-utmi.c
index f1ef4e1f41a9..df9f3fc3b6a6 100644
--- a/drivers/clk/at91/clk-utmi.c
+++ b/drivers/clk/at91/clk-utmi.c
@@ -120,9 +120,11 @@ static const struct clk_ops utmi_ops = {
 	.recalc_rate = clk_utmi_recalc_rate,
 };
 
-struct clk_hw * __init
-at91_clk_register_utmi(struct regmap *regmap_pmc, struct regmap *regmap_sfr,
-		       const char *name, const char *parent_name)
+static struct clk_hw * __init
+at91_clk_register_utmi_internal(struct regmap *regmap_pmc,
+				struct regmap *regmap_sfr,
+				const char *name, const char *parent_name,
+				const struct clk_ops *ops, unsigned long flags)
 {
 	struct clk_utmi *utmi;
 	struct clk_hw *hw;
@@ -134,10 +136,10 @@ at91_clk_register_utmi(struct regmap *regmap_pmc, struct regmap *regmap_sfr,
 		return ERR_PTR(-ENOMEM);
 
 	init.name = name;
-	init.ops = &utmi_ops;
+	init.ops = ops;
 	init.parent_names = parent_name ? &parent_name : NULL;
 	init.num_parents = parent_name ? 1 : 0;
-	init.flags = CLK_SET_RATE_GATE;
+	init.flags = flags;
 
 	utmi->hw.init = &init;
 	utmi->regmap_pmc = regmap_pmc;
@@ -152,3 +154,94 @@ at91_clk_register_utmi(struct regmap *regmap_pmc, struct regmap *regmap_sfr,
 
 	return hw;
 }
+
+struct clk_hw * __init
+at91_clk_register_utmi(struct regmap *regmap_pmc, struct regmap *regmap_sfr,
+		       const char *name, const char *parent_name)
+{
+	return at91_clk_register_utmi_internal(regmap_pmc, regmap_sfr, name,
+			parent_name, &utmi_ops, CLK_SET_RATE_GATE);
+}
+
+static int clk_utmi_sama7g5_prepare(struct clk_hw *hw)
+{
+	struct clk_utmi *utmi = to_clk_utmi(hw);
+	struct clk_hw *hw_parent;
+	unsigned long parent_rate;
+	unsigned int val;
+
+	hw_parent = clk_hw_get_parent(hw);
+	parent_rate = clk_hw_get_rate(hw_parent);
+
+	switch (parent_rate) {
+	case 16000000:
+		val = 0;
+		break;
+	case 20000000:
+		val = 2;
+		break;
+	case 24000000:
+		val = 3;
+		break;
+	case 32000000:
+		val = 5;
+		break;
+	default:
+		pr_err("UTMICK: unsupported main_xtal rate\n");
+		return -EINVAL;
+	}
+
+	regmap_write(utmi->regmap_pmc, AT91_PMC_XTALF, val);
+
+	return 0;
+
+}
+
+static int clk_utmi_sama7g5_is_prepared(struct clk_hw *hw)
+{
+	struct clk_utmi *utmi = to_clk_utmi(hw);
+	struct clk_hw *hw_parent;
+	unsigned long parent_rate;
+	unsigned int val;
+
+	hw_parent = clk_hw_get_parent(hw);
+	parent_rate = clk_hw_get_rate(hw_parent);
+
+	regmap_read(utmi->regmap_pmc, AT91_PMC_XTALF, &val);
+	switch (val & 0x7) {
+	case 0:
+		if (parent_rate == 16000000)
+			return 1;
+		break;
+	case 2:
+		if (parent_rate == 20000000)
+			return 1;
+		break;
+	case 3:
+		if (parent_rate == 24000000)
+			return 1;
+		break;
+	case 5:
+		if (parent_rate == 32000000)
+			return 1;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static const struct clk_ops sama7g5_utmi_ops = {
+	.prepare = clk_utmi_sama7g5_prepare,
+	.is_prepared = clk_utmi_sama7g5_is_prepared,
+	.recalc_rate = clk_utmi_recalc_rate,
+};
+
+struct clk_hw * __init
+at91_clk_sama7g5_register_utmi(struct regmap *regmap_pmc, const char *name,
+			       const char *parent_name)
+{
+	return at91_clk_register_utmi_internal(regmap_pmc, NULL, name,
+			parent_name, &sama7g5_utmi_ops, 0);
+}
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 6340b9be8205..7b86affc6d7c 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -236,6 +236,10 @@ struct clk_hw * __init
 at91_clk_register_utmi(struct regmap *regmap_pmc, struct regmap *regmap_sfr,
 		       const char *name, const char *parent_name);
 
+struct clk_hw * __init
+at91_clk_sama7g5_register_utmi(struct regmap *regmap, const char *name,
+			       const char *parent_name);
+
 #ifdef CONFIG_PM
 void pmc_register_id(u8 id);
 void pmc_register_pck(u8 pck);
diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h
index dc5e85f124e0..a4f82e836a7c 100644
--- a/include/linux/clk/at91_pmc.h
+++ b/include/linux/clk/at91_pmc.h
@@ -137,6 +137,8 @@
 #define			AT91_PMC_PLLADIV2_ON		(1 << 12)
 #define		AT91_PMC_H32MXDIV	BIT(24)
 
+#define AT91_PMC_XTALF		0x34			/* Main XTAL Frequency Register [SAMA7G5 only] */
+
 #define	AT91_PMC_USB		0x38			/* USB Clock Register [some SAM9 only] */
 #define		AT91_PMC_USBS		(0x1 <<  0)		/* USB OHCI Input clock selection */
 #define			AT91_PMC_USBS_PLLA		(0 << 0)

From cb783bbbcf54c36256006895c215e86c5e7266d8 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 22 Jul 2020 10:38:26 +0300
Subject: [PATCH 116/474] clk: at91: sama7g5: add clock support for sama7g5

Add clock support for SAMA7G5.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/1595403506-8209-19-git-send-email-claudiu.beznea@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/at91/Makefile  |    1 +
 drivers/clk/at91/sama7g5.c | 1059 ++++++++++++++++++++++++++++++++++++
 2 files changed, 1060 insertions(+)
 create mode 100644 drivers/clk/at91/sama7g5.c

diff --git a/drivers/clk/at91/Makefile b/drivers/clk/at91/Makefile
index 8b90357f2a93..79301e1c1c36 100644
--- a/drivers/clk/at91/Makefile
+++ b/drivers/clk/at91/Makefile
@@ -23,3 +23,4 @@ obj-$(CONFIG_SOC_SAM9X60) += sam9x60.o
 obj-$(CONFIG_SOC_SAMA5D3) += sama5d3.o
 obj-$(CONFIG_SOC_SAMA5D4) += sama5d4.o
 obj-$(CONFIG_SOC_SAMA5D2) += sama5d2.o
+obj-$(CONFIG_SOC_SAMA7G5) += sama7g5.o
diff --git a/drivers/clk/at91/sama7g5.c b/drivers/clk/at91/sama7g5.c
new file mode 100644
index 000000000000..0db2ab3eca14
--- /dev/null
+++ b/drivers/clk/at91/sama7g5.c
@@ -0,0 +1,1059 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SAMA7G5 PMC code.
+ *
+ * Copyright (C) 2020 Microchip Technology Inc. and its subsidiaries
+ *
+ * Author: Claudiu Beznea <claudiu.beznea@microchip.com>
+ *
+ */
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/mfd/syscon.h>
+#include <linux/slab.h>
+
+#include <dt-bindings/clock/at91.h>
+
+#include "pmc.h"
+
+#define SAMA7G5_INIT_TABLE(_table, _count)		\
+	do {						\
+		u8 _i;					\
+		for (_i = 0; _i < (_count); _i++)	\
+			(_table)[_i] = _i;		\
+	} while (0)
+
+#define SAMA7G5_FILL_TABLE(_to, _from, _count)		\
+	do {						\
+		u8 _i;					\
+		for (_i = 0; _i < (_count); _i++) {	\
+			(_to)[_i] = (_from)[_i];	\
+		}					\
+	} while (0)
+
+static DEFINE_SPINLOCK(pmc_pll_lock);
+static DEFINE_SPINLOCK(pmc_mckX_lock);
+
+/**
+ * PLL clocks identifiers
+ * @PLL_ID_CPU:		CPU PLL identifier
+ * @PLL_ID_SYS:		System PLL identifier
+ * @PLL_ID_DDR:		DDR PLL identifier
+ * @PLL_ID_IMG:		Image subsystem PLL identifier
+ * @PLL_ID_BAUD:	Baud PLL identifier
+ * @PLL_ID_AUDIO:	Audio PLL identifier
+ * @PLL_ID_ETH:		Ethernet PLL identifier
+ */
+enum pll_ids {
+	PLL_ID_CPU,
+	PLL_ID_SYS,
+	PLL_ID_DDR,
+	PLL_ID_IMG,
+	PLL_ID_BAUD,
+	PLL_ID_AUDIO,
+	PLL_ID_ETH,
+	PLL_ID_MAX,
+};
+
+/**
+ * PLL type identifiers
+ * @PLL_TYPE_FRAC:	fractional PLL identifier
+ * @PLL_TYPE_DIV:	divider PLL identifier
+ */
+enum pll_type {
+	PLL_TYPE_FRAC,
+	PLL_TYPE_DIV,
+};
+
+/* Layout for fractional PLLs. */
+static const struct clk_pll_layout pll_layout_frac = {
+	.mul_mask	= GENMASK(31, 24),
+	.frac_mask	= GENMASK(21, 0),
+	.mul_shift	= 24,
+	.frac_shift	= 0,
+};
+
+/* Layout for DIVPMC dividers. */
+static const struct clk_pll_layout pll_layout_divpmc = {
+	.div_mask	= GENMASK(7, 0),
+	.endiv_mask	= BIT(29),
+	.div_shift	= 0,
+	.endiv_shift	= 29,
+};
+
+/* Layout for DIVIO dividers. */
+static const struct clk_pll_layout pll_layout_divio = {
+	.div_mask	= GENMASK(19, 12),
+	.endiv_mask	= BIT(30),
+	.div_shift	= 12,
+	.endiv_shift	= 30,
+};
+
+/**
+ * PLL clocks description
+ * @n:		clock name
+ * @p:		clock parent
+ * @l:		clock layout
+ * @t:		clock type
+ * @f:		true if clock is critical and cannot be disabled
+ * @eid:	export index in sama7g5->chws[] array
+ */
+static const struct {
+	const char *n;
+	const char *p;
+	const struct clk_pll_layout *l;
+	u8 t;
+	u8 c;
+	u8 eid;
+} sama7g5_plls[][PLL_ID_MAX] = {
+	[PLL_ID_CPU] = {
+		{ .n = "cpupll_fracck",
+		  .p = "mainck",
+		  .l = &pll_layout_frac,
+		  .t = PLL_TYPE_FRAC,
+		  .c = 1, },
+
+		{ .n = "cpupll_divpmcck",
+		  .p = "cpupll_fracck",
+		  .l = &pll_layout_divpmc,
+		  .t = PLL_TYPE_DIV,
+		  .c = 1, },
+	},
+
+	[PLL_ID_SYS] = {
+		{ .n = "syspll_fracck",
+		  .p = "mainck",
+		  .l = &pll_layout_frac,
+		  .t = PLL_TYPE_FRAC,
+		  .c = 1, },
+
+		{ .n = "syspll_divpmcck",
+		  .p = "syspll_fracck",
+		  .l = &pll_layout_divpmc,
+		  .t = PLL_TYPE_DIV,
+		  .c = 1, },
+	},
+
+	[PLL_ID_DDR] = {
+		{ .n = "ddrpll_fracck",
+		  .p = "mainck",
+		  .l = &pll_layout_frac,
+		  .t = PLL_TYPE_FRAC,
+		  .c = 1, },
+
+		{ .n = "ddrpll_divpmcck",
+		  .p = "ddrpll_fracck",
+		  .l = &pll_layout_divpmc,
+		  .t = PLL_TYPE_DIV,
+		  .c = 1, },
+	},
+
+	[PLL_ID_IMG] = {
+		{ .n = "imgpll_fracck",
+		  .p = "mainck",
+		  .l = &pll_layout_frac,
+		  .t = PLL_TYPE_FRAC, },
+
+		{ .n = "imgpll_divpmcck",
+		  .p = "imgpll_fracck",
+		  .l = &pll_layout_divpmc,
+		  .t = PLL_TYPE_DIV, },
+	},
+
+	[PLL_ID_BAUD] = {
+		{ .n = "baudpll_fracck",
+		  .p = "mainck",
+		  .l = &pll_layout_frac,
+		  .t = PLL_TYPE_FRAC, },
+
+		{ .n = "baudpll_divpmcck",
+		  .p = "baudpll_fracck",
+		  .l = &pll_layout_divpmc,
+		  .t = PLL_TYPE_DIV, },
+	},
+
+	[PLL_ID_AUDIO] = {
+		{ .n = "audiopll_fracck",
+		  .p = "main_xtal",
+		  .l = &pll_layout_frac,
+		  .t = PLL_TYPE_FRAC, },
+
+		{ .n = "audiopll_divpmcck",
+		  .p = "audiopll_fracck",
+		  .l = &pll_layout_divpmc,
+		  .t = PLL_TYPE_DIV,
+		  .eid = PMC_I2S0_MUX, },
+
+		{ .n = "audiopll_diviock",
+		  .p = "audiopll_fracck",
+		  .l = &pll_layout_divio,
+		  .t = PLL_TYPE_DIV,
+		  .eid = PMC_I2S1_MUX, },
+	},
+
+	[PLL_ID_ETH] = {
+		{ .n = "ethpll_fracck",
+		  .p = "main_xtal",
+		  .l = &pll_layout_frac,
+		  .t = PLL_TYPE_FRAC, },
+
+		{ .n = "ethpll_divpmcck",
+		  .p = "ethpll_fracck",
+		  .l = &pll_layout_divpmc,
+		  .t = PLL_TYPE_DIV, },
+	},
+};
+
+/**
+ * Master clock (MCK[1..4]) description
+ * @n:			clock name
+ * @ep:			extra parents names array
+ * @ep_chg_chg_id:	index in parents array that specifies the changeable
+ *			parent
+ * @ep_count:		extra parents count
+ * @ep_mux_table:	mux table for extra parents
+ * @id:			clock id
+ * @c:			true if clock is critical and cannot be disabled
+ */
+static const struct {
+	const char *n;
+	const char *ep[4];
+	int ep_chg_id;
+	u8 ep_count;
+	u8 ep_mux_table[4];
+	u8 id;
+	u8 c;
+} sama7g5_mckx[] = {
+	{ .n = "mck1",
+	  .id = 1,
+	  .ep = { "syspll_divpmcck", },
+	  .ep_mux_table = { 5, },
+	  .ep_count = 1,
+	  .ep_chg_id = INT_MIN,
+	  .c = 1, },
+
+	{ .n = "mck2",
+	  .id = 2,
+	  .ep = { "ddrpll_divpmcck", },
+	  .ep_mux_table = { 6, },
+	  .ep_count = 1,
+	  .ep_chg_id = INT_MIN,
+	  .c = 1, },
+
+	{ .n = "mck3",
+	  .id = 3,
+	  .ep = { "syspll_divpmcck", "ddrpll_divpmcck", "imgpll_divpmcck", },
+	  .ep_mux_table = { 5, 6, 7, },
+	  .ep_count = 3,
+	  .ep_chg_id = 6, },
+
+	{ .n = "mck4",
+	  .id = 4,
+	  .ep = { "syspll_divpmcck", },
+	  .ep_mux_table = { 5, },
+	  .ep_count = 1,
+	  .ep_chg_id = INT_MIN,
+	  .c = 1, },
+};
+
+/**
+ * System clock description
+ * @n:	clock name
+ * @p:	clock parent name
+ * @id: clock id
+ */
+static const struct {
+	const char *n;
+	const char *p;
+	u8 id;
+} sama7g5_systemck[] = {
+	{ .n = "pck0",		.p = "prog0", .id = 8, },
+	{ .n = "pck1",		.p = "prog1", .id = 9, },
+	{ .n = "pck2",		.p = "prog2", .id = 10, },
+	{ .n = "pck3",		.p = "prog3", .id = 11, },
+	{ .n = "pck4",		.p = "prog4", .id = 12, },
+	{ .n = "pck5",		.p = "prog5", .id = 13, },
+	{ .n = "pck6",		.p = "prog6", .id = 14, },
+	{ .n = "pck7",		.p = "prog7", .id = 15, },
+};
+
+/* Mux table for programmable clocks. */
+static u32 sama7g5_prog_mux_table[] = { 0, 1, 2, 3, 5, 6, 7, 8, 9, 10, };
+
+/**
+ * Peripheral clock description
+ * @n:		clock name
+ * @p:		clock parent name
+ * @r:		clock range values
+ * @id:		clock id
+ * @chgp:	index in parent array of the changeable parent
+ */
+static const struct {
+	const char *n;
+	const char *p;
+	struct clk_range r;
+	u8 chgp;
+	u8 id;
+} sama7g5_periphck[] = {
+	{ .n = "pioA_clk",	.p = "mck0", .id = 11, },
+	{ .n = "sfr_clk",	.p = "mck1", .id = 19, },
+	{ .n = "hsmc_clk",	.p = "mck1", .id = 21, },
+	{ .n = "xdmac0_clk",	.p = "mck1", .id = 22, },
+	{ .n = "xdmac1_clk",	.p = "mck1", .id = 23, },
+	{ .n = "xdmac2_clk",	.p = "mck1", .id = 24, },
+	{ .n = "acc_clk",	.p = "mck1", .id = 25, },
+	{ .n = "aes_clk",	.p = "mck1", .id = 27, },
+	{ .n = "tzaesbasc_clk",	.p = "mck1", .id = 28, },
+	{ .n = "asrc_clk",	.p = "mck1", .id = 30, .r = { .max = 200000000, }, },
+	{ .n = "cpkcc_clk",	.p = "mck0", .id = 32, },
+	{ .n = "csi_clk",	.p = "mck3", .id = 33, .r = { .max = 266000000, }, .chgp = 1, },
+	{ .n = "csi2dc_clk",	.p = "mck3", .id = 34, .r = { .max = 266000000, }, .chgp = 1, },
+	{ .n = "eic_clk",	.p = "mck1", .id = 37, },
+	{ .n = "flex0_clk",	.p = "mck1", .id = 38, },
+	{ .n = "flex1_clk",	.p = "mck1", .id = 39, },
+	{ .n = "flex2_clk",	.p = "mck1", .id = 40, },
+	{ .n = "flex3_clk",	.p = "mck1", .id = 41, },
+	{ .n = "flex4_clk",	.p = "mck1", .id = 42, },
+	{ .n = "flex5_clk",	.p = "mck1", .id = 43, },
+	{ .n = "flex6_clk",	.p = "mck1", .id = 44, },
+	{ .n = "flex7_clk",	.p = "mck1", .id = 45, },
+	{ .n = "flex8_clk",	.p = "mck1", .id = 46, },
+	{ .n = "flex9_clk",	.p = "mck1", .id = 47, },
+	{ .n = "flex10_clk",	.p = "mck1", .id = 48, },
+	{ .n = "flex11_clk",	.p = "mck1", .id = 49, },
+	{ .n = "gmac0_clk",	.p = "mck1", .id = 51, },
+	{ .n = "gmac1_clk",	.p = "mck1", .id = 52, },
+	{ .n = "icm_clk",	.p = "mck1", .id = 55, },
+	{ .n = "isc_clk",	.p = "mck3", .id = 56, .r = { .max = 266000000, }, .chgp = 1, },
+	{ .n = "i2smcc0_clk",	.p = "mck1", .id = 57, .r = { .max = 200000000, }, },
+	{ .n = "i2smcc1_clk",	.p = "mck1", .id = 58, .r = { .max = 200000000, }, },
+	{ .n = "matrix_clk",	.p = "mck1", .id = 60, },
+	{ .n = "mcan0_clk",	.p = "mck1", .id = 61, .r = { .max = 200000000, }, },
+	{ .n = "mcan1_clk",	.p = "mck1", .id = 62, .r = { .max = 200000000, }, },
+	{ .n = "mcan2_clk",	.p = "mck1", .id = 63, .r = { .max = 200000000, }, },
+	{ .n = "mcan3_clk",	.p = "mck1", .id = 64, .r = { .max = 200000000, }, },
+	{ .n = "mcan4_clk",	.p = "mck1", .id = 65, .r = { .max = 200000000, }, },
+	{ .n = "mcan5_clk",	.p = "mck1", .id = 66, .r = { .max = 200000000, }, },
+	{ .n = "pdmc0_clk",	.p = "mck1", .id = 68, .r = { .max = 200000000, }, },
+	{ .n = "pdmc1_clk",	.p = "mck1", .id = 69, .r = { .max = 200000000, }, },
+	{ .n = "pit64b0_clk",	.p = "mck1", .id = 70, },
+	{ .n = "pit64b1_clk",	.p = "mck1", .id = 71, },
+	{ .n = "pit64b2_clk",	.p = "mck1", .id = 72, },
+	{ .n = "pit64b3_clk",	.p = "mck1", .id = 73, },
+	{ .n = "pit64b4_clk",	.p = "mck1", .id = 74, },
+	{ .n = "pit64b5_clk",	.p = "mck1", .id = 75, },
+	{ .n = "pwm_clk",	.p = "mck1", .id = 77, },
+	{ .n = "qspi0_clk",	.p = "mck1", .id = 78, },
+	{ .n = "qspi1_clk",	.p = "mck1", .id = 79, },
+	{ .n = "sdmmc0_clk",	.p = "mck1", .id = 80, },
+	{ .n = "sdmmc1_clk",	.p = "mck1", .id = 81, },
+	{ .n = "sdmmc2_clk",	.p = "mck1", .id = 82, },
+	{ .n = "sha_clk",	.p = "mck1", .id = 83, },
+	{ .n = "spdifrx_clk",	.p = "mck1", .id = 84, .r = { .max = 200000000, }, },
+	{ .n = "spdiftx_clk",	.p = "mck1", .id = 85, .r = { .max = 200000000, }, },
+	{ .n = "ssc0_clk",	.p = "mck1", .id = 86, .r = { .max = 200000000, }, },
+	{ .n = "ssc1_clk",	.p = "mck1", .id = 87, .r = { .max = 200000000, }, },
+	{ .n = "tcb0_ch0_clk",	.p = "mck1", .id = 88, .r = { .max = 200000000, }, },
+	{ .n = "tcb0_ch1_clk",	.p = "mck1", .id = 89, .r = { .max = 200000000, }, },
+	{ .n = "tcb0_ch2_clk",	.p = "mck1", .id = 90, .r = { .max = 200000000, }, },
+	{ .n = "tcb1_ch0_clk",	.p = "mck1", .id = 91, .r = { .max = 200000000, }, },
+	{ .n = "tcb1_ch1_clk",	.p = "mck1", .id = 92, .r = { .max = 200000000, }, },
+	{ .n = "tcb1_ch2_clk",	.p = "mck1", .id = 93, .r = { .max = 200000000, }, },
+	{ .n = "tcpca_clk",	.p = "mck1", .id = 94, },
+	{ .n = "tcpcb_clk",	.p = "mck1", .id = 95, },
+	{ .n = "tdes_clk",	.p = "mck1", .id = 96, },
+	{ .n = "trng_clk",	.p = "mck1", .id = 97, },
+	{ .n = "udphsa_clk",	.p = "mck1", .id = 104, },
+	{ .n = "udphsb_clk",	.p = "mck1", .id = 105, },
+	{ .n = "uhphs_clk",	.p = "mck1", .id = 106, },
+};
+
+/**
+ * Generic clock description
+ * @n:			clock name
+ * @pp:			PLL parents
+ * @pp_mux_table:	PLL parents mux table
+ * @r:			clock output range
+ * @pp_chg_id:		id in parrent array of changeable PLL parent
+ * @pp_count:		PLL parents count
+ * @id:			clock id
+ */
+static const struct {
+	const char *n;
+	const char *pp[8];
+	const char pp_mux_table[8];
+	struct clk_range r;
+	int pp_chg_id;
+	u8 pp_count;
+	u8 id;
+} sama7g5_gck[] = {
+	{ .n  = "adc_gclk",
+	  .id = 26,
+	  .r = { .max = 100000000, },
+	  .pp = { "syspll_divpmcck", "imgpll_divpmcck", "audiopll_divpmcck", },
+	  .pp_mux_table = { 5, 7, 9, },
+	  .pp_count = 3,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "asrc_gclk",
+	  .id = 30,
+	  .r = { .max = 200000000 },
+	  .pp = { "audiopll_divpmcck", },
+	  .pp_mux_table = { 9, },
+	  .pp_count = 1,
+	  .pp_chg_id = 4, },
+
+	{ .n  = "csi_gclk",
+	  .id = 33,
+	  .r = { .max = 27000000  },
+	  .pp = { "ddrpll_divpmcck", "imgpll_divpmcck", },
+	  .pp_mux_table = { 6, 7, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "flex0_gclk",
+	  .id = 38,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "flex1_gclk",
+	  .id = 39,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "flex2_gclk",
+	  .id = 40,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "flex3_gclk",
+	  .id = 41,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "flex4_gclk",
+	  .id = 42,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "flex5_gclk",
+	  .id = 43,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "flex6_gclk",
+	  .id = 44,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "flex7_gclk",
+	  .id = 45,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "flex8_gclk",
+	  .id = 46,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "flex9_gclk",
+	  .id = 47,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "flex10_gclk",
+	  .id = 48,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "flex11_gclk",
+	  .id = 49,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "gmac0_gclk",
+	  .id = 51,
+	  .r = { .max = 125000000 },
+	  .pp = { "ethpll_divpmcck", },
+	  .pp_mux_table = { 10, },
+	  .pp_count = 1,
+	  .pp_chg_id = 4, },
+
+	{ .n  = "gmac1_gclk",
+	  .id = 52,
+	  .r = { .max = 50000000  },
+	  .pp = { "ethpll_divpmcck", },
+	  .pp_mux_table = { 10, },
+	  .pp_count = 1,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "gmac0_tsu_gclk",
+	  .id = 53,
+	  .r = { .max = 300000000 },
+	  .pp = { "audiopll_divpmcck", "ethpll_divpmcck", },
+	  .pp_mux_table = { 9, 10, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "gmac1_tsu_gclk",
+	  .id = 54,
+	  .r = { .max = 300000000 },
+	  .pp = { "audiopll_divpmcck", "ethpll_divpmcck", },
+	  .pp_mux_table = { 9, 10, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "i2smcc0_gclk",
+	  .id = 57,
+	  .r = { .max = 100000000 },
+	  .pp = { "syspll_divpmcck", "audiopll_divpmcck", },
+	  .pp_mux_table = { 5, 9, },
+	  .pp_count = 2,
+	  .pp_chg_id = 5, },
+
+	{ .n  = "i2smcc1_gclk",
+	  .id = 58,
+	  .r = { .max = 100000000 },
+	  .pp = { "syspll_divpmcck", "audiopll_divpmcck", },
+	  .pp_mux_table = { 5, 9, },
+	  .pp_count = 2,
+	  .pp_chg_id = 5, },
+
+	{ .n  = "mcan0_gclk",
+	  .id = 61,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "mcan1_gclk",
+	  .id = 62,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "mcan2_gclk",
+	  .id = 63,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "mcan3_gclk",
+	  .id = 64,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "mcan4_gclk",
+	  .id = 65,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "mcan5_gclk",
+	  .id = 66,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "pdmc0_gclk",
+	  .id = 68,
+	  .r = { .max = 50000000  },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "pdmc1_gclk",
+	  .id = 69,
+	  .r = { .max = 50000000, },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "pit64b0_gclk",
+	  .id = 70,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "imgpll_divpmcck", "baudpll_divpmcck",
+		  "audiopll_divpmcck", "ethpll_divpmcck", },
+	  .pp_mux_table = { 5, 7, 8, 9, 10, },
+	  .pp_count = 5,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "pit64b1_gclk",
+	  .id = 71,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "imgpll_divpmcck", "baudpll_divpmcck",
+		  "audiopll_divpmcck", "ethpll_divpmcck", },
+	  .pp_mux_table = { 5, 7, 8, 9, 10, },
+	  .pp_count = 5,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "pit64b2_gclk",
+	  .id = 72,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "imgpll_divpmcck", "baudpll_divpmcck",
+		  "audiopll_divpmcck", "ethpll_divpmcck", },
+	  .pp_mux_table = { 5, 7, 8, 9, 10, },
+	  .pp_count = 5,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "pit64b3_gclk",
+	  .id = 73,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "imgpll_divpmcck", "baudpll_divpmcck",
+		  "audiopll_divpmcck", "ethpll_divpmcck", },
+	  .pp_mux_table = { 5, 7, 8, 9, 10, },
+	  .pp_count = 5,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "pit64b4_gclk",
+	  .id = 74,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "imgpll_divpmcck", "baudpll_divpmcck",
+		  "audiopll_divpmcck", "ethpll_divpmcck", },
+	  .pp_mux_table = { 5, 7, 8, 9, 10, },
+	  .pp_count = 5,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "pit64b5_gclk",
+	  .id = 75,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "imgpll_divpmcck", "baudpll_divpmcck",
+		  "audiopll_divpmcck", "ethpll_divpmcck", },
+	  .pp_mux_table = { 5, 7, 8, 9, 10, },
+	  .pp_count = 5,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "qspi0_gclk",
+	  .id = 78,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "qspi1_gclk",
+	  .id = 79,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "sdmmc0_gclk",
+	  .id = 80,
+	  .r = { .max = 208000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = 5, },
+
+	{ .n  = "sdmmc1_gclk",
+	  .id = 81,
+	  .r = { .max = 208000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = 5, },
+
+	{ .n  = "sdmmc2_gclk",
+	  .id = 82,
+	  .r = { .max = 208000000 },
+	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
+	  .pp_mux_table = { 5, 8, },
+	  .pp_count = 2,
+	  .pp_chg_id = 5, },
+
+	{ .n  = "spdifrx_gclk",
+	  .id = 84,
+	  .r = { .max = 150000000 },
+	  .pp = { "syspll_divpmcck", "audiopll_divpmcck", },
+	  .pp_mux_table = { 5, 9, },
+	  .pp_count = 2,
+	  .pp_chg_id = 5, },
+
+	{ .n = "spdiftx_gclk",
+	  .id = 85,
+	  .r = { .max = 25000000  },
+	  .pp = { "syspll_divpmcck", "audiopll_divpmcck", },
+	  .pp_mux_table = { 5, 9, },
+	  .pp_count = 2,
+	  .pp_chg_id = 5, },
+
+	{ .n  = "tcb0_ch0_gclk",
+	  .id = 88,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "imgpll_divpmcck", "baudpll_divpmcck",
+		  "audiopll_divpmcck", "ethpll_divpmcck", },
+	  .pp_mux_table = { 5, 7, 8, 9, 10, },
+	  .pp_count = 5,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "tcb1_ch0_gclk",
+	  .id = 91,
+	  .r = { .max = 200000000 },
+	  .pp = { "syspll_divpmcck", "imgpll_divpmcck", "baudpll_divpmcck",
+		  "audiopll_divpmcck", "ethpll_divpmcck", },
+	  .pp_mux_table = { 5, 7, 8, 9, 10, },
+	  .pp_count = 5,
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "tcpca_gclk",
+	  .id = 94,
+	  .r = { .max = 32768, },
+	  .pp_chg_id = INT_MIN, },
+
+	{ .n  = "tcpcb_gclk",
+	  .id = 95,
+	  .r = { .max = 32768, },
+	  .pp_chg_id = INT_MIN, },
+};
+
+/* PLL output range. */
+static const struct clk_range pll_outputs[] = {
+	{ .min = 2343750, .max = 1200000000 },
+};
+
+/* PLL characteristics. */
+static const struct clk_pll_characteristics pll_characteristics = {
+	.input = { .min = 12000000, .max = 50000000 },
+	.num_output = ARRAY_SIZE(pll_outputs),
+	.output = pll_outputs,
+};
+
+/* MCK0 characteristics. */
+static const struct clk_master_characteristics mck0_characteristics = {
+	.output = { .min = 140000000, .max = 200000000 },
+	.divisors = { 1, 2, 4, 3 },
+	.have_div3_pres = 1,
+};
+
+/* MCK0 layout. */
+static const struct clk_master_layout mck0_layout = {
+	.mask = 0x373,
+	.pres_shift = 4,
+	.offset = 0x28,
+};
+
+/* Programmable clock layout. */
+static const struct clk_programmable_layout programmable_layout = {
+	.pres_mask = 0xff,
+	.pres_shift = 8,
+	.css_mask = 0x1f,
+	.have_slck_mck = 0,
+	.is_pres_direct = 1,
+};
+
+/* Peripheral clock layout. */
+static const struct clk_pcr_layout sama7g5_pcr_layout = {
+	.offset = 0x88,
+	.cmd = BIT(31),
+	.gckcss_mask = GENMASK(12, 8),
+	.pid_mask = GENMASK(6, 0),
+};
+
+static void __init sama7g5_pmc_setup(struct device_node *np)
+{
+	const char *td_slck_name, *md_slck_name, *mainxtal_name;
+	struct pmc_data *sama7g5_pmc;
+	const char *parent_names[10];
+	void **alloc_mem = NULL;
+	int alloc_mem_size = 0;
+	struct regmap *regmap;
+	struct clk_hw *hw;
+	bool bypass;
+	int i, j;
+
+	i = of_property_match_string(np, "clock-names", "td_slck");
+	if (i < 0)
+		return;
+
+	td_slck_name = of_clk_get_parent_name(np, i);
+
+	i = of_property_match_string(np, "clock-names", "md_slck");
+	if (i < 0)
+		return;
+
+	md_slck_name = of_clk_get_parent_name(np, i);
+
+	i = of_property_match_string(np, "clock-names", "main_xtal");
+	if (i < 0)
+		return;
+
+	mainxtal_name = of_clk_get_parent_name(np, i);
+
+	regmap = device_node_to_regmap(np);
+	if (IS_ERR(regmap))
+		return;
+
+	sama7g5_pmc = pmc_data_allocate(PMC_I2S1_MUX + 1,
+					nck(sama7g5_systemck),
+					nck(sama7g5_periphck),
+					nck(sama7g5_gck));
+	if (!sama7g5_pmc)
+		return;
+
+	alloc_mem = kmalloc(sizeof(void *) *
+			    (ARRAY_SIZE(sama7g5_mckx) + ARRAY_SIZE(sama7g5_gck)),
+			    GFP_KERNEL);
+	if (!alloc_mem)
+		goto err_free;
+
+	hw = at91_clk_register_main_rc_osc(regmap, "main_rc_osc", 12000000,
+					   50000000);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	bypass = of_property_read_bool(np, "atmel,osc-bypass");
+
+	hw = at91_clk_register_main_osc(regmap, "main_osc", mainxtal_name,
+					bypass);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	parent_names[0] = "main_rc_osc";
+	parent_names[1] = "main_osc";
+	hw = at91_clk_register_sam9x5_main(regmap, "mainck", parent_names, 2);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	sama7g5_pmc->chws[PMC_MAIN] = hw;
+
+	for (i = 0; i < PLL_ID_MAX; i++) {
+		for (j = 0; j < 3; j++) {
+			struct clk_hw *parent_hw;
+
+			if (!sama7g5_plls[i][j].n)
+				continue;
+
+			switch (sama7g5_plls[i][j].t) {
+			case PLL_TYPE_FRAC:
+				if (!strcmp(sama7g5_plls[i][j].p, "mainck"))
+					parent_hw = sama7g5_pmc->chws[PMC_MAIN];
+				else
+					parent_hw = __clk_get_hw(of_clk_get_by_name(np,
+						sama7g5_plls[i][j].p));
+
+				hw = sam9x60_clk_register_frac_pll(regmap,
+					&pmc_pll_lock, sama7g5_plls[i][j].n,
+					sama7g5_plls[i][j].p, parent_hw, i,
+					&pll_characteristics,
+					sama7g5_plls[i][j].l,
+					sama7g5_plls[i][j].c);
+				break;
+
+			case PLL_TYPE_DIV:
+				hw = sam9x60_clk_register_div_pll(regmap,
+					&pmc_pll_lock, sama7g5_plls[i][j].n,
+					sama7g5_plls[i][j].p, i,
+					&pll_characteristics,
+					sama7g5_plls[i][j].l,
+					sama7g5_plls[i][j].c);
+				break;
+
+			default:
+				continue;
+			}
+
+			if (IS_ERR(hw))
+				goto err_free;
+
+			if (sama7g5_plls[i][j].eid)
+				sama7g5_pmc->chws[sama7g5_plls[i][j].eid] = hw;
+		}
+	}
+
+	parent_names[0] = md_slck_name;
+	parent_names[1] = "mainck";
+	parent_names[2] = "cpupll_divpmcck";
+	parent_names[3] = "syspll_divpmcck";
+	hw = at91_clk_register_master(regmap, "mck0", 4, parent_names,
+				      &mck0_layout, &mck0_characteristics);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	sama7g5_pmc->chws[PMC_MCK] = hw;
+
+	parent_names[0] = md_slck_name;
+	parent_names[1] = td_slck_name;
+	parent_names[2] = "mainck";
+	parent_names[3] = "mck0";
+	for (i = 0; i < ARRAY_SIZE(sama7g5_mckx); i++) {
+		u8 num_parents = 4 + sama7g5_mckx[i].ep_count;
+		u32 *mux_table;
+
+		mux_table = kmalloc_array(num_parents, sizeof(*mux_table),
+					  GFP_KERNEL);
+		if (!mux_table)
+			goto err_free;
+
+		SAMA7G5_INIT_TABLE(mux_table, 4);
+		SAMA7G5_FILL_TABLE(&mux_table[4], sama7g5_mckx[i].ep_mux_table,
+				   sama7g5_mckx[i].ep_count);
+		SAMA7G5_FILL_TABLE(&parent_names[4], sama7g5_mckx[i].ep,
+				   sama7g5_mckx[i].ep_count);
+
+		hw = at91_clk_sama7g5_register_master(regmap, sama7g5_mckx[i].n,
+				   num_parents, parent_names, mux_table,
+				   &pmc_mckX_lock, sama7g5_mckx[i].id,
+				   sama7g5_mckx[i].c,
+				   sama7g5_mckx[i].ep_chg_id);
+		if (IS_ERR(hw))
+			goto err_free;
+
+		alloc_mem[alloc_mem_size++] = mux_table;
+	}
+
+	hw = at91_clk_sama7g5_register_utmi(regmap, "utmick", "main_xtal");
+	if (IS_ERR(hw))
+		goto err_free;
+
+	sama7g5_pmc->chws[PMC_UTMI] = hw;
+
+	parent_names[0] = md_slck_name;
+	parent_names[1] = td_slck_name;
+	parent_names[2] = "mainck";
+	parent_names[3] = "mck0";
+	parent_names[4] = "syspll_divpmcck";
+	parent_names[5] = "ddrpll_divpmcck";
+	parent_names[6] = "imgpll_divpmcck";
+	parent_names[7] = "baudpll_divpmcck";
+	parent_names[8] = "audiopll_divpmcck";
+	parent_names[9] = "ethpll_divpmcck";
+	for (i = 0; i < 8; i++) {
+		char name[6];
+
+		snprintf(name, sizeof(name), "prog%d", i);
+
+		hw = at91_clk_register_programmable(regmap, name, parent_names,
+						    10, i,
+						    &programmable_layout,
+						    sama7g5_prog_mux_table);
+		if (IS_ERR(hw))
+			goto err_free;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(sama7g5_systemck); i++) {
+		hw = at91_clk_register_system(regmap, sama7g5_systemck[i].n,
+					      sama7g5_systemck[i].p,
+					      sama7g5_systemck[i].id);
+		if (IS_ERR(hw))
+			goto err_free;
+
+		sama7g5_pmc->shws[sama7g5_systemck[i].id] = hw;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(sama7g5_periphck); i++) {
+		hw = at91_clk_register_sam9x5_peripheral(regmap, &pmc_pcr_lock,
+						&sama7g5_pcr_layout,
+						sama7g5_periphck[i].n,
+						sama7g5_periphck[i].p,
+						sama7g5_periphck[i].id,
+						&sama7g5_periphck[i].r,
+						sama7g5_periphck[i].chgp ? 0 :
+						INT_MIN);
+		if (IS_ERR(hw))
+			goto err_free;
+
+		sama7g5_pmc->phws[sama7g5_periphck[i].id] = hw;
+	}
+
+	parent_names[0] = md_slck_name;
+	parent_names[1] = td_slck_name;
+	parent_names[2] = "mainck";
+	parent_names[3] = "mck0";
+	for (i = 0; i < ARRAY_SIZE(sama7g5_gck); i++) {
+		u8 num_parents = 4 + sama7g5_gck[i].pp_count;
+		u32 *mux_table;
+
+		mux_table = kmalloc_array(num_parents, sizeof(*mux_table),
+					  GFP_KERNEL);
+		if (!mux_table)
+			goto err_free;
+
+		SAMA7G5_INIT_TABLE(mux_table, 4);
+		SAMA7G5_FILL_TABLE(&mux_table[4], sama7g5_gck[i].pp_mux_table,
+				   sama7g5_gck[i].pp_count);
+		SAMA7G5_FILL_TABLE(&parent_names[4], sama7g5_gck[i].pp,
+				   sama7g5_gck[i].pp_count);
+
+		hw = at91_clk_register_generated(regmap, &pmc_pcr_lock,
+						 &sama7g5_pcr_layout,
+						 sama7g5_gck[i].n,
+						 parent_names, mux_table,
+						 num_parents,
+						 sama7g5_gck[i].id,
+						 &sama7g5_gck[i].r,
+						 sama7g5_gck[i].pp_chg_id);
+		if (IS_ERR(hw))
+			goto err_free;
+
+		sama7g5_pmc->ghws[sama7g5_gck[i].id] = hw;
+		alloc_mem[alloc_mem_size++] = mux_table;
+	}
+
+	of_clk_add_hw_provider(np, of_clk_hw_pmc_get, sama7g5_pmc);
+
+	return;
+
+err_free:
+	if (alloc_mem) {
+		for (i = 0; i < alloc_mem_size; i++)
+			kfree(alloc_mem[i]);
+		kfree(alloc_mem);
+	}
+
+	pmc_data_free(sama7g5_pmc);
+}
+
+/* Some clks are used for a clocksource */
+CLK_OF_DECLARE(sama7g5_pmc, "microchip,sama7g5-pmc", sama7g5_pmc_setup);

From 413d84b88bee08ed59713e782053ff38d206c606 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@kernel.org>
Date: Fri, 24 Jul 2020 02:40:25 -0700
Subject: [PATCH 117/474] clk: qcom: Export gdsc_gx_do_nothing_enable() to
 modules

A clk driver can be a module but the gdsc code is in the common module.
Export this symbol so that allmodconfig builds keep working.

Cc: Jonathan Marek <jonathan@marek.ca>
Fixes: 0638226dd095 ("clk: qcom: add common gdsc_gx_do_nothing_enable for gpucc drivers")
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20200724094025.3261266-1-sboyd@kernel.org
---
 drivers/clk/qcom/gdsc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/clk/qcom/gdsc.c b/drivers/clk/qcom/gdsc.c
index 628397703717..7e4273f314f7 100644
--- a/drivers/clk/qcom/gdsc.c
+++ b/drivers/clk/qcom/gdsc.c
@@ -6,6 +6,7 @@
 #include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/err.h>
+#include <linux/export.h>
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/ktime.h>
@@ -458,3 +459,4 @@ int gdsc_gx_do_nothing_enable(struct generic_pm_domain *domain)
 	/* Do nothing but give genpd the impression that we were successful */
 	return 0;
 }
+EXPORT_SYMBOL_GPL(gdsc_gx_do_nothing_enable);

From 6378cfdcc32d3790b04c953e7766324d8ee04a90 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@kernel.org>
Date: Mon, 22 Jun 2020 02:09:35 -0700
Subject: [PATCH 118/474] clk: Clean up kernel-doc errors

Two things aren't documented causing kernel-doc to fail when checking
the core clk.c file. Fix them so that this file is clean.

Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20200622090935.213833-1-sboyd@kernel.org
---
 drivers/clk/clk.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 236923b25543..47c0ee9da462 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -4135,6 +4135,7 @@ static int devm_clk_hw_match(struct device *dev, void *res, void *data)
 
 /**
  * devm_clk_unregister - resource managed clk_unregister()
+ * @dev: device that is unregistering the clock data
  * @clk: clock to unregister
  *
  * Deallocate a clock allocated with devm_clk_register(). Normally
@@ -4324,6 +4325,8 @@ static void clk_core_reparent_orphans(void)
  * @node: Pointer to device tree node of clock provider
  * @get: Get clock callback.  Returns NULL or a struct clk for the
  *       given clock specifier
+ * @get_hw: Get clk_hw callback.  Returns NULL, ERR_PTR or a
+ *       struct clk_hw for the given clock specifier
  * @data: context pointer to be passed into @get callback
  */
 struct of_clk_provider {

From 7d98404c8162b7f1d1b22eccce92f5ee7f93cab8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Fri, 24 Jul 2020 22:07:18 +0300
Subject: [PATCH 119/474] drm/omap: Use {} to zero initialize the mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The first member of drm_display_mode is no longer a structure, but
the code is still using {{0}} to zero initialize it. Make that just
{} so it works regardless of what lies inside.

Cc: Dave Airlie <airlied@redhat.com>
Cc: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Cc: Tomi Valkeinen <tomi.valkeinen@ti.com>
Fixes: 42acb06b01b1 ("drm: pahole struct drm_display_mode")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200724190718.23567-1-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch.ch>
---
 drivers/gpu/drm/omapdrm/omap_connector.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_connector.c b/drivers/gpu/drm/omapdrm/omap_connector.c
index 528764566b17..de95dc1b861c 100644
--- a/drivers/gpu/drm/omapdrm/omap_connector.c
+++ b/drivers/gpu/drm/omapdrm/omap_connector.c
@@ -89,7 +89,7 @@ static enum drm_mode_status omap_connector_mode_valid(struct drm_connector *conn
 				 struct drm_display_mode *mode)
 {
 	struct omap_connector *omap_connector = to_omap_connector(connector);
-	struct drm_display_mode new_mode = { { 0 } };
+	struct drm_display_mode new_mode = {};
 	enum drm_mode_status status;
 
 	status = omap_connector_mode_fixup(omap_connector->output, mode,

From 173722995cdb7c22d21abd484a5001c903df1e20 Mon Sep 17 00:00:00 2001
From: Taniya Das <tdas@codeaurora.org>
Date: Fri, 24 Jul 2020 21:37:55 +0530
Subject: [PATCH 120/474] clk: qcom: gdsc: Add support to enable retention of
 GSDCR

Add support for the RETAIN_FF_ENABLE feature which enables the
usage of retention registers. These registers maintain their
state after disabling and re-enabling a GDSC.

Signed-off-by: Taniya Das <tdas@codeaurora.org>
Link: https://lore.kernel.org/r/1595606878-2664-2-git-send-email-tdas@codeaurora.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/gdsc.c | 12 ++++++++++++
 drivers/clk/qcom/gdsc.h |  1 +
 2 files changed, 13 insertions(+)

diff --git a/drivers/clk/qcom/gdsc.c b/drivers/clk/qcom/gdsc.c
index 7e4273f314f7..bfc4ac02f9ea 100644
--- a/drivers/clk/qcom/gdsc.c
+++ b/drivers/clk/qcom/gdsc.c
@@ -30,6 +30,7 @@
 /* CFG_GDSCR */
 #define GDSC_POWER_UP_COMPLETE		BIT(16)
 #define GDSC_POWER_DOWN_COMPLETE	BIT(15)
+#define GDSC_RETAIN_FF_ENABLE		BIT(11)
 #define CFG_GDSCR_OFFSET		0x4
 
 /* Wait 2^n CXO cycles between all states. Here, n=2 (4 cycles). */
@@ -217,6 +218,14 @@ static inline void gdsc_assert_reset_aon(struct gdsc *sc)
 	regmap_update_bits(sc->regmap, sc->clamp_io_ctrl,
 			   GMEM_RESET_MASK, 0);
 }
+
+static void gdsc_retain_ff_on(struct gdsc *sc)
+{
+	u32 mask = GDSC_RETAIN_FF_ENABLE;
+
+	regmap_update_bits(sc->regmap, sc->gdscr, mask, mask);
+}
+
 static int gdsc_enable(struct generic_pm_domain *domain)
 {
 	struct gdsc *sc = domain_to_gdsc(domain);
@@ -269,6 +278,9 @@ static int gdsc_enable(struct generic_pm_domain *domain)
 		udelay(1);
 	}
 
+	if (sc->flags & RETAIN_FF_ENABLE)
+		gdsc_retain_ff_on(sc);
+
 	return 0;
 }
 
diff --git a/drivers/clk/qcom/gdsc.h b/drivers/clk/qcom/gdsc.h
index 1896bfb2bbd1..bd537438c793 100644
--- a/drivers/clk/qcom/gdsc.h
+++ b/drivers/clk/qcom/gdsc.h
@@ -50,6 +50,7 @@ struct gdsc {
 #define AON_RESET	BIT(4)
 #define POLL_CFG_GDSCR	BIT(5)
 #define ALWAYS_ON	BIT(6)
+#define RETAIN_FF_ENABLE	BIT(7)
 	struct reset_controller_dev	*rcdev;
 	unsigned int			*resets;
 	unsigned int			reset_count;

From 381cc6f97cdaf15dabceb1b48fa82c9de0163e58 Mon Sep 17 00:00:00 2001
From: Taniya Das <tdas@codeaurora.org>
Date: Fri, 24 Jul 2020 21:37:56 +0530
Subject: [PATCH 121/474] dt-bindings: clock: Add YAML schemas for LPASS clocks
 on SC7180

The LPASS(Low Power Audio Subsystem) clock provider have a bunch of generic
properties that are needed in a device tree. Also add clock ids for GCC
LPASS and LPASS Core clock IDs for LPASS client to request for the clocks.

Signed-off-by: Taniya Das <tdas@codeaurora.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/1595606878-2664-3-git-send-email-tdas@codeaurora.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../clock/qcom,sc7180-lpasscorecc.yaml        | 102 ++++++++++++++++++
 include/dt-bindings/clock/qcom,gcc-sc7180.h   |   1 +
 .../clock/qcom,lpasscorecc-sc7180.h           |  29 +++++
 3 files changed, 132 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/qcom,sc7180-lpasscorecc.yaml
 create mode 100644 include/dt-bindings/clock/qcom,lpasscorecc-sc7180.h

diff --git a/Documentation/devicetree/bindings/clock/qcom,sc7180-lpasscorecc.yaml b/Documentation/devicetree/bindings/clock/qcom,sc7180-lpasscorecc.yaml
new file mode 100644
index 000000000000..a838250b33e7
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,sc7180-lpasscorecc.yaml
@@ -0,0 +1,102 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,sc7180-lpasscorecc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm LPASS Core Clock Controller Binding for SC7180
+
+maintainers:
+  - Taniya Das <tdas@codeaurora.org>
+
+description: |
+  Qualcomm LPASS core clock control module which supports the clocks and
+  power domains on SC7180.
+
+  See also:
+  - dt-bindings/clock/qcom,lpasscorecc-sc7180.h
+
+properties:
+  compatible:
+    enum:
+      - qcom,sc7180-lpasshm
+      - qcom,sc7180-lpasscorecc
+
+  clocks:
+    items:
+      - description: gcc_lpass_sway clock from GCC
+
+  clock-names:
+    items:
+      - const: iface
+
+  power-domains:
+    maxItems: 1
+
+  '#clock-cells':
+    const: 1
+
+  '#power-domain-cells':
+    const: 1
+
+  reg:
+    minItems: 1
+    items:
+      - description: lpass core cc register
+      - description: lpass audio cc register
+
+  reg-names:
+    items:
+      - const: lpass_core_cc
+      - const: lpass_audio_cc
+
+if:
+  properties:
+    compatible:
+      contains:
+        const: qcom,sc7180-lpasshm
+then:
+  properties:
+    reg:
+      maxItems: 1
+
+else:
+  properties:
+    reg:
+      minItems: 2
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - '#clock-cells'
+  - '#power-domain-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,gcc-sc7180.h>
+    #include <dt-bindings/clock/qcom,lpasscorecc-sc7180.h>
+    clock-controller@63000000 {
+      compatible = "qcom,sc7180-lpasshm";
+      reg = <0x63000000 0x28>;
+      clocks = <&gcc GCC_LPASS_CFG_NOC_SWAY_CLK>;
+      clock-names = "iface";
+      #clock-cells = <1>;
+      #power-domain-cells = <1>;
+    };
+
+  - |
+    clock-controller@62d00000 {
+      compatible = "qcom,sc7180-lpasscorecc";
+      reg = <0x62d00000 0x50000>, <0x62780000 0x30000>;
+      reg-names = "lpass_core_cc", "lpass_audio_cc";
+      clocks = <&gcc GCC_LPASS_CFG_NOC_SWAY_CLK>;
+      clock-names = "iface";
+      power-domains = <&lpass_hm LPASS_CORE_HM_GDSCR>;
+      #clock-cells = <1>;
+      #power-domain-cells = <1>;
+    };
+...
diff --git a/include/dt-bindings/clock/qcom,gcc-sc7180.h b/include/dt-bindings/clock/qcom,gcc-sc7180.h
index 992b67b7e5e4..bdf43adc7897 100644
--- a/include/dt-bindings/clock/qcom,gcc-sc7180.h
+++ b/include/dt-bindings/clock/qcom,gcc-sc7180.h
@@ -138,6 +138,7 @@
 #define GCC_MSS_Q6_MEMNOC_AXI_CLK				128
 #define GCC_MSS_SNOC_AXI_CLK					129
 #define GCC_SEC_CTRL_CLK_SRC					130
+#define GCC_LPASS_CFG_NOC_SWAY_CLK				131
 
 /* GCC resets */
 #define GCC_QUSB2PHY_PRIM_BCR					0
diff --git a/include/dt-bindings/clock/qcom,lpasscorecc-sc7180.h b/include/dt-bindings/clock/qcom,lpasscorecc-sc7180.h
new file mode 100644
index 000000000000..a55d01db2b20
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,lpasscorecc-sc7180.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_LPASS_CORE_CC_SC7180_H
+#define _DT_BINDINGS_CLK_QCOM_LPASS_CORE_CC_SC7180_H
+
+/* LPASS_CORE_CC clocks */
+#define LPASS_LPAAUDIO_DIG_PLL				0
+#define LPASS_LPAAUDIO_DIG_PLL_OUT_ODD			1
+#define CORE_CLK_SRC					2
+#define EXT_MCLK0_CLK_SRC				3
+#define LPAIF_PRI_CLK_SRC				4
+#define LPAIF_SEC_CLK_SRC				5
+#define LPASS_AUDIO_CORE_CORE_CLK			6
+#define LPASS_AUDIO_CORE_EXT_MCLK0_CLK			7
+#define LPASS_AUDIO_CORE_LPAIF_PRI_IBIT_CLK		8
+#define LPASS_AUDIO_CORE_LPAIF_SEC_IBIT_CLK		9
+#define LPASS_AUDIO_CORE_SYSNOC_MPORT_CORE_CLK		10
+
+/* LPASS Core power domains */
+#define LPASS_CORE_HM_GDSCR				0
+
+/* LPASS Audio power domains */
+#define LPASS_AUDIO_HM_GDSCR				0
+#define LPASS_PDC_HM_GDSCR				1
+
+#endif

From 47110b6aa5c8269da4a3b5129b066211f978aa86 Mon Sep 17 00:00:00 2001
From: Taniya Das <tdas@codeaurora.org>
Date: Fri, 24 Jul 2020 21:37:57 +0530
Subject: [PATCH 122/474] clk: qcom: gcc: Add support for GCC LPASS clock for
 SC7180

Add the GCC lpass clock which is required to access the LPASS core
clocks.

Signed-off-by: Taniya Das <tdas@codeaurora.org>
Link: https://lore.kernel.org/r/1595606878-2664-4-git-send-email-tdas@codeaurora.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/gcc-sc7180.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/clk/qcom/gcc-sc7180.c b/drivers/clk/qcom/gcc-sc7180.c
index 538677befb86..68d8f7aaf64e 100644
--- a/drivers/clk/qcom/gcc-sc7180.c
+++ b/drivers/clk/qcom/gcc-sc7180.c
@@ -2251,6 +2251,19 @@ static struct clk_branch gcc_mss_q6_memnoc_axi_clk = {
 	},
 };
 
+static struct clk_branch gcc_lpass_cfg_noc_sway_clk = {
+	.halt_reg = 0x47018,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x47018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_lpass_cfg_noc_sway_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct gdsc ufs_phy_gdsc = {
 	.gdscr = 0x77004,
 	.pd = {
@@ -2428,6 +2441,7 @@ static struct clk_regmap *gcc_sc7180_clocks[] = {
 	[GCC_MSS_Q6_MEMNOC_AXI_CLK] = &gcc_mss_q6_memnoc_axi_clk.clkr,
 	[GCC_MSS_SNOC_AXI_CLK] = &gcc_mss_snoc_axi_clk.clkr,
 	[GCC_SEC_CTRL_CLK_SRC] = &gcc_sec_ctrl_clk_src.clkr,
+	[GCC_LPASS_CFG_NOC_SWAY_CLK] = &gcc_lpass_cfg_noc_sway_clk.clkr,
 };
 
 static const struct qcom_reset_map gcc_sc7180_resets[] = {

From edab812d802d248e3d07719c036a865c67ad3a87 Mon Sep 17 00:00:00 2001
From: Taniya Das <tdas@codeaurora.org>
Date: Fri, 24 Jul 2020 21:37:58 +0530
Subject: [PATCH 123/474] clk: qcom: lpass: Add support for LPASS clock
 controller for SC7180

The Low Power Audio subsystem clocks are required for Audio client
to be able to request for the clocks and power domains.

Signed-off-by: Taniya Das <tdas@codeaurora.org>
Link: https://lore.kernel.org/r/1595606878-2664-5-git-send-email-tdas@codeaurora.org
[sboyd@kernel.org: Drop unused ret in probe function]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/Kconfig              |   9 +
 drivers/clk/qcom/Makefile             |   1 +
 drivers/clk/qcom/lpasscorecc-sc7180.c | 476 ++++++++++++++++++++++++++
 3 files changed, 486 insertions(+)
 create mode 100644 drivers/clk/qcom/lpasscorecc-sc7180.c

diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index cd0f01136039..058327310c25 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -308,6 +308,15 @@ config SC_GCC_7180
 	  Say Y if you want to use peripheral devices such as UART, SPI,
 	  I2C, USB, UFS, SDCC, etc.
 
+config SC_LPASS_CORECC_7180
+	tristate "SC7180 LPASS Core Clock Controller"
+	select SC_GCC_7180
+	help
+	  Support for the LPASS(Low Power Audio Subsystem) core clock controller
+	  on SC7180 devices.
+	  Say Y if you want to use LPASS clocks and power domains of the LPASS
+	  core clock controller.
+
 config SC_GPUCC_7180
 	tristate "SC7180 Graphics Clock Controller"
 	select SC_GCC_7180
diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile
index 1e9a21882ed5..9677e769e7e9 100644
--- a/drivers/clk/qcom/Makefile
+++ b/drivers/clk/qcom/Makefile
@@ -54,6 +54,7 @@ obj-$(CONFIG_QCS_TURING_404) += turingcc-qcs404.o
 obj-$(CONFIG_SC_DISPCC_7180) += dispcc-sc7180.o
 obj-$(CONFIG_SC_GCC_7180) += gcc-sc7180.o
 obj-$(CONFIG_SC_GPUCC_7180) += gpucc-sc7180.o
+obj-$(CONFIG_SC_LPASS_CORECC_7180) += lpasscorecc-sc7180.o
 obj-$(CONFIG_SC_MSS_7180) += mss-sc7180.o
 obj-$(CONFIG_SC_VIDEOCC_7180) += videocc-sc7180.o
 obj-$(CONFIG_SDM_CAMCC_845) += camcc-sdm845.o
diff --git a/drivers/clk/qcom/lpasscorecc-sc7180.c b/drivers/clk/qcom/lpasscorecc-sc7180.c
new file mode 100644
index 000000000000..d4c1864e1ee9
--- /dev/null
+++ b/drivers/clk/qcom/lpasscorecc-sc7180.c
@@ -0,0 +1,476 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/pm_clock.h>
+#include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/regmap.h>
+
+#include <dt-bindings/clock/qcom,lpasscorecc-sc7180.h>
+
+#include "clk-alpha-pll.h"
+#include "clk-branch.h"
+#include "clk-rcg.h"
+#include "clk-regmap.h"
+#include "common.h"
+#include "gdsc.h"
+
+enum {
+	P_BI_TCXO,
+	P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD,
+	P_SLEEP_CLK,
+};
+
+static struct pll_vco fabia_vco[] = {
+	{ 249600000, 2000000000, 0 },
+};
+
+static const struct alpha_pll_config lpass_lpaaudio_dig_pll_config = {
+	.l = 0x20,
+	.alpha = 0x0,
+	.config_ctl_val = 0x20485699,
+	.config_ctl_hi_val = 0x00002067,
+	.test_ctl_val = 0x40000000,
+	.test_ctl_hi_val = 0x00000000,
+	.user_ctl_val = 0x00005105,
+	.user_ctl_hi_val = 0x00004805,
+};
+
+static const u8 clk_alpha_pll_regs_offset[][PLL_OFF_MAX_REGS] = {
+	[CLK_ALPHA_PLL_TYPE_FABIA] =  {
+		[PLL_OFF_L_VAL] = 0x04,
+		[PLL_OFF_CAL_L_VAL] = 0x8,
+		[PLL_OFF_USER_CTL] = 0x0c,
+		[PLL_OFF_USER_CTL_U] = 0x10,
+		[PLL_OFF_USER_CTL_U1] = 0x14,
+		[PLL_OFF_CONFIG_CTL] = 0x18,
+		[PLL_OFF_CONFIG_CTL_U] = 0x1C,
+		[PLL_OFF_CONFIG_CTL_U1] = 0x20,
+		[PLL_OFF_TEST_CTL] = 0x24,
+		[PLL_OFF_TEST_CTL_U] = 0x28,
+		[PLL_OFF_STATUS] = 0x30,
+		[PLL_OFF_OPMODE] = 0x38,
+		[PLL_OFF_FRAC] = 0x40,
+	},
+};
+
+static struct clk_alpha_pll lpass_lpaaudio_dig_pll = {
+	.offset = 0x1000,
+	.vco_table = fabia_vco,
+	.num_vco = ARRAY_SIZE(fabia_vco),
+	.regs = clk_alpha_pll_regs_offset[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "lpass_lpaaudio_dig_pll",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fabia_ops,
+		},
+	},
+};
+
+static const struct clk_div_table
+			post_div_table_lpass_lpaaudio_dig_pll_out_odd[] = {
+	{ 0x5, 5 },
+	{ }
+};
+
+static struct clk_alpha_pll_postdiv lpass_lpaaudio_dig_pll_out_odd = {
+	.offset = 0x1000,
+	.post_div_shift = 12,
+	.post_div_table = post_div_table_lpass_lpaaudio_dig_pll_out_odd,
+	.num_post_div =
+		ARRAY_SIZE(post_div_table_lpass_lpaaudio_dig_pll_out_odd),
+	.width = 4,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "lpass_lpaaudio_dig_pll_out_odd",
+		.parent_data = &(const struct clk_parent_data){
+			.hw = &lpass_lpaaudio_dig_pll.clkr.hw,
+		},
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_alpha_pll_postdiv_fabia_ops,
+	},
+};
+
+static const struct parent_map lpass_core_cc_parent_map_0[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 5 },
+};
+
+static const struct clk_parent_data lpass_core_cc_parent_data_0[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &lpass_lpaaudio_dig_pll_out_odd.clkr.hw },
+};
+
+static const struct parent_map lpass_core_cc_parent_map_2[] = {
+	{ P_BI_TCXO, 0 },
+};
+
+static struct clk_rcg2 core_clk_src = {
+	.cmd_rcgr = 0x1d000,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = lpass_core_cc_parent_map_2,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "core_clk_src",
+		.parent_data = &(const struct clk_parent_data){
+			.fw_name = "bi_tcxo",
+		},
+		.num_parents = 1,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_ext_mclk0_clk_src[] = {
+	F(9600000, P_BI_TCXO, 2, 0, 0),
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	{ }
+};
+
+static const struct freq_tbl ftbl_ext_lpaif_clk_src[] = {
+	F(256000, P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 15, 1, 32),
+	F(512000, P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 15, 1, 16),
+	F(768000, P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 10, 1, 16),
+	F(1024000, P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 15, 1, 8),
+	F(1536000, P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 10, 1, 8),
+	F(2048000, P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 15, 1, 4),
+	F(3072000, P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 10, 1, 4),
+	F(4096000, P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 15, 1, 2),
+	F(6144000, P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 10, 1, 2),
+	F(8192000, P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 15, 0, 0),
+	F(9600000, P_BI_TCXO, 2, 0, 0),
+	F(12288000, P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 10, 0, 0),
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(24576000, P_LPASS_LPAAUDIO_DIG_PLL_OUT_ODD, 5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 ext_mclk0_clk_src = {
+	.cmd_rcgr = 0x20000,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = lpass_core_cc_parent_map_0,
+	.freq_tbl = ftbl_ext_mclk0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "ext_mclk0_clk_src",
+		.parent_data = lpass_core_cc_parent_data_0,
+		.num_parents = 2,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 lpaif_pri_clk_src = {
+	.cmd_rcgr = 0x10000,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = lpass_core_cc_parent_map_0,
+	.freq_tbl = ftbl_ext_lpaif_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "lpaif_pri_clk_src",
+		.parent_data = lpass_core_cc_parent_data_0,
+		.num_parents = 2,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 lpaif_sec_clk_src = {
+	.cmd_rcgr = 0x11000,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = lpass_core_cc_parent_map_0,
+	.freq_tbl = ftbl_ext_lpaif_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "lpaif_sec_clk_src",
+		.parent_data = lpass_core_cc_parent_data_0,
+		.num_parents = 2,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch lpass_audio_core_ext_mclk0_clk = {
+	.halt_reg = 0x20014,
+	.halt_check = BRANCH_HALT,
+	.hwcg_reg = 0x20014,
+	.hwcg_bit = 1,
+	.clkr = {
+		.enable_reg = 0x20014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "lpass_audio_core_ext_mclk0_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &ext_mclk0_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch lpass_audio_core_lpaif_pri_ibit_clk = {
+	.halt_reg = 0x10018,
+	.halt_check = BRANCH_HALT,
+	.hwcg_reg = 0x10018,
+	.hwcg_bit = 1,
+	.clkr = {
+		.enable_reg = 0x10018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "lpass_audio_core_lpaif_pri_ibit_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &lpaif_pri_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch lpass_audio_core_lpaif_sec_ibit_clk = {
+	.halt_reg = 0x11018,
+	.halt_check = BRANCH_HALT,
+	.hwcg_reg = 0x11018,
+	.hwcg_bit = 1,
+	.clkr = {
+		.enable_reg = 0x11018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "lpass_audio_core_lpaif_sec_ibit_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &lpaif_sec_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch lpass_audio_core_sysnoc_mport_core_clk = {
+	.halt_reg = 0x23000,
+	.halt_check = BRANCH_HALT,
+	.hwcg_reg = 0x23000,
+	.hwcg_bit = 1,
+	.clkr = {
+		.enable_reg = 0x23000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "lpass_audio_core_sysnoc_mport_core_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &core_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_regmap *lpass_core_cc_sc7180_clocks[] = {
+	[EXT_MCLK0_CLK_SRC] = &ext_mclk0_clk_src.clkr,
+	[LPAIF_PRI_CLK_SRC] = &lpaif_pri_clk_src.clkr,
+	[LPAIF_SEC_CLK_SRC] = &lpaif_sec_clk_src.clkr,
+	[CORE_CLK_SRC] = &core_clk_src.clkr,
+	[LPASS_AUDIO_CORE_EXT_MCLK0_CLK] = &lpass_audio_core_ext_mclk0_clk.clkr,
+	[LPASS_AUDIO_CORE_LPAIF_PRI_IBIT_CLK] =
+		&lpass_audio_core_lpaif_pri_ibit_clk.clkr,
+	[LPASS_AUDIO_CORE_LPAIF_SEC_IBIT_CLK] =
+		&lpass_audio_core_lpaif_sec_ibit_clk.clkr,
+	[LPASS_AUDIO_CORE_SYSNOC_MPORT_CORE_CLK] =
+		&lpass_audio_core_sysnoc_mport_core_clk.clkr,
+	[LPASS_LPAAUDIO_DIG_PLL] = &lpass_lpaaudio_dig_pll.clkr,
+	[LPASS_LPAAUDIO_DIG_PLL_OUT_ODD] = &lpass_lpaaudio_dig_pll_out_odd.clkr,
+};
+
+static struct gdsc lpass_pdc_hm_gdsc = {
+	.gdscr = 0x3090,
+	.pd = {
+		.name = "lpass_pdc_hm_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = VOTABLE,
+};
+
+static struct gdsc lpass_audio_hm_gdsc = {
+	.gdscr = 0x9090,
+	.pd = {
+		.name = "lpass_audio_hm_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc lpass_core_hm_gdsc = {
+	.gdscr = 0x0,
+	.pd = {
+		.name = "lpass_core_hm_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = RETAIN_FF_ENABLE,
+};
+
+static struct gdsc *lpass_core_hm_sc7180_gdscs[] = {
+	[LPASS_CORE_HM_GDSCR] = &lpass_core_hm_gdsc,
+};
+
+static struct gdsc *lpass_audio_hm_sc7180_gdscs[] = {
+	[LPASS_PDC_HM_GDSCR] = &lpass_pdc_hm_gdsc,
+	[LPASS_AUDIO_HM_GDSCR] = &lpass_audio_hm_gdsc,
+};
+
+static struct regmap_config lpass_core_cc_sc7180_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.fast_io = true,
+};
+
+static const struct qcom_cc_desc lpass_core_hm_sc7180_desc = {
+	.config = &lpass_core_cc_sc7180_regmap_config,
+	.gdscs = lpass_core_hm_sc7180_gdscs,
+	.num_gdscs = ARRAY_SIZE(lpass_core_hm_sc7180_gdscs),
+};
+
+static const struct qcom_cc_desc lpass_core_cc_sc7180_desc = {
+	.config = &lpass_core_cc_sc7180_regmap_config,
+	.clks = lpass_core_cc_sc7180_clocks,
+	.num_clks = ARRAY_SIZE(lpass_core_cc_sc7180_clocks),
+};
+
+static const struct qcom_cc_desc lpass_audio_hm_sc7180_desc = {
+	.config = &lpass_core_cc_sc7180_regmap_config,
+	.gdscs = lpass_audio_hm_sc7180_gdscs,
+	.num_gdscs = ARRAY_SIZE(lpass_audio_hm_sc7180_gdscs),
+};
+
+static int lpass_core_cc_sc7180_probe(struct platform_device *pdev)
+{
+	const struct qcom_cc_desc *desc;
+	struct regmap *regmap;
+	int ret;
+
+	lpass_core_cc_sc7180_regmap_config.name = "lpass_audio_cc";
+	desc = &lpass_audio_hm_sc7180_desc;
+	ret = qcom_cc_probe_by_index(pdev, 1, desc);
+	if (ret)
+		return ret;
+
+	lpass_core_cc_sc7180_regmap_config.name = "lpass_core_cc";
+	regmap = qcom_cc_map(pdev, &lpass_core_cc_sc7180_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	/*
+	 * Keep the CLK always-ON
+	 * LPASS_AUDIO_CORE_SYSNOC_SWAY_CORE_CLK
+	 */
+	regmap_update_bits(regmap, 0x24000, BIT(0), BIT(0));
+
+	/* PLL settings */
+	regmap_write(regmap, 0x1008, 0x20);
+	regmap_update_bits(regmap, 0x1014, BIT(0), BIT(0));
+
+	clk_fabia_pll_configure(&lpass_lpaaudio_dig_pll, regmap,
+				&lpass_lpaaudio_dig_pll_config);
+
+	return qcom_cc_really_probe(pdev, &lpass_core_cc_sc7180_desc, regmap);
+}
+
+static int lpass_hm_core_probe(struct platform_device *pdev)
+{
+	const struct qcom_cc_desc *desc;
+
+	lpass_core_cc_sc7180_regmap_config.name = "lpass_hm_core";
+	desc = &lpass_core_hm_sc7180_desc;
+
+	return qcom_cc_probe_by_index(pdev, 0, desc);
+}
+
+static const struct of_device_id lpass_core_cc_sc7180_match_table[] = {
+	{
+		.compatible = "qcom,sc7180-lpasshm",
+		.data = lpass_hm_core_probe,
+	},
+	{
+		.compatible = "qcom,sc7180-lpasscorecc",
+		.data = lpass_core_cc_sc7180_probe,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, lpass_core_cc_sc7180_match_table);
+
+static int lpass_core_sc7180_probe(struct platform_device *pdev)
+{
+	int (*clk_probe)(struct platform_device *p);
+	int ret;
+
+	pm_runtime_enable(&pdev->dev);
+	ret = pm_clk_create(&pdev->dev);
+	if (ret)
+		return ret;
+
+	ret = pm_clk_add(&pdev->dev, "iface");
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to acquire iface clock\n");
+		goto disable_pm_runtime;
+	}
+
+	clk_probe = of_device_get_match_data(&pdev->dev);
+	if (!clk_probe)
+		return -EINVAL;
+
+	ret = clk_probe(pdev);
+	if (ret)
+		goto destroy_pm_clk;
+
+	return 0;
+
+destroy_pm_clk:
+	pm_clk_destroy(&pdev->dev);
+
+disable_pm_runtime:
+	pm_runtime_disable(&pdev->dev);
+
+	return ret;
+}
+
+static const struct dev_pm_ops lpass_core_cc_pm_ops = {
+	SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL)
+};
+
+static struct platform_driver lpass_core_cc_sc7180_driver = {
+	.probe = lpass_core_sc7180_probe,
+	.driver = {
+		.name = "lpass_core_cc-sc7180",
+		.of_match_table = lpass_core_cc_sc7180_match_table,
+		.pm = &lpass_core_cc_pm_ops,
+	},
+};
+
+static int __init lpass_core_cc_sc7180_init(void)
+{
+	return platform_driver_register(&lpass_core_cc_sc7180_driver);
+}
+subsys_initcall(lpass_core_cc_sc7180_init);
+
+static void __exit lpass_core_cc_sc7180_exit(void)
+{
+	platform_driver_unregister(&lpass_core_cc_sc7180_driver);
+}
+module_exit(lpass_core_cc_sc7180_exit);
+
+MODULE_DESCRIPTION("QTI LPASS_CORE_CC SC7180 Driver");
+MODULE_LICENSE("GPL v2");

From da3a9e9a6aa96ef589c153078f66e0646bf06b55 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Thu, 23 Jul 2020 11:05:50 +0200
Subject: [PATCH 124/474] drm/fourcc: fix Amlogic Video Framebuffer Compression
 macro

Fix the Amlogic Video Framebuffer Compression modifier macro to
correctly add the layout options, a pair of parenthesis was missing.

Fixes: d6528ec88309 ("drm/fourcc: Add modifier definitions for describing Amlogic Video Framebuffer Compression")
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20200723090551.27529-1-narmstrong@baylibre.com
---
 include/uapi/drm/drm_fourcc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 4bee7de5f306..82f327801267 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -1004,7 +1004,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
 #define DRM_FORMAT_MOD_AMLOGIC_FBC(__layout, __options) \
 	fourcc_mod_code(AMLOGIC, \
 			((__layout) & __fourcc_mod_amlogic_layout_mask) | \
-			((__options) & __fourcc_mod_amlogic_options_mask \
+			(((__options) & __fourcc_mod_amlogic_options_mask) \
 			 << __fourcc_mod_amlogic_options_shift))
 
 /* Amlogic FBC Layouts */

From 26afdd98821bd36e4e1de88dd00a8c70d83accdf Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Mon, 27 Jul 2020 13:43:36 -0600
Subject: [PATCH 125/474] vfio: Cleanup allowed driver naming

No functional change, avoid non-inclusive naming schemes.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 580099afeaff..262ab0efd06c 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -627,9 +627,10 @@ static struct vfio_device *vfio_group_get_device(struct vfio_group *group,
  * that error notification via MSI can be affected for platforms that handle
  * MSI within the same IOVA space as DMA.
  */
-static const char * const vfio_driver_whitelist[] = { "pci-stub" };
+static const char * const vfio_driver_allowed[] = { "pci-stub" };
 
-static bool vfio_dev_whitelisted(struct device *dev, struct device_driver *drv)
+static bool vfio_dev_driver_allowed(struct device *dev,
+				    struct device_driver *drv)
 {
 	if (dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(dev);
@@ -638,8 +639,8 @@ static bool vfio_dev_whitelisted(struct device *dev, struct device_driver *drv)
 			return true;
 	}
 
-	return match_string(vfio_driver_whitelist,
-			    ARRAY_SIZE(vfio_driver_whitelist),
+	return match_string(vfio_driver_allowed,
+			    ARRAY_SIZE(vfio_driver_allowed),
 			    drv->name) >= 0;
 }
 
@@ -648,7 +649,7 @@ static bool vfio_dev_whitelisted(struct device *dev, struct device_driver *drv)
  * one of the following states:
  *  - driver-less
  *  - bound to a vfio driver
- *  - bound to a whitelisted driver
+ *  - bound to an otherwise allowed driver
  *  - a PCI interconnect device
  *
  * We use two methods to determine whether a device is bound to a vfio
@@ -674,7 +675,7 @@ static int vfio_dev_viable(struct device *dev, void *data)
 	}
 	mutex_unlock(&group->unbound_lock);
 
-	if (!ret || !drv || vfio_dev_whitelisted(dev, drv))
+	if (!ret || !drv || vfio_dev_driver_allowed(dev, drv))
 		return 0;
 
 	device = vfio_group_get_device(group, dev);

From bf3551e150e5a231ac60f2bd750f63ab5484010a Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Mon, 27 Jul 2020 13:43:37 -0600
Subject: [PATCH 126/474] vfio/pci: Add Intel X550 to hidden INTx devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Intel document 333717-008, "Intel® Ethernet Controller X550
Specification Update", version 2.7, dated June 2020, includes errata
#22, added in version 2.1, May 2016, indicating X550 NICs suffer from
the same implementation deficiency as the 700-series NICs:

"The Interrupt Status bit in the Status register of the PCIe
 configuration space is not implemented and is not set as described
 in the PCIe specification."

Without the interrupt status bit, vfio-pci cannot determine when
these devices signal INTx.  They are therefore added to the nointx
quirk.

Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index de881a6cff35..b0258b79bb5b 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -207,6 +207,8 @@ static bool vfio_pci_nointx(struct pci_dev *pdev)
 		case 0x1580 ... 0x1581:
 		case 0x1583 ... 0x158b:
 		case 0x37d0 ... 0x37d2:
+		/* X550 */
+		case 0x1563:
 			return true;
 		default:
 			return false;

From e1907d6752a26ccfcda1573b5a7542b056553046 Mon Sep 17 00:00:00 2001
From: Xiang Zheng <zhengxiang9@huawei.com>
Date: Mon, 27 Jul 2020 13:43:37 -0600
Subject: [PATCH 127/474] vfio/type1: Add conditional rescheduling after iommu
 map failed

Commit c5e6688752c2 ("vfio/type1: Add conditional rescheduling")
missed a "cond_resched()" in vfio_iommu_map if iommu map failed.

This is a very tiny optimization and the case can hardly happen.

Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio_iommu_type1.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 5e556ac9102a..48fb9cc4a40a 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1225,8 +1225,10 @@ static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova,
 	return 0;
 
 unwind:
-	list_for_each_entry_continue_reverse(d, &iommu->domain_list, next)
+	list_for_each_entry_continue_reverse(d, &iommu->domain_list, next) {
 		iommu_unmap(d->domain, iova, npage << PAGE_SHIFT);
+		cond_resched();
+	}
 
 	return ret;
 }

From 9d532f286914add61e02312881733a90355f153c Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Mon, 27 Jul 2020 13:43:38 -0600
Subject: [PATCH 128/474] vfio/spapr_tce: convert get_user_pages() -->
 pin_user_pages()

This code was using get_user_pages*(), in a "Case 2" scenario
(DMA/RDMA), using the categorization from [1]. That means that it's
time to convert the get_user_pages*() + put_page() calls to
pin_user_pages*() + unpin_user_pages() calls.

There is some helpful background in [2]: basically, this is a small
part of fixing a long-standing disconnect between pinning pages, and
file systems' use of those pages.

[1] Documentation/core-api/pin_user_pages.rst

[2] "Explicit pinning of user-space pages":
    https://lwn.net/Articles/807108/

Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Cornelia Huck <cohuck@redhat.com>
Cc: kvm@vger.kernel.org
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio_iommu_spapr_tce.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 16b3adc508db..fe888b5dcc00 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -383,7 +383,7 @@ static void tce_iommu_unuse_page(struct tce_container *container,
 	struct page *page;
 
 	page = pfn_to_page(hpa >> PAGE_SHIFT);
-	put_page(page);
+	unpin_user_page(page);
 }
 
 static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
@@ -486,7 +486,7 @@ static int tce_iommu_use_page(unsigned long tce, unsigned long *hpa)
 	struct page *page = NULL;
 	enum dma_data_direction direction = iommu_tce_direction(tce);
 
-	if (get_user_pages_fast(tce & PAGE_MASK, 1,
+	if (pin_user_pages_fast(tce & PAGE_MASK, 1,
 			direction != DMA_TO_DEVICE ? FOLL_WRITE : 0,
 			&page) != 1)
 		return -EFAULT;

From 924b51abf961f1d888143fcfa3d63c92dc517679 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Mon, 27 Jul 2020 13:43:38 -0600
Subject: [PATCH 129/474] vfio/pci: Hold igate across releasing eventfd
 contexts

No need to release and immediately re-acquire igate while clearing
out the eventfd ctxs.

Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index b0258b79bb5b..dabca0450e6d 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -523,14 +523,12 @@ static void vfio_pci_release(void *device_data)
 		vfio_pci_vf_token_user_add(vdev, -1);
 		vfio_spapr_pci_eeh_release(vdev->pdev);
 		vfio_pci_disable(vdev);
+
 		mutex_lock(&vdev->igate);
 		if (vdev->err_trigger) {
 			eventfd_ctx_put(vdev->err_trigger);
 			vdev->err_trigger = NULL;
 		}
-		mutex_unlock(&vdev->igate);
-
-		mutex_lock(&vdev->igate);
 		if (vdev->req_trigger) {
 			eventfd_ctx_put(vdev->req_trigger);
 			vdev->req_trigger = NULL;

From 8b7beaf9f185249f29912b5e2d7bc4147c5c2a6a Mon Sep 17 00:00:00 2001
From: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Date: Mon, 27 Jul 2020 13:43:39 -0600
Subject: [PATCH 130/474] PCI: Add Intel QuickAssist device IDs

Add device IDs for the following Intel QuickAssist devices: DH895XCC,
C3XXX and C62X.

The defines in this patch are going to be referenced in two independent
drivers, qat and vfio-pci.

Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 include/linux/pci_ids.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 0ad57693f392..f3166b1425ca 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2659,6 +2659,8 @@
 #define PCI_DEVICE_ID_INTEL_80332_1	0x0332
 #define PCI_DEVICE_ID_INTEL_80333_0	0x0370
 #define PCI_DEVICE_ID_INTEL_80333_1	0x0372
+#define PCI_DEVICE_ID_INTEL_QAT_DH895XCC	0x0435
+#define PCI_DEVICE_ID_INTEL_QAT_DH895XCC_VF	0x0443
 #define PCI_DEVICE_ID_INTEL_82375	0x0482
 #define PCI_DEVICE_ID_INTEL_82424	0x0483
 #define PCI_DEVICE_ID_INTEL_82378	0x0484
@@ -2708,6 +2710,8 @@
 #define PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_4C_NHI     0x1577
 #define PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_4C_BRIDGE  0x1578
 #define PCI_DEVICE_ID_INTEL_80960_RP	0x1960
+#define PCI_DEVICE_ID_INTEL_QAT_C3XXX	0x19e2
+#define PCI_DEVICE_ID_INTEL_QAT_C3XXX_VF	0x19e3
 #define PCI_DEVICE_ID_INTEL_82840_HB	0x1a21
 #define PCI_DEVICE_ID_INTEL_82845_HB	0x1a30
 #define PCI_DEVICE_ID_INTEL_IOAT	0x1a38
@@ -2924,6 +2928,8 @@
 #define PCI_DEVICE_ID_INTEL_IOAT_JSF7	0x3717
 #define PCI_DEVICE_ID_INTEL_IOAT_JSF8	0x3718
 #define PCI_DEVICE_ID_INTEL_IOAT_JSF9	0x3719
+#define PCI_DEVICE_ID_INTEL_QAT_C62X	0x37c8
+#define PCI_DEVICE_ID_INTEL_QAT_C62X_VF	0x37c9
 #define PCI_DEVICE_ID_INTEL_ICH10_0	0x3a14
 #define PCI_DEVICE_ID_INTEL_ICH10_1	0x3a16
 #define PCI_DEVICE_ID_INTEL_ICH10_2	0x3a18

From 1f97970e6c8e60349b045599f4525608db895009 Mon Sep 17 00:00:00 2001
From: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Date: Mon, 27 Jul 2020 13:43:40 -0600
Subject: [PATCH 131/474] vfio/pci: Add device denylist

Add denylist of devices that by default are not probed by vfio-pci.
Devices in this list may be susceptible to untrusted application, even
if the IOMMU is enabled. To be accessed via vfio-pci, the user has to
explicitly disable the denylist.

The denylist can be disabled via the module parameter disable_denylist.

Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index dabca0450e6d..f368a3993ac1 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -60,6 +60,10 @@ module_param(enable_sriov, bool, 0644);
 MODULE_PARM_DESC(enable_sriov, "Enable support for SR-IOV configuration.  Enabling SR-IOV on a PF typically requires support of the userspace PF driver, enabling VFs without such support may result in non-functional VFs or PF.");
 #endif
 
+static bool disable_denylist;
+module_param(disable_denylist, bool, 0444);
+MODULE_PARM_DESC(disable_denylist, "Disable use of device denylist. Disabling the denylist allows binding to devices with known errata that may lead to exploitable stability or security issues when accessed by untrusted users.");
+
 static inline bool vfio_vga_disabled(void)
 {
 #ifdef CONFIG_VFIO_PCI_VGA
@@ -69,6 +73,29 @@ static inline bool vfio_vga_disabled(void)
 #endif
 }
 
+static bool vfio_pci_dev_in_denylist(struct pci_dev *pdev)
+{
+	return false;
+}
+
+static bool vfio_pci_is_denylisted(struct pci_dev *pdev)
+{
+	if (!vfio_pci_dev_in_denylist(pdev))
+		return false;
+
+	if (disable_denylist) {
+		pci_warn(pdev,
+			 "device denylist disabled - allowing device %04x:%04x.\n",
+			 pdev->vendor, pdev->device);
+		return false;
+	}
+
+	pci_warn(pdev, "%04x:%04x exists in vfio-pci device denylist, driver probing disallowed.\n",
+		 pdev->vendor, pdev->device);
+
+	return true;
+}
+
 /*
  * Our VGA arbiter participation is limited since we don't know anything
  * about the device itself.  However, if the device is the only VGA device
@@ -1856,6 +1883,9 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct iommu_group *group;
 	int ret;
 
+	if (vfio_pci_is_denylisted(pdev))
+		return -EINVAL;
+
 	if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
 		return -EINVAL;
 
@@ -2345,6 +2375,9 @@ static int __init vfio_pci_init(void)
 
 	vfio_pci_fill_ids();
 
+	if (disable_denylist)
+		pr_warn("device denylist disabled.\n");
+
 	return 0;
 
 out_driver:

From 50173329c8cc0c892eaa7a9d0f0692ac39cd7b04 Mon Sep 17 00:00:00 2001
From: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Date: Mon, 27 Jul 2020 13:43:40 -0600
Subject: [PATCH 132/474] vfio/pci: Add QAT devices to denylist
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The current generation of Intel® QuickAssist Technology devices
are not designed to run in an untrusted environment because of the
following issues reported in the document "Intel® QuickAssist Technology
(Intel® QAT) Software for Linux" (document number 336211-014):

QATE-39220 - GEN - Intel® QAT API submissions with bad addresses that
             trigger DMA to invalid or unmapped addresses can cause a
             platform hang
QATE-7495  - GEN - An incorrectly formatted request to Intel® QAT can
             hang the entire Intel® QAT Endpoint

The document is downloadable from https://01.org/intel-quickassist-technology
at the following link:
https://01.org/sites/default/files/downloads/336211-014-qatforlinux-releasenotes-hwv1.7_0.pdf

This patch adds the following QAT devices to the denylist: DH895XCC,
C3XXX and C62X.

Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reviewed-by: Fiona Trahe <fiona.trahe@intel.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index f368a3993ac1..620465c2a1da 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -75,6 +75,21 @@ static inline bool vfio_vga_disabled(void)
 
 static bool vfio_pci_dev_in_denylist(struct pci_dev *pdev)
 {
+	switch (pdev->vendor) {
+	case PCI_VENDOR_ID_INTEL:
+		switch (pdev->device) {
+		case PCI_DEVICE_ID_INTEL_QAT_C3XXX:
+		case PCI_DEVICE_ID_INTEL_QAT_C3XXX_VF:
+		case PCI_DEVICE_ID_INTEL_QAT_C62X:
+		case PCI_DEVICE_ID_INTEL_QAT_C62X_VF:
+		case PCI_DEVICE_ID_INTEL_QAT_DH895XCC:
+		case PCI_DEVICE_ID_INTEL_QAT_DH895XCC_VF:
+			return true;
+		default:
+			return false;
+		}
+	}
+
 	return false;
 }
 

From ccd59dce1a21f473518bf273bdf5b182bab955b3 Mon Sep 17 00:00:00 2001
From: Liu Yi L <yi.l.liu@intel.com>
Date: Sun, 12 Jul 2020 04:20:56 -0700
Subject: [PATCH 133/474] vfio/type1: Refactor vfio_iommu_type1_ioctl()

This patch refactors the vfio_iommu_type1_ioctl() to use switch instead of
if-else, and each command got a helper function.

Cc: Kevin Tian <kevin.tian@intel.com>
CC: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Eric Auger <eric.auger@redhat.com>
Cc: Jean-Philippe Brucker <jean-philippe@linaro.org>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio_iommu_type1.c | 490 +++++++++++++++++---------------
 1 file changed, 261 insertions(+), 229 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 48fb9cc4a40a..e1c00de50ff9 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -2455,6 +2455,23 @@ static int vfio_domains_have_iommu_cache(struct vfio_iommu *iommu)
 	return ret;
 }
 
+static int vfio_iommu_type1_check_extension(struct vfio_iommu *iommu,
+					    unsigned long arg)
+{
+	switch (arg) {
+	case VFIO_TYPE1_IOMMU:
+	case VFIO_TYPE1v2_IOMMU:
+	case VFIO_TYPE1_NESTING_IOMMU:
+		return 1;
+	case VFIO_DMA_CC_IOMMU:
+		if (!iommu)
+			return 0;
+		return vfio_domains_have_iommu_cache(iommu);
+	default:
+		return 0;
+	}
+}
+
 static int vfio_iommu_iova_add_cap(struct vfio_info_cap *caps,
 		 struct vfio_iommu_type1_info_cap_iova_range *cap_iovas,
 		 size_t size)
@@ -2531,241 +2548,256 @@ static int vfio_iommu_migration_build_caps(struct vfio_iommu *iommu,
 	return vfio_info_add_capability(caps, &cap_mig.header, sizeof(cap_mig));
 }
 
+static int vfio_iommu_type1_get_info(struct vfio_iommu *iommu,
+				     unsigned long arg)
+{
+	struct vfio_iommu_type1_info info;
+	unsigned long minsz;
+	struct vfio_info_cap caps = { .buf = NULL, .size = 0 };
+	unsigned long capsz;
+	int ret;
+
+	minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes);
+
+	/* For backward compatibility, cannot require this */
+	capsz = offsetofend(struct vfio_iommu_type1_info, cap_offset);
+
+	if (copy_from_user(&info, (void __user *)arg, minsz))
+		return -EFAULT;
+
+	if (info.argsz < minsz)
+		return -EINVAL;
+
+	if (info.argsz >= capsz) {
+		minsz = capsz;
+		info.cap_offset = 0; /* output, no-recopy necessary */
+	}
+
+	mutex_lock(&iommu->lock);
+	info.flags = VFIO_IOMMU_INFO_PGSIZES;
+
+	info.iova_pgsizes = iommu->pgsize_bitmap;
+
+	ret = vfio_iommu_migration_build_caps(iommu, &caps);
+
+	if (!ret)
+		ret = vfio_iommu_iova_build_caps(iommu, &caps);
+
+	mutex_unlock(&iommu->lock);
+
+	if (ret)
+		return ret;
+
+	if (caps.size) {
+		info.flags |= VFIO_IOMMU_INFO_CAPS;
+
+		if (info.argsz < sizeof(info) + caps.size) {
+			info.argsz = sizeof(info) + caps.size;
+		} else {
+			vfio_info_cap_shift(&caps, sizeof(info));
+			if (copy_to_user((void __user *)arg +
+					sizeof(info), caps.buf,
+					caps.size)) {
+				kfree(caps.buf);
+				return -EFAULT;
+			}
+			info.cap_offset = sizeof(info);
+		}
+
+		kfree(caps.buf);
+	}
+
+	return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
+}
+
+static int vfio_iommu_type1_map_dma(struct vfio_iommu *iommu,
+				    unsigned long arg)
+{
+	struct vfio_iommu_type1_dma_map map;
+	unsigned long minsz;
+	uint32_t mask = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE;
+
+	minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
+
+	if (copy_from_user(&map, (void __user *)arg, minsz))
+		return -EFAULT;
+
+	if (map.argsz < minsz || map.flags & ~mask)
+		return -EINVAL;
+
+	return vfio_dma_do_map(iommu, &map);
+}
+
+static int vfio_iommu_type1_unmap_dma(struct vfio_iommu *iommu,
+				      unsigned long arg)
+{
+	struct vfio_iommu_type1_dma_unmap unmap;
+	struct vfio_bitmap bitmap = { 0 };
+	unsigned long minsz;
+	int ret;
+
+	minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size);
+
+	if (copy_from_user(&unmap, (void __user *)arg, minsz))
+		return -EFAULT;
+
+	if (unmap.argsz < minsz ||
+	    unmap.flags & ~VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP)
+		return -EINVAL;
+
+	if (unmap.flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) {
+		unsigned long pgshift;
+
+		if (unmap.argsz < (minsz + sizeof(bitmap)))
+			return -EINVAL;
+
+		if (copy_from_user(&bitmap,
+				   (void __user *)(arg + minsz),
+				   sizeof(bitmap)))
+			return -EFAULT;
+
+		if (!access_ok((void __user *)bitmap.data, bitmap.size))
+			return -EINVAL;
+
+		pgshift = __ffs(bitmap.pgsize);
+		ret = verify_bitmap_size(unmap.size >> pgshift,
+					 bitmap.size);
+		if (ret)
+			return ret;
+	}
+
+	ret = vfio_dma_do_unmap(iommu, &unmap, &bitmap);
+	if (ret)
+		return ret;
+
+	return copy_to_user((void __user *)arg, &unmap, minsz) ?
+			-EFAULT : 0;
+}
+
+static int vfio_iommu_type1_dirty_pages(struct vfio_iommu *iommu,
+					unsigned long arg)
+{
+	struct vfio_iommu_type1_dirty_bitmap dirty;
+	uint32_t mask = VFIO_IOMMU_DIRTY_PAGES_FLAG_START |
+			VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP |
+			VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP;
+	unsigned long minsz;
+	int ret = 0;
+
+	if (!iommu->v2)
+		return -EACCES;
+
+	minsz = offsetofend(struct vfio_iommu_type1_dirty_bitmap, flags);
+
+	if (copy_from_user(&dirty, (void __user *)arg, minsz))
+		return -EFAULT;
+
+	if (dirty.argsz < minsz || dirty.flags & ~mask)
+		return -EINVAL;
+
+	/* only one flag should be set at a time */
+	if (__ffs(dirty.flags) != __fls(dirty.flags))
+		return -EINVAL;
+
+	if (dirty.flags & VFIO_IOMMU_DIRTY_PAGES_FLAG_START) {
+		size_t pgsize;
+
+		mutex_lock(&iommu->lock);
+		pgsize = 1 << __ffs(iommu->pgsize_bitmap);
+		if (!iommu->dirty_page_tracking) {
+			ret = vfio_dma_bitmap_alloc_all(iommu, pgsize);
+			if (!ret)
+				iommu->dirty_page_tracking = true;
+		}
+		mutex_unlock(&iommu->lock);
+		return ret;
+	} else if (dirty.flags & VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP) {
+		mutex_lock(&iommu->lock);
+		if (iommu->dirty_page_tracking) {
+			iommu->dirty_page_tracking = false;
+			vfio_dma_bitmap_free_all(iommu);
+		}
+		mutex_unlock(&iommu->lock);
+		return 0;
+	} else if (dirty.flags & VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP) {
+		struct vfio_iommu_type1_dirty_bitmap_get range;
+		unsigned long pgshift;
+		size_t data_size = dirty.argsz - minsz;
+		size_t iommu_pgsize;
+
+		if (!data_size || data_size < sizeof(range))
+			return -EINVAL;
+
+		if (copy_from_user(&range, (void __user *)(arg + minsz),
+				   sizeof(range)))
+			return -EFAULT;
+
+		if (range.iova + range.size < range.iova)
+			return -EINVAL;
+		if (!access_ok((void __user *)range.bitmap.data,
+			       range.bitmap.size))
+			return -EINVAL;
+
+		pgshift = __ffs(range.bitmap.pgsize);
+		ret = verify_bitmap_size(range.size >> pgshift,
+					 range.bitmap.size);
+		if (ret)
+			return ret;
+
+		mutex_lock(&iommu->lock);
+
+		iommu_pgsize = (size_t)1 << __ffs(iommu->pgsize_bitmap);
+
+		/* allow only smallest supported pgsize */
+		if (range.bitmap.pgsize != iommu_pgsize) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+		if (range.iova & (iommu_pgsize - 1)) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+		if (!range.size || range.size & (iommu_pgsize - 1)) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
+		if (iommu->dirty_page_tracking)
+			ret = vfio_iova_dirty_bitmap(range.bitmap.data,
+						     iommu, range.iova,
+						     range.size,
+						     range.bitmap.pgsize);
+		else
+			ret = -EINVAL;
+out_unlock:
+		mutex_unlock(&iommu->lock);
+
+		return ret;
+	}
+
+	return -EINVAL;
+}
+
 static long vfio_iommu_type1_ioctl(void *iommu_data,
 				   unsigned int cmd, unsigned long arg)
 {
 	struct vfio_iommu *iommu = iommu_data;
-	unsigned long minsz;
 
-	if (cmd == VFIO_CHECK_EXTENSION) {
-		switch (arg) {
-		case VFIO_TYPE1_IOMMU:
-		case VFIO_TYPE1v2_IOMMU:
-		case VFIO_TYPE1_NESTING_IOMMU:
-			return 1;
-		case VFIO_DMA_CC_IOMMU:
-			if (!iommu)
-				return 0;
-			return vfio_domains_have_iommu_cache(iommu);
-		default:
-			return 0;
-		}
-	} else if (cmd == VFIO_IOMMU_GET_INFO) {
-		struct vfio_iommu_type1_info info;
-		struct vfio_info_cap caps = { .buf = NULL, .size = 0 };
-		unsigned long capsz;
-		int ret;
-
-		minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes);
-
-		/* For backward compatibility, cannot require this */
-		capsz = offsetofend(struct vfio_iommu_type1_info, cap_offset);
-
-		if (copy_from_user(&info, (void __user *)arg, minsz))
-			return -EFAULT;
-
-		if (info.argsz < minsz)
-			return -EINVAL;
-
-		if (info.argsz >= capsz) {
-			minsz = capsz;
-			info.cap_offset = 0; /* output, no-recopy necessary */
-		}
-
-		mutex_lock(&iommu->lock);
-		info.flags = VFIO_IOMMU_INFO_PGSIZES;
-
-		info.iova_pgsizes = iommu->pgsize_bitmap;
-
-		ret = vfio_iommu_migration_build_caps(iommu, &caps);
-
-		if (!ret)
-			ret = vfio_iommu_iova_build_caps(iommu, &caps);
-
-		mutex_unlock(&iommu->lock);
-
-		if (ret)
-			return ret;
-
-		if (caps.size) {
-			info.flags |= VFIO_IOMMU_INFO_CAPS;
-
-			if (info.argsz < sizeof(info) + caps.size) {
-				info.argsz = sizeof(info) + caps.size;
-			} else {
-				vfio_info_cap_shift(&caps, sizeof(info));
-				if (copy_to_user((void __user *)arg +
-						sizeof(info), caps.buf,
-						caps.size)) {
-					kfree(caps.buf);
-					return -EFAULT;
-				}
-				info.cap_offset = sizeof(info);
-			}
-
-			kfree(caps.buf);
-		}
-
-		return copy_to_user((void __user *)arg, &info, minsz) ?
-			-EFAULT : 0;
-
-	} else if (cmd == VFIO_IOMMU_MAP_DMA) {
-		struct vfio_iommu_type1_dma_map map;
-		uint32_t mask = VFIO_DMA_MAP_FLAG_READ |
-				VFIO_DMA_MAP_FLAG_WRITE;
-
-		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
-
-		if (copy_from_user(&map, (void __user *)arg, minsz))
-			return -EFAULT;
-
-		if (map.argsz < minsz || map.flags & ~mask)
-			return -EINVAL;
-
-		return vfio_dma_do_map(iommu, &map);
-
-	} else if (cmd == VFIO_IOMMU_UNMAP_DMA) {
-		struct vfio_iommu_type1_dma_unmap unmap;
-		struct vfio_bitmap bitmap = { 0 };
-		int ret;
-
-		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size);
-
-		if (copy_from_user(&unmap, (void __user *)arg, minsz))
-			return -EFAULT;
-
-		if (unmap.argsz < minsz ||
-		    unmap.flags & ~VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP)
-			return -EINVAL;
-
-		if (unmap.flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) {
-			unsigned long pgshift;
-
-			if (unmap.argsz < (minsz + sizeof(bitmap)))
-				return -EINVAL;
-
-			if (copy_from_user(&bitmap,
-					   (void __user *)(arg + minsz),
-					   sizeof(bitmap)))
-				return -EFAULT;
-
-			if (!access_ok((void __user *)bitmap.data, bitmap.size))
-				return -EINVAL;
-
-			pgshift = __ffs(bitmap.pgsize);
-			ret = verify_bitmap_size(unmap.size >> pgshift,
-						 bitmap.size);
-			if (ret)
-				return ret;
-		}
-
-		ret = vfio_dma_do_unmap(iommu, &unmap, &bitmap);
-		if (ret)
-			return ret;
-
-		return copy_to_user((void __user *)arg, &unmap, minsz) ?
-			-EFAULT : 0;
-	} else if (cmd == VFIO_IOMMU_DIRTY_PAGES) {
-		struct vfio_iommu_type1_dirty_bitmap dirty;
-		uint32_t mask = VFIO_IOMMU_DIRTY_PAGES_FLAG_START |
-				VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP |
-				VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP;
-		int ret = 0;
-
-		if (!iommu->v2)
-			return -EACCES;
-
-		minsz = offsetofend(struct vfio_iommu_type1_dirty_bitmap,
-				    flags);
-
-		if (copy_from_user(&dirty, (void __user *)arg, minsz))
-			return -EFAULT;
-
-		if (dirty.argsz < minsz || dirty.flags & ~mask)
-			return -EINVAL;
-
-		/* only one flag should be set at a time */
-		if (__ffs(dirty.flags) != __fls(dirty.flags))
-			return -EINVAL;
-
-		if (dirty.flags & VFIO_IOMMU_DIRTY_PAGES_FLAG_START) {
-			size_t pgsize;
-
-			mutex_lock(&iommu->lock);
-			pgsize = 1 << __ffs(iommu->pgsize_bitmap);
-			if (!iommu->dirty_page_tracking) {
-				ret = vfio_dma_bitmap_alloc_all(iommu, pgsize);
-				if (!ret)
-					iommu->dirty_page_tracking = true;
-			}
-			mutex_unlock(&iommu->lock);
-			return ret;
-		} else if (dirty.flags & VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP) {
-			mutex_lock(&iommu->lock);
-			if (iommu->dirty_page_tracking) {
-				iommu->dirty_page_tracking = false;
-				vfio_dma_bitmap_free_all(iommu);
-			}
-			mutex_unlock(&iommu->lock);
-			return 0;
-		} else if (dirty.flags &
-				 VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP) {
-			struct vfio_iommu_type1_dirty_bitmap_get range;
-			unsigned long pgshift;
-			size_t data_size = dirty.argsz - minsz;
-			size_t iommu_pgsize;
-
-			if (!data_size || data_size < sizeof(range))
-				return -EINVAL;
-
-			if (copy_from_user(&range, (void __user *)(arg + minsz),
-					   sizeof(range)))
-				return -EFAULT;
-
-			if (range.iova + range.size < range.iova)
-				return -EINVAL;
-			if (!access_ok((void __user *)range.bitmap.data,
-				       range.bitmap.size))
-				return -EINVAL;
-
-			pgshift = __ffs(range.bitmap.pgsize);
-			ret = verify_bitmap_size(range.size >> pgshift,
-						 range.bitmap.size);
-			if (ret)
-				return ret;
-
-			mutex_lock(&iommu->lock);
-
-			iommu_pgsize = (size_t)1 << __ffs(iommu->pgsize_bitmap);
-
-			/* allow only smallest supported pgsize */
-			if (range.bitmap.pgsize != iommu_pgsize) {
-				ret = -EINVAL;
-				goto out_unlock;
-			}
-			if (range.iova & (iommu_pgsize - 1)) {
-				ret = -EINVAL;
-				goto out_unlock;
-			}
-			if (!range.size || range.size & (iommu_pgsize - 1)) {
-				ret = -EINVAL;
-				goto out_unlock;
-			}
-
-			if (iommu->dirty_page_tracking)
-				ret = vfio_iova_dirty_bitmap(range.bitmap.data,
-						iommu, range.iova, range.size,
-						range.bitmap.pgsize);
-			else
-				ret = -EINVAL;
-out_unlock:
-			mutex_unlock(&iommu->lock);
-
-			return ret;
-		}
+	switch (cmd) {
+	case VFIO_CHECK_EXTENSION:
+		return vfio_iommu_type1_check_extension(iommu, arg);
+	case VFIO_IOMMU_GET_INFO:
+		return vfio_iommu_type1_get_info(iommu, arg);
+	case VFIO_IOMMU_MAP_DMA:
+		return vfio_iommu_type1_map_dma(iommu, arg);
+	case VFIO_IOMMU_UNMAP_DMA:
+		return vfio_iommu_type1_unmap_dma(iommu, arg);
+	case VFIO_IOMMU_DIRTY_PAGES:
+		return vfio_iommu_type1_dirty_pages(iommu, arg);
+	default:
+		return -ENOTTY;
 	}
-
-	return -ENOTTY;
 }
 
 static int vfio_iommu_type1_register_notifier(void *iommu_data,

From 175233f92e80d09f78be51e5b9abf5ca1fc9dc26 Mon Sep 17 00:00:00 2001
From: Li Heng <liheng40@huawei.com>
Date: Thu, 23 Jul 2020 11:27:42 +0800
Subject: [PATCH 134/474] drm: Remove redundant NULL check

Fix below warnings reported by coccicheck:
./drivers/gpu/drm/drm_drv.c:819:2-7: WARNING: NULL check before some freeing functions is not needed.

Fixes: 5dad34f3c444 ("drm: Cleanups after drmm_add_final_kfree rollout")
Signed-off-by: Li Heng <liheng40@huawei.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/1595474863-33112-1-git-send-email-liheng40@huawei.com
---
 drivers/gpu/drm/drm_drv.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index bc38322f306e..13068fdf4331 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -815,8 +815,7 @@ static void drm_dev_release(struct kref *ref)
 
 	drm_managed_release(dev);
 
-	if (dev->managed.final_kfree)
-		kfree(dev->managed.final_kfree);
+	kfree(dev->managed.final_kfree);
 }
 
 /**

From b538304da7855f4e31f91f915f259936eb67a1e6 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konradybcio@gmail.com>
Date: Sun, 26 Jul 2020 13:11:58 +0200
Subject: [PATCH 135/474] clk: qcom: gcc-sdm660: Add missing modem reset

This will be required in order to support the
modem upstream.

Signed-off-by: Konrad Dybcio <konradybcio@gmail.com>
Link: https://lore.kernel.org/r/20200726111215.22361-2-konradybcio@gmail.com
Fixes: f2a76a2955c0 ("clk: qcom: Add Global Clock controller (GCC) driver for SDM660")
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/gcc-sdm660.c               | 1 +
 include/dt-bindings/clock/qcom,gcc-sdm660.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/clk/qcom/gcc-sdm660.c b/drivers/clk/qcom/gcc-sdm660.c
index bf5730832ef3..a85283786278 100644
--- a/drivers/clk/qcom/gcc-sdm660.c
+++ b/drivers/clk/qcom/gcc-sdm660.c
@@ -2402,6 +2402,7 @@ static const struct qcom_reset_map gcc_sdm660_resets[] = {
 	[GCC_USB_20_BCR] = { 0x2f000 },
 	[GCC_USB_30_BCR] = { 0xf000 },
 	[GCC_USB_PHY_CFG_AHB2PHY_BCR] = { 0x6a000 },
+	[GCC_MSS_RESTART] = { 0x79000 },
 };
 
 static const struct regmap_config gcc_sdm660_regmap_config = {
diff --git a/include/dt-bindings/clock/qcom,gcc-sdm660.h b/include/dt-bindings/clock/qcom,gcc-sdm660.h
index 468302282913..df8a6f3d367e 100644
--- a/include/dt-bindings/clock/qcom,gcc-sdm660.h
+++ b/include/dt-bindings/clock/qcom,gcc-sdm660.h
@@ -152,5 +152,6 @@
 #define GCC_USB_20_BCR                  6
 #define GCC_USB_30_BCR			7
 #define GCC_USB_PHY_CFG_AHB2PHY_BCR	8
+#define GCC_MSS_RESTART			9
 
 #endif

From 3386af51d3bcebcba3f7becdb1ef2e384abe90cf Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konradybcio@gmail.com>
Date: Sun, 26 Jul 2020 13:12:05 +0200
Subject: [PATCH 136/474] clk: qcom: gcc-sdm660: Fix up
 gcc_mss_mnoc_bimc_axi_clk

Add missing halt_check, hwcg_reg and hwcg_bit properties.
These were likely omitted when porting the driver upstream.

Signed-off-by: Konrad Dybcio <konradybcio@gmail.com>
Link: https://lore.kernel.org/r/20200726111215.22361-9-konradybcio@gmail.com
Fixes: f2a76a2955c0 ("clk: qcom: Add Global Clock controller (GCC) driver for SDM660")
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/gcc-sdm660.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/clk/qcom/gcc-sdm660.c b/drivers/clk/qcom/gcc-sdm660.c
index a85283786278..f0b47b7d50ca 100644
--- a/drivers/clk/qcom/gcc-sdm660.c
+++ b/drivers/clk/qcom/gcc-sdm660.c
@@ -1715,6 +1715,9 @@ static struct clk_branch gcc_mss_cfg_ahb_clk = {
 
 static struct clk_branch gcc_mss_mnoc_bimc_axi_clk = {
 	.halt_reg = 0x8a004,
+	.halt_check = BRANCH_HALT,
+	.hwcg_reg = 0x8a004,
+	.hwcg_bit = 1,
 	.clkr = {
 		.enable_reg = 0x8a004,
 		.enable_mask = BIT(0),

From d388e18f63b90a1256af490a856d67abd6558a38 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Mon, 27 Jul 2020 15:09:22 -0500
Subject: [PATCH 137/474] clk: imx: Use fallthrough pseudo-keyword

Replace the existing /* fall through */ comments and its variants with
the new pseudo-keyword macro fallthrough[1].

[1] https://www.kernel.org/doc/html/v5.7/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-through

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20200727200922.GA2326@embeddedor
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-pllv3.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/imx/clk-pllv3.c b/drivers/clk/imx/clk-pllv3.c
index a7db93030e02..b20cdea3e9cc 100644
--- a/drivers/clk/imx/clk-pllv3.c
+++ b/drivers/clk/imx/clk-pllv3.c
@@ -433,7 +433,7 @@ struct clk_hw *imx_clk_hw_pllv3(enum imx_pllv3_type type, const char *name,
 		break;
 	case IMX_PLLV3_USB_VF610:
 		pll->div_shift = 1;
-		/* fall through */
+		fallthrough;
 	case IMX_PLLV3_USB:
 		ops = &clk_pllv3_ops;
 		pll->powerup_set = true;
@@ -441,7 +441,7 @@ struct clk_hw *imx_clk_hw_pllv3(enum imx_pllv3_type type, const char *name,
 	case IMX_PLLV3_AV_IMX7:
 		pll->num_offset = PLL_IMX7_NUM_OFFSET;
 		pll->denom_offset = PLL_IMX7_DENOM_OFFSET;
-		/* fall through */
+		fallthrough;
 	case IMX_PLLV3_AV:
 		ops = &clk_pllv3_av_ops;
 		break;

From 7a346a37e46abd9bfe0e24aa2aabb68d832280b8 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Mon, 27 Jul 2020 15:11:22 -0500
Subject: [PATCH 138/474] clk: davinci: Use fallthrough pseudo-keyword

Replace the existing /* fall through */ comments and its variants with
the new pseudo-keyword macro fallthrough[1].

[1] https://www.kernel.org/doc/html/v5.7/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-through

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20200727201122.GA2593@embeddedor
Reviewed-by: David Lechner <david@lechnology.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/davinci/pll.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/davinci/pll.c b/drivers/clk/davinci/pll.c
index 8a23d5dfd1f8..6c35e4bb7940 100644
--- a/drivers/clk/davinci/pll.c
+++ b/drivers/clk/davinci/pll.c
@@ -651,7 +651,7 @@ static int davinci_pll_sysclk_rate_change(struct notifier_block *nb,
 		pllcmd = readl(pll->base + PLLCMD);
 		pllcmd |= PLLCMD_GOSET;
 		writel(pllcmd, pll->base + PLLCMD);
-		/* fallthrough */
+		fallthrough;
 	case PRE_RATE_CHANGE:
 		/* Wait until for outstanding changes to take effect */
 		do {

From 316810e883fbcfd88167fd53858294bf0c2bcd40 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=91=A8=E7=90=B0=E6=9D=B0=20=28Zhou=20Yanjie=29?=
 <zhouyanjie@wanyeetech.com>
Date: Sat, 25 Jul 2020 13:11:34 +0800
Subject: [PATCH 139/474] dt-bindings: clock: Add RTC related clocks for
 Ingenic SoCs.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add RTC related clocks bindings for the JZ4780 SoC, the X1000 SoC,
and the X1830 SoC from Ingenic.

Tested-by: 周正 (Zhou Zheng) <sernia.zhou@foxmail.com>
Signed-off-by: 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
Link: https://lore.kernel.org/r/20200725051136.58220-2-zhouyanjie@wanyeetech.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 include/dt-bindings/clock/jz4780-cgu.h | 2 ++
 include/dt-bindings/clock/x1000-cgu.h  | 2 ++
 include/dt-bindings/clock/x1830-cgu.h  | 2 ++
 3 files changed, 6 insertions(+)

diff --git a/include/dt-bindings/clock/jz4780-cgu.h b/include/dt-bindings/clock/jz4780-cgu.h
index 1859ce53ee38..cb07a0978301 100644
--- a/include/dt-bindings/clock/jz4780-cgu.h
+++ b/include/dt-bindings/clock/jz4780-cgu.h
@@ -85,5 +85,7 @@
 #define JZ4780_CLK_DES		70
 #define JZ4780_CLK_X2D		71
 #define JZ4780_CLK_CORE1	72
+#define JZ4780_CLK_EXCLK_DIV512	73
+#define JZ4780_CLK_RTC		74
 
 #endif /* __DT_BINDINGS_CLOCK_JZ4780_CGU_H__ */
diff --git a/include/dt-bindings/clock/x1000-cgu.h b/include/dt-bindings/clock/x1000-cgu.h
index 0367c8c02e16..f187e0719fd3 100644
--- a/include/dt-bindings/clock/x1000-cgu.h
+++ b/include/dt-bindings/clock/x1000-cgu.h
@@ -48,5 +48,7 @@
 #define X1000_CLK_SSI			33
 #define X1000_CLK_OST			34
 #define X1000_CLK_PDMA			35
+#define X1000_CLK_EXCLK_DIV512	36
+#define X1000_CLK_RTC			37
 
 #endif /* __DT_BINDINGS_CLOCK_X1000_CGU_H__ */
diff --git a/include/dt-bindings/clock/x1830-cgu.h b/include/dt-bindings/clock/x1830-cgu.h
index 801e1d09c881..88455376a950 100644
--- a/include/dt-bindings/clock/x1830-cgu.h
+++ b/include/dt-bindings/clock/x1830-cgu.h
@@ -51,5 +51,7 @@
 #define X1830_CLK_TCU			36
 #define X1830_CLK_DTRNG			37
 #define X1830_CLK_OST			38
+#define X1830_CLK_EXCLK_DIV512	39
+#define X1830_CLK_RTC			40
 
 #endif /* __DT_BINDINGS_CLOCK_X1830_CGU_H__ */

From acb3b78de3f7698724e59719fbe50b8c92928e83 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=91=A8=E7=90=B0=E6=9D=B0=20=28Zhou=20Yanjie=29?=
 <zhouyanjie@wanyeetech.com>
Date: Sat, 25 Jul 2020 13:11:35 +0800
Subject: [PATCH 140/474] dt-bindings: clock: Add tabs to align code.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The "JZ4780_CLK_LCD0PIXCLK" and the "JZ4780_CLK_LCD1PIXCLK"
in the "jz4780.h" and the new added "JZ4780_CLK_EXCLK_DIV512"
in the previous patch is too long, add tabs to other lines
to align them.

Tested-by: 周正 (Zhou Zheng) <sernia.zhou@foxmail.com>
Signed-off-by: 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
Link: https://lore.kernel.org/r/20200725051136.58220-3-zhouyanjie@wanyeetech.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 include/dt-bindings/clock/jz4780-cgu.h | 144 ++++++++++++-------------
 1 file changed, 72 insertions(+), 72 deletions(-)

diff --git a/include/dt-bindings/clock/jz4780-cgu.h b/include/dt-bindings/clock/jz4780-cgu.h
index cb07a0978301..85cf8eb5081b 100644
--- a/include/dt-bindings/clock/jz4780-cgu.h
+++ b/include/dt-bindings/clock/jz4780-cgu.h
@@ -12,80 +12,80 @@
 #ifndef __DT_BINDINGS_CLOCK_JZ4780_CGU_H__
 #define __DT_BINDINGS_CLOCK_JZ4780_CGU_H__
 
-#define JZ4780_CLK_EXCLK	0
-#define JZ4780_CLK_RTCLK	1
-#define JZ4780_CLK_APLL		2
-#define JZ4780_CLK_MPLL		3
-#define JZ4780_CLK_EPLL		4
-#define JZ4780_CLK_VPLL		5
-#define JZ4780_CLK_OTGPHY	6
-#define JZ4780_CLK_SCLKA	7
-#define JZ4780_CLK_CPUMUX	8
-#define JZ4780_CLK_CPU		9
-#define JZ4780_CLK_L2CACHE	10
-#define JZ4780_CLK_AHB0		11
-#define JZ4780_CLK_AHB2PMUX	12
-#define JZ4780_CLK_AHB2		13
-#define JZ4780_CLK_PCLK		14
-#define JZ4780_CLK_DDR		15
-#define JZ4780_CLK_VPU		16
-#define JZ4780_CLK_I2SPLL	17
-#define JZ4780_CLK_I2S		18
+#define JZ4780_CLK_EXCLK		0
+#define JZ4780_CLK_RTCLK		1
+#define JZ4780_CLK_APLL			2
+#define JZ4780_CLK_MPLL			3
+#define JZ4780_CLK_EPLL			4
+#define JZ4780_CLK_VPLL			5
+#define JZ4780_CLK_OTGPHY		6
+#define JZ4780_CLK_SCLKA		7
+#define JZ4780_CLK_CPUMUX		8
+#define JZ4780_CLK_CPU			9
+#define JZ4780_CLK_L2CACHE		10
+#define JZ4780_CLK_AHB0			11
+#define JZ4780_CLK_AHB2PMUX		12
+#define JZ4780_CLK_AHB2			13
+#define JZ4780_CLK_PCLK			14
+#define JZ4780_CLK_DDR			15
+#define JZ4780_CLK_VPU			16
+#define JZ4780_CLK_I2SPLL		17
+#define JZ4780_CLK_I2S			18
 #define JZ4780_CLK_LCD0PIXCLK	19
 #define JZ4780_CLK_LCD1PIXCLK	20
-#define JZ4780_CLK_MSCMUX	21
-#define JZ4780_CLK_MSC0		22
-#define JZ4780_CLK_MSC1		23
-#define JZ4780_CLK_MSC2		24
-#define JZ4780_CLK_UHC		25
-#define JZ4780_CLK_SSIPLL	26
-#define JZ4780_CLK_SSI		27
-#define JZ4780_CLK_CIMMCLK	28
-#define JZ4780_CLK_PCMPLL	29
-#define JZ4780_CLK_PCM		30
-#define JZ4780_CLK_GPU		31
-#define JZ4780_CLK_HDMI		32
-#define JZ4780_CLK_BCH		33
-#define JZ4780_CLK_NEMC		34
-#define JZ4780_CLK_OTG0		35
-#define JZ4780_CLK_SSI0		36
-#define JZ4780_CLK_SMB0		37
-#define JZ4780_CLK_SMB1		38
-#define JZ4780_CLK_SCC		39
-#define JZ4780_CLK_AIC		40
-#define JZ4780_CLK_TSSI0	41
-#define JZ4780_CLK_OWI		42
-#define JZ4780_CLK_KBC		43
-#define JZ4780_CLK_SADC		44
-#define JZ4780_CLK_UART0	45
-#define JZ4780_CLK_UART1	46
-#define JZ4780_CLK_UART2	47
-#define JZ4780_CLK_UART3	48
-#define JZ4780_CLK_SSI1		49
-#define JZ4780_CLK_SSI2		50
-#define JZ4780_CLK_PDMA		51
-#define JZ4780_CLK_GPS		52
-#define JZ4780_CLK_MAC		53
-#define JZ4780_CLK_SMB2		54
-#define JZ4780_CLK_CIM		55
-#define JZ4780_CLK_LCD		56
-#define JZ4780_CLK_TVE		57
-#define JZ4780_CLK_IPU		58
-#define JZ4780_CLK_DDR0		59
-#define JZ4780_CLK_DDR1		60
-#define JZ4780_CLK_SMB3		61
-#define JZ4780_CLK_TSSI1	62
-#define JZ4780_CLK_COMPRESS	63
-#define JZ4780_CLK_AIC1		64
-#define JZ4780_CLK_GPVLC	65
-#define JZ4780_CLK_OTG1		66
-#define JZ4780_CLK_UART4	67
-#define JZ4780_CLK_AHBMON	68
-#define JZ4780_CLK_SMB4		69
-#define JZ4780_CLK_DES		70
-#define JZ4780_CLK_X2D		71
-#define JZ4780_CLK_CORE1	72
+#define JZ4780_CLK_MSCMUX		21
+#define JZ4780_CLK_MSC0			22
+#define JZ4780_CLK_MSC1			23
+#define JZ4780_CLK_MSC2			24
+#define JZ4780_CLK_UHC			25
+#define JZ4780_CLK_SSIPLL		26
+#define JZ4780_CLK_SSI			27
+#define JZ4780_CLK_CIMMCLK		28
+#define JZ4780_CLK_PCMPLL		29
+#define JZ4780_CLK_PCM			30
+#define JZ4780_CLK_GPU			31
+#define JZ4780_CLK_HDMI			32
+#define JZ4780_CLK_BCH			33
+#define JZ4780_CLK_NEMC			34
+#define JZ4780_CLK_OTG0			35
+#define JZ4780_CLK_SSI0			36
+#define JZ4780_CLK_SMB0			37
+#define JZ4780_CLK_SMB1			38
+#define JZ4780_CLK_SCC			39
+#define JZ4780_CLK_AIC			40
+#define JZ4780_CLK_TSSI0		41
+#define JZ4780_CLK_OWI			42
+#define JZ4780_CLK_KBC			43
+#define JZ4780_CLK_SADC			44
+#define JZ4780_CLK_UART0		45
+#define JZ4780_CLK_UART1		46
+#define JZ4780_CLK_UART2		47
+#define JZ4780_CLK_UART3		48
+#define JZ4780_CLK_SSI1			49
+#define JZ4780_CLK_SSI2			50
+#define JZ4780_CLK_PDMA			51
+#define JZ4780_CLK_GPS			52
+#define JZ4780_CLK_MAC			53
+#define JZ4780_CLK_SMB2			54
+#define JZ4780_CLK_CIM			55
+#define JZ4780_CLK_LCD			56
+#define JZ4780_CLK_TVE			57
+#define JZ4780_CLK_IPU			58
+#define JZ4780_CLK_DDR0			59
+#define JZ4780_CLK_DDR1			60
+#define JZ4780_CLK_SMB3			61
+#define JZ4780_CLK_TSSI1		62
+#define JZ4780_CLK_COMPRESS		63
+#define JZ4780_CLK_AIC1			64
+#define JZ4780_CLK_GPVLC		65
+#define JZ4780_CLK_OTG1			66
+#define JZ4780_CLK_UART4		67
+#define JZ4780_CLK_AHBMON		68
+#define JZ4780_CLK_SMB4			69
+#define JZ4780_CLK_DES			70
+#define JZ4780_CLK_X2D			71
+#define JZ4780_CLK_CORE1		72
 #define JZ4780_CLK_EXCLK_DIV512	73
-#define JZ4780_CLK_RTC		74
+#define JZ4780_CLK_RTC			74
 
 #endif /* __DT_BINDINGS_CLOCK_JZ4780_CGU_H__ */

From 82df5b7329aaeb21b3e8fc86fa2d62a3d68602aa Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=91=A8=E7=90=B0=E6=9D=B0=20=28Zhou=20Yanjie=29?=
 <zhouyanjie@wanyeetech.com>
Date: Sat, 25 Jul 2020 13:11:36 +0800
Subject: [PATCH 141/474] clk: Ingenic: Add RTC related clocks for Ingenic
 SoCs.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The RTC unit in the Ingenic SoCs has two clock sources, one
is from an external 32.768kHz clock, and the other is from an
external 24MHz/48MHz main clock that is divided by 512. The
choice of these two clocks is controlled by the ERCS bit in
the OPCR register. The RNG unit will also use this clock.

Tested-by: 周正 (Zhou Zheng) <sernia.zhou@foxmail.com>
Signed-off-by: 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
Link: https://lore.kernel.org/r/20200725051136.58220-4-zhouyanjie@wanyeetech.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/ingenic/jz4780-cgu.c | 12 ++++++++++++
 drivers/clk/ingenic/x1000-cgu.c  | 13 +++++++++++++
 drivers/clk/ingenic/x1830-cgu.c  | 13 +++++++++++++
 3 files changed, 38 insertions(+)

diff --git a/drivers/clk/ingenic/jz4780-cgu.c b/drivers/clk/ingenic/jz4780-cgu.c
index 6c5b8029cc8a..288e9694285b 100644
--- a/drivers/clk/ingenic/jz4780-cgu.c
+++ b/drivers/clk/ingenic/jz4780-cgu.c
@@ -516,6 +516,18 @@ static const struct ingenic_cgu_clk_info jz4780_cgu_clocks[] = {
 		.gate = { CGU_REG_CLKGR0, 1 },
 	},
 
+	[JZ4780_CLK_EXCLK_DIV512] = {
+		"exclk_div512", CGU_CLK_FIXDIV,
+		.parents = { JZ4780_CLK_EXCLK },
+		.fixdiv = { 512 },
+	},
+
+	[JZ4780_CLK_RTC] = {
+		"rtc_ercs", CGU_CLK_MUX | CGU_CLK_GATE,
+		.parents = { JZ4780_CLK_EXCLK_DIV512, JZ4780_CLK_RTCLK },
+		.mux = { CGU_REG_OPCR, 2, 1},
+	},
+
 	/* Gate-only clocks */
 
 	[JZ4780_CLK_NEMC] = {
diff --git a/drivers/clk/ingenic/x1000-cgu.c b/drivers/clk/ingenic/x1000-cgu.c
index 453f3323cb99..3cc37466ce6b 100644
--- a/drivers/clk/ingenic/x1000-cgu.c
+++ b/drivers/clk/ingenic/x1000-cgu.c
@@ -278,6 +278,19 @@ static const struct ingenic_cgu_clk_info x1000_cgu_clocks[] = {
 		.mux = { CGU_REG_SSICDR, 30, 1 },
 	},
 
+	[X1000_CLK_EXCLK_DIV512] = {
+		"exclk_div512", CGU_CLK_FIXDIV,
+		.parents = { X1000_CLK_EXCLK },
+		.fixdiv = { 512 },
+	},
+
+	[X1000_CLK_RTC] = {
+		"rtc_ercs", CGU_CLK_MUX | CGU_CLK_GATE,
+		.parents = { X1000_CLK_EXCLK_DIV512, X1000_CLK_RTCLK },
+		.mux = { CGU_REG_OPCR, 2, 1},
+		.gate = { CGU_REG_CLKGR, 27 },
+	},
+
 	/* Gate-only clocks */
 
 	[X1000_CLK_EMC] = {
diff --git a/drivers/clk/ingenic/x1830-cgu.c b/drivers/clk/ingenic/x1830-cgu.c
index a1b2ff0ee487..950aee243364 100644
--- a/drivers/clk/ingenic/x1830-cgu.c
+++ b/drivers/clk/ingenic/x1830-cgu.c
@@ -329,6 +329,19 @@ static const struct ingenic_cgu_clk_info x1830_cgu_clocks[] = {
 		.mux = { CGU_REG_SSICDR, 29, 1 },
 	},
 
+	[X1830_CLK_EXCLK_DIV512] = {
+		"exclk_div512", CGU_CLK_FIXDIV,
+		.parents = { X1830_CLK_EXCLK },
+		.fixdiv = { 512 },
+	},
+
+	[X1830_CLK_RTC] = {
+		"rtc_ercs", CGU_CLK_MUX | CGU_CLK_GATE,
+		.parents = { X1830_CLK_EXCLK_DIV512, X1830_CLK_RTCLK },
+		.mux = { CGU_REG_OPCR, 2, 1},
+		.gate = { CGU_REG_CLKGR0, 29 },
+	},
+
 	/* Gate-only clocks */
 
 	[X1830_CLK_EMC] = {

From dcd062a88e46d4d2aeaf701e82e128117fc0f3a1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=91=A8=E7=90=B0=E6=9D=B0=20=28Zhou=20Yanjie=29?=
 <zhouyanjie@wanyeetech.com>
Date: Wed, 1 Jul 2020 00:38:50 +0800
Subject: [PATCH 142/474] clk: JZ4780: Add functions for enable and disable USB
 PHY.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add new functions to "jz4780_otg_phy_ops" to enable or disable the
USB PHY in the JZ4780 SoC.

Tested-by: 周正 (Zhou Zheng) <sernia.zhou@foxmail.com>
Signed-off-by: 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
Link: https://lore.kernel.org/r/20200630163852.47267-2-zhouyanjie@wanyeetech.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/ingenic/jz4780-cgu.c | 65 +++++++++++++++++---------------
 1 file changed, 35 insertions(+), 30 deletions(-)

diff --git a/drivers/clk/ingenic/jz4780-cgu.c b/drivers/clk/ingenic/jz4780-cgu.c
index 288e9694285b..fa54d6e3a3a8 100644
--- a/drivers/clk/ingenic/jz4780-cgu.c
+++ b/drivers/clk/ingenic/jz4780-cgu.c
@@ -4,6 +4,7 @@
  *
  * Copyright (c) 2013-2015 Imagination Technologies
  * Author: Paul Burton <paul.burton@mips.com>
+ * Copyright (c) 2020 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
  */
 
 #include <linux/clk-provider.h>
@@ -59,6 +60,7 @@
 #define USBPCR_VBUSVLDEXT	BIT(24)
 #define USBPCR_VBUSVLDEXTSEL	BIT(23)
 #define USBPCR_POR		BIT(22)
+#define USBPCR_SIDDQ		BIT(21)
 #define USBPCR_OTG_DISABLE	BIT(20)
 #define USBPCR_COMPDISTUNE_MASK	(0x7 << 17)
 #define USBPCR_OTGTUNE_MASK	(0x7 << 14)
@@ -100,32 +102,6 @@
 
 static struct ingenic_cgu *cgu;
 
-static u8 jz4780_otg_phy_get_parent(struct clk_hw *hw)
-{
-	/* we only use CLKCORE, revisit if that ever changes */
-	return 0;
-}
-
-static int jz4780_otg_phy_set_parent(struct clk_hw *hw, u8 idx)
-{
-	unsigned long flags;
-	u32 usbpcr1;
-
-	if (idx > 0)
-		return -EINVAL;
-
-	spin_lock_irqsave(&cgu->lock, flags);
-
-	usbpcr1 = readl(cgu->base + CGU_REG_USBPCR1);
-	usbpcr1 &= ~USBPCR1_REFCLKSEL_MASK;
-	/* we only use CLKCORE */
-	usbpcr1 |= USBPCR1_REFCLKSEL_CORE;
-	writel(usbpcr1, cgu->base + CGU_REG_USBPCR1);
-
-	spin_unlock_irqrestore(&cgu->lock, flags);
-	return 0;
-}
-
 static unsigned long jz4780_otg_phy_recalc_rate(struct clk_hw *hw,
 						unsigned long parent_rate)
 {
@@ -149,7 +125,6 @@ static unsigned long jz4780_otg_phy_recalc_rate(struct clk_hw *hw,
 		return 19200000;
 	}
 
-	BUG();
 	return parent_rate;
 }
 
@@ -206,13 +181,43 @@ static int jz4780_otg_phy_set_rate(struct clk_hw *hw, unsigned long req_rate,
 	return 0;
 }
 
-static const struct clk_ops jz4780_otg_phy_ops = {
-	.get_parent = jz4780_otg_phy_get_parent,
-	.set_parent = jz4780_otg_phy_set_parent,
+static int jz4780_otg_phy_enable(struct clk_hw *hw)
+{
+	void __iomem *reg_opcr		= cgu->base + CGU_REG_OPCR;
+	void __iomem *reg_usbpcr	= cgu->base + CGU_REG_USBPCR;
 
+	writel(readl(reg_opcr) | OPCR_SPENDN0, reg_opcr);
+	writel(readl(reg_usbpcr) & ~USBPCR_OTG_DISABLE & ~USBPCR_SIDDQ, reg_usbpcr);
+	return 0;
+}
+
+static void jz4780_otg_phy_disable(struct clk_hw *hw)
+{
+	void __iomem *reg_opcr		= cgu->base + CGU_REG_OPCR;
+	void __iomem *reg_usbpcr	= cgu->base + CGU_REG_USBPCR;
+
+	writel(readl(reg_opcr) & ~OPCR_SPENDN0, reg_opcr);
+	writel(readl(reg_usbpcr) | USBPCR_OTG_DISABLE | USBPCR_SIDDQ, reg_usbpcr);
+}
+
+static int jz4780_otg_phy_is_enabled(struct clk_hw *hw)
+{
+	void __iomem *reg_opcr		= cgu->base + CGU_REG_OPCR;
+	void __iomem *reg_usbpcr	= cgu->base + CGU_REG_USBPCR;
+
+	return (readl(reg_opcr) & OPCR_SPENDN0) &&
+		!(readl(reg_usbpcr) & USBPCR_SIDDQ) &&
+		!(readl(reg_usbpcr) & USBPCR_OTG_DISABLE);
+}
+
+static const struct clk_ops jz4780_otg_phy_ops = {
 	.recalc_rate = jz4780_otg_phy_recalc_rate,
 	.round_rate = jz4780_otg_phy_round_rate,
 	.set_rate = jz4780_otg_phy_set_rate,
+
+	.enable		= jz4780_otg_phy_enable,
+	.disable	= jz4780_otg_phy_disable,
+	.is_enabled	= jz4780_otg_phy_is_enabled,
 };
 
 static int jz4780_core1_enable(struct clk_hw *hw)

From beb61eb06880c06005b9855873d77547d43bab4b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=91=A8=E7=90=B0=E6=9D=B0=20=28Zhou=20Yanjie=29?=
 <zhouyanjie@wanyeetech.com>
Date: Wed, 1 Jul 2020 00:38:51 +0800
Subject: [PATCH 143/474] clk: JZ4780: Reformat the code to align it.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reformat the code (add one level of indentation before the values),
to align the code in the macro definition section.

Tested-by: 周正 (Zhou Zheng) <sernia.zhou@foxmail.com>
Signed-off-by: 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
Link: https://lore.kernel.org/r/20200630163852.47267-3-zhouyanjie@wanyeetech.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/ingenic/jz4780-cgu.c | 90 ++++++++++++++++----------------
 1 file changed, 45 insertions(+), 45 deletions(-)

diff --git a/drivers/clk/ingenic/jz4780-cgu.c b/drivers/clk/ingenic/jz4780-cgu.c
index fa54d6e3a3a8..0268d23ebe2e 100644
--- a/drivers/clk/ingenic/jz4780-cgu.c
+++ b/drivers/clk/ingenic/jz4780-cgu.c
@@ -20,50 +20,50 @@
 
 /* CGU register offsets */
 #define CGU_REG_CLOCKCONTROL	0x00
-#define CGU_REG_LCR			0x04
-#define CGU_REG_APLL		0x10
-#define CGU_REG_MPLL		0x14
-#define CGU_REG_EPLL		0x18
-#define CGU_REG_VPLL		0x1c
-#define CGU_REG_CLKGR0		0x20
-#define CGU_REG_OPCR		0x24
-#define CGU_REG_CLKGR1		0x28
-#define CGU_REG_DDRCDR		0x2c
-#define CGU_REG_VPUCDR		0x30
-#define CGU_REG_USBPCR		0x3c
-#define CGU_REG_USBRDT		0x40
-#define CGU_REG_USBVBFIL	0x44
-#define CGU_REG_USBPCR1		0x48
-#define CGU_REG_LP0CDR		0x54
-#define CGU_REG_I2SCDR		0x60
-#define CGU_REG_LP1CDR		0x64
-#define CGU_REG_MSC0CDR		0x68
-#define CGU_REG_UHCCDR		0x6c
-#define CGU_REG_SSICDR		0x74
-#define CGU_REG_CIMCDR		0x7c
-#define CGU_REG_PCMCDR		0x84
-#define CGU_REG_GPUCDR		0x88
-#define CGU_REG_HDMICDR		0x8c
-#define CGU_REG_MSC1CDR		0xa4
-#define CGU_REG_MSC2CDR		0xa8
-#define CGU_REG_BCHCDR		0xac
-#define CGU_REG_CLOCKSTATUS	0xd4
+#define CGU_REG_LCR				0x04
+#define CGU_REG_APLL			0x10
+#define CGU_REG_MPLL			0x14
+#define CGU_REG_EPLL			0x18
+#define CGU_REG_VPLL			0x1c
+#define CGU_REG_CLKGR0			0x20
+#define CGU_REG_OPCR			0x24
+#define CGU_REG_CLKGR1			0x28
+#define CGU_REG_DDRCDR			0x2c
+#define CGU_REG_VPUCDR			0x30
+#define CGU_REG_USBPCR			0x3c
+#define CGU_REG_USBRDT			0x40
+#define CGU_REG_USBVBFIL		0x44
+#define CGU_REG_USBPCR1			0x48
+#define CGU_REG_LP0CDR			0x54
+#define CGU_REG_I2SCDR			0x60
+#define CGU_REG_LP1CDR			0x64
+#define CGU_REG_MSC0CDR			0x68
+#define CGU_REG_UHCCDR			0x6c
+#define CGU_REG_SSICDR			0x74
+#define CGU_REG_CIMCDR			0x7c
+#define CGU_REG_PCMCDR			0x84
+#define CGU_REG_GPUCDR			0x88
+#define CGU_REG_HDMICDR			0x8c
+#define CGU_REG_MSC1CDR			0xa4
+#define CGU_REG_MSC2CDR			0xa8
+#define CGU_REG_BCHCDR			0xac
+#define CGU_REG_CLOCKSTATUS		0xd4
 
 /* bits within the OPCR register */
-#define OPCR_SPENDN0		BIT(7)
-#define OPCR_SPENDN1		BIT(6)
+#define OPCR_SPENDN0			BIT(7)
+#define OPCR_SPENDN1			BIT(6)
 
 /* bits within the USBPCR register */
-#define USBPCR_USB_MODE		BIT(31)
+#define USBPCR_USB_MODE			BIT(31)
 #define USBPCR_IDPULLUP_MASK	(0x3 << 28)
-#define USBPCR_COMMONONN	BIT(25)
-#define USBPCR_VBUSVLDEXT	BIT(24)
+#define USBPCR_COMMONONN		BIT(25)
+#define USBPCR_VBUSVLDEXT		BIT(24)
 #define USBPCR_VBUSVLDEXTSEL	BIT(23)
-#define USBPCR_POR		BIT(22)
-#define USBPCR_SIDDQ		BIT(21)
-#define USBPCR_OTG_DISABLE	BIT(20)
+#define USBPCR_POR				BIT(22)
+#define USBPCR_SIDDQ			BIT(21)
+#define USBPCR_OTG_DISABLE		BIT(20)
 #define USBPCR_COMPDISTUNE_MASK	(0x7 << 17)
-#define USBPCR_OTGTUNE_MASK	(0x7 << 14)
+#define USBPCR_OTGTUNE_MASK		(0x7 << 14)
 #define USBPCR_SQRXTUNE_MASK	(0x7 << 11)
 #define USBPCR_TXFSLSTUNE_MASK	(0xf << 7)
 #define USBPCR_TXPREEMPHTUNE	BIT(6)
@@ -80,13 +80,13 @@
 #define USBPCR1_REFCLKDIV_48	(0x2 << USBPCR1_REFCLKDIV_SHIFT)
 #define USBPCR1_REFCLKDIV_24	(0x1 << USBPCR1_REFCLKDIV_SHIFT)
 #define USBPCR1_REFCLKDIV_12	(0x0 << USBPCR1_REFCLKDIV_SHIFT)
-#define USBPCR1_USB_SEL		BIT(28)
-#define USBPCR1_WORD_IF0	BIT(19)
-#define USBPCR1_WORD_IF1	BIT(18)
+#define USBPCR1_USB_SEL			BIT(28)
+#define USBPCR1_WORD_IF0		BIT(19)
+#define USBPCR1_WORD_IF1		BIT(18)
 
 /* bits within the USBRDT register */
-#define USBRDT_VBFIL_LD_EN	BIT(25)
-#define USBRDT_USBRDT_MASK	0x7fffff
+#define USBRDT_VBFIL_LD_EN		BIT(25)
+#define USBRDT_USBRDT_MASK		0x7fffff
 
 /* bits within the USBVBFIL register */
 #define USBVBFIL_IDDIGFIL_SHIFT	16
@@ -94,11 +94,11 @@
 #define USBVBFIL_USBVBFIL_MASK	(0xffff)
 
 /* bits within the LCR register */
-#define LCR_PD_SCPU			BIT(31)
-#define LCR_SCPUS			BIT(27)
+#define LCR_PD_SCPU				BIT(31)
+#define LCR_SCPUS				BIT(27)
 
 /* bits within the CLKGR1 register */
-#define CLKGR1_CORE1		BIT(15)
+#define CLKGR1_CORE1			BIT(15)
 
 static struct ingenic_cgu *cgu;
 

From 810797c14508dae3c80eacaa483a900b03fdb780 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=91=A8=E7=90=B0=E6=9D=B0=20=28Zhou=20Yanjie=29?=
 <zhouyanjie@wanyeetech.com>
Date: Wed, 1 Jul 2020 00:38:52 +0800
Subject: [PATCH 144/474] clk: X1000: Add support for calculat REFCLK of USB
 PHY.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add functions for calculat the rate of REFCLK, which is needed by
USB PHY in Ingenic X1000 SoC.

Tested-by: 周正 (Zhou Zheng) <sernia.zhou@foxmail.com>
Signed-off-by: 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
Link: https://lore.kernel.org/r/20200630163852.47267-4-zhouyanjie@wanyeetech.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/ingenic/x1000-cgu.c | 84 ++++++++++++++++++++++++++++++++-
 1 file changed, 83 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/ingenic/x1000-cgu.c b/drivers/clk/ingenic/x1000-cgu.c
index 3cc37466ce6b..9aa20b52e1c3 100644
--- a/drivers/clk/ingenic/x1000-cgu.c
+++ b/drivers/clk/ingenic/x1000-cgu.c
@@ -48,8 +48,87 @@
 #define USBPCR_SIDDQ		BIT(21)
 #define USBPCR_OTG_DISABLE	BIT(20)
 
+/* bits within the USBPCR1 register */
+#define USBPCR1_REFCLKSEL_SHIFT	26
+#define USBPCR1_REFCLKSEL_MASK	(0x3 << USBPCR1_REFCLKSEL_SHIFT)
+#define USBPCR1_REFCLKSEL_CORE	(0x2 << USBPCR1_REFCLKSEL_SHIFT)
+#define USBPCR1_REFCLKDIV_SHIFT	24
+#define USBPCR1_REFCLKDIV_MASK	(0x3 << USBPCR1_REFCLKDIV_SHIFT)
+#define USBPCR1_REFCLKDIV_48	(0x2 << USBPCR1_REFCLKDIV_SHIFT)
+#define USBPCR1_REFCLKDIV_24	(0x1 << USBPCR1_REFCLKDIV_SHIFT)
+#define USBPCR1_REFCLKDIV_12	(0x0 << USBPCR1_REFCLKDIV_SHIFT)
+
 static struct ingenic_cgu *cgu;
 
+static unsigned long x1000_otg_phy_recalc_rate(struct clk_hw *hw,
+						unsigned long parent_rate)
+{
+	u32 usbpcr1;
+	unsigned refclk_div;
+
+	usbpcr1 = readl(cgu->base + CGU_REG_USBPCR1);
+	refclk_div = usbpcr1 & USBPCR1_REFCLKDIV_MASK;
+
+	switch (refclk_div) {
+	case USBPCR1_REFCLKDIV_12:
+		return 12000000;
+
+	case USBPCR1_REFCLKDIV_24:
+		return 24000000;
+
+	case USBPCR1_REFCLKDIV_48:
+		return 48000000;
+	}
+
+	return parent_rate;
+}
+
+static long x1000_otg_phy_round_rate(struct clk_hw *hw, unsigned long req_rate,
+				      unsigned long *parent_rate)
+{
+	if (req_rate < 18000000)
+		return 12000000;
+
+	if (req_rate < 36000000)
+		return 24000000;
+
+	return 48000000;
+}
+
+static int x1000_otg_phy_set_rate(struct clk_hw *hw, unsigned long req_rate,
+				   unsigned long parent_rate)
+{
+	unsigned long flags;
+	u32 usbpcr1, div_bits;
+
+	switch (req_rate) {
+	case 12000000:
+		div_bits = USBPCR1_REFCLKDIV_12;
+		break;
+
+	case 24000000:
+		div_bits = USBPCR1_REFCLKDIV_24;
+		break;
+
+	case 48000000:
+		div_bits = USBPCR1_REFCLKDIV_48;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&cgu->lock, flags);
+
+	usbpcr1 = readl(cgu->base + CGU_REG_USBPCR1);
+	usbpcr1 &= ~USBPCR1_REFCLKDIV_MASK;
+	usbpcr1 |= div_bits;
+	writel(usbpcr1, cgu->base + CGU_REG_USBPCR1);
+
+	spin_unlock_irqrestore(&cgu->lock, flags);
+	return 0;
+}
+
 static int x1000_usb_phy_enable(struct clk_hw *hw)
 {
 	void __iomem *reg_opcr		= cgu->base + CGU_REG_OPCR;
@@ -80,6 +159,10 @@ static int x1000_usb_phy_is_enabled(struct clk_hw *hw)
 }
 
 static const struct clk_ops x1000_otg_phy_ops = {
+	.recalc_rate = x1000_otg_phy_recalc_rate,
+	.round_rate = x1000_otg_phy_round_rate,
+	.set_rate = x1000_otg_phy_set_rate,
+
 	.enable		= x1000_usb_phy_enable,
 	.disable	= x1000_usb_phy_disable,
 	.is_enabled	= x1000_usb_phy_is_enabled,
@@ -144,7 +227,6 @@ static const struct ingenic_cgu_clk_info x1000_cgu_clocks[] = {
 		},
 	},
 
-
 	/* Custom (SoC-specific) OTG PHY */
 
 	[X1000_CLK_OTGPHY] = {

From fa64023763cf1a3da8bf3341df6c2a47e54fcead Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Thu, 9 Jul 2020 20:20:57 +0300
Subject: [PATCH 145/474] clk: tegra: pll: Improve PLLM enable-state detection

Power Management Controller (PMC) can override the PLLM clock settings,
including the enable-state. Although PMC could only act as a second level
gate, meaning that PLLM needs to be enabled by the Clock and Reset
Controller (CaR) anyways if we want it to be enabled. Hence, when PLLM is
overridden by PMC, it needs to be enabled by CaR and ungated by PMC in
order to be functional. Please note that this patch doesn't fix any known
problem, and thus, it's merely a minor improvement.

Link: https://lore.kernel.org/linux-arm-kernel/20191210120909.GA2703785@ulmo/T/
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20200709172057.13951-1-digetx@gmail.com
Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/tegra/clk-pll.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c
index 0b212cf2e794..f180c055d33f 100644
--- a/drivers/clk/tegra/clk-pll.c
+++ b/drivers/clk/tegra/clk-pll.c
@@ -327,16 +327,26 @@ int tegra_pll_wait_for_lock(struct tegra_clk_pll *pll)
 	return clk_pll_wait_for_lock(pll);
 }
 
+static bool pllm_clk_is_gated_by_pmc(struct tegra_clk_pll *pll)
+{
+	u32 val = readl_relaxed(pll->pmc + PMC_PLLP_WB0_OVERRIDE);
+
+	return (val & PMC_PLLP_WB0_OVERRIDE_PLLM_OVERRIDE) &&
+	      !(val & PMC_PLLP_WB0_OVERRIDE_PLLM_ENABLE);
+}
+
 static int clk_pll_is_enabled(struct clk_hw *hw)
 {
 	struct tegra_clk_pll *pll = to_clk_pll(hw);
 	u32 val;
 
-	if (pll->params->flags & TEGRA_PLLM) {
-		val = readl_relaxed(pll->pmc + PMC_PLLP_WB0_OVERRIDE);
-		if (val & PMC_PLLP_WB0_OVERRIDE_PLLM_OVERRIDE)
-			return val & PMC_PLLP_WB0_OVERRIDE_PLLM_ENABLE ? 1 : 0;
-	}
+	/*
+	 * Power Management Controller (PMC) can override the PLLM clock
+	 * settings, including the enable-state. The PLLM is enabled when
+	 * PLLM's CaR state is ON and when PLLM isn't gated by PMC.
+	 */
+	if ((pll->params->flags & TEGRA_PLLM) && pllm_clk_is_gated_by_pmc(pll))
+		return 0;
 
 	val = pll_readl_base(pll);
 

From 12b90b40854a8461a02ef19f6f4474cc88d64b66 Mon Sep 17 00:00:00 2001
From: Xu Wang <vulab@iscas.ac.cn>
Date: Mon, 13 Jul 2020 03:21:43 +0000
Subject: [PATCH 146/474] clk: clk-atlas6: fix return value check in
 atlas6_clk_init()

In case of error, the function clk_register() returns ERR_PTR()
and never returns NULL. The NULL test in the return value check
should be replaced with IS_ERR().

Signed-off-by: Xu Wang <vulab@iscas.ac.cn>
Link: https://lore.kernel.org/r/20200713032143.21362-1-vulab@iscas.ac.cn
Acked-by: Barry Song <baohua@kernel.org>
Fixes: 7bf21bc81f28 ("clk: sirf: re-arch to make the codes support both prima2 and atlas6")
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/sirf/clk-atlas6.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/sirf/clk-atlas6.c b/drivers/clk/sirf/clk-atlas6.c
index c84d5bab7ac2..b95483bb6a5e 100644
--- a/drivers/clk/sirf/clk-atlas6.c
+++ b/drivers/clk/sirf/clk-atlas6.c
@@ -135,7 +135,7 @@ static void __init atlas6_clk_init(struct device_node *np)
 
 	for (i = pll1; i < maxclk; i++) {
 		atlas6_clks[i] = clk_register(NULL, atlas6_clk_hw_array[i]);
-		BUG_ON(!atlas6_clks[i]);
+		BUG_ON(IS_ERR(atlas6_clks[i]));
 	}
 	clk_register_clkdev(atlas6_clks[cpu], NULL, "cpu");
 	clk_register_clkdev(atlas6_clks[io],  NULL, "io");

From 92df3a9bf3fd975949122b1779c142c2d007a7dc Mon Sep 17 00:00:00 2001
From: Michael Krummsdorf <michael.krummsdorf@tq-group.com>
Date: Wed, 10 Jun 2020 13:38:37 +0200
Subject: [PATCH 147/474] clk: qoriq: add LS1021A core pll mux options

This allows to clock the cores with 1 GHz, 500 MHz and 250 MHz.

Signed-off-by: Michael Krummsdorf <michael.krummsdorf@tq-group.com>
Signed-off-by: Matthias Schiffer <matthias.schiffer@ew.tq-group.com>
Link: https://lore.kernel.org/r/20200610113837.27117-1-matthias.schiffer@ew.tq-group.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-qoriq.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c
index 374afcab89af..5942e9874bc0 100644
--- a/drivers/clk/clk-qoriq.c
+++ b/drivers/clk/clk-qoriq.c
@@ -244,6 +244,14 @@ static const struct clockgen_muxinfo clockgen2_cmux_cgb = {
 	},
 };
 
+static const struct clockgen_muxinfo ls1021a_cmux = {
+	{
+		{ CLKSEL_VALID, CGA_PLL1, PLL_DIV1 },
+		{ CLKSEL_VALID, CGA_PLL1, PLL_DIV2 },
+		{ CLKSEL_VALID, CGA_PLL1, PLL_DIV4 },
+	}
+};
+
 static const struct clockgen_muxinfo ls1028a_hwa1 = {
 	{
 		{ CLKSEL_VALID, PLATFORM_PLL, PLL_DIV1 },
@@ -577,7 +585,7 @@ static const struct clockgen_chipinfo chipinfo[] = {
 	{
 		.compat = "fsl,ls1021a-clockgen",
 		.cmux_groups = {
-			&t1023_cmux
+			&ls1021a_cmux
 		},
 		.cmux_to_group = {
 			0, -1

From 48908a3833cc76c56e626e8e80ba8f808c8d03a5 Mon Sep 17 00:00:00 2001
From: Ram Pai <linuxram@us.ibm.com>
Date: Mon, 27 Jul 2020 11:07:14 -0700
Subject: [PATCH 148/474] KVM: PPC: Book3S HV: Fix function definition in
 book3s_hv_uvmem.c

Without this fix, git is confused. It generates wrong
function context for code changes in subsequent patches.
Weird, but true.

Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 09d8119024db..e6f76bc16d04 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -382,8 +382,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
  * Alloc a PFN from private device memory pool and copy page from normal
  * memory to secure memory using UV_PAGE_IN uvcall.
  */
-static int
-kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
+static int kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
 		   unsigned long end, unsigned long gpa, struct kvm *kvm,
 		   unsigned long page_shift, bool *downgrade)
 {
@@ -450,8 +449,8 @@ kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
  * In the former case, uses dev_pagemap_ops.migrate_to_ram handler
  * to unmap the device page from QEMU's page tables.
  */
-static unsigned long
-kvmppc_share_page(struct kvm *kvm, unsigned long gpa, unsigned long page_shift)
+static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
+		unsigned long page_shift)
 {
 
 	int ret = H_PARAMETER;
@@ -500,9 +499,9 @@ kvmppc_share_page(struct kvm *kvm, unsigned long gpa, unsigned long page_shift)
  * H_PAGE_IN_SHARED flag makes the page shared which means that the same
  * memory in is visible from both UV and HV.
  */
-unsigned long
-kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
-		     unsigned long flags, unsigned long page_shift)
+unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
+		unsigned long flags,
+		unsigned long page_shift)
 {
 	bool downgrade = false;
 	unsigned long start, end;
@@ -559,10 +558,10 @@ kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
  * Provision a new page on HV side and copy over the contents
  * from secure memory using UV_PAGE_OUT uvcall.
  */
-static int
-kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start,
-		    unsigned long end, unsigned long page_shift,
-		    struct kvm *kvm, unsigned long gpa)
+static int kvmppc_svm_page_out(struct vm_area_struct *vma,
+		unsigned long start,
+		unsigned long end, unsigned long page_shift,
+		struct kvm *kvm, unsigned long gpa)
 {
 	unsigned long src_pfn, dst_pfn = 0;
 	struct migrate_vma mig;

From 2027a24a75ce32cf48a22cc25a9d87b8c5b19328 Mon Sep 17 00:00:00 2001
From: Ram Pai <linuxram@us.ibm.com>
Date: Mon, 27 Jul 2020 11:07:15 -0700
Subject: [PATCH 149/474] KVM: PPC: Book3S HV: Disable page merging in
 H_SVM_INIT_START

Page-merging of pages in memory-slots associated with a Secure VM
is disabled in H_SVM_PAGE_IN handler.

This operation should have been done the much earlier; the moment the VM
is initiated for secure-transition. Delaying this operation increases
the probability for those pages to acquire new references, making it
impossible to migrate those pages in H_SVM_PAGE_IN handler.

Disable page-migration in H_SVM_INIT_START handling.

Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 Documentation/powerpc/ultravisor.rst |   1 +
 arch/powerpc/kvm/book3s_hv_uvmem.c   | 123 +++++++++++++++++++--------
 2 files changed, 89 insertions(+), 35 deletions(-)

diff --git a/Documentation/powerpc/ultravisor.rst b/Documentation/powerpc/ultravisor.rst
index df136c8f91fa..a1c8c37159a1 100644
--- a/Documentation/powerpc/ultravisor.rst
+++ b/Documentation/powerpc/ultravisor.rst
@@ -895,6 +895,7 @@ Return values
     One of the following values:
 
 	* H_SUCCESS	 on success.
+        * H_STATE        if the VM is not in a position to switch to secure.
 
 Description
 ~~~~~~~~~~~
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index e6f76bc16d04..533b608c8d20 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -211,10 +211,79 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
 	return false;
 }
 
+static int kvmppc_memslot_page_merge(struct kvm *kvm,
+		const struct kvm_memory_slot *memslot, bool merge)
+{
+	unsigned long gfn = memslot->base_gfn;
+	unsigned long end, start = gfn_to_hva(kvm, gfn);
+	int ret = 0;
+	struct vm_area_struct *vma;
+	int merge_flag = (merge) ? MADV_MERGEABLE : MADV_UNMERGEABLE;
+
+	if (kvm_is_error_hva(start))
+		return H_STATE;
+
+	end = start + (memslot->npages << PAGE_SHIFT);
+
+	mmap_write_lock(kvm->mm);
+	do {
+		vma = find_vma_intersection(kvm->mm, start, end);
+		if (!vma) {
+			ret = H_STATE;
+			break;
+		}
+		ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
+			  merge_flag, &vma->vm_flags);
+		if (ret) {
+			ret = H_STATE;
+			break;
+		}
+		start = vma->vm_end;
+	} while (end > vma->vm_end);
+
+	mmap_write_unlock(kvm->mm);
+	return ret;
+}
+
+static void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
+		const struct kvm_memory_slot *memslot)
+{
+	uv_unregister_mem_slot(kvm->arch.lpid, memslot->id);
+	kvmppc_uvmem_slot_free(kvm, memslot);
+	kvmppc_memslot_page_merge(kvm, memslot, true);
+}
+
+static int kvmppc_uvmem_memslot_create(struct kvm *kvm,
+		const struct kvm_memory_slot *memslot)
+{
+	int ret = H_PARAMETER;
+
+	if (kvmppc_memslot_page_merge(kvm, memslot, false))
+		return ret;
+
+	if (kvmppc_uvmem_slot_init(kvm, memslot))
+		goto out1;
+
+	ret = uv_register_mem_slot(kvm->arch.lpid,
+				   memslot->base_gfn << PAGE_SHIFT,
+				   memslot->npages * PAGE_SIZE,
+				   0, memslot->id);
+	if (ret < 0) {
+		ret = H_PARAMETER;
+		goto out;
+	}
+	return 0;
+out:
+	kvmppc_uvmem_slot_free(kvm, memslot);
+out1:
+	kvmppc_memslot_page_merge(kvm, memslot, true);
+	return ret;
+}
+
 unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 {
 	struct kvm_memslots *slots;
-	struct kvm_memory_slot *memslot;
+	struct kvm_memory_slot *memslot, *m;
 	int ret = H_SUCCESS;
 	int srcu_idx;
 
@@ -232,23 +301,24 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 		return H_AUTHORITY;
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
+
+	/* register the memslot */
 	slots = kvm_memslots(kvm);
 	kvm_for_each_memslot(memslot, slots) {
-		if (kvmppc_uvmem_slot_init(kvm, memslot)) {
-			ret = H_PARAMETER;
-			goto out;
-		}
-		ret = uv_register_mem_slot(kvm->arch.lpid,
-					   memslot->base_gfn << PAGE_SHIFT,
-					   memslot->npages * PAGE_SIZE,
-					   0, memslot->id);
-		if (ret < 0) {
-			kvmppc_uvmem_slot_free(kvm, memslot);
-			ret = H_PARAMETER;
-			goto out;
+		ret = kvmppc_uvmem_memslot_create(kvm, memslot);
+		if (ret)
+			break;
+	}
+
+	if (ret) {
+		slots = kvm_memslots(kvm);
+		kvm_for_each_memslot(m, slots) {
+			if (m == memslot)
+				break;
+			kvmppc_uvmem_memslot_delete(kvm, memslot);
 		}
 	}
-out:
+
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	return ret;
 }
@@ -384,7 +454,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
  */
 static int kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
 		   unsigned long end, unsigned long gpa, struct kvm *kvm,
-		   unsigned long page_shift, bool *downgrade)
+		   unsigned long page_shift)
 {
 	unsigned long src_pfn, dst_pfn = 0;
 	struct migrate_vma mig;
@@ -400,18 +470,6 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
 	mig.src = &src_pfn;
 	mig.dst = &dst_pfn;
 
-	/*
-	 * We come here with mmap_lock write lock held just for
-	 * ksm_madvise(), otherwise we only need read mmap_lock.
-	 * Hence downgrade to read lock once ksm_madvise() is done.
-	 */
-	ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
-			  MADV_UNMERGEABLE, &vma->vm_flags);
-	mmap_write_downgrade(kvm->mm);
-	*downgrade = true;
-	if (ret)
-		return ret;
-
 	ret = migrate_vma_setup(&mig);
 	if (ret)
 		return ret;
@@ -503,7 +561,6 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 		unsigned long flags,
 		unsigned long page_shift)
 {
-	bool downgrade = false;
 	unsigned long start, end;
 	struct vm_area_struct *vma;
 	int srcu_idx;
@@ -524,7 +581,7 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 
 	ret = H_PARAMETER;
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	mmap_write_lock(kvm->mm);
+	mmap_read_lock(kvm->mm);
 
 	start = gfn_to_hva(kvm, gfn);
 	if (kvm_is_error_hva(start))
@@ -540,16 +597,12 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 	if (!vma || vma->vm_start > start || vma->vm_end < end)
 		goto out_unlock;
 
-	if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift,
-				&downgrade))
+	if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift))
 		ret = H_SUCCESS;
 out_unlock:
 	mutex_unlock(&kvm->arch.uvmem_lock);
 out:
-	if (downgrade)
-		mmap_read_unlock(kvm->mm);
-	else
-		mmap_write_unlock(kvm->mm);
+	mmap_read_unlock(kvm->mm);
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	return ret;
 }

From 651a6310111ef8e09394e77d6d959ab3d066930d Mon Sep 17 00:00:00 2001
From: Ram Pai <linuxram@us.ibm.com>
Date: Mon, 27 Jul 2020 11:07:16 -0700
Subject: [PATCH 150/474] KVM: PPC: Book3S HV: Track the state GFNs associated
 with secure VMs

During the life of SVM, its GFNs transition through normal, secure and
shared states. Since the kernel does not track GFNs that are shared, it
is not possible to disambiguate a shared GFN from a GFN whose PFN has
not yet been migrated to a secure-PFN. Also it is not possible to
disambiguate a secure-GFN from a GFN whose GFN has been pagedout from
the ultravisor.

The ability to identify the state of a GFN is needed to skip migration
of its PFN to secure-PFN during ESM transition.

The code is re-organized to track the states of a GFN as explained
below.

************************************************************************
 1. States of a GFN
    ---------------
 The GFN can be in one of the following states.

 (a) Secure - The GFN is secure. The GFN is associated with
 	a Secure VM, the contents of the GFN is not accessible
 	to the Hypervisor.  This GFN can be backed by a secure-PFN,
 	or can be backed by a normal-PFN with contents encrypted.
 	The former is true when the GFN is paged-in into the
 	ultravisor. The latter is true when the GFN is paged-out
 	of the ultravisor.

 (b) Shared - The GFN is shared. The GFN is associated with a
 	a secure VM. The contents of the GFN is accessible to
 	Hypervisor. This GFN is backed by a normal-PFN and its
 	content is un-encrypted.

 (c) Normal - The GFN is a normal. The GFN is associated with
 	a normal VM. The contents of the GFN is accesible to
 	the Hypervisor. Its content is never encrypted.

 2. States of a VM.
    ---------------

 (a) Normal VM:  A VM whose contents are always accessible to
 	the hypervisor.  All its GFNs are normal-GFNs.

 (b) Secure VM: A VM whose contents are not accessible to the
 	hypervisor without the VM's consent.  Its GFNs are
 	either Shared-GFN or Secure-GFNs.

 (c) Transient VM: A Normal VM that is transitioning to secure VM.
 	The transition starts on successful return of
 	H_SVM_INIT_START, and ends on successful return
 	of H_SVM_INIT_DONE. This transient VM, can have GFNs
 	in any of the three states; i.e Secure-GFN, Shared-GFN,
 	and Normal-GFN.	The VM never executes in this state
 	in supervisor-mode.

 3. Memory slot State.
    ------------------
  	The state of a memory slot mirrors the state of the
  	VM the memory slot is associated with.

 4. VM State transition.
    --------------------

  A VM always starts in Normal Mode.

  H_SVM_INIT_START moves the VM into transient state. During this
  time the Ultravisor may request some of its GFNs to be shared or
  secured. So its GFNs can be in one of the three GFN states.

  H_SVM_INIT_DONE moves the VM entirely from transient state to
  secure-state. At this point any left-over normal-GFNs are
  transitioned to Secure-GFN.

  H_SVM_INIT_ABORT moves the transient VM back to normal VM.
  All its GFNs are moved to Normal-GFNs.

  UV_TERMINATE transitions the secure-VM back to normal-VM. All
  the secure-GFN and shared-GFNs are tranistioned to normal-GFN
  Note: The contents of the normal-GFN is undefined at this point.

 5. GFN state implementation:
    -------------------------

 Secure GFN is associated with a secure-PFN; also called uvmem_pfn,
 when the GFN is paged-in. Its pfn[] has KVMPPC_GFN_UVMEM_PFN flag
 set, and contains the value of the secure-PFN.
 It is associated with a normal-PFN; also called mem_pfn, when
 the GFN is pagedout. Its pfn[] has KVMPPC_GFN_MEM_PFN flag set.
 The value of the normal-PFN is not tracked.

 Shared GFN is associated with a normal-PFN. Its pfn[] has
 KVMPPC_UVMEM_SHARED_PFN flag set. The value of the normal-PFN
 is not tracked.

 Normal GFN is associated with normal-PFN. Its pfn[] has
 no flag set. The value of the normal-PFN is not tracked.

 6. Life cycle of a GFN
    --------------------
 --------------------------------------------------------------
 |        |     Share  |  Unshare | SVM       |H_SVM_INIT_DONE|
 |        |operation   |operation | abort/    |               |
 |        |            |          | terminate |               |
 -------------------------------------------------------------
 |        |            |          |           |               |
 | Secure |     Shared | Secure   |Normal     |Secure         |
 |        |            |          |           |               |
 | Shared |     Shared | Secure   |Normal     |Shared         |
 |        |            |          |           |               |
 | Normal |     Shared | Secure   |Normal     |Secure         |
 --------------------------------------------------------------

 7. Life cycle of a VM
    --------------------
 --------------------------------------------------------------------
 |         |  start    |  H_SVM_  |H_SVM_   |H_SVM_     |UV_SVM_    |
 |         |  VM       |INIT_START|INIT_DONE|INIT_ABORT |TERMINATE  |
 |         |           |          |         |           |           |
 --------- ----------------------------------------------------------
 |         |           |          |         |           |           |
 | Normal  | Normal    | Transient|Error    |Error      |Normal     |
 |         |           |          |         |           |           |
 | Secure  |   Error   | Error    |Error    |Error      |Normal     |
 |         |           |          |         |           |           |
 |Transient|   N/A     | Error    |Secure   |Normal     |Normal     |
 --------------------------------------------------------------------

************************************************************************

Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c | 193 ++++++++++++++++++++++++++---
 1 file changed, 173 insertions(+), 20 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 533b608c8d20..1b2b0293da40 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -98,7 +98,127 @@ static struct dev_pagemap kvmppc_uvmem_pgmap;
 static unsigned long *kvmppc_uvmem_bitmap;
 static DEFINE_SPINLOCK(kvmppc_uvmem_bitmap_lock);
 
-#define KVMPPC_UVMEM_PFN	(1UL << 63)
+/*
+ * States of a GFN
+ * ---------------
+ * The GFN can be in one of the following states.
+ *
+ * (a) Secure - The GFN is secure. The GFN is associated with
+ *	a Secure VM, the contents of the GFN is not accessible
+ *	to the Hypervisor.  This GFN can be backed by a secure-PFN,
+ *	or can be backed by a normal-PFN with contents encrypted.
+ *	The former is true when the GFN is paged-in into the
+ *	ultravisor. The latter is true when the GFN is paged-out
+ *	of the ultravisor.
+ *
+ * (b) Shared - The GFN is shared. The GFN is associated with a
+ *	a secure VM. The contents of the GFN is accessible to
+ *	Hypervisor. This GFN is backed by a normal-PFN and its
+ *	content is un-encrypted.
+ *
+ * (c) Normal - The GFN is a normal. The GFN is associated with
+ *	a normal VM. The contents of the GFN is accesible to
+ *	the Hypervisor. Its content is never encrypted.
+ *
+ * States of a VM.
+ * ---------------
+ *
+ * Normal VM:  A VM whose contents are always accessible to
+ *	the hypervisor.  All its GFNs are normal-GFNs.
+ *
+ * Secure VM: A VM whose contents are not accessible to the
+ *	hypervisor without the VM's consent.  Its GFNs are
+ *	either Shared-GFN or Secure-GFNs.
+ *
+ * Transient VM: A Normal VM that is transitioning to secure VM.
+ *	The transition starts on successful return of
+ *	H_SVM_INIT_START, and ends on successful return
+ *	of H_SVM_INIT_DONE. This transient VM, can have GFNs
+ *	in any of the three states; i.e Secure-GFN, Shared-GFN,
+ *	and Normal-GFN.	The VM never executes in this state
+ *	in supervisor-mode.
+ *
+ * Memory slot State.
+ * -----------------------------
+ *	The state of a memory slot mirrors the state of the
+ *	VM the memory slot is associated with.
+ *
+ * VM State transition.
+ * --------------------
+ *
+ *  A VM always starts in Normal Mode.
+ *
+ *  H_SVM_INIT_START moves the VM into transient state. During this
+ *  time the Ultravisor may request some of its GFNs to be shared or
+ *  secured. So its GFNs can be in one of the three GFN states.
+ *
+ *  H_SVM_INIT_DONE moves the VM entirely from transient state to
+ *  secure-state. At this point any left-over normal-GFNs are
+ *  transitioned to Secure-GFN.
+ *
+ *  H_SVM_INIT_ABORT moves the transient VM back to normal VM.
+ *  All its GFNs are moved to Normal-GFNs.
+ *
+ *  UV_TERMINATE transitions the secure-VM back to normal-VM. All
+ *  the secure-GFN and shared-GFNs are tranistioned to normal-GFN
+ *  Note: The contents of the normal-GFN is undefined at this point.
+ *
+ * GFN state implementation:
+ * -------------------------
+ *
+ * Secure GFN is associated with a secure-PFN; also called uvmem_pfn,
+ * when the GFN is paged-in. Its pfn[] has KVMPPC_GFN_UVMEM_PFN flag
+ * set, and contains the value of the secure-PFN.
+ * It is associated with a normal-PFN; also called mem_pfn, when
+ * the GFN is pagedout. Its pfn[] has KVMPPC_GFN_MEM_PFN flag set.
+ * The value of the normal-PFN is not tracked.
+ *
+ * Shared GFN is associated with a normal-PFN. Its pfn[] has
+ * KVMPPC_UVMEM_SHARED_PFN flag set. The value of the normal-PFN
+ * is not tracked.
+ *
+ * Normal GFN is associated with normal-PFN. Its pfn[] has
+ * no flag set. The value of the normal-PFN is not tracked.
+ *
+ * Life cycle of a GFN
+ * --------------------
+ *
+ * --------------------------------------------------------------
+ * |        |     Share  |  Unshare | SVM       |H_SVM_INIT_DONE|
+ * |        |operation   |operation | abort/    |               |
+ * |        |            |          | terminate |               |
+ * -------------------------------------------------------------
+ * |        |            |          |           |               |
+ * | Secure |     Shared | Secure   |Normal     |Secure         |
+ * |        |            |          |           |               |
+ * | Shared |     Shared | Secure   |Normal     |Shared         |
+ * |        |            |          |           |               |
+ * | Normal |     Shared | Secure   |Normal     |Secure         |
+ * --------------------------------------------------------------
+ *
+ * Life cycle of a VM
+ * --------------------
+ *
+ * --------------------------------------------------------------------
+ * |         |  start    |  H_SVM_  |H_SVM_   |H_SVM_     |UV_SVM_    |
+ * |         |  VM       |INIT_START|INIT_DONE|INIT_ABORT |TERMINATE  |
+ * |         |           |          |         |           |           |
+ * --------- ----------------------------------------------------------
+ * |         |           |          |         |           |           |
+ * | Normal  | Normal    | Transient|Error    |Error      |Normal     |
+ * |         |           |          |         |           |           |
+ * | Secure  |   Error   | Error    |Error    |Error      |Normal     |
+ * |         |           |          |         |           |           |
+ * |Transient|   N/A     | Error    |Secure   |Normal     |Normal     |
+ * --------------------------------------------------------------------
+ */
+
+#define KVMPPC_GFN_UVMEM_PFN	(1UL << 63)
+#define KVMPPC_GFN_MEM_PFN	(1UL << 62)
+#define KVMPPC_GFN_SHARED	(1UL << 61)
+#define KVMPPC_GFN_SECURE	(KVMPPC_GFN_UVMEM_PFN | KVMPPC_GFN_MEM_PFN)
+#define KVMPPC_GFN_FLAG_MASK	(KVMPPC_GFN_SECURE | KVMPPC_GFN_SHARED)
+#define KVMPPC_GFN_PFN_MASK	(~KVMPPC_GFN_FLAG_MASK)
 
 struct kvmppc_uvmem_slot {
 	struct list_head list;
@@ -106,11 +226,11 @@ struct kvmppc_uvmem_slot {
 	unsigned long base_pfn;
 	unsigned long *pfns;
 };
-
 struct kvmppc_uvmem_page_pvt {
 	struct kvm *kvm;
 	unsigned long gpa;
 	bool skip_page_out;
+	bool remove_gfn;
 };
 
 bool kvmppc_uvmem_available(void)
@@ -163,8 +283,8 @@ void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot)
 	mutex_unlock(&kvm->arch.uvmem_lock);
 }
 
-static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn,
-				    struct kvm *kvm)
+static void kvmppc_mark_gfn(unsigned long gfn, struct kvm *kvm,
+			unsigned long flag, unsigned long uvmem_pfn)
 {
 	struct kvmppc_uvmem_slot *p;
 
@@ -172,24 +292,41 @@ static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn,
 		if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
 			unsigned long index = gfn - p->base_pfn;
 
-			p->pfns[index] = uvmem_pfn | KVMPPC_UVMEM_PFN;
+			if (flag == KVMPPC_GFN_UVMEM_PFN)
+				p->pfns[index] = uvmem_pfn | flag;
+			else
+				p->pfns[index] = flag;
 			return;
 		}
 	}
 }
 
-static void kvmppc_uvmem_pfn_remove(unsigned long gfn, struct kvm *kvm)
+/* mark the GFN as secure-GFN associated with @uvmem pfn device-PFN. */
+static void kvmppc_gfn_secure_uvmem_pfn(unsigned long gfn,
+			unsigned long uvmem_pfn, struct kvm *kvm)
 {
-	struct kvmppc_uvmem_slot *p;
-
-	list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) {
-		if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
-			p->pfns[gfn - p->base_pfn] = 0;
-			return;
-		}
-	}
+	kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_UVMEM_PFN, uvmem_pfn);
 }
 
+/* mark the GFN as secure-GFN associated with a memory-PFN. */
+static void kvmppc_gfn_secure_mem_pfn(unsigned long gfn, struct kvm *kvm)
+{
+	kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_MEM_PFN, 0);
+}
+
+/* mark the GFN as a shared GFN. */
+static void kvmppc_gfn_shared(unsigned long gfn, struct kvm *kvm)
+{
+	kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_SHARED, 0);
+}
+
+/* mark the GFN as a non-existent GFN. */
+static void kvmppc_gfn_remove(unsigned long gfn, struct kvm *kvm)
+{
+	kvmppc_mark_gfn(gfn, kvm, 0, 0);
+}
+
+/* return true, if the GFN is a secure-GFN backed by a secure-PFN */
 static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
 				    unsigned long *uvmem_pfn)
 {
@@ -199,10 +336,10 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
 		if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
 			unsigned long index = gfn - p->base_pfn;
 
-			if (p->pfns[index] & KVMPPC_UVMEM_PFN) {
+			if (p->pfns[index] & KVMPPC_GFN_UVMEM_PFN) {
 				if (uvmem_pfn)
 					*uvmem_pfn = p->pfns[index] &
-						     ~KVMPPC_UVMEM_PFN;
+						     KVMPPC_GFN_PFN_MASK;
 				return true;
 			} else
 				return false;
@@ -354,6 +491,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
 
 		mutex_lock(&kvm->arch.uvmem_lock);
 		if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+			kvmppc_gfn_remove(gfn, kvm);
 			mutex_unlock(&kvm->arch.uvmem_lock);
 			continue;
 		}
@@ -361,6 +499,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
 		uvmem_page = pfn_to_page(uvmem_pfn);
 		pvt = uvmem_page->zone_device_data;
 		pvt->skip_page_out = skip_page_out;
+		pvt->remove_gfn = true;
 		mutex_unlock(&kvm->arch.uvmem_lock);
 
 		pfn = gfn_to_pfn(kvm, gfn);
@@ -430,7 +569,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
 		goto out_clear;
 
 	uvmem_pfn = bit + pfn_first;
-	kvmppc_uvmem_pfn_insert(gpa >> PAGE_SHIFT, uvmem_pfn, kvm);
+	kvmppc_gfn_secure_uvmem_pfn(gpa >> PAGE_SHIFT, uvmem_pfn, kvm);
 
 	pvt->gpa = gpa;
 	pvt->kvm = kvm;
@@ -525,6 +664,11 @@ static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
 		uvmem_page = pfn_to_page(uvmem_pfn);
 		pvt = uvmem_page->zone_device_data;
 		pvt->skip_page_out = true;
+		/*
+		 * do not drop the GFN. It is a valid GFN
+		 * that is transitioned to a shared GFN.
+		 */
+		pvt->remove_gfn = false;
 	}
 
 retry:
@@ -538,12 +682,16 @@ static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
 		uvmem_page = pfn_to_page(uvmem_pfn);
 		pvt = uvmem_page->zone_device_data;
 		pvt->skip_page_out = true;
+		pvt->remove_gfn = false; /* it continues to be a valid GFN */
 		kvm_release_pfn_clean(pfn);
 		goto retry;
 	}
 
-	if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, page_shift))
+	if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0,
+				page_shift)) {
+		kvmppc_gfn_shared(gfn, kvm);
 		ret = H_SUCCESS;
+	}
 	kvm_release_pfn_clean(pfn);
 	mutex_unlock(&kvm->arch.uvmem_lock);
 out:
@@ -599,6 +747,7 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 
 	if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift))
 		ret = H_SUCCESS;
+
 out_unlock:
 	mutex_unlock(&kvm->arch.uvmem_lock);
 out:
@@ -707,7 +856,8 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
 /*
  * Release the device PFN back to the pool
  *
- * Gets called when secure page becomes a normal page during H_SVM_PAGE_OUT.
+ * Gets called when secure GFN tranistions from a secure-PFN
+ * to a normal PFN during H_SVM_PAGE_OUT.
  * Gets called with kvm->arch.uvmem_lock held.
  */
 static void kvmppc_uvmem_page_free(struct page *page)
@@ -722,7 +872,10 @@ static void kvmppc_uvmem_page_free(struct page *page)
 
 	pvt = page->zone_device_data;
 	page->zone_device_data = NULL;
-	kvmppc_uvmem_pfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
+	if (pvt->remove_gfn)
+		kvmppc_gfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
+	else
+		kvmppc_gfn_secure_mem_pfn(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
 	kfree(pvt);
 }
 

From dfaa973ae9605e1731eaef9f30c2b056346a4efc Mon Sep 17 00:00:00 2001
From: Ram Pai <linuxram@us.ibm.com>
Date: Mon, 27 Jul 2020 11:07:17 -0700
Subject: [PATCH 151/474] KVM: PPC: Book3S HV: In H_SVM_INIT_DONE, migrate
 remaining normal-GFNs to secure-GFNs

The Ultravisor is expected to explicitly call H_SVM_PAGE_IN for all the
pages of the SVM before calling H_SVM_INIT_DONE. This causes a huge
delay in tranistioning the VM to SVM. The Ultravisor is only interested
in the pages that contain the kernel, initrd and other important data
structures. The rest contain throw-away content.

However if not all pages are requested by the Ultravisor, the Hypervisor
continues to consider the GFNs corresponding to the non-requested pages
as normal GFNs. This can lead to data-corruption and undefined behavior.

In H_SVM_INIT_DONE handler, move all the PFNs associated with the SVM's
GFNs to secure-PFNs. Skip the GFNs that are already Paged-in or Shared
or Paged-in followed by a Paged-out.

Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 Documentation/powerpc/ultravisor.rst |   2 +
 arch/powerpc/kvm/book3s_hv_uvmem.c   | 154 +++++++++++++++++++++++----
 2 files changed, 134 insertions(+), 22 deletions(-)

diff --git a/Documentation/powerpc/ultravisor.rst b/Documentation/powerpc/ultravisor.rst
index a1c8c37159a1..ba6b1bf1cc44 100644
--- a/Documentation/powerpc/ultravisor.rst
+++ b/Documentation/powerpc/ultravisor.rst
@@ -934,6 +934,8 @@ Return values
 	* H_UNSUPPORTED		if called from the wrong context (e.g.
 				from an SVM or before an H_SVM_INIT_START
 				hypercall).
+	* H_STATE		if the hypervisor could not successfully
+                                transition the VM to Secure VM.
 
 Description
 ~~~~~~~~~~~
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 1b2b0293da40..a1664ae4d81f 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -93,6 +93,7 @@
 #include <asm/ultravisor.h>
 #include <asm/mman.h>
 #include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s_uvmem.h>
 
 static struct dev_pagemap kvmppc_uvmem_pgmap;
 static unsigned long *kvmppc_uvmem_bitmap;
@@ -348,6 +349,41 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
 	return false;
 }
 
+/*
+ * starting from *gfn search for the next available GFN that is not yet
+ * transitioned to a secure GFN.  return the value of that GFN in *gfn.  If a
+ * GFN is found, return true, else return false
+ *
+ * Must be called with kvm->arch.uvmem_lock  held.
+ */
+static bool kvmppc_next_nontransitioned_gfn(const struct kvm_memory_slot *memslot,
+		struct kvm *kvm, unsigned long *gfn)
+{
+	struct kvmppc_uvmem_slot *p;
+	bool ret = false;
+	unsigned long i;
+
+	list_for_each_entry(p, &kvm->arch.uvmem_pfns, list)
+		if (*gfn >= p->base_pfn && *gfn < p->base_pfn + p->nr_pfns)
+			break;
+	if (!p)
+		return ret;
+	/*
+	 * The code below assumes, one to one correspondence between
+	 * kvmppc_uvmem_slot and memslot.
+	 */
+	for (i = *gfn; i < p->base_pfn + p->nr_pfns; i++) {
+		unsigned long index = i - p->base_pfn;
+
+		if (!(p->pfns[index] & KVMPPC_GFN_FLAG_MASK)) {
+			*gfn = i;
+			ret = true;
+			break;
+		}
+	}
+	return ret;
+}
+
 static int kvmppc_memslot_page_merge(struct kvm *kvm,
 		const struct kvm_memory_slot *memslot, bool merge)
 {
@@ -460,16 +496,6 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 	return ret;
 }
 
-unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
-{
-	if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
-		return H_UNSUPPORTED;
-
-	kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE;
-	pr_info("LPID %d went secure\n", kvm->arch.lpid);
-	return H_SUCCESS;
-}
-
 /*
  * Drop device pages that we maintain for the secure guest
  *
@@ -588,12 +614,14 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
 }
 
 /*
- * Alloc a PFN from private device memory pool and copy page from normal
- * memory to secure memory using UV_PAGE_IN uvcall.
+ * Alloc a PFN from private device memory pool. If @pagein is true,
+ * copy page from normal memory to secure memory using UV_PAGE_IN uvcall.
  */
-static int kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
-		   unsigned long end, unsigned long gpa, struct kvm *kvm,
-		   unsigned long page_shift)
+static int kvmppc_svm_page_in(struct vm_area_struct *vma,
+		unsigned long start,
+		unsigned long end, unsigned long gpa, struct kvm *kvm,
+		unsigned long page_shift,
+		bool pagein)
 {
 	unsigned long src_pfn, dst_pfn = 0;
 	struct migrate_vma mig;
@@ -624,11 +652,16 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
 		goto out_finalize;
 	}
 
-	pfn = *mig.src >> MIGRATE_PFN_SHIFT;
-	spage = migrate_pfn_to_page(*mig.src);
-	if (spage)
-		uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0,
-			   page_shift);
+	if (pagein) {
+		pfn = *mig.src >> MIGRATE_PFN_SHIFT;
+		spage = migrate_pfn_to_page(*mig.src);
+		if (spage) {
+			ret = uv_page_in(kvm->arch.lpid, pfn << page_shift,
+					gpa, 0, page_shift);
+			if (ret)
+				goto out_finalize;
+		}
+	}
 
 	*mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED;
 	migrate_vma_pages(&mig);
@@ -637,6 +670,80 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
 	return ret;
 }
 
+static int kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
+		const struct kvm_memory_slot *memslot)
+{
+	unsigned long gfn = memslot->base_gfn;
+	struct vm_area_struct *vma;
+	unsigned long start, end;
+	int ret = 0;
+
+	mmap_read_lock(kvm->mm);
+	mutex_lock(&kvm->arch.uvmem_lock);
+	while (kvmppc_next_nontransitioned_gfn(memslot, kvm, &gfn)) {
+		ret = H_STATE;
+		start = gfn_to_hva(kvm, gfn);
+		if (kvm_is_error_hva(start))
+			break;
+
+		end = start + (1UL << PAGE_SHIFT);
+		vma = find_vma_intersection(kvm->mm, start, end);
+		if (!vma || vma->vm_start > start || vma->vm_end < end)
+			break;
+
+		ret = kvmppc_svm_page_in(vma, start, end,
+				(gfn << PAGE_SHIFT), kvm, PAGE_SHIFT, false);
+		if (ret) {
+			ret = H_STATE;
+			break;
+		}
+
+		/* relinquish the cpu if needed */
+		cond_resched();
+	}
+	mutex_unlock(&kvm->arch.uvmem_lock);
+	mmap_read_unlock(kvm->mm);
+	return ret;
+}
+
+unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int srcu_idx;
+	long ret = H_SUCCESS;
+
+	if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
+		return H_UNSUPPORTED;
+
+	/* migrate any unmoved normal pfn to device pfns*/
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots) {
+		ret = kvmppc_uv_migrate_mem_slot(kvm, memslot);
+		if (ret) {
+			/*
+			 * The pages will remain transitioned.
+			 * Its the callers responsibility to
+			 * terminate the VM, which will undo
+			 * all state of the VM. Till then
+			 * this VM is in a erroneous state.
+			 * Its KVMPPC_SECURE_INIT_DONE will
+			 * remain unset.
+			 */
+			ret = H_STATE;
+			goto out;
+		}
+	}
+
+	kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE;
+	pr_info("LPID %d went secure\n", kvm->arch.lpid);
+
+out:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	return ret;
+}
+
 /*
  * Shares the page with HV, thus making it a normal page.
  *
@@ -745,8 +852,11 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 	if (!vma || vma->vm_start > start || vma->vm_end < end)
 		goto out_unlock;
 
-	if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift))
-		ret = H_SUCCESS;
+	if (kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift,
+				true))
+		goto out_unlock;
+
+	ret = H_SUCCESS;
 
 out_unlock:
 	mutex_unlock(&kvm->arch.uvmem_lock);

From a2ce72003863d0dcf680f0c49de4678ab2c6812b Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour@linux.ibm.com>
Date: Mon, 27 Jul 2020 11:07:18 -0700
Subject: [PATCH 152/474] KVM: PPC: Book3S HV: Migrate hot plugged memory

When a memory slot is hot plugged to a SVM, PFNs associated with the
GFNs in that slot must be migrated to the secure-PFNs, aka device-PFNs.

Call kvmppc_uv_migrate_mem_slot() to accomplish this.
Disable page-merge for all pages in the memory slot.

Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
[rearranged the code, and modified the commit log]
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/include/asm/kvm_book3s_uvmem.h | 14 +++++++++++++
 arch/powerpc/kvm/book3s_hv.c                | 14 ++++++-------
 arch/powerpc/kvm/book3s_hv_uvmem.c          | 23 +++++++++++++++++----
 3 files changed, 39 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
index 9cb7d8be2366..0a6319448cb6 100644
--- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h
+++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
@@ -23,6 +23,10 @@ int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn);
 unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm);
 void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
 			     struct kvm *kvm, bool skip_page_out);
+int kvmppc_uvmem_memslot_create(struct kvm *kvm,
+		const struct kvm_memory_slot *new);
+void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
+		const struct kvm_memory_slot *old);
 #else
 static inline int kvmppc_uvmem_init(void)
 {
@@ -82,5 +86,15 @@ static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
 static inline void
 kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
 			struct kvm *kvm, bool skip_page_out) { }
+
+static inline int  kvmppc_uvmem_memslot_create(struct kvm *kvm,
+		const struct kvm_memory_slot *new)
+{
+	return H_UNSUPPORTED;
+}
+
+static inline void  kvmppc_uvmem_memslot_delete(struct kvm *kvm,
+		const struct kvm_memory_slot *old) { }
+
 #endif /* CONFIG_PPC_UV */
 #endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index d64a2dc1ccca..d9a9dd743b8f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4523,16 +4523,14 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
 
 	switch (change) {
 	case KVM_MR_CREATE:
-		if (kvmppc_uvmem_slot_init(kvm, new))
-			return;
-		uv_register_mem_slot(kvm->arch.lpid,
-				     new->base_gfn << PAGE_SHIFT,
-				     new->npages * PAGE_SIZE,
-				     0, new->id);
+		/*
+		 * @TODO kvmppc_uvmem_memslot_create() can fail and
+		 * return error. Fix this.
+		 */
+		kvmppc_uvmem_memslot_create(kvm, new);
 		break;
 	case KVM_MR_DELETE:
-		uv_unregister_mem_slot(kvm->arch.lpid, old->id);
-		kvmppc_uvmem_slot_free(kvm, old);
+		kvmppc_uvmem_memslot_delete(kvm, old);
 		break;
 	default:
 		/* TODO: Handle KVM_MR_MOVE */
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index a1664ae4d81f..5b917ea2fbf6 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -418,7 +418,7 @@ static int kvmppc_memslot_page_merge(struct kvm *kvm,
 	return ret;
 }
 
-static void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
+static void __kvmppc_uvmem_memslot_delete(struct kvm *kvm,
 		const struct kvm_memory_slot *memslot)
 {
 	uv_unregister_mem_slot(kvm->arch.lpid, memslot->id);
@@ -426,7 +426,7 @@ static void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
 	kvmppc_memslot_page_merge(kvm, memslot, true);
 }
 
-static int kvmppc_uvmem_memslot_create(struct kvm *kvm,
+static int __kvmppc_uvmem_memslot_create(struct kvm *kvm,
 		const struct kvm_memory_slot *memslot)
 {
 	int ret = H_PARAMETER;
@@ -478,7 +478,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 	/* register the memslot */
 	slots = kvm_memslots(kvm);
 	kvm_for_each_memslot(memslot, slots) {
-		ret = kvmppc_uvmem_memslot_create(kvm, memslot);
+		ret = __kvmppc_uvmem_memslot_create(kvm, memslot);
 		if (ret)
 			break;
 	}
@@ -488,7 +488,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 		kvm_for_each_memslot(m, slots) {
 			if (m == memslot)
 				break;
-			kvmppc_uvmem_memslot_delete(kvm, memslot);
+			__kvmppc_uvmem_memslot_delete(kvm, memslot);
 		}
 	}
 
@@ -1057,6 +1057,21 @@ int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
 	return (ret == U_SUCCESS) ? RESUME_GUEST : -EFAULT;
 }
 
+int kvmppc_uvmem_memslot_create(struct kvm *kvm, const struct kvm_memory_slot *new)
+{
+	int ret = __kvmppc_uvmem_memslot_create(kvm, new);
+
+	if (!ret)
+		ret = kvmppc_uv_migrate_mem_slot(kvm, new);
+
+	return ret;
+}
+
+void kvmppc_uvmem_memslot_delete(struct kvm *kvm, const struct kvm_memory_slot *old)
+{
+	__kvmppc_uvmem_memslot_delete(kvm, old);
+}
+
 static u64 kvmppc_get_secmem_size(void)
 {
 	struct device_node *np;

From f1b87ea8784b8c79d9bffad60fe0720c2cb21ec7 Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour@linux.ibm.com>
Date: Mon, 27 Jul 2020 12:24:28 -0700
Subject: [PATCH 153/474] KVM: PPC: Book3S HV: Move kvmppc_svm_page_out up

kvmppc_svm_page_out() will need to be called by kvmppc_uvmem_drop_pages()
so move it up earlier in this file.

Furthermore it will be interesting to call this function when already
holding the kvm->arch.uvmem_lock, so prefix the original function with __
and remove the locking in it, and introduce a wrapper which call that
function with the lock held.

There is no functional change.

Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c | 166 ++++++++++++++++-------------
 1 file changed, 90 insertions(+), 76 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 5b917ea2fbf6..565f24bbccf1 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -496,6 +496,96 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 	return ret;
 }
 
+/*
+ * Provision a new page on HV side and copy over the contents
+ * from secure memory using UV_PAGE_OUT uvcall.
+ * Caller must held kvm->arch.uvmem_lock.
+ */
+static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
+		unsigned long start,
+		unsigned long end, unsigned long page_shift,
+		struct kvm *kvm, unsigned long gpa)
+{
+	unsigned long src_pfn, dst_pfn = 0;
+	struct migrate_vma mig;
+	struct page *dpage, *spage;
+	struct kvmppc_uvmem_page_pvt *pvt;
+	unsigned long pfn;
+	int ret = U_SUCCESS;
+
+	memset(&mig, 0, sizeof(mig));
+	mig.vma = vma;
+	mig.start = start;
+	mig.end = end;
+	mig.src = &src_pfn;
+	mig.dst = &dst_pfn;
+	mig.src_owner = &kvmppc_uvmem_pgmap;
+
+	/* The requested page is already paged-out, nothing to do */
+	if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
+		return ret;
+
+	ret = migrate_vma_setup(&mig);
+	if (ret)
+		return -1;
+
+	spage = migrate_pfn_to_page(*mig.src);
+	if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE))
+		goto out_finalize;
+
+	if (!is_zone_device_page(spage))
+		goto out_finalize;
+
+	dpage = alloc_page_vma(GFP_HIGHUSER, vma, start);
+	if (!dpage) {
+		ret = -1;
+		goto out_finalize;
+	}
+
+	lock_page(dpage);
+	pvt = spage->zone_device_data;
+	pfn = page_to_pfn(dpage);
+
+	/*
+	 * This function is used in two cases:
+	 * - When HV touches a secure page, for which we do UV_PAGE_OUT
+	 * - When a secure page is converted to shared page, we *get*
+	 *   the page to essentially unmap the device page. In this
+	 *   case we skip page-out.
+	 */
+	if (!pvt->skip_page_out)
+		ret = uv_page_out(kvm->arch.lpid, pfn << page_shift,
+				  gpa, 0, page_shift);
+
+	if (ret == U_SUCCESS)
+		*mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED;
+	else {
+		unlock_page(dpage);
+		__free_page(dpage);
+		goto out_finalize;
+	}
+
+	migrate_vma_pages(&mig);
+
+out_finalize:
+	migrate_vma_finalize(&mig);
+	return ret;
+}
+
+static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
+				      unsigned long start, unsigned long end,
+				      unsigned long page_shift,
+				      struct kvm *kvm, unsigned long gpa)
+{
+	int ret;
+
+	mutex_lock(&kvm->arch.uvmem_lock);
+	ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa);
+	mutex_unlock(&kvm->arch.uvmem_lock);
+
+	return ret;
+}
+
 /*
  * Drop device pages that we maintain for the secure guest
  *
@@ -866,82 +956,6 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 	return ret;
 }
 
-/*
- * Provision a new page on HV side and copy over the contents
- * from secure memory using UV_PAGE_OUT uvcall.
- */
-static int kvmppc_svm_page_out(struct vm_area_struct *vma,
-		unsigned long start,
-		unsigned long end, unsigned long page_shift,
-		struct kvm *kvm, unsigned long gpa)
-{
-	unsigned long src_pfn, dst_pfn = 0;
-	struct migrate_vma mig;
-	struct page *dpage, *spage;
-	struct kvmppc_uvmem_page_pvt *pvt;
-	unsigned long pfn;
-	int ret = U_SUCCESS;
-
-	memset(&mig, 0, sizeof(mig));
-	mig.vma = vma;
-	mig.start = start;
-	mig.end = end;
-	mig.src = &src_pfn;
-	mig.dst = &dst_pfn;
-	mig.src_owner = &kvmppc_uvmem_pgmap;
-
-	mutex_lock(&kvm->arch.uvmem_lock);
-	/* The requested page is already paged-out, nothing to do */
-	if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
-		goto out;
-
-	ret = migrate_vma_setup(&mig);
-	if (ret)
-		goto out;
-
-	spage = migrate_pfn_to_page(*mig.src);
-	if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE))
-		goto out_finalize;
-
-	if (!is_zone_device_page(spage))
-		goto out_finalize;
-
-	dpage = alloc_page_vma(GFP_HIGHUSER, vma, start);
-	if (!dpage) {
-		ret = -1;
-		goto out_finalize;
-	}
-
-	lock_page(dpage);
-	pvt = spage->zone_device_data;
-	pfn = page_to_pfn(dpage);
-
-	/*
-	 * This function is used in two cases:
-	 * - When HV touches a secure page, for which we do UV_PAGE_OUT
-	 * - When a secure page is converted to shared page, we *get*
-	 *   the page to essentially unmap the device page. In this
-	 *   case we skip page-out.
-	 */
-	if (!pvt->skip_page_out)
-		ret = uv_page_out(kvm->arch.lpid, pfn << page_shift,
-				  gpa, 0, page_shift);
-
-	if (ret == U_SUCCESS)
-		*mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED;
-	else {
-		unlock_page(dpage);
-		__free_page(dpage);
-		goto out_finalize;
-	}
-
-	migrate_vma_pages(&mig);
-out_finalize:
-	migrate_vma_finalize(&mig);
-out:
-	mutex_unlock(&kvm->arch.uvmem_lock);
-	return ret;
-}
 
 /*
  * Fault handler callback that gets called when HV touches any page that

From 81ab595ddd3c3036806b460526e1fbc5b271ff33 Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour@linux.ibm.com>
Date: Mon, 27 Jul 2020 12:24:29 -0700
Subject: [PATCH 154/474] KVM: PPC: Book3S HV: Rework secure mem slot dropping

When a secure memslot is dropped, all the pages backed in the secure
device (aka really backed by secure memory by the Ultravisor)
should be paged out to a normal page. Previously, this was
achieved by triggering the page fault mechanism which is calling
kvmppc_svm_page_out() on each pages.

This can't work when hot unplugging a memory slot because the memory
slot is flagged as invalid and gfn_to_pfn() is then not trying to access
the page, so the page fault mechanism is not triggered.

Since the final goal is to make a call to kvmppc_svm_page_out() it seems
simpler to call directly instead of triggering such a mechanism. This
way kvmppc_uvmem_drop_pages() can be called even when hot unplugging a
memslot.

Since kvmppc_uvmem_drop_pages() is already holding kvm->arch.uvmem_lock,
the call to __kvmppc_svm_page_out() is made.  As
__kvmppc_svm_page_out needs the vma pointer to migrate the pages,
the VMA is fetched in a lazy way, to not trigger find_vma() all
the time. In addition, the mmap_sem is held in read mode during
that time, not in write mode since the virual memory layout is not
impacted, and kvm->arch.uvmem_lock prevents concurrent operation
on the secure device.

Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
        [modified check on the VMA in kvmppc_uvmem_drop_pages]
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
	[modified the changelog description]
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c | 56 ++++++++++++++++++++----------
 1 file changed, 37 insertions(+), 19 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 565f24bbccf1..0d49e3425a12 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -594,35 +594,53 @@ static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
  * fault on them, do fault time migration to replace the device PTEs in
  * QEMU page table with normal PTEs from newly allocated pages.
  */
-void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
+void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
 			     struct kvm *kvm, bool skip_page_out)
 {
 	int i;
 	struct kvmppc_uvmem_page_pvt *pvt;
-	unsigned long pfn, uvmem_pfn;
-	unsigned long gfn = free->base_gfn;
+	struct page *uvmem_page;
+	struct vm_area_struct *vma = NULL;
+	unsigned long uvmem_pfn, gfn;
+	unsigned long addr;
 
-	for (i = free->npages; i; --i, ++gfn) {
-		struct page *uvmem_page;
+	mmap_read_lock(kvm->mm);
 
-		mutex_lock(&kvm->arch.uvmem_lock);
-		if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
-			kvmppc_gfn_remove(gfn, kvm);
-			mutex_unlock(&kvm->arch.uvmem_lock);
-			continue;
+	addr = slot->userspace_addr;
+
+	gfn = slot->base_gfn;
+	for (i = slot->npages; i; --i, ++gfn, addr += PAGE_SIZE) {
+
+		/* Fetch the VMA if addr is not in the latest fetched one */
+		if (!vma || addr >= vma->vm_end) {
+			vma = find_vma_intersection(kvm->mm, addr, addr+1);
+			if (!vma) {
+				pr_err("Can't find VMA for gfn:0x%lx\n", gfn);
+				break;
+			}
 		}
 
-		uvmem_page = pfn_to_page(uvmem_pfn);
-		pvt = uvmem_page->zone_device_data;
-		pvt->skip_page_out = skip_page_out;
-		pvt->remove_gfn = true;
-		mutex_unlock(&kvm->arch.uvmem_lock);
+		mutex_lock(&kvm->arch.uvmem_lock);
 
-		pfn = gfn_to_pfn(kvm, gfn);
-		if (is_error_noslot_pfn(pfn))
-			continue;
-		kvm_release_pfn_clean(pfn);
+		if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+			uvmem_page = pfn_to_page(uvmem_pfn);
+			pvt = uvmem_page->zone_device_data;
+			pvt->skip_page_out = skip_page_out;
+			pvt->remove_gfn = true;
+
+			if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE,
+						  PAGE_SHIFT, kvm, pvt->gpa))
+				pr_err("Can't page out gpa:0x%lx addr:0x%lx\n",
+				       pvt->gpa, addr);
+		} else {
+			/* Remove the shared flag if any */
+			kvmppc_gfn_remove(gfn, kvm);
+		}
+
+		mutex_unlock(&kvm->arch.uvmem_lock);
 	}
+
+	mmap_read_unlock(kvm->mm);
 }
 
 unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)

From 24f69c0fa4e252f706884114b7d6353aa07678b5 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Tue, 21 Jul 2020 10:44:44 +0100
Subject: [PATCH 155/474] KVM: arm64: Make nVHE ASLR conditional on
 RANDOMIZE_BASE

If there are spare bits in non-VHE hyp VA, KVM unconditionally replaces them
with a random tag chosen at init. Disable this if the kernel is built without
RANDOMIZE_BASE to align with kernel behavior.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200721094445.82184-2-dbrazdil@google.com
---
 arch/arm64/kvm/va_layout.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index a4f48c1ac28c..e0404bcab019 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -48,7 +48,7 @@ __init void kvm_compute_layout(void)
 	va_mask = GENMASK_ULL(tag_lsb - 1, 0);
 	tag_val = hyp_va_msb;
 
-	if (tag_lsb != (vabits_actual - 1)) {
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && tag_lsb != (vabits_actual - 1)) {
 		/* We have some free bits to insert a random tag. */
 		tag_val |= get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb);
 	}

From a59a2edbbba7397fede86e40a3da17e5beebf98b Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Tue, 21 Jul 2020 10:44:45 +0100
Subject: [PATCH 156/474] KVM: arm64: Substitute RANDOMIZE_BASE for
 HARDEN_EL2_VECTORS

The HARDEN_EL2_VECTORS config maps vectors at a fixed location on cores which
are susceptible to Spector variant 3a (A57, A72) to prevent defeating hyp
layout randomization by leaking the value of VBAR_EL2.

Since this feature is only applicable when EL2 layout randomization is enabled,
unify both behind the same RANDOMIZE_BASE Kconfig. Majority of code remains
conditional on a capability selected for the affected cores.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200721094445.82184-3-dbrazdil@google.com
---
 arch/arm64/Kconfig             | 16 ----------------
 arch/arm64/include/asm/mmu.h   |  6 ++----
 arch/arm64/kernel/cpu_errata.c |  4 ++--
 arch/arm64/kvm/Kconfig         |  2 +-
 4 files changed, 5 insertions(+), 23 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 31380da53689..152deef3277e 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1182,22 +1182,6 @@ config HARDEN_BRANCH_PREDICTOR
 
 	  If unsure, say Y.
 
-config HARDEN_EL2_VECTORS
-	bool "Harden EL2 vector mapping against system register leak" if EXPERT
-	default y
-	help
-	  Speculation attacks against some high-performance processors can
-	  be used to leak privileged information such as the vector base
-	  register, resulting in a potential defeat of the EL2 layout
-	  randomization.
-
-	  This config option will map the vectors to a fixed location,
-	  independent of the EL2 code mapping, so that revealing VBAR_EL2
-	  to an attacker does not give away any extra information. This
-	  only gets enabled on affected CPUs.
-
-	  If unsure, say Y.
-
 config ARM64_SSBD
 	bool "Speculative Store Bypass Disable" if EXPERT
 	default y
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 68140fdd89d6..bd12011eb560 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -42,12 +42,10 @@ struct bp_hardening_data {
 	bp_hardening_cb_t	fn;
 };
 
-#if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) ||	\
-     defined(CONFIG_HARDEN_EL2_VECTORS))
-
+#ifdef CONFIG_KVM_INDIRECT_VECTORS
 extern char __bp_harden_hyp_vecs[];
 extern atomic_t arm64_el2_vector_last_slot;
-#endif  /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */
+#endif
 
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index ad06d6802d2e..a524142e55d0 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -635,7 +635,7 @@ has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
 	return is_midr_in_range(midr, &range) && has_dic;
 }
 
-#if defined(CONFIG_HARDEN_EL2_VECTORS)
+#ifdef CONFIG_RANDOMIZE_BASE
 
 static const struct midr_range ca57_a72[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
@@ -880,7 +880,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = check_branch_predictor,
 	},
-#ifdef CONFIG_HARDEN_EL2_VECTORS
+#ifdef CONFIG_RANDOMIZE_BASE
 	{
 		.desc = "EL2 vector hardening",
 		.capability = ARM64_HARDEN_EL2_VECTORS,
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 13489aff4440..318c8f2df245 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -58,7 +58,7 @@ config KVM_ARM_PMU
 	  virtual machines.
 
 config KVM_INDIRECT_VECTORS
-	def_bool HARDEN_BRANCH_PREDICTOR || HARDEN_EL2_VECTORS
+	def_bool HARDEN_BRANCH_PREDICTOR || RANDOMIZE_BASE
 
 endif # KVM
 

From 4299f85a67480cdb43a3c4c1840a05259727e83c Mon Sep 17 00:00:00 2001
From: Lars Povlsen <lars.povlsen@microchip.com>
Date: Mon, 27 Jul 2020 10:42:08 +0200
Subject: [PATCH 157/474] dt-bindings: clock: sparx5: Add bindings include file

The Sparx5 support 9 different clock outputs. This include file has
defines for each supported clock ordinal.

Signed-off-by: Lars Povlsen <lars.povlsen@microchip.com>
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20200727084211.6632-8-lars.povlsen@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 include/dt-bindings/clock/microchip,sparx5.h | 23 ++++++++++++++++++++
 1 file changed, 23 insertions(+)
 create mode 100644 include/dt-bindings/clock/microchip,sparx5.h

diff --git a/include/dt-bindings/clock/microchip,sparx5.h b/include/dt-bindings/clock/microchip,sparx5.h
new file mode 100644
index 000000000000..4b04dabacec2
--- /dev/null
+++ b/include/dt-bindings/clock/microchip,sparx5.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2019 Microchip Inc.
+ *
+ * Author: Lars Povlsen <lars.povlsen@microchip.com>
+ */
+
+#ifndef _DT_BINDINGS_CLK_SPARX5_H
+#define _DT_BINDINGS_CLK_SPARX5_H
+
+#define CLK_ID_CORE	0
+#define CLK_ID_DDR	1
+#define CLK_ID_CPU2	2
+#define CLK_ID_ARM2	3
+#define CLK_ID_AUX1	4
+#define CLK_ID_AUX2	5
+#define CLK_ID_AUX3	6
+#define CLK_ID_AUX4	7
+#define CLK_ID_SYNCE	8
+
+#define N_CLOCKS	9
+
+#endif

From 53727eb6b3c210e826bb4c9d0aa89f65a5ae9342 Mon Sep 17 00:00:00 2001
From: Lars Povlsen <lars.povlsen@microchip.com>
Date: Mon, 27 Jul 2020 10:42:09 +0200
Subject: [PATCH 158/474] clk: sparx5: Add Sparx5 SoC DPLL clock driver

This adds a device driver for the Sparx5 SoC DPLL clock

Signed-off-by: Lars Povlsen <lars.povlsen@microchip.com>
Link: https://lore.kernel.org/r/20200727084211.6632-9-lars.povlsen@microchip.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/Makefile     |   1 +
 drivers/clk/clk-sparx5.c | 295 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 296 insertions(+)
 create mode 100644 drivers/clk/clk-sparx5.c

diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index ca9af11d3391..da8fcf147eb1 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_COMMON_CLK_CDCE925)	+= clk-cdce925.o
 obj-$(CONFIG_ARCH_CLPS711X)		+= clk-clps711x.o
 obj-$(CONFIG_COMMON_CLK_CS2000_CP)	+= clk-cs2000-cp.o
 obj-$(CONFIG_ARCH_EFM32)		+= clk-efm32gg.o
+obj-$(CONFIG_ARCH_SPARX5)		+= clk-sparx5.o
 obj-$(CONFIG_COMMON_CLK_FIXED_MMIO)	+= clk-fixed-mmio.o
 obj-$(CONFIG_COMMON_CLK_FSL_SAI)	+= clk-fsl-sai.o
 obj-$(CONFIG_COMMON_CLK_GEMINI)		+= clk-gemini.o
diff --git a/drivers/clk/clk-sparx5.c b/drivers/clk/clk-sparx5.c
new file mode 100644
index 000000000000..0fad0c1a0186
--- /dev/null
+++ b/drivers/clk/clk-sparx5.c
@@ -0,0 +1,295 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Microchip Sparx5 SoC Clock driver.
+ *
+ * Copyright (c) 2019 Microchip Inc.
+ *
+ * Author: Lars Povlsen <lars.povlsen@microchip.com>
+ */
+
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/clk-provider.h>
+#include <linux/bitfield.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <dt-bindings/clock/microchip,sparx5.h>
+
+#define PLL_DIV		GENMASK(7, 0)
+#define PLL_PRE_DIV	GENMASK(10, 8)
+#define PLL_ROT_DIR	BIT(11)
+#define PLL_ROT_SEL	GENMASK(13, 12)
+#define PLL_ROT_ENA	BIT(14)
+#define PLL_CLK_ENA	BIT(15)
+
+#define MAX_SEL 4
+#define MAX_PRE BIT(3)
+
+static const u8 sel_rates[MAX_SEL] = { 0, 2*8, 2*4, 2*2 };
+
+static const char *clk_names[N_CLOCKS] = {
+	"core", "ddr", "cpu2", "arm2",
+	"aux1", "aux2", "aux3", "aux4",
+	"synce",
+};
+
+struct s5_hw_clk {
+	struct clk_hw hw;
+	void __iomem *reg;
+};
+
+struct s5_clk_data {
+	void __iomem *base;
+	struct s5_hw_clk s5_hw[N_CLOCKS];
+};
+
+struct s5_pll_conf {
+	unsigned long freq;
+	u8 div;
+	bool rot_ena;
+	u8 rot_sel;
+	u8 rot_dir;
+	u8 pre_div;
+};
+
+#define to_s5_pll(hw) container_of(hw, struct s5_hw_clk, hw)
+
+static unsigned long s5_calc_freq(unsigned long parent_rate,
+				  const struct s5_pll_conf *conf)
+{
+	unsigned long rate = parent_rate / conf->div;
+
+	if (conf->rot_ena) {
+		int sign = conf->rot_dir ? -1 : 1;
+		int divt = sel_rates[conf->rot_sel] * (1 + conf->pre_div);
+		int divb = divt + sign;
+
+		rate = mult_frac(rate, divt, divb);
+		rate = roundup(rate, 1000);
+	}
+
+	return rate;
+}
+
+static void s5_search_fractional(unsigned long rate,
+				 unsigned long parent_rate,
+				 int div,
+				 struct s5_pll_conf *conf)
+{
+	struct s5_pll_conf best;
+	ulong cur_offset, best_offset = rate;
+	int d, i, j;
+
+	memset(conf, 0, sizeof(*conf));
+	conf->div = div;
+	conf->rot_ena = 1;	/* Fractional rate */
+
+	for (d = 0; best_offset > 0 && d <= 1 ; d++) {
+		conf->rot_dir = !!d;
+		for (i = 0; best_offset > 0 && i < MAX_PRE; i++) {
+			conf->pre_div = i;
+			for (j = 1; best_offset > 0 && j < MAX_SEL; j++) {
+				conf->rot_sel = j;
+				conf->freq = s5_calc_freq(parent_rate, conf);
+				cur_offset = abs(rate - conf->freq);
+				if (cur_offset < best_offset) {
+					best_offset = cur_offset;
+					best = *conf;
+				}
+			}
+		}
+	}
+
+	/* Best match */
+	*conf = best;
+}
+
+static unsigned long s5_calc_params(unsigned long rate,
+				    unsigned long parent_rate,
+				    struct s5_pll_conf *conf)
+{
+	if (parent_rate % rate) {
+		struct s5_pll_conf alt1, alt2;
+		int div;
+
+		div = DIV_ROUND_CLOSEST_ULL(parent_rate, rate);
+		s5_search_fractional(rate, parent_rate, div, &alt1);
+
+		/* Straight match? */
+		if (alt1.freq == rate) {
+			*conf = alt1;
+		} else {
+			/* Try without rounding divider */
+			div = parent_rate / rate;
+			if (div != alt1.div) {
+				s5_search_fractional(rate, parent_rate, div,
+						     &alt2);
+				/* Select the better match */
+				if (abs(rate - alt1.freq) <
+				    abs(rate - alt2.freq))
+					*conf = alt1;
+				else
+					*conf = alt2;
+			}
+		}
+	} else {
+		/* Straight fit */
+		memset(conf, 0, sizeof(*conf));
+		conf->div = parent_rate / rate;
+	}
+
+	return conf->freq;
+}
+
+static int s5_pll_enable(struct clk_hw *hw)
+{
+	struct s5_hw_clk *pll = to_s5_pll(hw);
+	u32 val = readl(pll->reg);
+
+	val |= PLL_CLK_ENA;
+	writel(val, pll->reg);
+
+	return 0;
+}
+
+static void s5_pll_disable(struct clk_hw *hw)
+{
+	struct s5_hw_clk *pll = to_s5_pll(hw);
+	u32 val = readl(pll->reg);
+
+	val &= ~PLL_CLK_ENA;
+	writel(val, pll->reg);
+}
+
+static int s5_pll_set_rate(struct clk_hw *hw,
+			   unsigned long rate,
+			   unsigned long parent_rate)
+{
+	struct s5_hw_clk *pll = to_s5_pll(hw);
+	struct s5_pll_conf conf;
+	unsigned long eff_rate;
+	u32 val;
+
+	eff_rate = s5_calc_params(rate, parent_rate, &conf);
+	if (eff_rate != rate)
+		return -EOPNOTSUPP;
+
+	val = readl(pll->reg) & PLL_CLK_ENA;
+	val |= FIELD_PREP(PLL_DIV, conf.div);
+	if (conf.rot_ena) {
+		val |= PLL_ROT_ENA;
+		val |= FIELD_PREP(PLL_ROT_SEL, conf.rot_sel);
+		val |= FIELD_PREP(PLL_PRE_DIV, conf.pre_div);
+		if (conf.rot_dir)
+			val |= PLL_ROT_DIR;
+	}
+	writel(val, pll->reg);
+
+	return 0;
+}
+
+static unsigned long s5_pll_recalc_rate(struct clk_hw *hw,
+					unsigned long parent_rate)
+{
+	struct s5_hw_clk *pll = to_s5_pll(hw);
+	struct s5_pll_conf conf;
+	u32 val;
+
+	val = readl(pll->reg);
+
+	if (val & PLL_CLK_ENA) {
+		conf.div     = FIELD_GET(PLL_DIV, val);
+		conf.pre_div = FIELD_GET(PLL_PRE_DIV, val);
+		conf.rot_ena = FIELD_GET(PLL_ROT_ENA, val);
+		conf.rot_dir = FIELD_GET(PLL_ROT_DIR, val);
+		conf.rot_sel = FIELD_GET(PLL_ROT_SEL, val);
+
+		conf.freq = s5_calc_freq(parent_rate, &conf);
+	} else {
+		conf.freq = 0;
+	}
+
+	return conf.freq;
+}
+
+static long s5_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+			      unsigned long *parent_rate)
+{
+	struct s5_pll_conf conf;
+
+	return s5_calc_params(rate, *parent_rate, &conf);
+}
+
+static const struct clk_ops s5_pll_ops = {
+	.enable		= s5_pll_enable,
+	.disable	= s5_pll_disable,
+	.set_rate	= s5_pll_set_rate,
+	.round_rate	= s5_pll_round_rate,
+	.recalc_rate	= s5_pll_recalc_rate,
+};
+
+static struct clk_hw *s5_clk_hw_get(struct of_phandle_args *clkspec, void *data)
+{
+	struct s5_clk_data *s5_clk = data;
+	unsigned int idx = clkspec->args[0];
+
+	if (idx >= N_CLOCKS) {
+		pr_err("%s: invalid index %u\n", __func__, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return &s5_clk->s5_hw[idx].hw;
+}
+
+static int s5_clk_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	int i, ret;
+	struct s5_clk_data *s5_clk;
+	struct clk_parent_data pdata = { .index = 0 };
+	struct clk_init_data init = {
+		.ops = &s5_pll_ops,
+		.num_parents = 1,
+		.parent_data = &pdata,
+	};
+
+	s5_clk = devm_kzalloc(dev, sizeof(*s5_clk), GFP_KERNEL);
+	if (!s5_clk)
+		return -ENOMEM;
+
+	s5_clk->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(s5_clk->base))
+		return PTR_ERR(s5_clk->base);
+
+	for (i = 0; i < N_CLOCKS; i++) {
+		struct s5_hw_clk *s5_hw = &s5_clk->s5_hw[i];
+
+		init.name = clk_names[i];
+		s5_hw->reg = s5_clk->base + (i * 4);
+		s5_hw->hw.init = &init;
+		ret = devm_clk_hw_register(dev, &s5_hw->hw);
+		if (ret) {
+			dev_err(dev, "failed to register %s clock\n",
+				init.name);
+			return ret;
+		}
+	}
+
+	return devm_of_clk_add_hw_provider(dev, s5_clk_hw_get, s5_clk);
+}
+
+static const struct of_device_id s5_clk_dt_ids[] = {
+	{ .compatible = "microchip,sparx5-dpll", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, s5_clk_dt_ids);
+
+static struct platform_driver s5_clk_driver = {
+	.probe  = s5_clk_probe,
+	.driver = {
+		.name = "sparx5-clk",
+		.of_match_table = s5_clk_dt_ids,
+	},
+};
+builtin_platform_driver(s5_clk_driver);

From 4aeccdf0671125adee903b651fb134a4759ce161 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 29 Jul 2020 13:34:39 +0200
Subject: [PATCH 159/474] clk: mmp: avoid missing prototype warning

The kernel test robot points out two harmless warnings in the
mmp clk drivers:

drivers/clk/mmp/clk-pxa168.c:68:13: warning: no previous prototype for 'pxa168_clk_init' [-Wmissing-prototypes]
drivers/clk/mmp/clk-pxa910.c:66:13: warning: no previous prototype for 'pxa910_clk_init' [-Wmissing-prototypes]

Fix these by including corresponding header file.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20200729113456.4072290-1-arnd@arndb.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/mmp/clk-pxa168.c | 1 +
 drivers/clk/mmp/clk-pxa910.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/clk/mmp/clk-pxa168.c b/drivers/clk/mmp/clk-pxa168.c
index 8e2551ab8462..b351039cac09 100644
--- a/drivers/clk/mmp/clk-pxa168.c
+++ b/drivers/clk/mmp/clk-pxa168.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/clk/mmp.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
diff --git a/drivers/clk/mmp/clk-pxa910.c b/drivers/clk/mmp/clk-pxa910.c
index 7a7965141918..f254ceff3ea7 100644
--- a/drivers/clk/mmp/clk-pxa910.c
+++ b/drivers/clk/mmp/clk-pxa910.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/clk/mmp.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/spinlock.h>

From be13d94b7d7f1a3e7290573faa16267941917106 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 24 Jul 2020 12:12:58 +0100
Subject: [PATCH 160/474] drm: xlnx: fix spelling mistake "failes" -> "failed"

There is a spelling mistake in a dev_dbg messages. Fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Hyun Kwon <hyun.kwon@xilinx.com>
Signed-off-by: Hyun Kwon <hyun.kwon@xilinx.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200724111258.14762-1-colin.king@canonical.com
---
 drivers/gpu/drm/xlnx/zynqmp_dp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xlnx/zynqmp_dp.c b/drivers/gpu/drm/xlnx/zynqmp_dp.c
index 821f7a71e182..0e1c818746eb 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dp.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_dp.c
@@ -1308,7 +1308,7 @@ zynqmp_dp_connector_detect(struct drm_connector *connector, bool force)
 		ret = drm_dp_dpcd_read(&dp->aux, 0x0, dp->dpcd,
 				       sizeof(dp->dpcd));
 		if (ret < 0) {
-			dev_dbg(dp->dev, "DPCD read failes");
+			dev_dbg(dp->dev, "DPCD read failed");
 			goto disconnected;
 		}
 

From 2d889db7626d2b6d67f402e2478b11f9a49b44e3 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Sat, 25 Jul 2020 06:34:29 +0000
Subject: [PATCH 161/474] drm: xlnx: Fix typo in parameter description

Fix typo in parameter description.

Fixes: d76271d22694 ("drm: xlnx: DRM/KMS driver for Xilinx ZynqMP DisplayPort Subsystem")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Hyun Kwon <hyun.kwon@xilinx.com>
Signed-off-by: Hyun Kwon <hyun.kwon@xilinx.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200725063429.172139-1-weiyongjun1@huawei.com
---
 drivers/gpu/drm/xlnx/zynqmp_dp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xlnx/zynqmp_dp.c b/drivers/gpu/drm/xlnx/zynqmp_dp.c
index 0e1c818746eb..b735072a702d 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dp.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_dp.c
@@ -44,7 +44,7 @@ MODULE_PARM_DESC(aux_timeout_ms, "DP aux timeout value in msec (default: 50)");
  */
 static uint zynqmp_dp_power_on_delay_ms = 4;
 module_param_named(power_on_delay_ms, zynqmp_dp_power_on_delay_ms, uint, 0444);
-MODULE_PARM_DESC(aux_timeout_ms, "DP power on delay in msec (default: 4)");
+MODULE_PARM_DESC(power_on_delay_ms, "DP power on delay in msec (default: 4)");
 
 /* Link configuration registers */
 #define ZYNQMP_DP_LINK_BW_SET				0x0

From c0001213d195d1bac83e0744c06ff06dd5a8ba53 Mon Sep 17 00:00:00 2001
From: Felix Kuehling <Felix.Kuehling@amd.com>
Date: Tue, 28 Jul 2020 14:27:04 -0400
Subject: [PATCH 162/474] drm/ttm: fix offset in VMAs with a pg_offs in
 ttm_bo_vm_access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

VMAs with a pg_offs that's offset from the start of the vma_node need
to adjust the offset within the BO accordingly. This matches the
offset calculation in ttm_bo_vm_fault_reserved.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Laurent Morichetti <laurent.morichetti@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/381169/
---
 drivers/gpu/drm/ttm/ttm_bo_vm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index fa03fab02076..33526c5df0e8 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -505,8 +505,10 @@ static int ttm_bo_vm_access_kmap(struct ttm_buffer_object *bo,
 int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
 		     void *buf, int len, int write)
 {
-	unsigned long offset = (addr) - vma->vm_start;
 	struct ttm_buffer_object *bo = vma->vm_private_data;
+	unsigned long offset = (addr) - vma->vm_start +
+		((vma->vm_pgoff - drm_vma_node_start(&bo->base.vma_node))
+		 << PAGE_SHIFT);
 	int ret;
 
 	if (len < 1 || (offset + len) >> PAGE_SHIFT > bo->num_pages)

From bdbc0c7a070c0cbe3009cd271c6ec8d87d69cc7a Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Thu, 30 Jul 2020 14:25:19 +0100
Subject: [PATCH 163/474] KVM: arm64: Ensure that all nVHE hyp code is in
 .hyp.text

Some compilers may put a subset of generated functions into '.text.*'
ELF sections and the linker may leverage this division to optimize ELF
layout. Unfortunately, the recently introduced HYPCOPY command assumes
that all executable code (with the exception of specialized sections
such as '.hyp.idmap.text') is in the '.text' section. If this
assumption is broken, code in '.text.*' will be merged into kernel
proper '.text' instead of the '.hyp.text' that is mapped in EL2.

To ensure that this cannot happen, insert an OBJDUMP assertion into
HYPCOPY. The command dumps a list of ELF sections in the input object
file and greps for '.text.'. If found, compilation fails. Tested with
both binutils' and LLVM's objdump (the output format is different).

GCC offers '-fno-reorder-functions' to disable this behaviour. Select
the flag if it is available. From inspection of GCC source (latest
Git in July 2020), this flag does force all code into '.text'.
By default, GCC uses profile data, heuristics and attributes to select
a subsection.

LLVM/Clang currently does not have a similar optimization pass. It can
place static constructors into '.text.startup' and it's optimizer can
be provided with profile data to reorder hot/cold functions. Neither
of these is applicable to nVHE hyp code. If this changes in the future,
the OBJDUMP assertion should alert users to the problem.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200730132519.48787-1-dbrazdil@google.com
---
 arch/arm64/kvm/hyp/nvhe/Makefile | 26 +++++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 0b34414557d6..aef76487edc2 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -20,10 +20,30 @@ $(obj)/%.hyp.tmp.o: $(src)/%.S FORCE
 $(obj)/%.hyp.o: $(obj)/%.hyp.tmp.o FORCE
 	$(call if_changed,hypcopy)
 
+# Disable reordering functions by GCC (enabled at -O2).
+# This pass puts functions into '.text.*' sections to aid the linker
+# in optimizing ELF layout. See HYPCOPY comment below for more info.
+ccflags-y += $(call cc-option,-fno-reorder-functions)
+
+# The HYPCOPY command uses `objcopy` to prefix all ELF symbol names
+# and relevant ELF section names to avoid clashes with VHE code/data.
+#
+# Hyp code is assumed to be in the '.text' section of the input object
+# files (with the exception of specialized sections such as
+# '.hyp.idmap.text'). This assumption may be broken by a compiler that
+# divides code into sections like '.text.unlikely' so as to optimize
+# ELF layout. HYPCOPY checks that no such sections exist in the input
+# using `objdump`, otherwise they would be linked together with other
+# kernel code and not memory-mapped correctly at runtime.
 quiet_cmd_hypcopy = HYPCOPY $@
-      cmd_hypcopy = $(OBJCOPY)	--prefix-symbols=__kvm_nvhe_		\
-				--rename-section=.text=.hyp.text	\
-				$< $@
+      cmd_hypcopy =							\
+	if $(OBJDUMP) -h $< | grep -F '.text.'; then			\
+		echo "$@: function reordering not supported in nVHE hyp code" >&2; \
+		/bin/false;						\
+	fi;								\
+	$(OBJCOPY) --prefix-symbols=__kvm_nvhe_				\
+		   --rename-section=.text=.hyp.text			\
+		   $< $@
 
 # Remove ftrace and Shadow Call Stack CFLAGS.
 # This is equivalent to the 'notrace' and '__noscs' annotations.

From 1ccf2fe35c30f79102ad129c5aa71059daaaed7f Mon Sep 17 00:00:00 2001
From: Alexander Graf <graf@amazon.com>
Date: Thu, 30 Jul 2020 11:44:41 +0200
Subject: [PATCH 164/474] KVM: arm: Add trace name for ARM_NISV

Commit c726200dd106d ("KVM: arm/arm64: Allow reporting non-ISV data aborts
to userspace") introduced a mechanism to deflect MMIO traffic the kernel
can not handle to user space. For that, it introduced a new exit reason.

However, it did not update the trace point array that gives human readable
names to these exit reasons inside the trace log.

Let's fix that up after the fact, so that trace logs are pretty even when
we get user space MMIO traps on ARM.

Fixes: c726200dd106d ("KVM: arm/arm64: Allow reporting non-ISV data aborts to userspace")
Signed-off-by: Alexander Graf <graf@amazon.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200730094441.18231-1-graf@amazon.com
---
 include/trace/events/kvm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 2c735a3e6613..9417a34aad08 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -17,7 +17,7 @@
 	ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL),	\
 	ERSN(S390_UCONTROL), ERSN(WATCHDOG), ERSN(S390_TSCH), ERSN(EPR),\
 	ERSN(SYSTEM_EVENT), ERSN(S390_STSI), ERSN(IOAPIC_EOI),          \
-	ERSN(HYPERV)
+	ERSN(HYPERV), ERSN(ARM_NISV)
 
 TRACE_EVENT(kvm_userspace_exit,
 	    TP_PROTO(__u32 reason, int errno),

From c9a636f29b5f236441ff059cef0b2fe734c05afd Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Wed, 29 Jul 2020 11:28:18 +0100
Subject: [PATCH 165/474] KVM: arm64: Rename kvm_vcpu_dabt_isextabt()

kvm_vcpu_dabt_isextabt() is not specific to data aborts and, unlike
kvm_vcpu_dabt_issext(), has nothing to do with sign extension.

Rename it to 'kvm_vcpu_abt_issea()'.

Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20200729102821.23392-2-will@kernel.org
---
 arch/arm64/include/asm/kvm_emulate.h | 2 +-
 arch/arm64/kvm/hyp/switch.c          | 2 +-
 arch/arm64/kvm/mmu.c                 | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index c9ba0df47f7d..e0536946abed 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -366,7 +366,7 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vc
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
 }
 
-static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
 {
 	switch (kvm_vcpu_trap_get_fault(vcpu)) {
 	case FSC_SEA:
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 5164074c1ae1..36a1f0a9ce2e 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -594,7 +594,7 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
 			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
-			!kvm_vcpu_dabt_isextabt(vcpu) &&
+			!kvm_vcpu_abt_issea(vcpu) &&
 			!kvm_vcpu_dabt_iss1tw(vcpu);
 
 		if (valid) {
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 36506112480e..8004f1f68946 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2074,7 +2074,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
 	/* Synchronous External Abort? */
-	if (kvm_vcpu_dabt_isextabt(vcpu)) {
+	if (kvm_vcpu_abt_issea(vcpu)) {
 		/*
 		 * For RAS the host kernel may handle this abort.
 		 * There is no need to pass the error into the guest.

From 84b951a803a5464b0bff2fb1366e96f07f75b066 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Wed, 29 Jul 2020 11:28:19 +0100
Subject: [PATCH 166/474] KVM: arm64: Handle data and instruction external
 aborts the same way

If the guest generates a synchronous external abort which is not handled
by the host, we inject it back into the guest as a virtual SError, but
only if the original fault was reported on the data side. Instruction
faults are reported as "Unsupported FSC", causing the vCPU run loop to
bail with -EFAULT.

Although synchronous external aborts from a guest are pretty unusual,
treat them the same regardless of whether they are taken as data or
instruction aborts by EL2.

Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20200729102821.23392-3-will@kernel.org
---
 arch/arm64/kvm/mmu.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8004f1f68946..14c6a9df5c9f 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2079,13 +2079,10 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * For RAS the host kernel may handle this abort.
 		 * There is no need to pass the error into the guest.
 		 */
-		if (!kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
-			return 1;
-
-		if (unlikely(!is_iabt)) {
+		if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
 			kvm_inject_vabt(vcpu);
-			return 1;
-		}
+
+		return 1;
 	}
 
 	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),

From 54dc0d2404dd7aa0dd4e4f388a65622b68c6eaff Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Wed, 29 Jul 2020 11:28:20 +0100
Subject: [PATCH 167/474] KVM: arm64: Don't skip cache maintenance for
 read-only memslots

If a guest performs cache maintenance on a read-only memslot, we should
inform userspace rather than skip the instruction altogether.

Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20200729102821.23392-4-will@kernel.org
---
 arch/arm64/kvm/mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 14c6a9df5c9f..85b0ec9dd9ef 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2121,7 +2121,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * So let's assume that the guest is just being
 		 * cautious, and skip the instruction.
 		 */
-		if (kvm_vcpu_dabt_is_cm(vcpu)) {
+		if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) {
 			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 			ret = 1;
 			goto out_unlock;

From 022c8328dc8021248047b373b9f67790641b8f2d Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Wed, 29 Jul 2020 11:28:21 +0100
Subject: [PATCH 168/474] KVM: arm64: Move S1PTW S2 fault logic out of
 io_mem_abort()

To allow for re-injection of stage-2 faults on stage-1 page-table walks
due to either a missing or read-only memslot, move the triage logic out
of io_mem_abort() and into kvm_handle_guest_abort(), where these aborts
can be handled before anything else.

Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20200729102821.23392-5-will@kernel.org
---
 arch/arm64/kvm/mmio.c |  6 ------
 arch/arm64/kvm/mmu.c  | 13 ++++++++++++-
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c
index 4e0366759726..58de2ae4f6bb 100644
--- a/arch/arm64/kvm/mmio.c
+++ b/arch/arm64/kvm/mmio.c
@@ -145,12 +145,6 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		return -ENOSYS;
 	}
 
-	/* Page table accesses IO mem: tell guest to fix its TTBR */
-	if (kvm_vcpu_dabt_iss1tw(vcpu)) {
-		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
-		return 1;
-	}
-
 	/*
 	 * Prepare MMIO operation. First decode the syndrome data we get
 	 * from the CPU. Then try if some in-kernel emulation feels
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 85b0ec9dd9ef..dc8464669efd 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2105,12 +2105,23 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
 	write_fault = kvm_is_write_fault(vcpu);
 	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
+		/*
+		 * The guest has put either its instructions or its page-tables
+		 * somewhere it shouldn't have. Userspace won't be able to do
+		 * anything about this (there's no syndrome for a start), so
+		 * re-inject the abort back into the guest.
+		 */
 		if (is_iabt) {
-			/* Prefetch Abort on I/O address */
 			ret = -ENOEXEC;
 			goto out;
 		}
 
+		if (kvm_vcpu_dabt_iss1tw(vcpu)) {
+			kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+			ret = 1;
+			goto out_unlock;
+		}
+
 		/*
 		 * Check for a cache maintenance operation. Since we
 		 * ended-up here, we know it is outside of any memory

From a9e10b169e65f0f7061233ebe843a4b4f488dbae Mon Sep 17 00:00:00 2001
From: Steve Cohen <cohens@codeaurora.org>
Date: Wed, 29 Jul 2020 01:35:52 -0400
Subject: [PATCH 169/474] drm: re-add deleted doc for drm_gem_open_ioctl

Add back the removed documentation for drm_gem_open_ioctl.
This patch is submitted in response to [1].

[1] https://lore.kernel.org/linux-arm-msm/20200728085244.GY6419@phenom.ffwll.local/

Signed-off-by: Steve Cohen <cohens@codeaurora.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/1596000952-27621-1-git-send-email-cohens@codeaurora.org
---
 drivers/gpu/drm/drm_gem.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index ee2058ad482c..fe9412219b1e 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -871,6 +871,9 @@ drm_gem_flink_ioctl(struct drm_device *dev, void *data,
  * @file_priv: drm file-private structure
  *
  * Open an object using the global name, returning a handle and the size.
+ *
+ * This handle (of course) holds a reference to the object, so the object
+ * will not go away until the handle is deleted.
  */
 int
 drm_gem_open_ioctl(struct drm_device *dev, void *data,

From 9f4db31ea09e3c1e25b60b1d93e549fd38360197 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Fri, 31 Jul 2020 13:30:10 -0700
Subject: [PATCH 170/474] dt-bindings: clock: Fix YAML schemas for LPASS clocks
 on SC7180

The YAML schemas that landed forgot one clock: "bi_tcxo".  Presumably
the bindings were developed against the v4 version of the driver and
when the ".name" was removed in v5 of the driver things broke.

While touching this, add the needed includes in each example.  I
believe both examples are supposed to be independent of each other.

Let's fix the bindings.

Fixes: 381cc6f97cda ("dt-bindings: clock: Add YAML schemas for LPASS clocks on SC7180")
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20200731133006.1.Iee81b115f5be50d6d69500fe1bda11bba6e16143@changeid
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../bindings/clock/qcom,sc7180-lpasscorecc.yaml    | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/clock/qcom,sc7180-lpasscorecc.yaml b/Documentation/devicetree/bindings/clock/qcom,sc7180-lpasscorecc.yaml
index a838250b33e7..c54172fbf29f 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sc7180-lpasscorecc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sc7180-lpasscorecc.yaml
@@ -25,10 +25,12 @@ properties:
   clocks:
     items:
       - description: gcc_lpass_sway clock from GCC
+      - description: Board XO source
 
   clock-names:
     items:
       - const: iface
+      - const: bi_tcxo
 
   power-domains:
     maxItems: 1
@@ -77,24 +79,28 @@ additionalProperties: false
 
 examples:
   - |
+    #include <dt-bindings/clock/qcom,rpmh.h>
     #include <dt-bindings/clock/qcom,gcc-sc7180.h>
     #include <dt-bindings/clock/qcom,lpasscorecc-sc7180.h>
     clock-controller@63000000 {
       compatible = "qcom,sc7180-lpasshm";
       reg = <0x63000000 0x28>;
-      clocks = <&gcc GCC_LPASS_CFG_NOC_SWAY_CLK>;
-      clock-names = "iface";
+      clocks = <&gcc GCC_LPASS_CFG_NOC_SWAY_CLK>, <&rpmhcc RPMH_CXO_CLK>;
+      clock-names = "iface", "bi_tcxo";
       #clock-cells = <1>;
       #power-domain-cells = <1>;
     };
 
   - |
+    #include <dt-bindings/clock/qcom,rpmh.h>
+    #include <dt-bindings/clock/qcom,gcc-sc7180.h>
+    #include <dt-bindings/clock/qcom,lpasscorecc-sc7180.h>
     clock-controller@62d00000 {
       compatible = "qcom,sc7180-lpasscorecc";
       reg = <0x62d00000 0x50000>, <0x62780000 0x30000>;
       reg-names = "lpass_core_cc", "lpass_audio_cc";
-      clocks = <&gcc GCC_LPASS_CFG_NOC_SWAY_CLK>;
-      clock-names = "iface";
+      clocks = <&gcc GCC_LPASS_CFG_NOC_SWAY_CLK>, <&rpmhcc RPMH_CXO_CLK>;
+      clock-names = "iface", "bi_tcxo";
       power-domains = <&lpass_hm LPASS_CORE_HM_GDSCR>;
       #clock-cells = <1>;
       #power-domain-cells = <1>;

From 70c8b4b8ab3714fb2d075be22aec05ae9c9a6a09 Mon Sep 17 00:00:00 2001
From: Hyun Kwon <hyun.kwon@xilinx.com>
Date: Wed, 29 Jul 2020 16:30:45 -0700
Subject: [PATCH 171/474] drm: xlnx: zynqmp: Use switch - case for link rate
 downshift

Use switch - case to downshift from the current link rate. It's a small
loop now, so fine to be replaced with switch - case. With a loop, it is
confusing and hard to follow as reported below.

The patch d76271d22694: "drm: xlnx: DRM/KMS driver for Xilinx ZynqMP
DisplayPort Subsystem" from Jul 7, 2018, leads to the following
static checker warning:

	drivers/gpu/drm/xlnx/zynqmp_dp.c:594 zynqmp_dp_mode_configure()
	error: iterator underflow 'bws' (-1)-2

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Hyun Kwon <hyun.kwon@xilinx.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1596065445-4630-1-git-send-email-hyun.kwon@xilinx.com
---
 drivers/gpu/drm/xlnx/zynqmp_dp.c | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/xlnx/zynqmp_dp.c b/drivers/gpu/drm/xlnx/zynqmp_dp.c
index b735072a702d..99158ee67d02 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dp.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_dp.c
@@ -567,34 +567,37 @@ static int zynqmp_dp_mode_configure(struct zynqmp_dp *dp, int pclock,
 				    u8 current_bw)
 {
 	int max_rate = dp->link_config.max_rate;
-	u8 bws[3] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7, DP_LINK_BW_5_4 };
+	u8 bw_code;
 	u8 max_lanes = dp->link_config.max_lanes;
 	u8 max_link_rate_code = drm_dp_link_rate_to_bw_code(max_rate);
 	u8 bpp = dp->config.bpp;
 	u8 lane_cnt;
-	s8 i;
 
-	if (current_bw == DP_LINK_BW_1_62) {
+	/* Downshift from current bandwidth */
+	switch (current_bw) {
+	case DP_LINK_BW_5_4:
+		bw_code = DP_LINK_BW_2_7;
+		break;
+	case DP_LINK_BW_2_7:
+		bw_code = DP_LINK_BW_1_62;
+		break;
+	case DP_LINK_BW_1_62:
 		dev_err(dp->dev, "can't downshift. already lowest link rate\n");
 		return -EINVAL;
-	}
-
-	for (i = ARRAY_SIZE(bws) - 1; i >= 0; i--) {
-		if (current_bw && bws[i] >= current_bw)
-			continue;
-
-		if (bws[i] <= max_link_rate_code)
-			break;
+	default:
+		/* If not given, start with max supported */
+		bw_code = max_link_rate_code;
+		break;
 	}
 
 	for (lane_cnt = 1; lane_cnt <= max_lanes; lane_cnt <<= 1) {
 		int bw;
 		u32 rate;
 
-		bw = drm_dp_bw_code_to_link_rate(bws[i]);
+		bw = drm_dp_bw_code_to_link_rate(bw_code);
 		rate = zynqmp_dp_max_rate(bw, lane_cnt, bpp);
 		if (pclock <= rate) {
-			dp->mode.bw_code = bws[i];
+			dp->mode.bw_code = bw_code;
 			dp->mode.lane_cnt = lane_cnt;
 			dp->mode.pclock = pclock;
 			return dp->mode.bw_code;

From f369bc3f9096f5d355e8b80540bc30ac9a602912 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 1 Aug 2020 08:17:13 +0200
Subject: [PATCH 172/474] vgaarb: mark vga_tryget static

This symbols isn't used anywhere outside of vgaarb.c.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20200801061713.307434-1-hch@lst.de
---
 drivers/gpu/vga/vgaarb.c | 3 +--
 include/linux/vgaarb.h   | 6 ------
 2 files changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index f2f3ef8af271..5180c5687ee5 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -529,7 +529,7 @@ EXPORT_SYMBOL(vga_get);
  *
  * 0 on success, negative error code on failure.
  */
-int vga_tryget(struct pci_dev *pdev, unsigned int rsrc)
+static int vga_tryget(struct pci_dev *pdev, unsigned int rsrc)
 {
 	struct vga_device *vgadev;
 	unsigned long flags;
@@ -554,7 +554,6 @@ int vga_tryget(struct pci_dev *pdev, unsigned int rsrc)
 	spin_unlock_irqrestore(&vga_lock, flags);
 	return rc;
 }
-EXPORT_SYMBOL(vga_tryget);
 
 /**
  * vga_put - release lock on legacy VGA resources
diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h
index 553b34c8b5f7..977caf96c8d2 100644
--- a/include/linux/vgaarb.h
+++ b/include/linux/vgaarb.h
@@ -109,12 +109,6 @@ static inline int vga_get_uninterruptible(struct pci_dev *pdev,
        return vga_get(pdev, rsrc, 0);
 }
 
-#if defined(CONFIG_VGA_ARB)
-extern int vga_tryget(struct pci_dev *pdev, unsigned int rsrc);
-#else
-static inline int vga_tryget(struct pci_dev *pdev, unsigned int rsrc) { return 0; }
-#endif
-
 #if defined(CONFIG_VGA_ARB)
 extern void vga_put(struct pci_dev *pdev, unsigned int rsrc);
 #else

From 5133ba8f15911e98567cdb6b767be8080a636b0b Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Wed, 10 Jun 2020 14:41:30 +0200
Subject: [PATCH 173/474] libceph: use target_copy() in send_linger()

Instead of copying just oloc, oid and flags, copy the entire
linger target.  This is more for consistency than anything else,
as send_linger() -> submit_request() -> __submit_request() sends
the request regardless of what calc_target() says (i.e. both on
CALC_TARGET_NO_ACTION and CALC_TARGET_NEED_RESEND).

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 net/ceph/osd_client.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 2db8b44e70c2..db6abb5a5511 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -3076,9 +3076,7 @@ static void send_linger(struct ceph_osd_linger_request *lreq)
 		cancel_linger_request(req);
 
 	request_reinit(req);
-	ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
-	ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
-	req->r_flags = lreq->t.flags;
+	target_copy(&req->r_t, &lreq->t);
 	req->r_mtime = lreq->mtime;
 
 	mutex_lock(&lreq->lock);

From 6e6f0f0116079d6be42080064fe7079283a507ed Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Tue, 16 Jun 2020 09:58:49 +0200
Subject: [PATCH 174/474] libceph: dump class and method names on method calls

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 net/ceph/debugfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 409d505ff320..2110439f8a24 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -223,6 +223,9 @@ static void dump_request(struct seq_file *s, struct ceph_osd_request *req)
 		if (op->op == CEPH_OSD_OP_WATCH)
 			seq_printf(s, "-%s",
 				   ceph_osd_watch_op_name(op->watch.op));
+		else if (op->op == CEPH_OSD_OP_CALL)
+			seq_printf(s, "-%s/%s", op->cls.class_name,
+				   op->cls.method_name);
 	}
 
 	seq_putc(s, '\n');

From 3e699bd865527004773012da38febdf444fd5fa8 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Tue, 30 Jun 2020 03:52:15 -0400
Subject: [PATCH 175/474] ceph: add check_session_state() helper and make it
 global

And remove the unsed mdsc parameter to simplify the code.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 47 +++++++++++++++++++++++++-------------------
 fs/ceph/mds_client.h |  3 +++
 2 files changed, 30 insertions(+), 20 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a50497142e59..58c54d41aa40 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1785,8 +1785,7 @@ static void renewed_caps(struct ceph_mds_client *mdsc,
 /*
  * send a session close request
  */
-static int request_close_session(struct ceph_mds_client *mdsc,
-				 struct ceph_mds_session *session)
+static int request_close_session(struct ceph_mds_session *session)
 {
 	struct ceph_msg *msg;
 
@@ -1809,7 +1808,7 @@ static int __close_session(struct ceph_mds_client *mdsc,
 	if (session->s_state >= CEPH_MDS_SESSION_CLOSING)
 		return 0;
 	session->s_state = CEPH_MDS_SESSION_CLOSING;
-	return request_close_session(mdsc, session);
+	return request_close_session(session);
 }
 
 static bool drop_negative_children(struct dentry *dentry)
@@ -4263,6 +4262,29 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc)
 	ceph_force_reconnect(fsc->sb);
 }
 
+bool check_session_state(struct ceph_mds_session *s)
+{
+	if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
+		dout("resending session close request for mds%d\n",
+				s->s_mds);
+		request_close_session(s);
+		return false;
+	}
+	if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
+		if (s->s_state == CEPH_MDS_SESSION_OPEN) {
+			s->s_state = CEPH_MDS_SESSION_HUNG;
+			pr_info("mds%d hung\n", s->s_mds);
+		}
+	}
+	if (s->s_state == CEPH_MDS_SESSION_NEW ||
+	    s->s_state == CEPH_MDS_SESSION_RESTARTING ||
+	    s->s_state == CEPH_MDS_SESSION_REJECTED)
+		/* this mds is failed or recovering, just wait */
+		return false;
+
+	return true;
+}
+
 /*
  * delayed work -- periodically trim expired leases, renew caps with mds
  */
@@ -4294,23 +4316,8 @@ static void delayed_work(struct work_struct *work)
 		struct ceph_mds_session *s = __ceph_lookup_mds_session(mdsc, i);
 		if (!s)
 			continue;
-		if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
-			dout("resending session close request for mds%d\n",
-			     s->s_mds);
-			request_close_session(mdsc, s);
-			ceph_put_mds_session(s);
-			continue;
-		}
-		if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
-			if (s->s_state == CEPH_MDS_SESSION_OPEN) {
-				s->s_state = CEPH_MDS_SESSION_HUNG;
-				pr_info("mds%d hung\n", s->s_mds);
-			}
-		}
-		if (s->s_state == CEPH_MDS_SESSION_NEW ||
-		    s->s_state == CEPH_MDS_SESSION_RESTARTING ||
-		    s->s_state == CEPH_MDS_SESSION_REJECTED) {
-			/* this mds is failed or recovering, just wait */
+
+		if (!check_session_state(s)) {
 			ceph_put_mds_session(s);
 			continue;
 		}
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 5e0c4073a6be..6147ff0a1cdf 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -18,6 +18,7 @@
 #include <linux/ceph/auth.h>
 
 #include "metric.h"
+#include "super.h"
 
 /* The first 8 bits are reserved for old ceph releases */
 enum ceph_feature_type {
@@ -476,6 +477,8 @@ struct ceph_mds_client {
 
 extern const char *ceph_mds_op_name(int op);
 
+extern bool check_session_state(struct ceph_mds_session *s);
+
 extern struct ceph_mds_session *
 __ceph_lookup_mds_session(struct ceph_mds_client *, int mds);
 

From 4f1d756def68588b88068af1d5a4a3b6dc7e6e2a Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Tue, 30 Jun 2020 03:52:16 -0400
Subject: [PATCH 176/474] ceph: add global total_caps to count the mdsc's total
 caps number

This will help to reduce using the global mdsc->mutex lock in many
places.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/caps.c       |  2 ++
 fs/ceph/debugfs.c    | 14 ++------------
 fs/ceph/mds_client.c |  1 +
 fs/ceph/metric.c     |  1 +
 fs/ceph/metric.h     |  1 +
 5 files changed, 7 insertions(+), 12 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 972c13aa4225..5f4894063a73 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -668,6 +668,7 @@ void ceph_add_cap(struct inode *inode,
 		spin_lock(&session->s_cap_lock);
 		list_add_tail(&cap->session_caps, &session->s_caps);
 		session->s_nr_caps++;
+		atomic64_inc(&mdsc->metric.total_caps);
 		spin_unlock(&session->s_cap_lock);
 	} else {
 		spin_lock(&session->s_cap_lock);
@@ -1161,6 +1162,7 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 	} else {
 		list_del_init(&cap->session_caps);
 		session->s_nr_caps--;
+		atomic64_dec(&mdsc->metric.total_caps);
 		cap->session = NULL;
 		removed = 1;
 	}
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 070ed8481340..3030f5585085 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -145,7 +145,7 @@ static int metric_show(struct seq_file *s, void *p)
 	struct ceph_fs_client *fsc = s->private;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_client_metric *m = &mdsc->metric;
-	int i, nr_caps = 0;
+	int nr_caps = 0;
 	s64 total, sum, avg, min, max, sq;
 
 	seq_printf(s, "item          total       avg_lat(us)     min_lat(us)     max_lat(us)     stdev(us)\n");
@@ -190,17 +190,7 @@ static int metric_show(struct seq_file *s, void *p)
 		   percpu_counter_sum(&m->d_lease_mis),
 		   percpu_counter_sum(&m->d_lease_hit));
 
-	mutex_lock(&mdsc->mutex);
-	for (i = 0; i < mdsc->max_sessions; i++) {
-		struct ceph_mds_session *s;
-
-		s = __ceph_lookup_mds_session(mdsc, i);
-		if (!s)
-			continue;
-		nr_caps += s->s_nr_caps;
-		ceph_put_mds_session(s);
-	}
-	mutex_unlock(&mdsc->mutex);
+	nr_caps = atomic64_read(&m->total_caps);
 	seq_printf(s, "%-14s%-16d%-16lld%lld\n", "caps", nr_caps,
 		   percpu_counter_sum(&m->i_caps_mis),
 		   percpu_counter_sum(&m->i_caps_hit));
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 58c54d41aa40..f3c71230df93 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1485,6 +1485,7 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session,
 			cap->session = NULL;
 			list_del_init(&cap->session_caps);
 			session->s_nr_caps--;
+			atomic64_dec(&session->s_mdsc->metric.total_caps);
 			if (cap->queue_release)
 				__ceph_queue_cap_release(session, cap);
 			else
diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
index 9217f35bc2b9..269eacbd2a15 100644
--- a/fs/ceph/metric.c
+++ b/fs/ceph/metric.c
@@ -22,6 +22,7 @@ int ceph_metric_init(struct ceph_client_metric *m)
 	if (ret)
 		goto err_d_lease_mis;
 
+	atomic64_set(&m->total_caps, 0);
 	ret = percpu_counter_init(&m->i_caps_hit, 0, GFP_KERNEL);
 	if (ret)
 		goto err_i_caps_hit;
diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
index ccd81285a450..23a3373d5a3d 100644
--- a/fs/ceph/metric.h
+++ b/fs/ceph/metric.h
@@ -12,6 +12,7 @@ struct ceph_client_metric {
 	struct percpu_counter d_lease_hit;
 	struct percpu_counter d_lease_mis;
 
+	atomic64_t            total_caps;
 	struct percpu_counter i_caps_hit;
 	struct percpu_counter i_caps_mis;
 

From b682c6d41bc23353b5d80e02ca4961ac67624f4c Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Tue, 30 Jun 2020 03:52:18 -0400
Subject: [PATCH 177/474] ceph: switch to WARN_ON_ONCE in
 encode_supported_features()

...and let the errnos bubble up to the callers.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 46 +++++++++++++++++++++++++++++++++-----------
 1 file changed, 35 insertions(+), 11 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f3c71230df93..d5e523cc40e6 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1168,7 +1168,7 @@ static struct ceph_msg *create_session_msg(u32 op, u64 seq)
 
 static const unsigned char feature_bits[] = CEPHFS_FEATURES_CLIENT_SUPPORTED;
 #define FEATURE_BYTES(c) (DIV_ROUND_UP((size_t)feature_bits[c - 1] + 1, 64) * 8)
-static void encode_supported_features(void **p, void *end)
+static int encode_supported_features(void **p, void *end)
 {
 	static const size_t count = ARRAY_SIZE(feature_bits);
 
@@ -1176,16 +1176,22 @@ static void encode_supported_features(void **p, void *end)
 		size_t i;
 		size_t size = FEATURE_BYTES(count);
 
-		BUG_ON(*p + 4 + size > end);
+		if (WARN_ON_ONCE(*p + 4 + size > end))
+			return -ERANGE;
+
 		ceph_encode_32(p, size);
 		memset(*p, 0, size);
 		for (i = 0; i < count; i++)
 			((unsigned char*)(*p))[i / 8] |= BIT(feature_bits[i] % 8);
 		*p += size;
 	} else {
-		BUG_ON(*p + 4 > end);
+		if (WARN_ON_ONCE(*p + 4 > end))
+			return -ERANGE;
+
 		ceph_encode_32(p, 0);
 	}
+
+	return 0;
 }
 
 /*
@@ -1203,6 +1209,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 	struct ceph_mount_options *fsopt = mdsc->fsc->mount_options;
 	size_t size, count;
 	void *p, *end;
+	int ret;
 
 	const char* metadata[][2] = {
 		{"hostname", mdsc->nodename},
@@ -1232,7 +1239,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 			   GFP_NOFS, false);
 	if (!msg) {
 		pr_err("create_session_msg ENOMEM creating msg\n");
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	p = msg->front.iov_base;
 	end = p + msg->front.iov_len;
@@ -1269,7 +1276,13 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 		p += val_len;
 	}
 
-	encode_supported_features(&p, end);
+	ret = encode_supported_features(&p, end);
+	if (ret) {
+		pr_err("encode_supported_features failed!\n");
+		ceph_msg_put(msg);
+		return ERR_PTR(ret);
+	}
+
 	msg->front.iov_len = p - msg->front.iov_base;
 	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 
@@ -1297,8 +1310,8 @@ static int __open_session(struct ceph_mds_client *mdsc,
 
 	/* send connect message */
 	msg = create_session_open_msg(mdsc, session->s_seq);
-	if (!msg)
-		return -ENOMEM;
+	if (IS_ERR(msg))
+		return PTR_ERR(msg);
 	ceph_con_send(&session->s_con, msg);
 	return 0;
 }
@@ -1312,6 +1325,7 @@ static struct ceph_mds_session *
 __open_export_target_session(struct ceph_mds_client *mdsc, int target)
 {
 	struct ceph_mds_session *session;
+	int ret;
 
 	session = __ceph_lookup_mds_session(mdsc, target);
 	if (!session) {
@@ -1320,8 +1334,11 @@ __open_export_target_session(struct ceph_mds_client *mdsc, int target)
 			return session;
 	}
 	if (session->s_state == CEPH_MDS_SESSION_NEW ||
-	    session->s_state == CEPH_MDS_SESSION_CLOSING)
-		__open_session(mdsc, session);
+	    session->s_state == CEPH_MDS_SESSION_CLOSING) {
+		ret = __open_session(mdsc, session);
+		if (ret)
+			return ERR_PTR(ret);
+	}
 
 	return session;
 }
@@ -2520,7 +2537,12 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 		ceph_encode_copy(&p, &ts, sizeof(ts));
 	}
 
-	BUG_ON(p > end);
+	if (WARN_ON_ONCE(p > end)) {
+		ceph_msg_put(msg);
+		msg = ERR_PTR(-ERANGE);
+		goto out_free2;
+	}
+
 	msg->front.iov_len = p - msg->front.iov_base;
 	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 
@@ -2756,7 +2778,9 @@ static void __do_request(struct ceph_mds_client *mdsc,
 		}
 		if (session->s_state == CEPH_MDS_SESSION_NEW ||
 		    session->s_state == CEPH_MDS_SESSION_CLOSING) {
-			__open_session(mdsc, session);
+			err = __open_session(mdsc, session);
+			if (err)
+				goto out_session;
 			/* retry the same mds later */
 			if (random)
 				req->r_resend_mds = mds;

From fa9967734227b44acb1b6918033f9122dc7825b9 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Wed, 1 Jul 2020 01:52:48 -0400
Subject: [PATCH 178/474] ceph: fix potential mdsc use-after-free crash

Make sure the delayed work stopped before releasing the resources.

cancel_delayed_work_sync() will only guarantee that the work finishes
executing if the work is already in the ->worklist.  That means after
the cancel_delayed_work_sync() returns, it will leave the work requeued
if it was rearmed at the end. That can lead to a use after free once the
work struct is freed.

Fix it by flushing the delayed work instead of trying to cancel it, and
ensure that the work doesn't rearm if the mdsc is stopping.

URL: https://tracker.ceph.com/issues/46293
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d5e523cc40e6..9a09d12569bd 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4330,6 +4330,9 @@ static void delayed_work(struct work_struct *work)
 
 	dout("mdsc delayed_work\n");
 
+	if (mdsc->stopping)
+		return;
+
 	mutex_lock(&mdsc->mutex);
 	renew_interval = mdsc->mdsmap->m_session_timeout >> 2;
 	renew_caps = time_after_eq(jiffies, HZ*renew_interval +
@@ -4689,7 +4692,16 @@ void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc)
 static void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
 {
 	dout("stop\n");
-	cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */
+	/*
+	 * Make sure the delayed work stopped before releasing
+	 * the resources.
+	 *
+	 * Because the cancel_delayed_work_sync() will only
+	 * guarantee that the work finishes executing. But the
+	 * delayed work will re-arm itself again after that.
+	 */
+	flush_delayed_work(&mdsc->delayed_work);
+
 	if (mdsc->mdsmap)
 		ceph_mdsmap_destroy(mdsc->mdsmap);
 	kfree(mdsc->sessions);

From 585d72f33e7083972030fac7792ea3050a4a8dff Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Tue, 30 Jun 2020 15:36:21 -0400
Subject: [PATCH 179/474] ceph: clean up and optimize ceph_check_delayed_caps()

Make this loop look a bit more sane. Also optimize away the spinlock
release/reacquire if we can't get an inode reference.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/caps.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 5f4894063a73..55ccccf77cea 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -4189,10 +4189,8 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
 	struct ceph_inode_info *ci;
 
 	dout("check_delayed_caps\n");
-	while (1) {
-		spin_lock(&mdsc->cap_delay_lock);
-		if (list_empty(&mdsc->cap_delay_list))
-			break;
+	spin_lock(&mdsc->cap_delay_lock);
+	while (!list_empty(&mdsc->cap_delay_list)) {
 		ci = list_first_entry(&mdsc->cap_delay_list,
 				      struct ceph_inode_info,
 				      i_cap_delay_list);
@@ -4202,13 +4200,13 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
 		list_del_init(&ci->i_cap_delay_list);
 
 		inode = igrab(&ci->vfs_inode);
-		spin_unlock(&mdsc->cap_delay_lock);
-
 		if (inode) {
+			spin_unlock(&mdsc->cap_delay_lock);
 			dout("check_delayed_caps on %p\n", inode);
 			ceph_check_caps(ci, 0, NULL);
 			/* avoid calling iput_final() in tick thread */
 			ceph_async_iput(inode);
+			spin_lock(&mdsc->cap_delay_lock);
 		}
 	}
 	spin_unlock(&mdsc->cap_delay_lock);

From d1d9655052606fd9078e896668ec90191372d513 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Mon, 6 Jul 2020 08:51:35 -0400
Subject: [PATCH 180/474] ceph: do not access the kiocb after aio requests

In aio case, if the completion comes very fast just before the
ceph_read_iter() returns to fs/aio.c, the kiocb will be freed in
the completion callback, then if ceph_read_iter() access again
we will potentially hit the use-after-free bug.

[ jlayton: initialize direct_lock early, and use it everywhere ]

URL: https://tracker.ceph.com/issues/45649
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/file.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 160644ddaeed..d51c3f2fdca0 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1538,6 +1538,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *inode = file_inode(filp);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct page *pinned_page = NULL;
+	bool direct_lock = iocb->ki_flags & IOCB_DIRECT;
 	ssize_t ret;
 	int want, got = 0;
 	int retry_op = 0, read = 0;
@@ -1546,7 +1547,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n",
 	     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode);
 
-	if (iocb->ki_flags & IOCB_DIRECT)
+	if (direct_lock)
 		ceph_start_io_direct(inode);
 	else
 		ceph_start_io_read(inode);
@@ -1603,7 +1604,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	}
 	ceph_put_cap_refs(ci, got);
 
-	if (iocb->ki_flags & IOCB_DIRECT)
+	if (direct_lock)
 		ceph_end_io_direct(inode);
 	else
 		ceph_end_io_read(inode);

From 042f649810f61c4a834f3d6d866c567f7f6b3f8c Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 1 Jul 2020 11:54:43 -0400
Subject: [PATCH 181/474] libceph: just have osd_req_op_init() return a pointer

The caller can just ignore the return. No need for this wrapper that
just casts the other function to void.

[ idryomov: argument alignment ]

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osd_client.h |  2 +-
 net/ceph/osd_client.c           | 39 ++++++++++++++-------------------
 2 files changed, 17 insertions(+), 24 deletions(-)

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index c60b59e9291b..83fa08a06507 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -404,7 +404,7 @@ void ceph_osdc_clear_abort_err(struct ceph_osd_client *osdc);
 	&__oreq->r_ops[__whch].typ.fld;					\
 })
 
-extern void osd_req_op_init(struct ceph_osd_request *osd_req,
+struct ceph_osd_req_op *osd_req_op_init(struct ceph_osd_request *osd_req,
 			    unsigned int which, u16 opcode, u32 flags);
 
 extern void osd_req_op_raw_data_in_pages(struct ceph_osd_request *,
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index db6abb5a5511..e4fbcad6e7d8 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -525,7 +525,7 @@ EXPORT_SYMBOL(ceph_osdc_put_request);
 
 static void request_init(struct ceph_osd_request *req)
 {
-	/* req only, each op is zeroed in _osd_req_op_init() */
+	/* req only, each op is zeroed in osd_req_op_init() */
 	memset(req, 0, sizeof(*req));
 
 	kref_init(&req->r_kref);
@@ -746,8 +746,8 @@ EXPORT_SYMBOL(ceph_osdc_alloc_messages);
  * other information associated with them.  It also serves as a
  * common init routine for all the other init functions, below.
  */
-static struct ceph_osd_req_op *
-_osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
+struct ceph_osd_req_op *
+osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
 		 u16 opcode, u32 flags)
 {
 	struct ceph_osd_req_op *op;
@@ -762,12 +762,6 @@ _osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
 
 	return op;
 }
-
-void osd_req_op_init(struct ceph_osd_request *osd_req,
-		     unsigned int which, u16 opcode, u32 flags)
-{
-	(void)_osd_req_op_init(osd_req, which, opcode, flags);
-}
 EXPORT_SYMBOL(osd_req_op_init);
 
 void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
@@ -775,8 +769,8 @@ void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
 				u64 offset, u64 length,
 				u64 truncate_size, u32 truncate_seq)
 {
-	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
-						      opcode, 0);
+	struct ceph_osd_req_op *op = osd_req_op_init(osd_req, which,
+						     opcode, 0);
 	size_t payload_len = 0;
 
 	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
@@ -822,7 +816,7 @@ void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req,
 	BUG_ON(which + 1 >= osd_req->r_num_ops);
 
 	prev_op = &osd_req->r_ops[which];
-	op = _osd_req_op_init(osd_req, which + 1, prev_op->op, prev_op->flags);
+	op = osd_req_op_init(osd_req, which + 1, prev_op->op, prev_op->flags);
 	/* dup previous one */
 	op->indata_len = prev_op->indata_len;
 	op->outdata_len = prev_op->outdata_len;
@@ -845,7 +839,7 @@ int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
 	size_t size;
 	int ret;
 
-	op = _osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0);
+	op = osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0);
 
 	pagelist = ceph_pagelist_alloc(GFP_NOFS);
 	if (!pagelist)
@@ -883,8 +877,8 @@ int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
 			  u16 opcode, const char *name, const void *value,
 			  size_t size, u8 cmp_op, u8 cmp_mode)
 {
-	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
-						      opcode, 0);
+	struct ceph_osd_req_op *op = osd_req_op_init(osd_req, which,
+						     opcode, 0);
 	struct ceph_pagelist *pagelist;
 	size_t payload_len;
 	int ret;
@@ -928,7 +922,7 @@ static void osd_req_op_watch_init(struct ceph_osd_request *req, int which,
 {
 	struct ceph_osd_req_op *op;
 
-	op = _osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0);
+	op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0);
 	op->watch.cookie = cookie;
 	op->watch.op = watch_opcode;
 	op->watch.gen = 0;
@@ -943,10 +937,9 @@ void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
 				u64 expected_write_size,
 				u32 flags)
 {
-	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
-						      CEPH_OSD_OP_SETALLOCHINT,
-						      0);
+	struct ceph_osd_req_op *op;
 
+	op = osd_req_op_init(osd_req, which, CEPH_OSD_OP_SETALLOCHINT, 0);
 	op->alloc_hint.expected_object_size = expected_object_size;
 	op->alloc_hint.expected_write_size = expected_write_size;
 	op->alloc_hint.flags = flags;
@@ -4799,7 +4792,7 @@ static int osd_req_op_notify_ack_init(struct ceph_osd_request *req, int which,
 	struct ceph_pagelist *pl;
 	int ret;
 
-	op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0);
+	op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0);
 
 	pl = ceph_pagelist_alloc(GFP_NOIO);
 	if (!pl)
@@ -4868,7 +4861,7 @@ static int osd_req_op_notify_init(struct ceph_osd_request *req, int which,
 	struct ceph_pagelist *pl;
 	int ret;
 
-	op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
+	op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
 	op->notify.cookie = cookie;
 
 	pl = ceph_pagelist_alloc(GFP_NOIO);
@@ -5332,8 +5325,8 @@ static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
 	if (IS_ERR(pages))
 		return PTR_ERR(pages);
 
-	op = _osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM2,
-			      dst_fadvise_flags);
+	op = osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM2,
+			     dst_fadvise_flags);
 	op->copy_from.snapid = src_snapid;
 	op->copy_from.src_version = src_version;
 	op->copy_from.flags = copy_from_flags;

From c00e4522adff010141ce86839bb4fe494c853077 Mon Sep 17 00:00:00 2001
From: Xu Wang <vulab@iscas.ac.cn>
Date: Wed, 8 Jul 2020 07:03:22 +0000
Subject: [PATCH 182/474] ceph: remove unnecessary cast in kfree()

Remove unnecassary casts in the argument to kfree.

Signed-off-by: Xu Wang <vulab@iscas.ac.cn>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/xattr.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 71ee34d160c3..3a733ac33d9b 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -497,10 +497,10 @@ static int __set_xattr(struct ceph_inode_info *ci,
 		kfree(*newxattr);
 		*newxattr = NULL;
 		if (xattr->should_free_val)
-			kfree((void *)xattr->val);
+			kfree(xattr->val);
 
 		if (update_xattr) {
-			kfree((void *)name);
+			kfree(name);
 			name = xattr->name;
 		}
 		ci->i_xattrs.names_size -= xattr->name_len;
@@ -566,9 +566,9 @@ static void __free_xattr(struct ceph_inode_xattr *xattr)
 	BUG_ON(!xattr);
 
 	if (xattr->should_free_name)
-		kfree((void *)xattr->name);
+		kfree(xattr->name);
 	if (xattr->should_free_val)
-		kfree((void *)xattr->val);
+		kfree(xattr->val);
 
 	kfree(xattr);
 }
@@ -582,9 +582,9 @@ static int __remove_xattr(struct ceph_inode_info *ci,
 	rb_erase(&xattr->node, &ci->i_xattrs.index);
 
 	if (xattr->should_free_name)
-		kfree((void *)xattr->name);
+		kfree(xattr->name);
 	if (xattr->should_free_val)
-		kfree((void *)xattr->val);
+		kfree(xattr->val);
 
 	ci->i_xattrs.names_size -= xattr->name_len;
 	ci->i_xattrs.vals_size -= xattr->val_len;

From 94f17c00d6687993101372f996cf6690ec9adf83 Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Wed, 8 Jul 2020 08:53:28 +0200
Subject: [PATCH 183/474] libceph: replace HTTP links with HTTPS ones

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `\bxmlns\b`:
        For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
	  If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`:
            If both the HTTP and HTTPS versions
            return 200 OK and serve the same content:
              Replace HTTP with HTTPS.

[ idryomov: Do the same for the CRUSH paper and replace
  ceph.newdream.net with ceph.io. ]

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/Kconfig             | 2 +-
 include/linux/crush/crush.h | 2 +-
 net/ceph/Kconfig            | 2 +-
 net/ceph/ceph_hash.c        | 2 +-
 net/ceph/crush/hash.c       | 2 +-
 net/ceph/crush/mapper.c     | 2 +-
 6 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index cf235f6eacf9..471e40156065 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -13,7 +13,7 @@ config CEPH_FS
 	  scalable file system designed to provide high performance,
 	  reliable access to petabytes of storage.
 
-	  More information at http://ceph.newdream.net/.
+	  More information at https://ceph.io/.
 
 	  If unsure, say N.
 
diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 33c16f2de7f6..2f811baf78d2 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -17,7 +17,7 @@
  * The algorithm was originally described in detail in this paper
  * (although the algorithm has evolved somewhat since then):
  *
- *     http://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf
+ *     https://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf
  *
  * LGPL2
  */
diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig
index d7bec7adc267..f36f9a3a4e20 100644
--- a/net/ceph/Kconfig
+++ b/net/ceph/Kconfig
@@ -13,7 +13,7 @@ config CEPH_LIB
 	  common functionality to both the Ceph filesystem and
 	  to the rados block device (rbd).
 
-	  More information at http://ceph.newdream.net/.
+	  More information at https://ceph.io/.
 
 	  If unsure, say N.
 
diff --git a/net/ceph/ceph_hash.c b/net/ceph/ceph_hash.c
index 9a5850f264ed..81e1e006c540 100644
--- a/net/ceph/ceph_hash.c
+++ b/net/ceph/ceph_hash.c
@@ -4,7 +4,7 @@
 
 /*
  * Robert Jenkin's hash function.
- * http://burtleburtle.net/bob/hash/evahash.html
+ * https://burtleburtle.net/bob/hash/evahash.html
  * This is in the public domain.
  */
 #define mix(a, b, c)						\
diff --git a/net/ceph/crush/hash.c b/net/ceph/crush/hash.c
index e5cc603cdb17..fe79f6d2d0db 100644
--- a/net/ceph/crush/hash.c
+++ b/net/ceph/crush/hash.c
@@ -7,7 +7,7 @@
 
 /*
  * Robert Jenkins' function for mixing 32-bit values
- * http://burtleburtle.net/bob/hash/evahash.html
+ * https://burtleburtle.net/bob/hash/evahash.html
  * a, b = random bits, c = input and output
  */
 #define crush_hashmix(a, b, c) do {			\
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 3f323ed9df52..07e5614eb3f1 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -298,7 +298,7 @@ static __u64 crush_ln(unsigned int xin)
  *
  * for reference, see:
  *
- * http://en.wikipedia.org/wiki/Exponential_distribution#Distribution_of_the_minimum_of_exponential_random_variables
+ * https://en.wikipedia.org/wiki/Exponential_distribution#Distribution_of_the_minimum_of_exponential_random_variables
  *
  */
 

From aaf5a476201bf93bdab75d6922340516ee63f7e2 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Fri, 17 Jul 2020 09:25:13 -0400
Subject: [PATCH 184/474] ceph: check the sesion state and return false in case
 it is closed

If the session is already in closed state, we should skip it.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 9a09d12569bd..ef8a1179171b 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4303,6 +4303,7 @@ bool check_session_state(struct ceph_mds_session *s)
 	}
 	if (s->s_state == CEPH_MDS_SESSION_NEW ||
 	    s->s_state == CEPH_MDS_SESSION_RESTARTING ||
+	    s->s_state == CEPH_MDS_SESSION_CLOSED ||
 	    s->s_state == CEPH_MDS_SESSION_REJECTED)
 		/* this mds is failed or recovering, just wait */
 		return false;

From 18f473b384a64cef69f166a3e2b73d3d2eca82c6 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 16 Jul 2020 10:05:57 -0400
Subject: [PATCH 185/474] ceph: periodically send perf metrics to MDSes

This will send the caps/read/write/metadata metrics to any available MDS
once per second, which will be the same as the userland client.  It will
skip the MDS sessions which don't support the metric collection, as the
MDSs will close socket connections when they get an unknown type
message.

We can disable the metric sending via the disable_send_metrics module
parameter.

[ jlayton: fix up endianness bug in ceph_mdsc_send_metrics() ]

URL: https://tracker.ceph.com/issues/43215
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c         |   3 +
 fs/ceph/mds_client.h         |   4 +-
 fs/ceph/metric.c             | 148 +++++++++++++++++++++++++++++++++++
 fs/ceph/metric.h             |  77 ++++++++++++++++++
 fs/ceph/super.c              |  42 ++++++++++
 fs/ceph/super.h              |   2 +
 include/linux/ceph/ceph_fs.h |   1 +
 7 files changed, 276 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index ef8a1179171b..d6cd2e4f0bc8 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3334,6 +3334,8 @@ static void handle_session(struct ceph_mds_session *session,
 		session->s_state = CEPH_MDS_SESSION_OPEN;
 		session->s_features = features;
 		renewed_caps(mdsc, session, 0);
+		if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features))
+			metric_schedule_delayed(&mdsc->metric);
 		wake = 1;
 		if (mdsc->stopping)
 			__close_session(mdsc, session);
@@ -4725,6 +4727,7 @@ void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
 
 	ceph_metric_destroy(&mdsc->metric);
 
+	flush_delayed_work(&mdsc->metric.delayed_work);
 	fsc->mdsc = NULL;
 	kfree(mdsc);
 	dout("mdsc_destroy %p done\n", mdsc);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 6147ff0a1cdf..bc9e95937d7c 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -28,8 +28,9 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_LAZY_CAP_WANTED,
 	CEPHFS_FEATURE_MULTI_RECONNECT,
 	CEPHFS_FEATURE_DELEG_INO,
+	CEPHFS_FEATURE_METRIC_COLLECT,
 
-	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_DELEG_INO,
+	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_METRIC_COLLECT,
 };
 
 /*
@@ -43,6 +44,7 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_LAZY_CAP_WANTED,		\
 	CEPHFS_FEATURE_MULTI_RECONNECT,		\
 	CEPHFS_FEATURE_DELEG_INO,		\
+	CEPHFS_FEATURE_METRIC_COLLECT,		\
 						\
 	CEPHFS_FEATURE_MAX,			\
 }
diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
index 269eacbd2a15..2466b261fba2 100644
--- a/fs/ceph/metric.c
+++ b/fs/ceph/metric.c
@@ -1,10 +1,150 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/types.h>
 #include <linux/percpu_counter.h>
 #include <linux/math64.h>
 
 #include "metric.h"
+#include "mds_client.h"
+
+static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
+				   struct ceph_mds_session *s)
+{
+	struct ceph_metric_head *head;
+	struct ceph_metric_cap *cap;
+	struct ceph_metric_read_latency *read;
+	struct ceph_metric_write_latency *write;
+	struct ceph_metric_metadata_latency *meta;
+	struct ceph_client_metric *m = &mdsc->metric;
+	u64 nr_caps = atomic64_read(&m->total_caps);
+	struct ceph_msg *msg;
+	struct timespec64 ts;
+	s64 sum;
+	s32 items = 0;
+	s32 len;
+
+	len = sizeof(*head) + sizeof(*cap) + sizeof(*read) + sizeof(*write)
+	      + sizeof(*meta);
+
+	msg = ceph_msg_new(CEPH_MSG_CLIENT_METRICS, len, GFP_NOFS, true);
+	if (!msg) {
+		pr_err("send metrics to mds%d, failed to allocate message\n",
+		       s->s_mds);
+		return false;
+	}
+
+	head = msg->front.iov_base;
+
+	/* encode the cap metric */
+	cap = (struct ceph_metric_cap *)(head + 1);
+	cap->type = cpu_to_le32(CLIENT_METRIC_TYPE_CAP_INFO);
+	cap->ver = 1;
+	cap->compat = 1;
+	cap->data_len = cpu_to_le32(sizeof(*cap) - 10);
+	cap->hit = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_hit));
+	cap->mis = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_mis));
+	cap->total = cpu_to_le64(nr_caps);
+	items++;
+
+	/* encode the read latency metric */
+	read = (struct ceph_metric_read_latency *)(cap + 1);
+	read->type = cpu_to_le32(CLIENT_METRIC_TYPE_READ_LATENCY);
+	read->ver = 1;
+	read->compat = 1;
+	read->data_len = cpu_to_le32(sizeof(*read) - 10);
+	sum = m->read_latency_sum;
+	jiffies_to_timespec64(sum, &ts);
+	read->sec = cpu_to_le32(ts.tv_sec);
+	read->nsec = cpu_to_le32(ts.tv_nsec);
+	items++;
+
+	/* encode the write latency metric */
+	write = (struct ceph_metric_write_latency *)(read + 1);
+	write->type = cpu_to_le32(CLIENT_METRIC_TYPE_WRITE_LATENCY);
+	write->ver = 1;
+	write->compat = 1;
+	write->data_len = cpu_to_le32(sizeof(*write) - 10);
+	sum = m->write_latency_sum;
+	jiffies_to_timespec64(sum, &ts);
+	write->sec = cpu_to_le32(ts.tv_sec);
+	write->nsec = cpu_to_le32(ts.tv_nsec);
+	items++;
+
+	/* encode the metadata latency metric */
+	meta = (struct ceph_metric_metadata_latency *)(write + 1);
+	meta->type = cpu_to_le32(CLIENT_METRIC_TYPE_METADATA_LATENCY);
+	meta->ver = 1;
+	meta->compat = 1;
+	meta->data_len = cpu_to_le32(sizeof(*meta) - 10);
+	sum = m->metadata_latency_sum;
+	jiffies_to_timespec64(sum, &ts);
+	meta->sec = cpu_to_le32(ts.tv_sec);
+	meta->nsec = cpu_to_le32(ts.tv_nsec);
+	items++;
+
+	put_unaligned_le32(items, &head->num);
+	msg->front.iov_len = len;
+	msg->hdr.version = cpu_to_le16(1);
+	msg->hdr.compat_version = cpu_to_le16(1);
+	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
+	dout("client%llu send metrics to mds%d\n",
+	     ceph_client_gid(mdsc->fsc->client), s->s_mds);
+	ceph_con_send(&s->s_con, msg);
+
+	return true;
+}
+
+
+static void metric_get_session(struct ceph_mds_client *mdsc)
+{
+	struct ceph_mds_session *s;
+	int i;
+
+	mutex_lock(&mdsc->mutex);
+	for (i = 0; i < mdsc->max_sessions; i++) {
+		s = __ceph_lookup_mds_session(mdsc, i);
+		if (!s)
+			continue;
+
+		/*
+		 * Skip it if MDS doesn't support the metric collection,
+		 * or the MDS will close the session's socket connection
+		 * directly when it get this message.
+		 */
+		if (check_session_state(s) &&
+		    test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features)) {
+			mdsc->metric.session = s;
+			break;
+		}
+
+		ceph_put_mds_session(s);
+	}
+	mutex_unlock(&mdsc->mutex);
+}
+
+static void metric_delayed_work(struct work_struct *work)
+{
+	struct ceph_client_metric *m =
+		container_of(work, struct ceph_client_metric, delayed_work.work);
+	struct ceph_mds_client *mdsc =
+		container_of(m, struct ceph_mds_client, metric);
+
+	if (mdsc->stopping)
+		return;
+
+	if (!m->session || !check_session_state(m->session)) {
+		if (m->session) {
+			ceph_put_mds_session(m->session);
+			m->session = NULL;
+		}
+		metric_get_session(mdsc);
+	}
+	if (m->session) {
+		ceph_mdsc_send_metrics(mdsc, m->session);
+		metric_schedule_delayed(m);
+	}
+}
 
 int ceph_metric_init(struct ceph_client_metric *m)
 {
@@ -52,6 +192,9 @@ int ceph_metric_init(struct ceph_client_metric *m)
 	m->total_metadatas = 0;
 	m->metadata_latency_sum = 0;
 
+	m->session = NULL;
+	INIT_DELAYED_WORK(&m->delayed_work, metric_delayed_work);
+
 	return 0;
 
 err_i_caps_mis:
@@ -73,6 +216,11 @@ void ceph_metric_destroy(struct ceph_client_metric *m)
 	percpu_counter_destroy(&m->i_caps_hit);
 	percpu_counter_destroy(&m->d_lease_mis);
 	percpu_counter_destroy(&m->d_lease_hit);
+
+	cancel_delayed_work_sync(&m->delayed_work);
+
+	if (m->session)
+		ceph_put_mds_session(m->session);
 }
 
 static inline void __update_latency(ktime_t *totalp, ktime_t *lsump,
diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
index 23a3373d5a3d..fe5d07d2e63a 100644
--- a/fs/ceph/metric.h
+++ b/fs/ceph/metric.h
@@ -6,6 +6,71 @@
 #include <linux/percpu_counter.h>
 #include <linux/ktime.h>
 
+extern bool disable_send_metrics;
+
+enum ceph_metric_type {
+	CLIENT_METRIC_TYPE_CAP_INFO,
+	CLIENT_METRIC_TYPE_READ_LATENCY,
+	CLIENT_METRIC_TYPE_WRITE_LATENCY,
+	CLIENT_METRIC_TYPE_METADATA_LATENCY,
+	CLIENT_METRIC_TYPE_DENTRY_LEASE,
+
+	CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_DENTRY_LEASE,
+};
+
+/* metric caps header */
+struct ceph_metric_cap {
+	__le32 type;     /* ceph metric type */
+
+	__u8  ver;
+	__u8  compat;
+
+	__le32 data_len; /* length of sizeof(hit + mis + total) */
+	__le64 hit;
+	__le64 mis;
+	__le64 total;
+} __packed;
+
+/* metric read latency header */
+struct ceph_metric_read_latency {
+	__le32 type;     /* ceph metric type */
+
+	__u8  ver;
+	__u8  compat;
+
+	__le32 data_len; /* length of sizeof(sec + nsec) */
+	__le32 sec;
+	__le32 nsec;
+} __packed;
+
+/* metric write latency header */
+struct ceph_metric_write_latency {
+	__le32 type;     /* ceph metric type */
+
+	__u8  ver;
+	__u8  compat;
+
+	__le32 data_len; /* length of sizeof(sec + nsec) */
+	__le32 sec;
+	__le32 nsec;
+} __packed;
+
+/* metric metadata latency header */
+struct ceph_metric_metadata_latency {
+	__le32 type;     /* ceph metric type */
+
+	__u8  ver;
+	__u8  compat;
+
+	__le32 data_len; /* length of sizeof(sec + nsec) */
+	__le32 sec;
+	__le32 nsec;
+} __packed;
+
+struct ceph_metric_head {
+	__le32 num;	/* the number of metrics that will be sent */
+} __packed;
+
 /* This is the global metrics */
 struct ceph_client_metric {
 	atomic64_t            total_dentries;
@@ -36,8 +101,20 @@ struct ceph_client_metric {
 	ktime_t metadata_latency_sq_sum;
 	ktime_t metadata_latency_min;
 	ktime_t metadata_latency_max;
+
+	struct ceph_mds_session *session;
+	struct delayed_work delayed_work;  /* delayed work */
 };
 
+static inline void metric_schedule_delayed(struct ceph_client_metric *m)
+{
+	if (disable_send_metrics)
+		return;
+
+	/* per second */
+	schedule_delayed_work(&m->delayed_work, round_jiffies_relative(HZ));
+}
+
 extern int ceph_metric_init(struct ceph_client_metric *m);
 extern void ceph_metric_destroy(struct ceph_client_metric *m);
 
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index c9784eb1159a..933f5df5da7d 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -27,6 +27,9 @@
 #include <linux/ceph/auth.h>
 #include <linux/ceph/debugfs.h>
 
+static DEFINE_SPINLOCK(ceph_fsc_lock);
+static LIST_HEAD(ceph_fsc_list);
+
 /*
  * Ceph superblock operations
  *
@@ -691,6 +694,10 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	if (!fsc->wb_pagevec_pool)
 		goto fail_cap_wq;
 
+	spin_lock(&ceph_fsc_lock);
+	list_add_tail(&fsc->metric_wakeup, &ceph_fsc_list);
+	spin_unlock(&ceph_fsc_lock);
+
 	return fsc;
 
 fail_cap_wq:
@@ -717,6 +724,10 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
 {
 	dout("destroy_fs_client %p\n", fsc);
 
+	spin_lock(&ceph_fsc_lock);
+	list_del(&fsc->metric_wakeup);
+	spin_unlock(&ceph_fsc_lock);
+
 	ceph_mdsc_destroy(fsc);
 	destroy_workqueue(fsc->inode_wq);
 	destroy_workqueue(fsc->cap_wq);
@@ -1282,6 +1293,37 @@ static void __exit exit_ceph(void)
 	destroy_caches();
 }
 
+static int param_set_metrics(const char *val, const struct kernel_param *kp)
+{
+	struct ceph_fs_client *fsc;
+	int ret;
+
+	ret = param_set_bool(val, kp);
+	if (ret) {
+		pr_err("Failed to parse sending metrics switch value '%s'\n",
+		       val);
+		return ret;
+	} else if (!disable_send_metrics) {
+		// wake up all the mds clients
+		spin_lock(&ceph_fsc_lock);
+		list_for_each_entry(fsc, &ceph_fsc_list, metric_wakeup) {
+			metric_schedule_delayed(&fsc->mdsc->metric);
+		}
+		spin_unlock(&ceph_fsc_lock);
+	}
+
+	return 0;
+}
+
+static const struct kernel_param_ops param_ops_metrics = {
+	.set = param_set_metrics,
+	.get = param_get_bool,
+};
+
+bool disable_send_metrics = false;
+module_param_cb(disable_send_metrics, &param_ops_metrics, &disable_send_metrics, 0644);
+MODULE_PARM_DESC(disable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)");
+
 module_init(init_ceph);
 module_exit(exit_ceph);
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 5a6cdd39bc10..2dcb6a90c636 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -101,6 +101,8 @@ struct ceph_mount_options {
 struct ceph_fs_client {
 	struct super_block *sb;
 
+	struct list_head metric_wakeup;
+
 	struct ceph_mount_options *mount_options;
 	struct ceph_client *client;
 
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index ebf5ba62b772..455e9b9e2adf 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -130,6 +130,7 @@ struct ceph_dir_layout {
 #define CEPH_MSG_CLIENT_REQUEST         24
 #define CEPH_MSG_CLIENT_REQUEST_FORWARD 25
 #define CEPH_MSG_CLIENT_REPLY           26
+#define CEPH_MSG_CLIENT_METRICS         29
 #define CEPH_MSG_CLIENT_CAPS            0x310
 #define CEPH_MSG_CLIENT_LEASE           0x311
 #define CEPH_MSG_CLIENT_SNAP            0x312

From 3b4168dd8b1d3e0bb129cf41e6bb50e217fe7781 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 16 Jul 2020 10:05:58 -0400
Subject: [PATCH 186/474] ceph: send client provided metric flags in client
 metadata

Send metric flags to the MDS, indicating what metrics the client
supports. Currently that consists of cap statistics, and read, write and
metadata latencies.

URL: https://tracker.ceph.com/issues/43435
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 60 ++++++++++++++++++++++++++++++++++++++++++--
 fs/ceph/metric.h     | 13 ++++++++++
 2 files changed, 71 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d6cd2e4f0bc8..af7221d1c610 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1194,6 +1194,48 @@ static int encode_supported_features(void **p, void *end)
 	return 0;
 }
 
+static const unsigned char metric_bits[] = CEPHFS_METRIC_SPEC_CLIENT_SUPPORTED;
+#define METRIC_BYTES(cnt) (DIV_ROUND_UP((size_t)metric_bits[cnt - 1] + 1, 64) * 8)
+static int encode_metric_spec(void **p, void *end)
+{
+	static const size_t count = ARRAY_SIZE(metric_bits);
+
+	/* header */
+	if (WARN_ON_ONCE(*p + 2 > end))
+		return -ERANGE;
+
+	ceph_encode_8(p, 1); /* version */
+	ceph_encode_8(p, 1); /* compat */
+
+	if (count > 0) {
+		size_t i;
+		size_t size = METRIC_BYTES(count);
+
+		if (WARN_ON_ONCE(*p + 4 + 4 + size > end))
+			return -ERANGE;
+
+		/* metric spec info length */
+		ceph_encode_32(p, 4 + size);
+
+		/* metric spec */
+		ceph_encode_32(p, size);
+		memset(*p, 0, size);
+		for (i = 0; i < count; i++)
+			((unsigned char *)(*p))[i / 8] |= BIT(metric_bits[i] % 8);
+		*p += size;
+	} else {
+		if (WARN_ON_ONCE(*p + 4 + 4 > end))
+			return -ERANGE;
+
+		/* metric spec info length */
+		ceph_encode_32(p, 4);
+		/* metric spec */
+		ceph_encode_32(p, 0);
+	}
+
+	return 0;
+}
+
 /*
  * session message, specialization for CEPH_SESSION_REQUEST_OPEN
  * to include additional client metadata fields.
@@ -1234,6 +1276,13 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 		size = FEATURE_BYTES(count);
 	extra_bytes += 4 + size;
 
+	/* metric spec */
+	size = 0;
+	count = ARRAY_SIZE(metric_bits);
+	if (count > 0)
+		size = METRIC_BYTES(count);
+	extra_bytes += 2 + 4 + 4 + size;
+
 	/* Allocate the message */
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + extra_bytes,
 			   GFP_NOFS, false);
@@ -1252,9 +1301,9 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 	 * Serialize client metadata into waiting buffer space, using
 	 * the format that userspace expects for map<string, string>
 	 *
-	 * ClientSession messages with metadata are v3
+	 * ClientSession messages with metadata are v4
 	 */
-	msg->hdr.version = cpu_to_le16(3);
+	msg->hdr.version = cpu_to_le16(4);
 	msg->hdr.compat_version = cpu_to_le16(1);
 
 	/* The write pointer, following the session_head structure */
@@ -1283,6 +1332,13 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 		return ERR_PTR(ret);
 	}
 
+	ret = encode_metric_spec(&p, end);
+	if (ret) {
+		pr_err("encode_metric_spec failed!\n");
+		ceph_msg_put(msg);
+		return ERR_PTR(ret);
+	}
+
 	msg->front.iov_len = p - msg->front.iov_base;
 	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 
diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
index fe5d07d2e63a..1d0959d669d7 100644
--- a/fs/ceph/metric.h
+++ b/fs/ceph/metric.h
@@ -18,6 +18,19 @@ enum ceph_metric_type {
 	CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_DENTRY_LEASE,
 };
 
+/*
+ * This will always have the highest metric bit value
+ * as the last element of the array.
+ */
+#define CEPHFS_METRIC_SPEC_CLIENT_SUPPORTED {	\
+	CLIENT_METRIC_TYPE_CAP_INFO,		\
+	CLIENT_METRIC_TYPE_READ_LATENCY,	\
+	CLIENT_METRIC_TYPE_WRITE_LATENCY,	\
+	CLIENT_METRIC_TYPE_METADATA_LATENCY,	\
+						\
+	CLIENT_METRIC_TYPE_MAX,			\
+}
+
 /* metric caps header */
 struct ceph_metric_cap {
 	__le32 type;     /* ceph metric type */

From f1f565a26976612121f97464f9245307422d0ce8 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 17 Jul 2020 16:36:04 -0700
Subject: [PATCH 187/474] ceph: delete repeated words in fs/ceph/

Drop duplicated words "down" and "the" in fs/ceph/.

[ idryomov: merge into a single patch ]

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/super.c                    | 2 +-
 fs/ceph/super.h                    | 2 +-
 include/linux/ceph/ceph_features.h | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 933f5df5da7d..585aecea5cad 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -839,7 +839,7 @@ static void destroy_caches(void)
 }
 
 /*
- * ceph_umount_begin - initiate forced umount.  Tear down down the
+ * ceph_umount_begin - initiate forced umount.  Tear down the
  * mount, skipping steps that may hang while waiting for server(s).
  */
 static void ceph_umount_begin(struct super_block *sb)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 2dcb6a90c636..9001a896ae8c 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -355,7 +355,7 @@ struct ceph_inode_info {
 	unsigned i_dirty_caps, i_flushing_caps;     /* mask of dirtied fields */
 
 	/*
-	 * Link to the the auth cap's session's s_cap_dirty list. s_cap_dirty
+	 * Link to the auth cap's session's s_cap_dirty list. s_cap_dirty
 	 * is protected by the mdsc->cap_dirty_lock, but each individual item
 	 * is also protected by the inode's i_ceph_lock. Walking s_cap_dirty
 	 * requires the mdsc->cap_dirty_lock. List presence for an item can
diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 39e6f4c57580..fcd84e8d88f4 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -58,7 +58,7 @@
  *    because 10.2.z (jewel) did not care if its peers advertised this
  *    feature bit.
  *
- *  - In the second phase we stop advertising the the bit and call it
+ *  - In the second phase we stop advertising the bit and call it
  *    RETIRED.  This can normally be done in the *next* major release
  *    following the one in which we marked the feature DEPRECATED.  In
  *    the above example, for 12.0.z (luminous) we can say:

From 8e298deb8d8c449d87acceab8c8bfef71b67b08d Mon Sep 17 00:00:00 2001
From: Jia Yang <jiayang5@huawei.com>
Date: Thu, 23 Jul 2020 10:25:52 +0800
Subject: [PATCH 188/474] ceph: remove unused variables in ceph_mdsmap_decode()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix build warnings:

  fs/ceph/mdsmap.c: In function ‘ceph_mdsmap_decode’:
  fs/ceph/mdsmap.c:192:7: warning: variable ‘info_cv’ set but not used [-Wunused-but-set-variable]
  fs/ceph/mdsmap.c:177:7: warning: variable ‘state_seq’ set but not used [-Wunused-but-set-variable]
  fs/ceph/mdsmap.c:123:15: warning: variable ‘mdsmap_cv’ set but not used [-Wunused-but-set-variable]

Note that p is increased in ceph_decode_*.

Signed-off-by: Jia Yang <jiayang5@huawei.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mdsmap.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 889627817e52..e4aba6c6d3b5 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -120,7 +120,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 	const void *start = *p;
 	int i, j, n;
 	int err;
-	u8 mdsmap_v, mdsmap_cv;
+	u8 mdsmap_v;
 	u16 mdsmap_ev;
 
 	m = kzalloc(sizeof(*m), GFP_NOFS);
@@ -129,7 +129,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 
 	ceph_decode_need(p, end, 1 + 1, bad);
 	mdsmap_v = ceph_decode_8(p);
-	mdsmap_cv = ceph_decode_8(p);
+	*p += sizeof(u8);			/* mdsmap_cv */
 	if (mdsmap_v >= 4) {
 	       u32 mdsmap_len;
 	       ceph_decode_32_safe(p, end, mdsmap_len, bad);
@@ -174,7 +174,6 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 		u64 global_id;
 		u32 namelen;
 		s32 mds, inc, state;
-		u64 state_seq;
 		u8 info_v;
 		void *info_end = NULL;
 		struct ceph_entity_addr addr;
@@ -189,9 +188,8 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 		info_v= ceph_decode_8(p);
 		if (info_v >= 4) {
 			u32 info_len;
-			u8 info_cv;
 			ceph_decode_need(p, end, 1 + sizeof(u32), bad);
-			info_cv = ceph_decode_8(p);
+			*p += sizeof(u8);	/* info_cv */
 			info_len = ceph_decode_32(p);
 			info_end = *p + info_len;
 			if (info_end > end)
@@ -210,7 +208,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 		mds = ceph_decode_32(p);
 		inc = ceph_decode_32(p);
 		state = ceph_decode_32(p);
-		state_seq = ceph_decode_64(p);
+		*p += sizeof(u64);		/* state_seq */
 		err = ceph_decode_entity_addr(p, end, &addr);
 		if (err)
 			goto corrupt;

From a7caa88f8b72c136f9a401f498471b8a8e35370d Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 23 Jul 2020 15:32:25 +0800
Subject: [PATCH 189/474] ceph: fix use-after-free for fsc->mdsc

If the ceph_mdsc_init() fails, it will free the mdsc already.

Reported-by: syzbot+b57f46d8d6ea51960b8c@syzkaller.appspotmail.com
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index af7221d1c610..590822fab767 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4453,7 +4453,6 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 		goto err_mdsc;
 	}
 
-	fsc->mdsc = mdsc;
 	init_completion(&mdsc->safe_umount_waiters);
 	init_waitqueue_head(&mdsc->session_close_wq);
 	INIT_LIST_HEAD(&mdsc->waiting_for_map);
@@ -4508,6 +4507,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 
 	strscpy(mdsc->nodename, utsname()->nodename,
 		sizeof(mdsc->nodename));
+
+	fsc->mdsc = mdsc;
 	return 0;
 
 err_mdsmap:

From 2c81ef286c42c5bfc0d0a60219b781791d4bd55c Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 23 Jul 2020 16:22:40 +0100
Subject: [PATCH 190/474] ceph: remove redundant initialization of variable mds

The variable mds is being initialized with a value that is never read
and it is being updated later with a new value.  The initialization is
redundant and can be removed.

Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/debugfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 3030f5585085..97539b497e4c 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -262,7 +262,7 @@ static int mds_sessions_show(struct seq_file *s, void *ptr)
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_auth_client *ac = fsc->client->monc.auth;
 	struct ceph_options *opt = fsc->client->options;
-	int mds = -1;
+	int mds;
 
 	mutex_lock(&mdsc->mutex);
 

From bd8548d0dcdab514e08e35a3451667486d879dae Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Mon, 3 Aug 2020 10:48:35 +0200
Subject: [PATCH 191/474] clk: hsdk: Fix bad dependency on IOMEM

CONFIG_IOMEM does not exist.  The correct symbol to depend on is
CONFIG_HAS_IOMEM.

Fixes: 1e7468bd9d30a21e ("clk: Specify IOMEM dependency for HSDK pll driver")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20200803084835.21838-1-geert+renesas@glider.be
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 690a2587e0c5..4026fac9fac3 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -50,7 +50,7 @@ source "drivers/clk/versatile/Kconfig"
 config CLK_HSDK
 	bool "PLL Driver for HSDK platform"
 	depends on OF || COMPILE_TEST
-	depends on IOMEM
+	depends on HAS_IOMEM
 	help
 	  This driver supports the HSDK core, system, ddr, tunnel and hdmi PLLs
 	  control.

From 6cfde88418fe95240e32d2955b51988360ee0942 Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@inria.fr>
Date: Sat, 1 Aug 2020 10:53:42 +0200
Subject: [PATCH 192/474] clk: drop unused function __clk_get_flags

The function __clk_get_flags has not been used since the April 2019
commit a348f05361c9 ("ARM: omap2+: hwmod: drop CLK_IS_BASIC
flag usage").  Other uses were removed in June 2015, eg by
commit 98d8a60eccee ("clk: Convert __clk_get_flags() to
clk_hw_get_flags()"), which shows how clk_hw_get_flags can easily
be used instead.

Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Link: https://lore.kernel.org/r/1596272022-14173-1-git-send-email-Julia.Lawall@inria.fr
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk.c            | 6 ------
 include/linux/clk-provider.h | 1 -
 2 files changed, 7 deletions(-)

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 3f588ed06ce3..d71456aad11d 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -500,12 +500,6 @@ static unsigned long clk_core_get_accuracy_no_lock(struct clk_core *core)
 	return core->accuracy;
 }
 
-unsigned long __clk_get_flags(struct clk *clk)
-{
-	return !clk ? 0 : clk->core->flags;
-}
-EXPORT_SYMBOL_GPL(__clk_get_flags);
-
 unsigned long clk_hw_get_flags(const struct clk_hw *hw)
 {
 	return hw->core->flags;
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index bd1ee9039558..93a78a5256d1 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -1096,7 +1096,6 @@ int clk_hw_get_parent_index(struct clk_hw *hw);
 int clk_hw_set_parent(struct clk_hw *hw, struct clk_hw *new_parent);
 unsigned int __clk_get_enable_count(struct clk *clk);
 unsigned long clk_hw_get_rate(const struct clk_hw *hw);
-unsigned long __clk_get_flags(struct clk *clk);
 unsigned long clk_hw_get_flags(const struct clk_hw *hw);
 #define clk_hw_can_set_rate_parent(hw) \
 	(clk_hw_get_flags((hw)) & CLK_SET_RATE_PARENT)

From f34e4651ce66a754f41203284acf09b28b9dd955 Mon Sep 17 00:00:00 2001
From: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Date: Thu, 30 Jul 2020 20:26:19 +0200
Subject: [PATCH 193/474] clk: bcm2835: Do not use prediv with bcm2711's PLLs

Contrary to previous SoCs, bcm2711 doesn't have a prescaler in the PLL
feedback loop. Bypass it by zeroing fb_prediv_mask when running on
bcm2711.

Note that, since the prediv configuration bits were re-purposed, this
was triggering miscalculations on all clocks hanging from the VPU clock,
notably the aux UART, making its output unintelligible.

Fixes: 42de9ad400af ("clk: bcm2835: Add BCM2711_CLOCK_EMMC2 support")
Reported-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Link: https://lore.kernel.org/r/20200730182619.23246-1-nsaenzjulienne@suse.de
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/bcm/clk-bcm2835.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c
index 027eba31f793..3439bc65bb4e 100644
--- a/drivers/clk/bcm/clk-bcm2835.c
+++ b/drivers/clk/bcm/clk-bcm2835.c
@@ -314,6 +314,7 @@ struct bcm2835_cprman {
 	struct device *dev;
 	void __iomem *regs;
 	spinlock_t regs_lock; /* spinlock for all clocks */
+	unsigned int soc;
 
 	/*
 	 * Real names of cprman clock parents looked up through
@@ -526,6 +527,20 @@ static int bcm2835_pll_is_on(struct clk_hw *hw)
 		A2W_PLL_CTRL_PRST_DISABLE;
 }
 
+static u32 bcm2835_pll_get_prediv_mask(struct bcm2835_cprman *cprman,
+				       const struct bcm2835_pll_data *data)
+{
+	/*
+	 * On BCM2711 there isn't a pre-divisor available in the PLL feedback
+	 * loop. Bits 13:14 of ANA1 (PLLA,PLLB,PLLC,PLLD) have been re-purposed
+	 * for to for VCO RANGE bits.
+	 */
+	if (cprman->soc & SOC_BCM2711)
+		return 0;
+
+	return data->ana->fb_prediv_mask;
+}
+
 static void bcm2835_pll_choose_ndiv_and_fdiv(unsigned long rate,
 					     unsigned long parent_rate,
 					     u32 *ndiv, u32 *fdiv)
@@ -583,7 +598,7 @@ static unsigned long bcm2835_pll_get_rate(struct clk_hw *hw,
 	ndiv = (a2wctrl & A2W_PLL_CTRL_NDIV_MASK) >> A2W_PLL_CTRL_NDIV_SHIFT;
 	pdiv = (a2wctrl & A2W_PLL_CTRL_PDIV_MASK) >> A2W_PLL_CTRL_PDIV_SHIFT;
 	using_prediv = cprman_read(cprman, data->ana_reg_base + 4) &
-		data->ana->fb_prediv_mask;
+		       bcm2835_pll_get_prediv_mask(cprman, data);
 
 	if (using_prediv) {
 		ndiv *= 2;
@@ -666,6 +681,7 @@ static int bcm2835_pll_set_rate(struct clk_hw *hw,
 	struct bcm2835_pll *pll = container_of(hw, struct bcm2835_pll, hw);
 	struct bcm2835_cprman *cprman = pll->cprman;
 	const struct bcm2835_pll_data *data = pll->data;
+	u32 prediv_mask = bcm2835_pll_get_prediv_mask(cprman, data);
 	bool was_using_prediv, use_fb_prediv, do_ana_setup_first;
 	u32 ndiv, fdiv, a2w_ctl;
 	u32 ana[4];
@@ -683,7 +699,7 @@ static int bcm2835_pll_set_rate(struct clk_hw *hw,
 	for (i = 3; i >= 0; i--)
 		ana[i] = cprman_read(cprman, data->ana_reg_base + i * 4);
 
-	was_using_prediv = ana[1] & data->ana->fb_prediv_mask;
+	was_using_prediv = ana[1] & prediv_mask;
 
 	ana[0] &= ~data->ana->mask0;
 	ana[0] |= data->ana->set0;
@@ -693,10 +709,10 @@ static int bcm2835_pll_set_rate(struct clk_hw *hw,
 	ana[3] |= data->ana->set3;
 
 	if (was_using_prediv && !use_fb_prediv) {
-		ana[1] &= ~data->ana->fb_prediv_mask;
+		ana[1] &= ~prediv_mask;
 		do_ana_setup_first = true;
 	} else if (!was_using_prediv && use_fb_prediv) {
-		ana[1] |= data->ana->fb_prediv_mask;
+		ana[1] |= prediv_mask;
 		do_ana_setup_first = false;
 	} else {
 		do_ana_setup_first = true;
@@ -2262,6 +2278,7 @@ static int bcm2835_clk_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, cprman);
 
 	cprman->onecell.num = asize;
+	cprman->soc = pdata->soc;
 	hws = cprman->onecell.hws;
 
 	for (i = 0; i < asize; i++) {

From d88ca7e1a27eb2df056bbf37ddef62e1c73d37ea Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Date: Thu, 30 Jul 2020 19:47:14 +0900
Subject: [PATCH 194/474] fbmem: pull fbcon_update_vcs() out of fb_set_var()

syzbot is reporting OOB read bug in vc_do_resize() [1] caused by memcpy()
based on outdated old_{rows,row_size} values, for resize_screen() can
recurse into vc_do_resize() which changes vc->vc_{cols,rows} that outdates
old_{rows,row_size} values which were saved before calling resize_screen().

Daniel Vetter explained that resize_screen() should not recurse into
fbcon_update_vcs() path due to FBINFO_MISC_USEREVENT being still set
when calling resize_screen().

Instead of masking FBINFO_MISC_USEREVENT before calling fbcon_update_vcs(),
we can remove FBINFO_MISC_USEREVENT by calling fbcon_update_vcs() only if
fb_set_var() returned 0. This change assumes that it is harmless to call
fbcon_update_vcs() when fb_set_var() returned 0 without reaching
fb_notifier_call_chain().

[1] https://syzkaller.appspot.com/bug?id=c70c88cfd16dcf6e1d3c7f0ab8648b3144b5b25e

Reported-and-tested-by: syzbot <syzbot+c37a14770d51a085a520@syzkaller.appspotmail.com>
Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reported-by: kernel test robot <lkp@intel.com> for missing #include
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/075b7e37-3278-cd7d-31ab-c5073cfa8e92@i-love.sakura.ne.jp
---
 drivers/video/fbdev/core/fbmem.c   | 8 ++------
 drivers/video/fbdev/core/fbsysfs.c | 4 ++--
 drivers/video/fbdev/ps3fb.c        | 5 +++--
 include/linux/fb.h                 | 2 --
 4 files changed, 7 insertions(+), 12 deletions(-)

diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 30e73ec4ad5c..da7c88ffaa6a 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -957,7 +957,6 @@ static int fb_check_caps(struct fb_info *info, struct fb_var_screeninfo *var,
 int
 fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var)
 {
-	int flags = info->flags;
 	int ret = 0;
 	u32 activate;
 	struct fb_var_screeninfo old_var;
@@ -1052,9 +1051,6 @@ fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var)
 	event.data = &mode;
 	fb_notifier_call_chain(FB_EVENT_MODE_CHANGE, &event);
 
-	if (flags & FBINFO_MISC_USEREVENT)
-		fbcon_update_vcs(info, activate & FB_ACTIVATE_ALL);
-
 	return 0;
 }
 EXPORT_SYMBOL(fb_set_var);
@@ -1105,9 +1101,9 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd,
 			return -EFAULT;
 		console_lock();
 		lock_fb_info(info);
-		info->flags |= FBINFO_MISC_USEREVENT;
 		ret = fb_set_var(info, &var);
-		info->flags &= ~FBINFO_MISC_USEREVENT;
+		if (!ret)
+			fbcon_update_vcs(info, var.activate & FB_ACTIVATE_ALL);
 		unlock_fb_info(info);
 		console_unlock();
 		if (!ret && copy_to_user(argp, &var, sizeof(var)))
diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c
index d54c88f88991..65dae05fff8e 100644
--- a/drivers/video/fbdev/core/fbsysfs.c
+++ b/drivers/video/fbdev/core/fbsysfs.c
@@ -91,9 +91,9 @@ static int activate(struct fb_info *fb_info, struct fb_var_screeninfo *var)
 
 	var->activate |= FB_ACTIVATE_FORCE;
 	console_lock();
-	fb_info->flags |= FBINFO_MISC_USEREVENT;
 	err = fb_set_var(fb_info, var);
-	fb_info->flags &= ~FBINFO_MISC_USEREVENT;
+	if (!err)
+		fbcon_update_vcs(fb_info, var->activate & FB_ACTIVATE_ALL);
 	console_unlock();
 	if (err)
 		return err;
diff --git a/drivers/video/fbdev/ps3fb.c b/drivers/video/fbdev/ps3fb.c
index 9df78fb77267..203c254f8f6c 100644
--- a/drivers/video/fbdev/ps3fb.c
+++ b/drivers/video/fbdev/ps3fb.c
@@ -29,6 +29,7 @@
 #include <linux/freezer.h>
 #include <linux/uaccess.h>
 #include <linux/fb.h>
+#include <linux/fbcon.h>
 #include <linux/init.h>
 
 #include <asm/cell-regs.h>
@@ -824,12 +825,12 @@ static int ps3fb_ioctl(struct fb_info *info, unsigned int cmd,
 				var = info->var;
 				fb_videomode_to_var(&var, vmode);
 				console_lock();
-				info->flags |= FBINFO_MISC_USEREVENT;
 				/* Force, in case only special bits changed */
 				var.activate |= FB_ACTIVATE_FORCE;
 				par->new_mode_id = val;
 				retval = fb_set_var(info, &var);
-				info->flags &= ~FBINFO_MISC_USEREVENT;
+				if (!retval)
+					fbcon_update_vcs(info, var.activate & FB_ACTIVATE_ALL);
 				console_unlock();
 			}
 			break;
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 2b530e6d86e4..850f79e9a7cb 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -400,8 +400,6 @@ struct fb_tile_ops {
 #define FBINFO_HWACCEL_YPAN		0x2000 /* optional */
 #define FBINFO_HWACCEL_YWRAP		0x4000 /* optional */
 
-#define FBINFO_MISC_USEREVENT          0x10000 /* event request
-						  from userspace */
 #define FBINFO_MISC_TILEBLITTING       0x20000 /* use tile blitting */
 
 /* A driver may set this flag to indicate that it does want a set_par to be

From a72a6a16d51034045cb6355924b62221a8221ca3 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ti.com>
Date: Thu, 4 Jun 2020 11:02:14 +0300
Subject: [PATCH 195/474] drm/tidss: fix modeset init for DPI panels

The connector type for DISPC's DPI videoport was set the LVDS instead of
DPI. This causes any DPI panel setup to fail with tidss, making all DPI
panels unusable.

Fix this by using correct connector type.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Fixes: 32a1795f57eecc39749017 ("drm/tidss: New driver for TI Keystone platform Display SubSystem")
Cc: stable@vger.kernel.org # v5.7+
Link: https://patchwork.freedesktop.org/patch/msgid/20200604080214.107159-1-tomi.valkeinen@ti.com
Reviewed-by: Jyri Sarha <jsarha@ti.com>
---
 drivers/gpu/drm/tidss/tidss_kms.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/tidss/tidss_kms.c b/drivers/gpu/drm/tidss/tidss_kms.c
index 4b99e9fa84a5..c0240f7e0b19 100644
--- a/drivers/gpu/drm/tidss/tidss_kms.c
+++ b/drivers/gpu/drm/tidss/tidss_kms.c
@@ -154,7 +154,7 @@ static int tidss_dispc_modeset_init(struct tidss_device *tidss)
 				break;
 			case DISPC_VP_DPI:
 				enc_type = DRM_MODE_ENCODER_DPI;
-				conn_type = DRM_MODE_CONNECTOR_LVDS;
+				conn_type = DRM_MODE_CONNECTOR_DPI;
 				break;
 			default:
 				WARN_ON(1);

From ecfdedd7da5d54416db5ca0f851264dca8736f59 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ti.com>
Date: Thu, 18 Jun 2020 12:51:52 +0300
Subject: [PATCH 196/474] drm/omap: force runtime PM suspend on system suspend

Use SET_LATE_SYSTEM_SLEEP_PM_OPS in DSS submodules to force runtime PM
suspend and resume.

We use suspend late version so that omapdrm's system suspend callback is
called first, as that will disable all the display outputs after which
it's safe to force DSS into suspend.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200618095153.611071-1-tomi.valkeinen@ti.com
Acked-by: Tony Lindgren <tony@atomide.com>
Fixes: cef766300353 ("drm/omap: Prepare DSS for probing without legacy platform data")
Cc: stable@vger.kernel.org # v5.7+
Tested-by: Tony Lindgren <tony@atomide.com>
---
 drivers/gpu/drm/omapdrm/dss/dispc.c | 1 +
 drivers/gpu/drm/omapdrm/dss/dsi.c   | 1 +
 drivers/gpu/drm/omapdrm/dss/dss.c   | 1 +
 drivers/gpu/drm/omapdrm/dss/venc.c  | 1 +
 4 files changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/omapdrm/dss/dispc.c b/drivers/gpu/drm/omapdrm/dss/dispc.c
index 6639ee9b05d3..48593932bddf 100644
--- a/drivers/gpu/drm/omapdrm/dss/dispc.c
+++ b/drivers/gpu/drm/omapdrm/dss/dispc.c
@@ -4915,6 +4915,7 @@ static int dispc_runtime_resume(struct device *dev)
 static const struct dev_pm_ops dispc_pm_ops = {
 	.runtime_suspend = dispc_runtime_suspend,
 	.runtime_resume = dispc_runtime_resume,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
 };
 
 struct platform_driver omap_dispchw_driver = {
diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c
index 79ddfbfd1b58..eeccf40bae41 100644
--- a/drivers/gpu/drm/omapdrm/dss/dsi.c
+++ b/drivers/gpu/drm/omapdrm/dss/dsi.c
@@ -5467,6 +5467,7 @@ static int dsi_runtime_resume(struct device *dev)
 static const struct dev_pm_ops dsi_pm_ops = {
 	.runtime_suspend = dsi_runtime_suspend,
 	.runtime_resume = dsi_runtime_resume,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
 };
 
 struct platform_driver omap_dsihw_driver = {
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index 4d5739fa4a5d..6ccbc29c4ce4 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -1614,6 +1614,7 @@ static int dss_runtime_resume(struct device *dev)
 static const struct dev_pm_ops dss_pm_ops = {
 	.runtime_suspend = dss_runtime_suspend,
 	.runtime_resume = dss_runtime_resume,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
 };
 
 struct platform_driver omap_dsshw_driver = {
diff --git a/drivers/gpu/drm/omapdrm/dss/venc.c b/drivers/gpu/drm/omapdrm/dss/venc.c
index 9701843ccf09..01ee6c50b663 100644
--- a/drivers/gpu/drm/omapdrm/dss/venc.c
+++ b/drivers/gpu/drm/omapdrm/dss/venc.c
@@ -902,6 +902,7 @@ static int venc_runtime_resume(struct device *dev)
 static const struct dev_pm_ops venc_pm_ops = {
 	.runtime_suspend = venc_runtime_suspend,
 	.runtime_resume = venc_runtime_resume,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
 };
 
 static const struct of_device_id venc_of_match[] = {

From b5ac98cbb8e5e30c34ebc837d1e5a3982d2b5f5c Mon Sep 17 00:00:00 2001
From: Marius Iacob <themariusus@gmail.com>
Date: Sat, 1 Aug 2020 15:34:46 +0300
Subject: [PATCH 197/474] drm: Added orientation quirk for ASUS tablet model
 T103HAF

Signed-off-by: Marius Iacob <themariusus@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20200801123445.1514567-1-themariusus@gmail.com
---
 drivers/gpu/drm/drm_panel_orientation_quirks.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index d00ea384dcbf..58f5dc2f6dd5 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -121,6 +121,12 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T101HA"),
 		},
 		.driver_data = (void *)&lcd800x1280_rightside_up,
+	}, {	/* Asus T103HAF */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T103HAF"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* GPD MicroPC (generic strings, also match on bios date) */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Default string"),

From a34a0a632dd991a371fec56431d73279f9c54029 Mon Sep 17 00:00:00 2001
From: Xin Xiong <xiongx18@fudan.edu.cn>
Date: Sun, 19 Jul 2020 23:45:45 +0800
Subject: [PATCH 198/474] drm: fix drm_dp_mst_port refcount leaks in
 drm_dp_mst_allocate_vcpi
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

drm_dp_mst_allocate_vcpi() invokes
drm_dp_mst_topology_get_port_validated(), which increases the refcount
of the "port".

These reference counting issues take place in two exception handling
paths separately. Either when “slots” is less than 0 or when
drm_dp_init_vcpi() returns a negative value, the function forgets to
reduce the refcnt increased drm_dp_mst_topology_get_port_validated(),
which results in a refcount leak.

Fix these issues by pulling up the error handling when "slots" is less
than 0, and calling drm_dp_mst_topology_put_port() before termination
when drm_dp_init_vcpi() returns a negative value.

Fixes: 1e797f556c61 ("drm/dp: Split drm_dp_mst_allocate_vcpi")
Cc: <stable@vger.kernel.org> # v4.12+
Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Signed-off-by: Xin Xiong <xiongx18@fudan.edu.cn>
Reviewed-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Lyude Paul <lyude@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200719154545.GA41231@xin-virtual-machine
---
 drivers/gpu/drm/drm_dp_mst_topology.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 09b32289497e..b23cb2fec3f3 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -4308,11 +4308,11 @@ bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr,
 {
 	int ret;
 
-	port = drm_dp_mst_topology_get_port_validated(mgr, port);
-	if (!port)
+	if (slots < 0)
 		return false;
 
-	if (slots < 0)
+	port = drm_dp_mst_topology_get_port_validated(mgr, port);
+	if (!port)
 		return false;
 
 	if (port->vcpi.vcpi > 0) {
@@ -4328,6 +4328,7 @@ bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr,
 	if (ret) {
 		DRM_DEBUG_KMS("failed to init vcpi slots=%d max=63 ret=%d\n",
 			      DIV_ROUND_UP(pbn, mgr->pbn_div), ret);
+		drm_dp_mst_topology_put_port(port);
 		goto out;
 	}
 	DRM_DEBUG_KMS("initing vcpi for pbn=%d slots=%d\n",

From b748fc7a8763a5b3f8149f12c45711cd73ef8176 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Tue, 28 Jul 2020 10:34:20 -0400
Subject: [PATCH 199/474] ceph: set sec_context xattr on symlink creation

Symlink inodes should have the security context set in their xattrs on
creation. We already set the context on creation, but we don't attach
the pagelist. The effect is that symlink inodes don't get an SELinux
context set on them at creation, so they end up unlabeled instead of
inheriting the proper context. Make it do so.

Cc: stable@vger.kernel.org
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/dir.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 39f5311404b0..060bdcc5ce32 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -930,6 +930,10 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
 	req->r_num_caps = 2;
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
+	if (as_ctx.pagelist) {
+		req->r_pagelist = as_ctx.pagelist;
+		as_ctx.pagelist = NULL;
+	}
 	err = ceph_mdsc_do_request(mdsc, dir, req);
 	if (!err && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);

From a0102bda5bc0991c5c8c7c07770b236894a810fd Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 30 Jul 2020 11:03:55 -0400
Subject: [PATCH 200/474] ceph: move sb->wb_pagevec_pool to be a global mempool

When doing some testing recently, I hit some page allocation failures
on mount, when creating the wb_pagevec_pool for the mount. That
requires 128k (32 contiguous pages), and after thrashing the memory
during an xfstests run, sometimes that would fail.

128k for each mount seems like a lot to hold in reserve for a rainy
day, so let's change this to a global mempool that gets allocated
when the module is plugged in.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c               | 23 +++++++++++------------
 fs/ceph/super.c              | 22 ++++++++--------------
 fs/ceph/super.h              |  2 --
 include/linux/ceph/libceph.h |  1 +
 4 files changed, 20 insertions(+), 28 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 01ad09733ac7..6ea761c84494 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -862,8 +862,7 @@ static void writepages_finish(struct ceph_osd_request *req)
 
 	osd_data = osd_req_op_extent_osd_data(req, 0);
 	if (osd_data->pages_from_pool)
-		mempool_free(osd_data->pages,
-			     ceph_sb_to_client(inode->i_sb)->wb_pagevec_pool);
+		mempool_free(osd_data->pages, ceph_wb_pagevec_pool);
 	else
 		kfree(osd_data->pages);
 	ceph_osdc_put_request(req);
@@ -955,10 +954,10 @@ static int ceph_writepages_start(struct address_space *mapping,
 		int num_ops = 0, op_idx;
 		unsigned i, pvec_pages, max_pages, locked_pages = 0;
 		struct page **pages = NULL, **data_pages;
-		mempool_t *pool = NULL;	/* Becomes non-null if mempool used */
 		struct page *page;
 		pgoff_t strip_unit_end = 0;
 		u64 offset = 0, len = 0;
+		bool from_pool = false;
 
 		max_pages = wsize >> PAGE_SHIFT;
 
@@ -1057,16 +1056,16 @@ static int ceph_writepages_start(struct address_space *mapping,
 						      sizeof(*pages),
 						      GFP_NOFS);
 				if (!pages) {
-					pool = fsc->wb_pagevec_pool;
-					pages = mempool_alloc(pool, GFP_NOFS);
+					from_pool = true;
+					pages = mempool_alloc(ceph_wb_pagevec_pool, GFP_NOFS);
 					BUG_ON(!pages);
 				}
 
 				len = 0;
 			} else if (page->index !=
 				   (offset + len) >> PAGE_SHIFT) {
-				if (num_ops >= (pool ?  CEPH_OSD_SLAB_OPS :
-							CEPH_OSD_MAX_OPS)) {
+				if (num_ops >= (from_pool ?  CEPH_OSD_SLAB_OPS :
+							     CEPH_OSD_MAX_OPS)) {
 					redirty_page_for_writepage(wbc, page);
 					unlock_page(page);
 					break;
@@ -1161,7 +1160,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 				     offset, len);
 				osd_req_op_extent_osd_data_pages(req, op_idx,
 							data_pages, len, 0,
-							!!pool, false);
+							from_pool, false);
 				osd_req_op_extent_update(req, op_idx, len);
 
 				len = 0;
@@ -1188,12 +1187,12 @@ static int ceph_writepages_start(struct address_space *mapping,
 		dout("writepages got pages at %llu~%llu\n", offset, len);
 
 		osd_req_op_extent_osd_data_pages(req, op_idx, data_pages, len,
-						 0, !!pool, false);
+						 0, from_pool, false);
 		osd_req_op_extent_update(req, op_idx, len);
 
 		BUG_ON(op_idx + 1 != req->r_num_ops);
 
-		pool = NULL;
+		from_pool = false;
 		if (i < locked_pages) {
 			BUG_ON(num_ops <= req->r_num_ops);
 			num_ops -= req->r_num_ops;
@@ -1204,8 +1203,8 @@ static int ceph_writepages_start(struct address_space *mapping,
 			pages = kmalloc_array(locked_pages, sizeof(*pages),
 					      GFP_NOFS);
 			if (!pages) {
-				pool = fsc->wb_pagevec_pool;
-				pages = mempool_alloc(pool, GFP_NOFS);
+				from_pool = true;
+				pages = mempool_alloc(ceph_wb_pagevec_pool, GFP_NOFS);
 				BUG_ON(!pages);
 			}
 			memcpy(pages, data_pages + i,
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 585aecea5cad..7ec0e6d03d10 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -637,8 +637,6 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 					struct ceph_options *opt)
 {
 	struct ceph_fs_client *fsc;
-	int page_count;
-	size_t size;
 	int err;
 
 	fsc = kzalloc(sizeof(*fsc), GFP_KERNEL);
@@ -686,22 +684,12 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	if (!fsc->cap_wq)
 		goto fail_inode_wq;
 
-	/* set up mempools */
-	err = -ENOMEM;
-	page_count = fsc->mount_options->wsize >> PAGE_SHIFT;
-	size = sizeof (struct page *) * (page_count ? page_count : 1);
-	fsc->wb_pagevec_pool = mempool_create_kmalloc_pool(10, size);
-	if (!fsc->wb_pagevec_pool)
-		goto fail_cap_wq;
-
 	spin_lock(&ceph_fsc_lock);
 	list_add_tail(&fsc->metric_wakeup, &ceph_fsc_list);
 	spin_unlock(&ceph_fsc_lock);
 
 	return fsc;
 
-fail_cap_wq:
-	destroy_workqueue(fsc->cap_wq);
 fail_inode_wq:
 	destroy_workqueue(fsc->inode_wq);
 fail_client:
@@ -732,8 +720,6 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
 	destroy_workqueue(fsc->inode_wq);
 	destroy_workqueue(fsc->cap_wq);
 
-	mempool_destroy(fsc->wb_pagevec_pool);
-
 	destroy_mount_options(fsc->mount_options);
 
 	ceph_destroy_client(fsc->client);
@@ -752,6 +738,7 @@ struct kmem_cache *ceph_dentry_cachep;
 struct kmem_cache *ceph_file_cachep;
 struct kmem_cache *ceph_dir_file_cachep;
 struct kmem_cache *ceph_mds_request_cachep;
+mempool_t *ceph_wb_pagevec_pool;
 
 static void ceph_inode_init_once(void *foo)
 {
@@ -796,6 +783,10 @@ static int __init init_caches(void)
 	if (!ceph_mds_request_cachep)
 		goto bad_mds_req;
 
+	ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10, CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT);
+	if (!ceph_wb_pagevec_pool)
+		goto bad_pagevec_pool;
+
 	error = ceph_fscache_register();
 	if (error)
 		goto bad_fscache;
@@ -804,6 +795,8 @@ static int __init init_caches(void)
 
 bad_fscache:
 	kmem_cache_destroy(ceph_mds_request_cachep);
+bad_pagevec_pool:
+	mempool_destroy(ceph_wb_pagevec_pool);
 bad_mds_req:
 	kmem_cache_destroy(ceph_dir_file_cachep);
 bad_dir_file:
@@ -834,6 +827,7 @@ static void destroy_caches(void)
 	kmem_cache_destroy(ceph_file_cachep);
 	kmem_cache_destroy(ceph_dir_file_cachep);
 	kmem_cache_destroy(ceph_mds_request_cachep);
+	mempool_destroy(ceph_wb_pagevec_pool);
 
 	ceph_fscache_unregister();
 }
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 9001a896ae8c..4c3c964b1c54 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -118,8 +118,6 @@ struct ceph_fs_client {
 
 	struct ceph_mds_client *mdsc;
 
-	/* writeback */
-	mempool_t *wb_pagevec_pool;
 	atomic_long_t writeback_count;
 
 	struct workqueue_struct *inode_wq;
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index e5ed1c541e7f..c8645f0b797d 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -282,6 +282,7 @@ extern struct kmem_cache *ceph_dentry_cachep;
 extern struct kmem_cache *ceph_file_cachep;
 extern struct kmem_cache *ceph_dir_file_cachep;
 extern struct kmem_cache *ceph_mds_request_cachep;
+extern mempool_t *ceph_wb_pagevec_pool;
 
 /* ceph_common.c */
 extern bool libceph_compatible(void *data);

From 224c7b6778fe08e1880ef88867051bec0a154d6c Mon Sep 17 00:00:00 2001
From: Yanhu Cao <gmayyyha@gmail.com>
Date: Fri, 31 Jul 2020 16:25:13 +0800
Subject: [PATCH 201/474] ceph: use frag's MDS in either mode

When doing some tests with multiple mds, we were seeing many mds
forwarding requests between them, causing clients to resend.

If the request is a modification operation and the mode is set to
USE_AUTH_MDS, then the auth mds should be selected to handle the
request. If auth mds for frag is already set, then it should be returned
directly without further processing.

The current logic is wrong because it only returns directly if
mode is USE_AUTH_MDS, but we want to do that for all modes. If we don't,
then when the frag's mds is not equal to cap session's mds, the request
will get sent to the wrong MDS needlessly.

Drop the mode check in this condition.

Signed-off-by: Yanhu Cao <gmayyyha@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 590822fab767..1095802ad9bd 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1103,8 +1103,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 				     frag.frag, mds);
 				if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
 				    CEPH_MDS_STATE_ACTIVE) {
-					if (mode == USE_ANY_MDS &&
-					    !ceph_mdsmap_is_laggy(mdsc->mdsmap,
+					if (!ceph_mdsmap_is_laggy(mdsc->mdsmap,
 								  mds))
 						goto out;
 				}

From 9bf1306257589b3a5ad46175538af9922d94e26f Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Mon, 27 Jul 2020 15:46:14 +1200
Subject: [PATCH 202/474] rtc: ds1307: provide an indication that the watchdog
 has fired

There's not much feedback when the ds1388 watchdog fires. Generally it
yanks on the reset line and the board reboots. Capture the fact that the
watchdog has fired in the past so that userspace can retrieve it via
WDIOC_GETBOOTSTATUS. This should help distinguish a watchdog triggered
reset from a power interruption.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200727034615.19755-1-chris.packham@alliedtelesis.co.nz
---
 drivers/rtc/rtc-ds1307.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index 49702942bb08..54c85cdd019d 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -1668,6 +1668,8 @@ static const struct watchdog_ops ds1388_wdt_ops = {
 static void ds1307_wdt_register(struct ds1307 *ds1307)
 {
 	struct watchdog_device	*wdt;
+	int err;
+	int val;
 
 	if (ds1307->type != ds_1388)
 		return;
@@ -1676,6 +1678,10 @@ static void ds1307_wdt_register(struct ds1307 *ds1307)
 	if (!wdt)
 		return;
 
+	err = regmap_read(ds1307->regmap, DS1388_REG_FLAG, &val);
+	if (!err && val & DS1388_BIT_WF)
+		wdt->bootstatus = WDIOF_CARDRESET;
+
 	wdt->info = &ds1388_wdt_info;
 	wdt->ops = &ds1388_wdt_ops;
 	wdt->timeout = 99;

From 02e37571f9e79022498fd0525c073b07e9d9ac69 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Tue, 4 Aug 2020 12:31:56 -0400
Subject: [PATCH 203/474] ceph: handle zero-length feature mask in session
 messages

Most session messages contain a feature mask, but the MDS will
routinely send a REJECT message with one that is zero-length.

Commit 0fa8263367db ("ceph: fix endianness bug when handling MDS
session feature bits") fixed the decoding of the feature mask,
but failed to account for the MDS sending a zero-length feature
mask. This causes REJECT message decoding to fail.

Skip trying to decode a feature mask if the word count is zero.

Cc: stable@vger.kernel.org
URL: https://tracker.ceph.com/issues/46823
Fixes: 0fa8263367db ("ceph: fix endianness bug when handling MDS session feature bits")
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Tested-by: Patrick Donnelly <pdonnell@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 1095802ad9bd..4a26862d7667 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3358,8 +3358,10 @@ static void handle_session(struct ceph_mds_session *session,
 			goto bad;
 		/* version >= 3, feature bits */
 		ceph_decode_32_safe(&p, end, len, bad);
-		ceph_decode_64_safe(&p, end, features, bad);
-		p += len - sizeof(features);
+		if (len) {
+			ceph_decode_64_safe(&p, end, features, bad);
+			p += len - sizeof(features);
+		}
 	}
 
 	mutex_lock(&mdsc->mutex);

From 923a3a863ae0c26876d704fb3453069e11ebdcb6 Mon Sep 17 00:00:00 2001
From: Michael Shych <michaelsh@mellanox.com>
Date: Mon, 4 May 2020 17:14:24 +0300
Subject: [PATCH 204/474] platform_data/mlxreg: support new watchdog type with
 longer timeout period

Add new watchdog type 3 with longer timeout period.
Extend size of health_cntr field that that can be used to init watchdog
timeout period.

Signed-off-by: Michael Shych <michaelsh@mellanox.com>
Reviewed-by: Vadim Pasternak <vadimp@mellanox.com>
Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200504141427.17685-2-michaelsh@mellanox.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 include/linux/platform_data/mlxreg.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h
index b8da8aef2446..2c5e58d1d77b 100644
--- a/include/linux/platform_data/mlxreg.h
+++ b/include/linux/platform_data/mlxreg.h
@@ -43,10 +43,13 @@
  *
  * TYPE1 HW watchdog implementation exist in old systems.
  * All new systems have TYPE2 HW watchdog.
+ * TYPE3 HW watchdog can exist on all systems with new CPLD.
+ * TYPE3 is selected by WD capability bit.
  */
 enum mlxreg_wdt_type {
 	MLX_WDT_TYPE1,
 	MLX_WDT_TYPE2,
+	MLX_WDT_TYPE3,
 };
 
 /**
@@ -90,7 +93,7 @@ struct mlxreg_core_data {
 	umode_t	mode;
 	struct device_node *np;
 	struct mlxreg_hotplug_device hpdev;
-	u8 health_cntr;
+	u32 health_cntr;
 	bool attached;
 };
 

From 7772b993fd96dc8f776356b1d5e18a4df7e68268 Mon Sep 17 00:00:00 2001
From: Michael Shych <michaelsh@mellanox.com>
Date: Mon, 4 May 2020 17:14:25 +0300
Subject: [PATCH 205/474] platform/x86: mlx-platform: support new watchdog type
 with longer timeout

Add verification of WD capability in order to distinguish between
the existing WD types and new type, implemented in CPLD.
Add configuration for a new WD type.
Change access mode for watchdog registers.

Signed-off-by: Michael Shych <michaelsh@mellanox.com>
Reviewed-by: Vadim Pasternak <vadimp@mellanox.com>
Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200504141427.17685-3-michaelsh@mellanox.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/platform/x86/mlx-platform.c | 106 ++++++++++++++++++++++++++++
 1 file changed, 106 insertions(+)

diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c
index c27548fd386a..9d3371cd58d5 100644
--- a/drivers/platform/x86/mlx-platform.c
+++ b/drivers/platform/x86/mlx-platform.c
@@ -178,7 +178,9 @@
 #define MLXPLAT_CPLD_WD_RESET_ACT_MASK	GENMASK(7, 1)
 #define MLXPLAT_CPLD_WD_FAN_ACT_MASK	(GENMASK(7, 0) & ~BIT(4))
 #define MLXPLAT_CPLD_WD_COUNT_ACT_MASK	(GENMASK(7, 0) & ~BIT(7))
+#define MLXPLAT_CPLD_WD_CPBLTY_MASK	(GENMASK(7, 0) & ~BIT(6))
 #define MLXPLAT_CPLD_WD_DFLT_TIMEOUT	30
+#define MLXPLAT_CPLD_WD3_DFLT_TIMEOUT	600
 #define MLXPLAT_CPLD_WD_MAX_DEVS	2
 
 /* mlxplat_priv - platform private data
@@ -1959,6 +1961,84 @@ static struct mlxreg_core_platform_data mlxplat_mlxcpld_wd_set_type2[] = {
 	},
 };
 
+/* Watchdog type3: hardware implementation version 3
+ * Can be on all systems. It's differentiated by WD capability bit.
+ * Old systems (MSN2700, MSN2410, MSN2740, MSN2100 and MSN2140)
+ * still have only one main watchdog.
+ */
+static struct mlxreg_core_data mlxplat_mlxcpld_wd_main_regs_type3[] = {
+	{
+		.label = "action",
+		.reg = MLXPLAT_CPLD_LPC_REG_WD2_ACT_OFFSET,
+		.mask = MLXPLAT_CPLD_WD_RESET_ACT_MASK,
+		.bit = 0,
+	},
+	{
+		.label = "timeout",
+		.reg = MLXPLAT_CPLD_LPC_REG_WD2_TMR_OFFSET,
+		.mask = MLXPLAT_CPLD_WD_TYPE2_TO_MASK,
+		.health_cntr = MLXPLAT_CPLD_WD3_DFLT_TIMEOUT,
+	},
+	{
+		.label = "timeleft",
+		.reg = MLXPLAT_CPLD_LPC_REG_WD2_TMR_OFFSET,
+		.mask = MLXPLAT_CPLD_WD_TYPE2_TO_MASK,
+	},
+	{
+		.label = "ping",
+		.reg = MLXPLAT_CPLD_LPC_REG_WD2_ACT_OFFSET,
+		.mask = MLXPLAT_CPLD_WD_RESET_ACT_MASK,
+		.bit = 0,
+	},
+	{
+		.label = "reset",
+		.reg = MLXPLAT_CPLD_LPC_REG_RESET_CAUSE_OFFSET,
+		.mask = GENMASK(7, 0) & ~BIT(6),
+		.bit = 6,
+	},
+};
+
+static struct mlxreg_core_data mlxplat_mlxcpld_wd_aux_regs_type3[] = {
+	{
+		.label = "action",
+		.reg = MLXPLAT_CPLD_LPC_REG_WD3_ACT_OFFSET,
+		.mask = MLXPLAT_CPLD_WD_FAN_ACT_MASK,
+		.bit = 4,
+	},
+	{
+		.label = "timeout",
+		.reg = MLXPLAT_CPLD_LPC_REG_WD3_TMR_OFFSET,
+		.mask = MLXPLAT_CPLD_WD_TYPE2_TO_MASK,
+		.health_cntr = MLXPLAT_CPLD_WD3_DFLT_TIMEOUT,
+	},
+	{
+		.label = "timeleft",
+		.reg = MLXPLAT_CPLD_LPC_REG_WD3_TMR_OFFSET,
+		.mask = MLXPLAT_CPLD_WD_TYPE2_TO_MASK,
+	},
+	{
+		.label = "ping",
+		.reg = MLXPLAT_CPLD_LPC_REG_WD3_ACT_OFFSET,
+		.mask = MLXPLAT_CPLD_WD_FAN_ACT_MASK,
+		.bit = 4,
+	},
+};
+
+static struct mlxreg_core_platform_data mlxplat_mlxcpld_wd_set_type3[] = {
+	{
+		.data = mlxplat_mlxcpld_wd_main_regs_type3,
+		.counter = ARRAY_SIZE(mlxplat_mlxcpld_wd_main_regs_type3),
+		.version = MLX_WDT_TYPE3,
+		.identity = "mlx-wdt-main",
+	},
+	{
+		.data = mlxplat_mlxcpld_wd_aux_regs_type3,
+		.counter = ARRAY_SIZE(mlxplat_mlxcpld_wd_aux_regs_type3),
+		.version = MLX_WDT_TYPE3,
+		.identity = "mlx-wdt-aux",
+	},
+};
+
 static bool mlxplat_mlxcpld_writeable_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
@@ -1989,8 +2069,10 @@ static bool mlxplat_mlxcpld_writeable_reg(struct device *dev, unsigned int reg)
 	case MLXPLAT_CPLD_LPC_REG_WD1_TMR_OFFSET:
 	case MLXPLAT_CPLD_LPC_REG_WD1_ACT_OFFSET:
 	case MLXPLAT_CPLD_LPC_REG_WD2_TMR_OFFSET:
+	case MLXPLAT_CPLD_LPC_REG_WD2_TLEFT_OFFSET:
 	case MLXPLAT_CPLD_LPC_REG_WD2_ACT_OFFSET:
 	case MLXPLAT_CPLD_LPC_REG_WD3_TMR_OFFSET:
+	case MLXPLAT_CPLD_LPC_REG_WD3_TLEFT_OFFSET:
 	case MLXPLAT_CPLD_LPC_REG_WD3_ACT_OFFSET:
 	case MLXPLAT_CPLD_LPC_REG_PWM1_OFFSET:
 	case MLXPLAT_CPLD_LPC_REG_PWM_CONTROL_OFFSET:
@@ -2601,6 +2683,27 @@ static int mlxplat_mlxcpld_verify_bus_topology(int *nr)
 	return 0;
 }
 
+static int mlxplat_mlxcpld_check_wd_capability(void *regmap)
+{
+	u32 regval;
+	int i, rc;
+
+	rc = regmap_read(regmap, MLXPLAT_CPLD_LPC_REG_PSU_I2C_CAP_OFFSET,
+			 &regval);
+	if (rc)
+		return rc;
+
+	if (!(regval & ~MLXPLAT_CPLD_WD_CPBLTY_MASK)) {
+		for (i = 0; i < ARRAY_SIZE(mlxplat_mlxcpld_wd_set_type3); i++) {
+			if (mlxplat_wd_data[i])
+				mlxplat_wd_data[i] =
+					&mlxplat_mlxcpld_wd_set_type3[i];
+		}
+	}
+
+	return 0;
+}
+
 static int __init mlxplat_init(void)
 {
 	struct mlxplat_priv *priv;
@@ -2733,6 +2836,9 @@ static int __init mlxplat_init(void)
 	}
 
 	/* Add WD drivers. */
+	err = mlxplat_mlxcpld_check_wd_capability(priv->regmap);
+	if (err)
+		goto fail_platform_wd_register;
 	for (j = 0; j < MLXPLAT_CPLD_WD_MAX_DEVS; j++) {
 		if (mlxplat_wd_data[j]) {
 			mlxplat_wd_data[j]->regmap = priv->regmap;

From eee851143bca4422eeee3bb2e104b85537ba449d Mon Sep 17 00:00:00 2001
From: Michael Shych <michaelsh@mellanox.com>
Date: Mon, 4 May 2020 17:14:26 +0300
Subject: [PATCH 206/474] watchdog: mlx-wdt: support new watchdog type with
 longer timeout period

New programmable logic device can have watchdog type 3 implementation.
It's same as Type 2 with extended maximum timeout period.
Maximum timeout is up-to 65535 sec.
Type 3 HW watchdog implementation can exist on all Mellanox systems.
It is differentiated by WD capability bit.

Signed-off-by: Michael Shych <michaelsh@mellanox.com>
Reviewed-by: Vadim Pasternak <vadimp@mellanox.com>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200504141427.17685-4-michaelsh@mellanox.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/mlx_wdt.c | 73 ++++++++++++++++++++++++++++++++------
 1 file changed, 62 insertions(+), 11 deletions(-)

diff --git a/drivers/watchdog/mlx_wdt.c b/drivers/watchdog/mlx_wdt.c
index 03b9ac4b99af..54193369e85c 100644
--- a/drivers/watchdog/mlx_wdt.c
+++ b/drivers/watchdog/mlx_wdt.c
@@ -21,6 +21,7 @@
 #define MLXREG_WDT_CLOCK_SCALE		1000
 #define MLXREG_WDT_MAX_TIMEOUT_TYPE1	32
 #define MLXREG_WDT_MAX_TIMEOUT_TYPE2	255
+#define MLXREG_WDT_MAX_TIMEOUT_TYPE3	65535
 #define MLXREG_WDT_MIN_TIMEOUT		1
 #define MLXREG_WDT_OPTIONS_BASE (WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE | \
 				 WDIOF_SETTIMEOUT)
@@ -49,6 +50,7 @@ struct mlxreg_wdt {
 	int tleft_idx;
 	int ping_idx;
 	int reset_idx;
+	int regmap_val_sz;
 	enum mlxreg_wdt_type wdt_type;
 };
 
@@ -111,7 +113,8 @@ static int mlxreg_wdt_set_timeout(struct watchdog_device *wdd,
 	u32 regval, set_time, hw_timeout;
 	int rc;
 
-	if (wdt->wdt_type == MLX_WDT_TYPE1) {
+	switch (wdt->wdt_type) {
+	case MLX_WDT_TYPE1:
 		rc = regmap_read(wdt->regmap, reg_data->reg, &regval);
 		if (rc)
 			return rc;
@@ -120,14 +123,32 @@ static int mlxreg_wdt_set_timeout(struct watchdog_device *wdd,
 		regval = (regval & reg_data->mask) | hw_timeout;
 		/* Rowndown to actual closest number of sec. */
 		set_time = BIT(hw_timeout) / MLXREG_WDT_CLOCK_SCALE;
-	} else {
+		rc = regmap_write(wdt->regmap, reg_data->reg, regval);
+		break;
+	case MLX_WDT_TYPE2:
 		set_time = timeout;
-		regval = timeout;
+		rc = regmap_write(wdt->regmap, reg_data->reg, timeout);
+		break;
+	case MLX_WDT_TYPE3:
+		/* WD_TYPE3 has 2B set time register */
+		set_time = timeout;
+		if (wdt->regmap_val_sz == 1) {
+			regval = timeout & 0xff;
+			rc = regmap_write(wdt->regmap, reg_data->reg, regval);
+			if (!rc) {
+				regval = (timeout & 0xff00) >> 8;
+				rc = regmap_write(wdt->regmap,
+						reg_data->reg + 1, regval);
+			}
+		} else {
+			rc = regmap_write(wdt->regmap, reg_data->reg, timeout);
+		}
+		break;
+	default:
+		return -EINVAL;
 	}
 
 	wdd->timeout = set_time;
-	rc = regmap_write(wdt->regmap, reg_data->reg, regval);
-
 	if (!rc) {
 		/*
 		 * Restart watchdog with new timeout period
@@ -147,10 +168,25 @@ static unsigned int mlxreg_wdt_get_timeleft(struct watchdog_device *wdd)
 {
 	struct mlxreg_wdt *wdt = watchdog_get_drvdata(wdd);
 	struct mlxreg_core_data *reg_data = &wdt->pdata->data[wdt->tleft_idx];
-	u32 regval;
+	u32 regval, msb, lsb;
 	int rc;
 
-	rc = regmap_read(wdt->regmap, reg_data->reg, &regval);
+	if (wdt->wdt_type == MLX_WDT_TYPE2) {
+		rc = regmap_read(wdt->regmap, reg_data->reg, &regval);
+	} else {
+		/* WD_TYPE3 has 2 byte timeleft register */
+		if (wdt->regmap_val_sz == 1) {
+			rc = regmap_read(wdt->regmap, reg_data->reg, &lsb);
+			if (!rc) {
+				rc = regmap_read(wdt->regmap,
+						reg_data->reg + 1, &msb);
+				regval = (msb & 0xff) << 8 | (lsb & 0xff);
+			}
+		} else {
+			rc = regmap_read(wdt->regmap, reg_data->reg, &regval);
+		}
+	}
+
 	/* Return 0 timeleft in case of failure register read. */
 	return rc == 0 ? regval : 0;
 }
@@ -212,13 +248,23 @@ static void mlxreg_wdt_config(struct mlxreg_wdt *wdt,
 		wdt->wdd.info = &mlxreg_wdt_aux_info;
 
 	wdt->wdt_type = pdata->version;
-	if (wdt->wdt_type == MLX_WDT_TYPE2) {
-		wdt->wdd.ops = &mlxreg_wdt_ops_type2;
-		wdt->wdd.max_timeout = MLXREG_WDT_MAX_TIMEOUT_TYPE2;
-	} else {
+	switch (wdt->wdt_type) {
+	case MLX_WDT_TYPE1:
 		wdt->wdd.ops = &mlxreg_wdt_ops_type1;
 		wdt->wdd.max_timeout = MLXREG_WDT_MAX_TIMEOUT_TYPE1;
+		break;
+	case MLX_WDT_TYPE2:
+		wdt->wdd.ops = &mlxreg_wdt_ops_type2;
+		wdt->wdd.max_timeout = MLXREG_WDT_MAX_TIMEOUT_TYPE2;
+		break;
+	case MLX_WDT_TYPE3:
+		wdt->wdd.ops = &mlxreg_wdt_ops_type2;
+		wdt->wdd.max_timeout = MLXREG_WDT_MAX_TIMEOUT_TYPE3;
+		break;
+	default:
+		break;
 	}
+
 	wdt->wdd.min_timeout = MLXREG_WDT_MIN_TIMEOUT;
 }
 
@@ -249,6 +295,11 @@ static int mlxreg_wdt_probe(struct platform_device *pdev)
 
 	wdt->wdd.parent = dev;
 	wdt->regmap = pdata->regmap;
+	rc = regmap_get_val_bytes(wdt->regmap);
+	if (rc < 0)
+		return -EINVAL;
+
+	wdt->regmap_val_sz = rc;
 	mlxreg_wdt_config(wdt, pdata);
 
 	if ((pdata->features & MLXREG_CORE_WD_FEATURE_NOWAYOUT))

From d6e6d5627f0aaa16d6b6e94238d62a594a35b5ce Mon Sep 17 00:00:00 2001
From: Michael Shych <michaelsh@mellanox.com>
Date: Mon, 4 May 2020 17:14:27 +0300
Subject: [PATCH 207/474] docs: watchdog: mlx-wdt: Add description of new
 watchdog type 3

Add documentation with details of new type of Mellanox watchdog driver.

Signed-off-by: Michael Shych <michaelsh@mellanox.com>
Reviewed-by: Vadim Pasternak <vadimp@mellanox.com>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200504141427.17685-5-michaelsh@mellanox.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 Documentation/watchdog/mlx-wdt.rst | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/watchdog/mlx-wdt.rst b/Documentation/watchdog/mlx-wdt.rst
index bf5bafac47f0..35e690dea9db 100644
--- a/Documentation/watchdog/mlx-wdt.rst
+++ b/Documentation/watchdog/mlx-wdt.rst
@@ -24,10 +24,19 @@ Type 2:
   Maximum timeout is 255 sec.
   Get time-left is supported.
 
+Type 3:
+  Same as Type 2 with extended maximum timeout period.
+  Maximum timeout is 65535 sec.
+
 Type 1 HW watchdog implementation exist in old systems and
 all new systems have type 2 HW watchdog.
 Two types of HW implementation have also different register map.
 
+Type 3 HW watchdog implementation can exist on all Mellanox systems
+with new programmer logic device.
+It's differentiated by WD capability bit.
+Old systems still have only one main watchdog.
+
 Mellanox system can have 2 watchdogs: main and auxiliary.
 Main and auxiliary watchdog devices can be enabled together
 on the same system.
@@ -54,3 +63,4 @@ The driver checks during initialization if the previous system reset
 was done by the watchdog. If yes, it makes a notification about this event.
 
 Access to HW registers is performed through a generic regmap interface.
+Programmable logic device registers have little-endian order.

From 0be01476dd527dfa00976911208332c706a1b752 Mon Sep 17 00:00:00 2001
From: Bumsik Kim <kbumsik@gmail.com>
Date: Fri, 29 May 2020 10:24:28 +0900
Subject: [PATCH 208/474] watchdog: test_bit() => watchdog_active()

Use the dedicated function watchdog_active()
instead of the generic test_bit() function.

It is done using the following Coccinelle script:

@@
identifier wdd;
@@
- test_bit(WDOG_ACTIVE, &wdd->status)
+ watchdog_active(wdd)

Signed-off-by: Bumsik Kim <k.bumsik@gmail.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200529012428.84684-1-k.bumsik@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/watchdog_dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index 7e4cd34a8c20..3ae608d78af2 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -916,7 +916,7 @@ static int watchdog_release(struct inode *inode, struct file *file)
 	 * or if WDIOF_MAGICCLOSE is not set. If nowayout was set then
 	 * watchdog_stop will fail.
 	 */
-	if (!test_bit(WDOG_ACTIVE, &wdd->status))
+	if (!watchdog_active(wdd))
 		err = 0;
 	else if (test_and_clear_bit(_WDOG_ALLOW_RELEASE, &wd_data->status) ||
 		 !(wdd->info->options & WDIOF_MAGICCLOSE))

From ff01cb1ca1f9e02e54e562bb97999e4bf1726a9e Mon Sep 17 00:00:00 2001
From: Martin Wu <wuyan@allwinnertech.com>
Date: Fri, 29 May 2020 17:45:14 +0800
Subject: [PATCH 209/474] watchdog: sunxi_wdt: fix improper error exit code

sunxi_wdt_probe() should return -ENOMEM when devm_kzalloc() fails.

Signed-off-by: Martin Wu <wuyan@allwinnertech.com>
Signed-off-by: Frank Lee <frank@allwinnertech.com>
Acked-by: Maxime Ripard <mripard@kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200529094514.26374-1-frank@allwinnertech.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/sunxi_wdt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/sunxi_wdt.c b/drivers/watchdog/sunxi_wdt.c
index 5f05a45ac187..b50757882a98 100644
--- a/drivers/watchdog/sunxi_wdt.c
+++ b/drivers/watchdog/sunxi_wdt.c
@@ -235,7 +235,7 @@ static int sunxi_wdt_probe(struct platform_device *pdev)
 
 	sunxi_wdt = devm_kzalloc(dev, sizeof(*sunxi_wdt), GFP_KERNEL);
 	if (!sunxi_wdt)
-		return -EINVAL;
+		return -ENOMEM;
 
 	sunxi_wdt->wdt_regs = of_device_get_match_data(dev);
 	if (!sunxi_wdt->wdt_regs)

From fd998972458f06d3fadbf4e55a3725c4edc17c12 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 25 May 2020 15:31:04 +0800
Subject: [PATCH 210/474] watchdog: bcm_kona_wdt: Use correct return value for
 bcm_kona_wdt_probe()

When call function devm_platform_ioremap_resource(), we should use IS_ERR()
to check the return value and return PTR_ERR() if failed.

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/1590391864-308-1-git-send-email-yangtiezhu@loongson.cn
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/bcm_kona_wdt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/bcm_kona_wdt.c b/drivers/watchdog/bcm_kona_wdt.c
index eb850a8d19df..8237c4e9c2a0 100644
--- a/drivers/watchdog/bcm_kona_wdt.c
+++ b/drivers/watchdog/bcm_kona_wdt.c
@@ -279,7 +279,7 @@ static int bcm_kona_wdt_probe(struct platform_device *pdev)
 
 	wdt->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(wdt->base))
-		return -ENODEV;
+		return PTR_ERR(wdt->base);
 
 	wdt->resolution = SECWDOG_DEFAULT_RESOLUTION;
 	ret = bcm_kona_wdt_set_resolution_reg(wdt);

From 893c3d82b425d8d448da030c80420072ff4edbf1 Mon Sep 17 00:00:00 2001
From: Wang Qing <wangqing@vivo.com>
Date: Fri, 12 Jun 2020 15:03:04 +0800
Subject: [PATCH 211/474] watchdog: Use kobj_to_dev() API

Use kobj_to_dev() API instead of container_of().

Signed-off-by: Wang Qing <wangqing@vivo.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/1591945384-14587-1-git-send-email-wangqing@vivo.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/watchdog_dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index 3ae608d78af2..de02d90a4878 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -587,7 +587,7 @@ static DEVICE_ATTR_RW(pretimeout_governor);
 static umode_t wdt_is_visible(struct kobject *kobj, struct attribute *attr,
 				int n)
 {
-	struct device *dev = container_of(kobj, struct device, kobj);
+	struct device *dev = kobj_to_dev(kobj);
 	struct watchdog_device *wdd = dev_get_drvdata(dev);
 	umode_t mode = attr->mode;
 

From 04daa8c049bc0cd4747d671d8b855f3d0fa39997 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Tue, 2 Jun 2020 07:21:04 +0200
Subject: [PATCH 212/474] MAINTAINERS: rectify entry in ARM SMC WATCHDOG DRIVER

Commit 5c24a28b4eb8 ("dt-bindings: watchdog: Add ARM smc wdt for mt8173
watchdog") added the new ARM SMC WATCHDOG DRIVER entry in MAINTAINERS, but
slipped in a minor mistake.

Luckily, ./scripts/get_maintainer.pl --self-test=patterns complains:

  warning: no file matches F: devicetree/bindings/watchdog/arm-smc-wdt.yaml

Update file entry to intended file location.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Julius Werner <jwerner@chromium.org>
Reviewed-by: Evan Benn <evanbenn@chromium.org>
Link: https://lore.kernel.org/r/20200602052104.7795-1-lukas.bulwahn@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index f0569cf304ca..284c14fe080c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1489,7 +1489,7 @@ ARM SMC WATCHDOG DRIVER
 M:	Julius Werner <jwerner@chromium.org>
 R:	Evan Benn <evanbenn@chromium.org>
 S:	Maintained
-F:	devicetree/bindings/watchdog/arm-smc-wdt.yaml
+F:	Documentation/devicetree/bindings/watchdog/arm-smc-wdt.yaml
 F:	drivers/watchdog/arm_smc_wdt.c
 
 ARM SMMU DRIVERS

From 9807a8884143148f2ee5a882d6273806403e9345 Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Sat, 30 May 2020 10:35:51 +0300
Subject: [PATCH 213/474] dt-bindings: watchdog: Convert DW WDT binding to DT
 schema

Modern device tree bindings are supposed to be created as YAML-files
in accordance with dt-schema. This commit replaces the DW Watchdog
legacy bare text bindings with YAML file. As before the binding states
that the corresponding dts node is supposed to have a registers
range, a watchdog timer references clock source, optional reset line and
pre-timeout interrupt.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Cc: Alexey Malahov <Alexey.Malahov@baikalelectronics.ru>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: linux-mips@vger.kernel.org
Link: https://lore.kernel.org/r/20200530073557.22661-2-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 .../devicetree/bindings/watchdog/dw_wdt.txt   | 24 ---------
 .../bindings/watchdog/snps,dw-wdt.yaml        | 50 +++++++++++++++++++
 2 files changed, 50 insertions(+), 24 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/watchdog/dw_wdt.txt
 create mode 100644 Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml

diff --git a/Documentation/devicetree/bindings/watchdog/dw_wdt.txt b/Documentation/devicetree/bindings/watchdog/dw_wdt.txt
deleted file mode 100644
index eb0914420c7c..000000000000
--- a/Documentation/devicetree/bindings/watchdog/dw_wdt.txt
+++ /dev/null
@@ -1,24 +0,0 @@
-Synopsys Designware Watchdog Timer
-
-Required Properties:
-
-- compatible	: Should contain "snps,dw-wdt"
-- reg		: Base address and size of the watchdog timer registers.
-- clocks	: phandle + clock-specifier for the clock that drives the
-		watchdog timer.
-
-Optional Properties:
-
-- interrupts	: The interrupt used for the watchdog timeout warning.
-- resets	: phandle pointing to the system reset controller with
-		line index for the watchdog.
-
-Example:
-
-	watchdog0: wd@ffd02000 {
-		compatible = "snps,dw-wdt";
-		reg = <0xffd02000 0x1000>;
-		interrupts = <0 171 4>;
-		clocks = <&per_base_clk>;
-		resets = <&rst WDT0_RESET>;
-	};
diff --git a/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml b/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml
new file mode 100644
index 000000000000..4f6944756ab4
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml
@@ -0,0 +1,50 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/watchdog/snps,dw-wdt.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Synopsys Designware Watchdog Timer
+
+allOf:
+  - $ref: "watchdog.yaml#"
+
+maintainers:
+  - Jamie Iles <jamie@jamieiles.com>
+
+properties:
+  compatible:
+    const: snps,dw-wdt
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    description: DW Watchdog pre-timeout interrupt
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Watchdog timer reference clock
+
+  resets:
+    description: Phandle to the DW Watchdog reset lane
+    maxItems: 1
+
+unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+  - clocks
+
+examples:
+  - |
+    watchdog@ffd02000 {
+      compatible = "snps,dw-wdt";
+      reg = <0xffd02000 0x1000>;
+      interrupts = <0 171 4>;
+      clocks = <&per_base_clk>;
+      resets = <&wdt_rst>;
+    };
+...

From 5b4f68f808ff96a0a48456ff8da250a2caf3f545 Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Sat, 30 May 2020 10:35:52 +0300
Subject: [PATCH 214/474] dt-bindings: watchdog: dw-wdt: Support devices with
 asynch clocks

DW Watchdog IP core can be synthesised with asynchronous timer/APB
clocks support (WDT_ASYNC_CLK_MODE_ENABLE == 1). In this case
separate clock signals are supposed to be used to feed watchdog timer
and APB interface of the device. Let's update the DW Watchdog DT node
schema so it would support the optional APB3 bus clock specified along
with the mandatory watchdog timer reference clock.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Cc: Alexey Malahov <Alexey.Malahov@baikalelectronics.ru>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: linux-mips@vger.kernel.org
Link: https://lore.kernel.org/r/20200530073557.22661-3-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 .../devicetree/bindings/watchdog/snps,dw-wdt.yaml         | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml b/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml
index 4f6944756ab4..5bf6dc6377f3 100644
--- a/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml
@@ -24,8 +24,16 @@ properties:
     maxItems: 1
 
   clocks:
+    minItems: 1
     items:
       - description: Watchdog timer reference clock
+      - description: APB3 interface clock
+
+  clock-names:
+    minItems: 1
+    items:
+      - const: tclk
+      - const: pclk
 
   resets:
     description: Phandle to the DW Watchdog reset lane

From 4ce4e7fdc3c924ea3e6d5d68178127b46568d8df Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Sat, 30 May 2020 10:35:53 +0300
Subject: [PATCH 215/474] dt-bindings: watchdog: dw-wdt: Add watchdog TOPs
 array property

In case if DW Watchdog IP core is built with WDT_USE_FIX_TOP == false,
a custom timeout periods are used to preset the timer counter. In
this case that periods should be specified in a new "snps,watchdog-tops"
property of the DW watchdog dts node.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Cc: Alexey Malahov <Alexey.Malahov@baikalelectronics.ru>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: linux-mips@vger.kernel.org
Link: https://lore.kernel.org/r/20200530073557.22661-4-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 .../bindings/watchdog/snps,dw-wdt.yaml        | 32 +++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml b/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml
index 5bf6dc6377f3..d9fc7bb851b1 100644
--- a/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml
@@ -39,6 +39,23 @@ properties:
     description: Phandle to the DW Watchdog reset lane
     maxItems: 1
 
+  snps,watchdog-tops:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    description: |
+      DW APB Watchdog custom timer intervals - Timeout Period ranges (TOPs).
+      Each TOP is a number loaded into the watchdog counter at the moment of
+      the timer restart. The counter decrementing happens each tick of the
+      reference clock. Therefore the TOPs array is equivalent to an array of
+      the timer expiration intervals supported by the DW APB Watchdog. Note
+      DW APB Watchdog IP-core might be synthesized with fixed TOP values,
+      in which case this property is unnecessary with default TOPs utilized.
+    default: [0x0001000 0x0002000 0x0004000 0x0008000
+      0x0010000 0x0020000 0x0040000 0x0080000
+      0x0100000 0x0200000 0x0400000 0x0800000
+      0x1000000 0x2000000 0x4000000 0x8000000]
+    minItems: 16
+    maxItems: 16
+
 unevaluatedProperties: false
 
 required:
@@ -55,4 +72,19 @@ examples:
       clocks = <&per_base_clk>;
       resets = <&wdt_rst>;
     };
+
+  - |
+    watchdog@ffd02000 {
+      compatible = "snps,dw-wdt";
+      reg = <0xffd02000 0x1000>;
+      interrupts = <0 171 4>;
+      clocks = <&per_base_clk>;
+      clock-names = "tclk";
+      snps,watchdog-tops = <0x000000FF 0x000001FF 0x000003FF
+                            0x000007FF 0x0000FFFF 0x0001FFFF
+                            0x0003FFFF 0x0007FFFF 0x000FFFFF
+                            0x001FFFFF 0x003FFFFF 0x007FFFFF
+                            0x00FFFFFF 0x01FFFFFF 0x03FFFFFF
+                            0x07FFFFFF>;
+    };
 ...

From 86445535887e580036d0094a849126703a33fd62 Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Sat, 30 May 2020 10:35:54 +0300
Subject: [PATCH 216/474] watchdog: dw_wdt: Support devices with non-fixed TOP
 values

In case if the DW Watchdog IP core is synthesised with
WDT_USE_FIX_TOP == false, the TOP interval indexes make the device
to load a custom periods to the counter. These periods are hardwired
at the IP synthesis stage and can be within [2^8, 2^(WDT_CNT_WIDTH - 1)].
Alas their values can't be detected at runtime and must be somehow
supplied to the driver so one could properly determine the watchdog
timeout intervals. For this purpose we suggest to have a vendor-
specific dts property "snps,watchdog-tops" utilized, which would
provide an array of sixteen counter values. At device probe stage they
will be used to initialize the watchdog device timeouts determined
from the array values and current clocks source rate.

In order to have custom TOP values supported the driver must be
altered in the following way. First of all the fixed-top values
ready-to-use array must be determined for compatibility with currently
supported devices, which were synthesised with WDT_USE_FIX_TOP == true.
It will be used if either fixed TOP feature is detected being enabled or
no custom TOPs are fetched from the device dt node. Secondly at the probe
stage we must initialize an array of the watchdog timeouts corresponding
to the detected TOPs list and the reference clock rate. For generality the
procedure of initialization is designed in a way to support the TOPs array
with no limitations on the items order or value. Finally the watchdog
period search methods should be altered to support the new timeouts data
structure.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Cc: Alexey Malahov <Alexey.Malahov@baikalelectronics.ru>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: linux-mips@vger.kernel.org
Cc: devicetree@vger.kernel.org
Link: https://lore.kernel.org/r/20200530073557.22661-5-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/dw_wdt.c | 191 +++++++++++++++++++++++++++++++++-----
 1 file changed, 167 insertions(+), 24 deletions(-)

diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c
index fba21de2bbad..693c0d1fd796 100644
--- a/drivers/watchdog/dw_wdt.c
+++ b/drivers/watchdog/dw_wdt.c
@@ -13,6 +13,8 @@
  */
 
 #include <linux/bitops.h>
+#include <linux/limits.h>
+#include <linux/kernel.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/err.h>
@@ -34,21 +36,40 @@
 #define WDOG_CURRENT_COUNT_REG_OFFSET	    0x08
 #define WDOG_COUNTER_RESTART_REG_OFFSET     0x0c
 #define WDOG_COUNTER_RESTART_KICK_VALUE	    0x76
+#define WDOG_COMP_PARAMS_1_REG_OFFSET       0xf4
+#define WDOG_COMP_PARAMS_1_USE_FIX_TOP      BIT(6)
 
-/* The maximum TOP (timeout period) value that can be set in the watchdog. */
-#define DW_WDT_MAX_TOP		15
+/* There are sixteen TOPs (timeout periods) that can be set in the watchdog. */
+#define DW_WDT_NUM_TOPS		16
+#define DW_WDT_FIX_TOP(_idx)	(1U << (16 + _idx))
 
 #define DW_WDT_DEFAULT_SECONDS	30
 
+static const u32 dw_wdt_fix_tops[DW_WDT_NUM_TOPS] = {
+	DW_WDT_FIX_TOP(0), DW_WDT_FIX_TOP(1), DW_WDT_FIX_TOP(2),
+	DW_WDT_FIX_TOP(3), DW_WDT_FIX_TOP(4), DW_WDT_FIX_TOP(5),
+	DW_WDT_FIX_TOP(6), DW_WDT_FIX_TOP(7), DW_WDT_FIX_TOP(8),
+	DW_WDT_FIX_TOP(9), DW_WDT_FIX_TOP(10), DW_WDT_FIX_TOP(11),
+	DW_WDT_FIX_TOP(12), DW_WDT_FIX_TOP(13), DW_WDT_FIX_TOP(14),
+	DW_WDT_FIX_TOP(15)
+};
+
 static bool nowayout = WATCHDOG_NOWAYOUT;
 module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
 		 "(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
+struct dw_wdt_timeout {
+	u32 top_val;
+	unsigned int sec;
+	unsigned int msec;
+};
+
 struct dw_wdt {
 	void __iomem		*regs;
 	struct clk		*clk;
 	unsigned long		rate;
+	struct dw_wdt_timeout	timeouts[DW_WDT_NUM_TOPS];
 	struct watchdog_device	wdd;
 	struct reset_control	*rst;
 	/* Save/restore */
@@ -64,20 +85,66 @@ static inline int dw_wdt_is_enabled(struct dw_wdt *dw_wdt)
 		WDOG_CONTROL_REG_WDT_EN_MASK;
 }
 
-static inline int dw_wdt_top_in_seconds(struct dw_wdt *dw_wdt, unsigned top)
+static unsigned int dw_wdt_find_best_top(struct dw_wdt *dw_wdt,
+					 unsigned int timeout, u32 *top_val)
 {
+	int idx;
+
 	/*
-	 * There are 16 possible timeout values in 0..15 where the number of
-	 * cycles is 2 ^ (16 + i) and the watchdog counts down.
+	 * Find a TOP with timeout greater or equal to the requested number.
+	 * Note we'll select a TOP with maximum timeout if the requested
+	 * timeout couldn't be reached.
 	 */
-	return (1U << (16 + top)) / dw_wdt->rate;
+	for (idx = 0; idx < DW_WDT_NUM_TOPS; ++idx) {
+		if (dw_wdt->timeouts[idx].sec >= timeout)
+			break;
+	}
+
+	if (idx == DW_WDT_NUM_TOPS)
+		--idx;
+
+	*top_val = dw_wdt->timeouts[idx].top_val;
+
+	return dw_wdt->timeouts[idx].sec;
 }
 
-static int dw_wdt_get_top(struct dw_wdt *dw_wdt)
+static unsigned int dw_wdt_get_min_timeout(struct dw_wdt *dw_wdt)
 {
-	int top = readl(dw_wdt->regs + WDOG_TIMEOUT_RANGE_REG_OFFSET) & 0xF;
+	int idx;
 
-	return dw_wdt_top_in_seconds(dw_wdt, top);
+	/*
+	 * We'll find a timeout greater or equal to one second anyway because
+	 * the driver probe would have failed if there was none.
+	 */
+	for (idx = 0; idx < DW_WDT_NUM_TOPS; ++idx) {
+		if (dw_wdt->timeouts[idx].sec)
+			break;
+	}
+
+	return dw_wdt->timeouts[idx].sec;
+}
+
+static unsigned int dw_wdt_get_max_timeout_ms(struct dw_wdt *dw_wdt)
+{
+	struct dw_wdt_timeout *timeout = &dw_wdt->timeouts[DW_WDT_NUM_TOPS - 1];
+	u64 msec;
+
+	msec = (u64)timeout->sec * MSEC_PER_SEC + timeout->msec;
+
+	return msec < UINT_MAX ? msec : UINT_MAX;
+}
+
+static unsigned int dw_wdt_get_timeout(struct dw_wdt *dw_wdt)
+{
+	int top_val = readl(dw_wdt->regs + WDOG_TIMEOUT_RANGE_REG_OFFSET) & 0xF;
+	int idx;
+
+	for (idx = 0; idx < DW_WDT_NUM_TOPS; ++idx) {
+		if (dw_wdt->timeouts[idx].top_val == top_val)
+			break;
+	}
+
+	return dw_wdt->timeouts[idx].sec;
 }
 
 static int dw_wdt_ping(struct watchdog_device *wdd)
@@ -93,17 +160,10 @@ static int dw_wdt_ping(struct watchdog_device *wdd)
 static int dw_wdt_set_timeout(struct watchdog_device *wdd, unsigned int top_s)
 {
 	struct dw_wdt *dw_wdt = to_dw_wdt(wdd);
-	int i, top_val = DW_WDT_MAX_TOP;
+	unsigned int timeout;
+	u32 top_val;
 
-	/*
-	 * Iterate over the timeout values until we find the closest match. We
-	 * always look for >=.
-	 */
-	for (i = 0; i <= DW_WDT_MAX_TOP; ++i)
-		if (dw_wdt_top_in_seconds(dw_wdt, i) >= top_s) {
-			top_val = i;
-			break;
-		}
+	timeout = dw_wdt_find_best_top(dw_wdt, top_s, &top_val);
 
 	/*
 	 * Set the new value in the watchdog.  Some versions of dw_wdt
@@ -120,7 +180,7 @@ static int dw_wdt_set_timeout(struct watchdog_device *wdd, unsigned int top_s)
 	 * wdd->max_hw_heartbeat_ms
 	 */
 	if (top_s * 1000 <= wdd->max_hw_heartbeat_ms)
-		wdd->timeout = dw_wdt_top_in_seconds(dw_wdt, top_val);
+		wdd->timeout = timeout;
 	else
 		wdd->timeout = top_s;
 
@@ -238,6 +298,86 @@ static int dw_wdt_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(dw_wdt_pm_ops, dw_wdt_suspend, dw_wdt_resume);
 
+/*
+ * In case if DW WDT IP core is synthesized with fixed TOP feature disabled the
+ * TOPs array can be arbitrary ordered with nearly any sixteen uint numbers
+ * depending on the system engineer imagination. The next method handles the
+ * passed TOPs array to pre-calculate the effective timeouts and to sort the
+ * TOP items out in the ascending order with respect to the timeouts.
+ */
+
+static void dw_wdt_handle_tops(struct dw_wdt *dw_wdt, const u32 *tops)
+{
+	struct dw_wdt_timeout tout, *dst;
+	int val, tidx;
+	u64 msec;
+
+	/*
+	 * We walk over the passed TOPs array and calculate corresponding
+	 * timeouts in seconds and milliseconds. The milliseconds granularity
+	 * is needed to distinguish the TOPs with very close timeouts and to
+	 * set the watchdog max heartbeat setting further.
+	 */
+	for (val = 0; val < DW_WDT_NUM_TOPS; ++val) {
+		tout.top_val = val;
+		tout.sec = tops[val] / dw_wdt->rate;
+		msec = (u64)tops[val] * MSEC_PER_SEC;
+		do_div(msec, dw_wdt->rate);
+		tout.msec = msec - ((u64)tout.sec * MSEC_PER_SEC);
+
+		/*
+		 * Find a suitable place for the current TOP in the timeouts
+		 * array so that the list is remained in the ascending order.
+		 */
+		for (tidx = 0; tidx < val; ++tidx) {
+			dst = &dw_wdt->timeouts[tidx];
+			if (tout.sec > dst->sec || (tout.sec == dst->sec &&
+			    tout.msec >= dst->msec))
+				continue;
+			else
+				swap(*dst, tout);
+		}
+
+		dw_wdt->timeouts[val] = tout;
+	}
+}
+
+static int dw_wdt_init_timeouts(struct dw_wdt *dw_wdt, struct device *dev)
+{
+	u32 data, of_tops[DW_WDT_NUM_TOPS];
+	const u32 *tops;
+	int ret;
+
+	/*
+	 * Retrieve custom or fixed counter values depending on the
+	 * WDT_USE_FIX_TOP flag found in the component specific parameters
+	 * #1 register.
+	 */
+	data = readl(dw_wdt->regs + WDOG_COMP_PARAMS_1_REG_OFFSET);
+	if (data & WDOG_COMP_PARAMS_1_USE_FIX_TOP) {
+		tops = dw_wdt_fix_tops;
+	} else {
+		ret = of_property_read_variable_u32_array(dev_of_node(dev),
+			"snps,watchdog-tops", of_tops, DW_WDT_NUM_TOPS,
+			DW_WDT_NUM_TOPS);
+		if (ret < 0) {
+			dev_warn(dev, "No valid TOPs array specified\n");
+			tops = dw_wdt_fix_tops;
+		} else {
+			tops = of_tops;
+		}
+	}
+
+	/* Convert the specified TOPs into an array of watchdog timeouts. */
+	dw_wdt_handle_tops(dw_wdt, tops);
+	if (!dw_wdt->timeouts[DW_WDT_NUM_TOPS - 1].sec) {
+		dev_err(dev, "No any valid TOP detected\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int dw_wdt_drv_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -275,12 +415,15 @@ static int dw_wdt_drv_probe(struct platform_device *pdev)
 
 	reset_control_deassert(dw_wdt->rst);
 
+	ret = dw_wdt_init_timeouts(dw_wdt, dev);
+	if (ret)
+		goto out_disable_clk;
+
 	wdd = &dw_wdt->wdd;
 	wdd->info = &dw_wdt_ident;
 	wdd->ops = &dw_wdt_ops;
-	wdd->min_timeout = 1;
-	wdd->max_hw_heartbeat_ms =
-		dw_wdt_top_in_seconds(dw_wdt, DW_WDT_MAX_TOP) * 1000;
+	wdd->min_timeout = dw_wdt_get_min_timeout(dw_wdt);
+	wdd->max_hw_heartbeat_ms = dw_wdt_get_max_timeout_ms(dw_wdt);
 	wdd->parent = dev;
 
 	watchdog_set_drvdata(wdd, dw_wdt);
@@ -293,7 +436,7 @@ static int dw_wdt_drv_probe(struct platform_device *pdev)
 	 * devicetree.
 	 */
 	if (dw_wdt_is_enabled(dw_wdt)) {
-		wdd->timeout = dw_wdt_get_top(dw_wdt);
+		wdd->timeout = dw_wdt_get_timeout(dw_wdt);
 		set_bit(WDOG_HW_RUNNING, &wdd->status);
 	} else {
 		wdd->timeout = DW_WDT_DEFAULT_SECONDS;

From a16f58bf154cdf589cf72cb1596b6217da5872a1 Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Sat, 30 May 2020 10:35:55 +0300
Subject: [PATCH 217/474] watchdog: dw_wdt: Support devices with asynch clocks

DW Watchdog IP core can be synthesised with asynchronous timer/APB
clocks support (WDT_ASYNC_CLK_MODE_ENABLE == 1). In this case
separate clock signals are supposed to be used to feed watchdog timer
and APB interface of the device. Currently the driver supports
the synchronous mode only. Since there is no way to determine which
mode was actually activated for device from its registers, we have to
rely on the platform device configuration data. If optional "pclk"
clock source is supplied, we consider the device working in asynchronous
mode, otherwise the driver falls back to the synchronous configuration.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Cc: Alexey Malahov <Alexey.Malahov@baikalelectronics.ru>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: linux-mips@vger.kernel.org
Cc: devicetree@vger.kernel.org
Link: https://lore.kernel.org/r/20200530073557.22661-6-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/dw_wdt.c | 48 +++++++++++++++++++++++++++++++++++----
 1 file changed, 43 insertions(+), 5 deletions(-)

diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c
index 693c0d1fd796..efbc36872670 100644
--- a/drivers/watchdog/dw_wdt.c
+++ b/drivers/watchdog/dw_wdt.c
@@ -68,6 +68,7 @@ struct dw_wdt_timeout {
 struct dw_wdt {
 	void __iomem		*regs;
 	struct clk		*clk;
+	struct clk		*pclk;
 	unsigned long		rate;
 	struct dw_wdt_timeout	timeouts[DW_WDT_NUM_TOPS];
 	struct watchdog_device	wdd;
@@ -274,6 +275,7 @@ static int dw_wdt_suspend(struct device *dev)
 	dw_wdt->control = readl(dw_wdt->regs + WDOG_CONTROL_REG_OFFSET);
 	dw_wdt->timeout = readl(dw_wdt->regs + WDOG_TIMEOUT_RANGE_REG_OFFSET);
 
+	clk_disable_unprepare(dw_wdt->pclk);
 	clk_disable_unprepare(dw_wdt->clk);
 
 	return 0;
@@ -287,6 +289,12 @@ static int dw_wdt_resume(struct device *dev)
 	if (err)
 		return err;
 
+	err = clk_prepare_enable(dw_wdt->pclk);
+	if (err) {
+		clk_disable_unprepare(dw_wdt->clk);
+		return err;
+	}
+
 	writel(dw_wdt->timeout, dw_wdt->regs + WDOG_TIMEOUT_RANGE_REG_OFFSET);
 	writel(dw_wdt->control, dw_wdt->regs + WDOG_CONTROL_REG_OFFSET);
 
@@ -393,9 +401,18 @@ static int dw_wdt_drv_probe(struct platform_device *pdev)
 	if (IS_ERR(dw_wdt->regs))
 		return PTR_ERR(dw_wdt->regs);
 
-	dw_wdt->clk = devm_clk_get(dev, NULL);
-	if (IS_ERR(dw_wdt->clk))
-		return PTR_ERR(dw_wdt->clk);
+	/*
+	 * Try to request the watchdog dedicated timer clock source. It must
+	 * be supplied if asynchronous mode is enabled. Otherwise fallback
+	 * to the common timer/bus clocks configuration, in which the very
+	 * first found clock supply both timer and APB signals.
+	 */
+	dw_wdt->clk = devm_clk_get(dev, "tclk");
+	if (IS_ERR(dw_wdt->clk)) {
+		dw_wdt->clk = devm_clk_get(dev, NULL);
+		if (IS_ERR(dw_wdt->clk))
+			return PTR_ERR(dw_wdt->clk);
+	}
 
 	ret = clk_prepare_enable(dw_wdt->clk);
 	if (ret)
@@ -407,10 +424,27 @@ static int dw_wdt_drv_probe(struct platform_device *pdev)
 		goto out_disable_clk;
 	}
 
+	/*
+	 * Request APB clock if device is configured with async clocks mode.
+	 * In this case both tclk and pclk clocks are supposed to be specified.
+	 * Alas we can't know for sure whether async mode was really activated,
+	 * so the pclk phandle reference is left optional. If it couldn't be
+	 * found we consider the device configured in synchronous clocks mode.
+	 */
+	dw_wdt->pclk = devm_clk_get_optional(dev, "pclk");
+	if (IS_ERR(dw_wdt->pclk)) {
+		ret = PTR_ERR(dw_wdt->pclk);
+		goto out_disable_clk;
+	}
+
+	ret = clk_prepare_enable(dw_wdt->pclk);
+	if (ret)
+		goto out_disable_clk;
+
 	dw_wdt->rst = devm_reset_control_get_optional_shared(&pdev->dev, NULL);
 	if (IS_ERR(dw_wdt->rst)) {
 		ret = PTR_ERR(dw_wdt->rst);
-		goto out_disable_clk;
+		goto out_disable_pclk;
 	}
 
 	reset_control_deassert(dw_wdt->rst);
@@ -449,10 +483,13 @@ static int dw_wdt_drv_probe(struct platform_device *pdev)
 
 	ret = watchdog_register_device(wdd);
 	if (ret)
-		goto out_disable_clk;
+		goto out_disable_pclk;
 
 	return 0;
 
+out_disable_pclk:
+	clk_disable_unprepare(dw_wdt->pclk);
+
 out_disable_clk:
 	clk_disable_unprepare(dw_wdt->clk);
 	return ret;
@@ -464,6 +501,7 @@ static int dw_wdt_drv_remove(struct platform_device *pdev)
 
 	watchdog_unregister_device(&dw_wdt->wdd);
 	reset_control_assert(dw_wdt->rst);
+	clk_disable_unprepare(dw_wdt->pclk);
 	clk_disable_unprepare(dw_wdt->clk);
 
 	return 0;

From 46a1946314bfe7db46e1f28e0ce2b6f701fae50b Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Sat, 30 May 2020 10:35:56 +0300
Subject: [PATCH 218/474] watchdog: dw_wdt: Add pre-timeouts support

DW Watchdog can rise an interrupt in case if IRQ request mode is enabled
and timer reaches the zero value. In this case the IRQ lane is left
pending until either the next watchdog kick event (watchdog restart) or
until the WDT_EOI register is read or the device/system reset. This
interface can be used to implement the pre-timeout functionality
optionally provided by the Linux kernel watchdog devices.

IRQ mode provides a two stages timeout interface. It means the IRQ is
raised when the counter reaches zero, while the system reset occurs only
after subsequent timeout if the timer restart is not performed. Due to
this peculiarity the pre-timeout value is actually set to the achieved
hardware timeout, while the real watchdog timeout is considered to be
twice as much of it. This applies a significant limitation on the
pre-timeout values, so current implementation supports either zero value,
which disables the pre-timeout events, or non-zero values, which imply
the pre-timeout to be at least half of the current watchdog timeout.

Note that we ask the interrupt controller to detect the rising-edge
pre-timeout interrupts to prevent the high-level-IRQs flood, since
if the pre-timeout happens, the IRQ lane will be left pending until
it's cleared by the timer restart.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Cc: Alexey Malahov <Alexey.Malahov@baikalelectronics.ru>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: linux-mips@vger.kernel.org
Cc: devicetree@vger.kernel.org
Link: https://lore.kernel.org/r/20200530073557.22661-7-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/dw_wdt.c | 138 +++++++++++++++++++++++++++++++++++---
 1 file changed, 130 insertions(+), 8 deletions(-)

diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c
index efbc36872670..7a171920dd21 100644
--- a/drivers/watchdog/dw_wdt.c
+++ b/drivers/watchdog/dw_wdt.c
@@ -22,6 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/interrupt.h>
 #include <linux/of.h>
 #include <linux/pm.h>
 #include <linux/platform_device.h>
@@ -36,6 +37,8 @@
 #define WDOG_CURRENT_COUNT_REG_OFFSET	    0x08
 #define WDOG_COUNTER_RESTART_REG_OFFSET     0x0c
 #define WDOG_COUNTER_RESTART_KICK_VALUE	    0x76
+#define WDOG_INTERRUPT_STATUS_REG_OFFSET    0x10
+#define WDOG_INTERRUPT_CLEAR_REG_OFFSET     0x14
 #define WDOG_COMP_PARAMS_1_REG_OFFSET       0xf4
 #define WDOG_COMP_PARAMS_1_USE_FIX_TOP      BIT(6)
 
@@ -59,6 +62,11 @@ module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
 		 "(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
+enum dw_wdt_rmod {
+	DW_WDT_RMOD_RESET = 1,
+	DW_WDT_RMOD_IRQ = 2
+};
+
 struct dw_wdt_timeout {
 	u32 top_val;
 	unsigned int sec;
@@ -70,6 +78,7 @@ struct dw_wdt {
 	struct clk		*clk;
 	struct clk		*pclk;
 	unsigned long		rate;
+	enum dw_wdt_rmod	rmod;
 	struct dw_wdt_timeout	timeouts[DW_WDT_NUM_TOPS];
 	struct watchdog_device	wdd;
 	struct reset_control	*rst;
@@ -86,6 +95,20 @@ static inline int dw_wdt_is_enabled(struct dw_wdt *dw_wdt)
 		WDOG_CONTROL_REG_WDT_EN_MASK;
 }
 
+static void dw_wdt_update_mode(struct dw_wdt *dw_wdt, enum dw_wdt_rmod rmod)
+{
+	u32 val;
+
+	val = readl(dw_wdt->regs + WDOG_CONTROL_REG_OFFSET);
+	if (rmod == DW_WDT_RMOD_IRQ)
+		val |= WDOG_CONTROL_REG_RESP_MODE_MASK;
+	else
+		val &= ~WDOG_CONTROL_REG_RESP_MODE_MASK;
+	writel(val, dw_wdt->regs + WDOG_CONTROL_REG_OFFSET);
+
+	dw_wdt->rmod = rmod;
+}
+
 static unsigned int dw_wdt_find_best_top(struct dw_wdt *dw_wdt,
 					 unsigned int timeout, u32 *top_val)
 {
@@ -145,7 +168,11 @@ static unsigned int dw_wdt_get_timeout(struct dw_wdt *dw_wdt)
 			break;
 	}
 
-	return dw_wdt->timeouts[idx].sec;
+	/*
+	 * In IRQ mode due to the two stages counter, the actual timeout is
+	 * twice greater than the TOP setting.
+	 */
+	return dw_wdt->timeouts[idx].sec * dw_wdt->rmod;
 }
 
 static int dw_wdt_ping(struct watchdog_device *wdd)
@@ -164,7 +191,20 @@ static int dw_wdt_set_timeout(struct watchdog_device *wdd, unsigned int top_s)
 	unsigned int timeout;
 	u32 top_val;
 
-	timeout = dw_wdt_find_best_top(dw_wdt, top_s, &top_val);
+	/*
+	 * Note IRQ mode being enabled means having a non-zero pre-timeout
+	 * setup. In this case we try to find a TOP as close to the half of the
+	 * requested timeout as possible since DW Watchdog IRQ mode is designed
+	 * in two stages way - first timeout rises the pre-timeout interrupt,
+	 * second timeout performs the system reset. So basically the effective
+	 * watchdog-caused reset happens after two watchdog TOPs elapsed.
+	 */
+	timeout = dw_wdt_find_best_top(dw_wdt, DIV_ROUND_UP(top_s, dw_wdt->rmod),
+				       &top_val);
+	if (dw_wdt->rmod == DW_WDT_RMOD_IRQ)
+		wdd->pretimeout = timeout;
+	else
+		wdd->pretimeout = 0;
 
 	/*
 	 * Set the new value in the watchdog.  Some versions of dw_wdt
@@ -175,25 +215,47 @@ static int dw_wdt_set_timeout(struct watchdog_device *wdd, unsigned int top_s)
 	writel(top_val | top_val << WDOG_TIMEOUT_RANGE_TOPINIT_SHIFT,
 	       dw_wdt->regs + WDOG_TIMEOUT_RANGE_REG_OFFSET);
 
+	/* Kick new TOP value into the watchdog counter if activated. */
+	if (watchdog_active(wdd))
+		dw_wdt_ping(wdd);
+
 	/*
 	 * In case users set bigger timeout value than HW can support,
 	 * kernel(watchdog_dev.c) helps to feed watchdog before
 	 * wdd->max_hw_heartbeat_ms
 	 */
 	if (top_s * 1000 <= wdd->max_hw_heartbeat_ms)
-		wdd->timeout = timeout;
+		wdd->timeout = timeout * dw_wdt->rmod;
 	else
 		wdd->timeout = top_s;
 
 	return 0;
 }
 
+static int dw_wdt_set_pretimeout(struct watchdog_device *wdd, unsigned int req)
+{
+	struct dw_wdt *dw_wdt = to_dw_wdt(wdd);
+
+	/*
+	 * We ignore actual value of the timeout passed from user-space
+	 * using it as a flag whether the pretimeout functionality is intended
+	 * to be activated.
+	 */
+	dw_wdt_update_mode(dw_wdt, req ? DW_WDT_RMOD_IRQ : DW_WDT_RMOD_RESET);
+	dw_wdt_set_timeout(wdd, wdd->timeout);
+
+	return 0;
+}
+
 static void dw_wdt_arm_system_reset(struct dw_wdt *dw_wdt)
 {
 	u32 val = readl(dw_wdt->regs + WDOG_CONTROL_REG_OFFSET);
 
-	/* Disable interrupt mode; always perform system reset. */
-	val &= ~WDOG_CONTROL_REG_RESP_MODE_MASK;
+	/* Disable/enable interrupt mode depending on the RMOD flag. */
+	if (dw_wdt->rmod == DW_WDT_RMOD_IRQ)
+		val |= WDOG_CONTROL_REG_RESP_MODE_MASK;
+	else
+		val &= ~WDOG_CONTROL_REG_RESP_MODE_MASK;
 	/* Enable watchdog. */
 	val |= WDOG_CONTROL_REG_WDT_EN_MASK;
 	writel(val, dw_wdt->regs + WDOG_CONTROL_REG_OFFSET);
@@ -231,6 +293,7 @@ static int dw_wdt_restart(struct watchdog_device *wdd,
 	struct dw_wdt *dw_wdt = to_dw_wdt(wdd);
 
 	writel(0, dw_wdt->regs + WDOG_TIMEOUT_RANGE_REG_OFFSET);
+	dw_wdt_update_mode(dw_wdt, DW_WDT_RMOD_RESET);
 	if (dw_wdt_is_enabled(dw_wdt))
 		writel(WDOG_COUNTER_RESTART_KICK_VALUE,
 		       dw_wdt->regs + WDOG_COUNTER_RESTART_REG_OFFSET);
@@ -246,9 +309,19 @@ static int dw_wdt_restart(struct watchdog_device *wdd,
 static unsigned int dw_wdt_get_timeleft(struct watchdog_device *wdd)
 {
 	struct dw_wdt *dw_wdt = to_dw_wdt(wdd);
+	unsigned int sec;
+	u32 val;
 
-	return readl(dw_wdt->regs + WDOG_CURRENT_COUNT_REG_OFFSET) /
-		dw_wdt->rate;
+	val = readl(dw_wdt->regs + WDOG_CURRENT_COUNT_REG_OFFSET);
+	sec = val / dw_wdt->rate;
+
+	if (dw_wdt->rmod == DW_WDT_RMOD_IRQ) {
+		val = readl(dw_wdt->regs + WDOG_INTERRUPT_STATUS_REG_OFFSET);
+		if (!val)
+			sec += wdd->pretimeout;
+	}
+
+	return sec;
 }
 
 static const struct watchdog_info dw_wdt_ident = {
@@ -257,16 +330,41 @@ static const struct watchdog_info dw_wdt_ident = {
 	.identity	= "Synopsys DesignWare Watchdog",
 };
 
+static const struct watchdog_info dw_wdt_pt_ident = {
+	.options	= WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT |
+			  WDIOF_PRETIMEOUT | WDIOF_MAGICCLOSE,
+	.identity	= "Synopsys DesignWare Watchdog",
+};
+
 static const struct watchdog_ops dw_wdt_ops = {
 	.owner		= THIS_MODULE,
 	.start		= dw_wdt_start,
 	.stop		= dw_wdt_stop,
 	.ping		= dw_wdt_ping,
 	.set_timeout	= dw_wdt_set_timeout,
+	.set_pretimeout	= dw_wdt_set_pretimeout,
 	.get_timeleft	= dw_wdt_get_timeleft,
 	.restart	= dw_wdt_restart,
 };
 
+static irqreturn_t dw_wdt_irq(int irq, void *devid)
+{
+	struct dw_wdt *dw_wdt = devid;
+	u32 val;
+
+	/*
+	 * We don't clear the IRQ status. It's supposed to be done by the
+	 * following ping operations.
+	 */
+	val = readl(dw_wdt->regs + WDOG_INTERRUPT_STATUS_REG_OFFSET);
+	if (!val)
+		return IRQ_NONE;
+
+	watchdog_notify_pretimeout(&dw_wdt->wdd);
+
+	return IRQ_HANDLED;
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int dw_wdt_suspend(struct device *dev)
 {
@@ -447,6 +545,31 @@ static int dw_wdt_drv_probe(struct platform_device *pdev)
 		goto out_disable_pclk;
 	}
 
+	/* Enable normal reset without pre-timeout by default. */
+	dw_wdt_update_mode(dw_wdt, DW_WDT_RMOD_RESET);
+
+	/*
+	 * Pre-timeout IRQ is optional, since some hardware may lack support
+	 * of it. Note we must request rising-edge IRQ, since the lane is left
+	 * pending either until the next watchdog kick event or up to the
+	 * system reset.
+	 */
+	ret = platform_get_irq_optional(pdev, 0);
+	if (ret > 0) {
+		ret = devm_request_irq(dev, ret, dw_wdt_irq,
+				       IRQF_SHARED | IRQF_TRIGGER_RISING,
+				       pdev->name, dw_wdt);
+		if (ret)
+			goto out_disable_pclk;
+
+		dw_wdt->wdd.info = &dw_wdt_pt_ident;
+	} else {
+		if (ret == -EPROBE_DEFER)
+			goto out_disable_pclk;
+
+		dw_wdt->wdd.info = &dw_wdt_ident;
+	}
+
 	reset_control_deassert(dw_wdt->rst);
 
 	ret = dw_wdt_init_timeouts(dw_wdt, dev);
@@ -454,7 +577,6 @@ static int dw_wdt_drv_probe(struct platform_device *pdev)
 		goto out_disable_clk;
 
 	wdd = &dw_wdt->wdd;
-	wdd->info = &dw_wdt_ident;
 	wdd->ops = &dw_wdt_ops;
 	wdd->min_timeout = dw_wdt_get_min_timeout(dw_wdt);
 	wdd->max_hw_heartbeat_ms = dw_wdt_get_max_timeout_ms(dw_wdt);

From 4105f19fd0ce51b571f8112457182dfad142768e Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Sat, 30 May 2020 10:35:57 +0300
Subject: [PATCH 219/474] watchdog: dw_wdt: Add DebugFS files

For the sake of the easier device-driver debug procedure, we added a
DebugFS file with the controller registers state. It's available only if
kernel is configured with DebugFS support.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Cc: Alexey Malahov <Alexey.Malahov@baikalelectronics.ru>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: linux-mips@vger.kernel.org
Cc: devicetree@vger.kernel.org
Link: https://lore.kernel.org/r/20200530073557.22661-8-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/dw_wdt.c | 68 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 68 insertions(+)

diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c
index 7a171920dd21..4fec2c6a3c01 100644
--- a/drivers/watchdog/dw_wdt.c
+++ b/drivers/watchdog/dw_wdt.c
@@ -28,6 +28,7 @@
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <linux/watchdog.h>
+#include <linux/debugfs.h>
 
 #define WDOG_CONTROL_REG_OFFSET		    0x00
 #define WDOG_CONTROL_REG_WDT_EN_MASK	    0x01
@@ -39,8 +40,14 @@
 #define WDOG_COUNTER_RESTART_KICK_VALUE	    0x76
 #define WDOG_INTERRUPT_STATUS_REG_OFFSET    0x10
 #define WDOG_INTERRUPT_CLEAR_REG_OFFSET     0x14
+#define WDOG_COMP_PARAMS_5_REG_OFFSET       0xe4
+#define WDOG_COMP_PARAMS_4_REG_OFFSET       0xe8
+#define WDOG_COMP_PARAMS_3_REG_OFFSET       0xec
+#define WDOG_COMP_PARAMS_2_REG_OFFSET       0xf0
 #define WDOG_COMP_PARAMS_1_REG_OFFSET       0xf4
 #define WDOG_COMP_PARAMS_1_USE_FIX_TOP      BIT(6)
+#define WDOG_COMP_VERSION_REG_OFFSET        0xf8
+#define WDOG_COMP_TYPE_REG_OFFSET           0xfc
 
 /* There are sixteen TOPs (timeout periods) that can be set in the watchdog. */
 #define DW_WDT_NUM_TOPS		16
@@ -85,6 +92,10 @@ struct dw_wdt {
 	/* Save/restore */
 	u32			control;
 	u32			timeout;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry		*dbgfs_dir;
+#endif
 };
 
 #define to_dw_wdt(wdd)	container_of(wdd, struct dw_wdt, wdd)
@@ -484,6 +495,59 @@ static int dw_wdt_init_timeouts(struct dw_wdt *dw_wdt, struct device *dev)
 	return 0;
 }
 
+#ifdef CONFIG_DEBUG_FS
+
+#define DW_WDT_DBGFS_REG(_name, _off) \
+{				      \
+	.name = _name,		      \
+	.offset = _off		      \
+}
+
+static const struct debugfs_reg32 dw_wdt_dbgfs_regs[] = {
+	DW_WDT_DBGFS_REG("cr", WDOG_CONTROL_REG_OFFSET),
+	DW_WDT_DBGFS_REG("torr", WDOG_TIMEOUT_RANGE_REG_OFFSET),
+	DW_WDT_DBGFS_REG("ccvr", WDOG_CURRENT_COUNT_REG_OFFSET),
+	DW_WDT_DBGFS_REG("crr", WDOG_COUNTER_RESTART_REG_OFFSET),
+	DW_WDT_DBGFS_REG("stat", WDOG_INTERRUPT_STATUS_REG_OFFSET),
+	DW_WDT_DBGFS_REG("param5", WDOG_COMP_PARAMS_5_REG_OFFSET),
+	DW_WDT_DBGFS_REG("param4", WDOG_COMP_PARAMS_4_REG_OFFSET),
+	DW_WDT_DBGFS_REG("param3", WDOG_COMP_PARAMS_3_REG_OFFSET),
+	DW_WDT_DBGFS_REG("param2", WDOG_COMP_PARAMS_2_REG_OFFSET),
+	DW_WDT_DBGFS_REG("param1", WDOG_COMP_PARAMS_1_REG_OFFSET),
+	DW_WDT_DBGFS_REG("version", WDOG_COMP_VERSION_REG_OFFSET),
+	DW_WDT_DBGFS_REG("type", WDOG_COMP_TYPE_REG_OFFSET)
+};
+
+static void dw_wdt_dbgfs_init(struct dw_wdt *dw_wdt)
+{
+	struct device *dev = dw_wdt->wdd.parent;
+	struct debugfs_regset32 *regset;
+
+	regset = devm_kzalloc(dev, sizeof(*regset), GFP_KERNEL);
+	if (!regset)
+		return;
+
+	regset->regs = dw_wdt_dbgfs_regs;
+	regset->nregs = ARRAY_SIZE(dw_wdt_dbgfs_regs);
+	regset->base = dw_wdt->regs;
+
+	dw_wdt->dbgfs_dir = debugfs_create_dir(dev_name(dev), NULL);
+
+	debugfs_create_regset32("registers", 0444, dw_wdt->dbgfs_dir, regset);
+}
+
+static void dw_wdt_dbgfs_clear(struct dw_wdt *dw_wdt)
+{
+	debugfs_remove_recursive(dw_wdt->dbgfs_dir);
+}
+
+#else /* !CONFIG_DEBUG_FS */
+
+static void dw_wdt_dbgfs_init(struct dw_wdt *dw_wdt) {}
+static void dw_wdt_dbgfs_clear(struct dw_wdt *dw_wdt) {}
+
+#endif /* !CONFIG_DEBUG_FS */
+
 static int dw_wdt_drv_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -607,6 +671,8 @@ static int dw_wdt_drv_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_disable_pclk;
 
+	dw_wdt_dbgfs_init(dw_wdt);
+
 	return 0;
 
 out_disable_pclk:
@@ -621,6 +687,8 @@ static int dw_wdt_drv_remove(struct platform_device *pdev)
 {
 	struct dw_wdt *dw_wdt = platform_get_drvdata(pdev);
 
+	dw_wdt_dbgfs_clear(dw_wdt);
+
 	watchdog_unregister_device(&dw_wdt->wdd);
 	reset_control_assert(dw_wdt->rst);
 	clk_disable_unprepare(dw_wdt->pclk);

From 137e9e68dd3805deb9fa43b3eb1a963a2d093746 Mon Sep 17 00:00:00 2001
From: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
Date: Fri, 26 Jun 2020 00:59:04 +0530
Subject: [PATCH 220/474] dt-bindings: watchdog: Convert QCOM watchdog timer
 bindings to YAML

Convert QCOM watchdog timer bindings to DT schema format using
json-schema.

Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/77b47aad9d17cb4ec8359bdbbb30c33d818117e6.1593112534.git.saiprakash.ranjan@codeaurora.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 .../devicetree/bindings/watchdog/qcom-wdt.txt | 28 ------------
 .../bindings/watchdog/qcom-wdt.yaml           | 44 +++++++++++++++++++
 2 files changed, 44 insertions(+), 28 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/watchdog/qcom-wdt.txt
 create mode 100644 Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml

diff --git a/Documentation/devicetree/bindings/watchdog/qcom-wdt.txt b/Documentation/devicetree/bindings/watchdog/qcom-wdt.txt
deleted file mode 100644
index 41aeaa2ff0f8..000000000000
--- a/Documentation/devicetree/bindings/watchdog/qcom-wdt.txt
+++ /dev/null
@@ -1,28 +0,0 @@
-Qualcomm Krait Processor Sub-system (KPSS) Watchdog
----------------------------------------------------
-
-Required properties :
-- compatible : shall contain only one of the following:
-
-			"qcom,kpss-wdt-msm8960"
-			"qcom,kpss-wdt-apq8064"
-			"qcom,kpss-wdt-ipq8064"
-			"qcom,kpss-wdt-ipq4019"
-			"qcom,kpss-timer"
-			"qcom,scss-timer"
-			"qcom,kpss-wdt"
-
-- reg : shall contain base register location and length
-- clocks : shall contain the input clock
-
-Optional properties :
-- timeout-sec : shall contain the default watchdog timeout in seconds,
-                if unset, the default timeout is 30 seconds
-
-Example:
-	watchdog@208a038 {
-		compatible = "qcom,kpss-wdt-ipq8064";
-		reg = <0x0208a038 0x40>;
-		clocks = <&sleep_clk>;
-		timeout-sec = <10>;
-	};
diff --git a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml
new file mode 100644
index 000000000000..5448cc537a03
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml
@@ -0,0 +1,44 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/watchdog/qcom-wdt.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Krait Processor Sub-system (KPSS) Watchdog timer
+
+maintainers:
+  - Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
+
+allOf:
+  - $ref: watchdog.yaml#
+
+properties:
+  compatible:
+    enum:
+      - qcom,kpss-timer
+      - qcom,kpss-wdt
+      - qcom,kpss-wdt-apq8064
+      - qcom,kpss-wdt-ipq4019
+      - qcom,kpss-wdt-ipq8064
+      - qcom,kpss-wdt-msm8960
+      - qcom,scss-timer
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+
+examples:
+  - |
+    watchdog@208a038 {
+      compatible = "qcom,kpss-wdt-ipq8064";
+      reg = <0x0208a038 0x40>;
+      clocks = <&sleep_clk>;
+      timeout-sec = <10>;
+    };

From a4fd26f6187b13cace0f90029fe790799e34e4e2 Mon Sep 17 00:00:00 2001
From: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
Date: Fri, 26 Jun 2020 00:59:05 +0530
Subject: [PATCH 221/474] dt-bindings: watchdog: Add compatible for QCS404,
 SC7180, SDM845, SM8150

Add missing compatible for watchdog timer on QCS404,
SC7180, SDM845 and SM8150 SoCs.

Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Acked-by: Rob Herring <robh@kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/09da1ba319dc4a27ef4e4e177e67e68f1cb4f35b.1593112534.git.saiprakash.ranjan@codeaurora.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml
index 5448cc537a03..0709ddf0b6a5 100644
--- a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml
@@ -15,6 +15,10 @@ allOf:
 properties:
   compatible:
     enum:
+      - qcom,apss-wdt-qcs404
+      - qcom,apss-wdt-sc7180
+      - qcom,apss-wdt-sdm845
+      - qcom,apss-wdt-sm8150
       - qcom,kpss-timer
       - qcom,kpss-wdt
       - qcom,kpss-wdt-apq8064

From d51d3852d1fd28409107274dc1d8077022cc0dc2 Mon Sep 17 00:00:00 2001
From: Ahmad Fatoum <a.fatoum@pengutronix.de>
Date: Thu, 11 Jun 2020 21:17:42 +0200
Subject: [PATCH 222/474] docs: watchdog: codify ident.options as superset of
 possible status flags

The FIXME comment has been in-tree since the very first git commit.
The described behavior has been since relied on by some userspace, e.g.
the util-linux wdctl command and has been ignored by some kernelspace,
like the f71808e_wdt driver.

The functionality is useful to have to be able to differentiate between a
driver that doesn't support WDIOF_CARDRESET and one that does, but hasn't
had a watchdog reset, thus drop the FIXME to encourage drivers adopting
this convention.

Signed-off-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200611191750.28096-2-a.fatoum@pengutronix.de
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 Documentation/watchdog/watchdog-api.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/watchdog/watchdog-api.rst b/Documentation/watchdog/watchdog-api.rst
index c6c1e9fa9f73..800dcd7586f2 100644
--- a/Documentation/watchdog/watchdog-api.rst
+++ b/Documentation/watchdog/watchdog-api.rst
@@ -168,7 +168,7 @@ the fields returned in the ident struct are:
 
 the options field can have the following bits set, and describes what
 kind of information that the GET_STATUS and GET_BOOT_STATUS ioctls can
-return.   [FIXME -- Is this correct?]
+return.
 
 	================	=========================
 	WDIOF_OVERHEAT		Reset due to CPU overheat

From e871e93fb08a619dfc015974a05768ed6880fd82 Mon Sep 17 00:00:00 2001
From: Ahmad Fatoum <a.fatoum@pengutronix.de>
Date: Thu, 11 Jun 2020 21:17:43 +0200
Subject: [PATCH 223/474] watchdog: f71808e_wdt: indicate WDIOF_CARDRESET
 support in watchdog_info.options

The driver supports populating bootstatus with WDIOF_CARDRESET, but so
far userspace couldn't portably determine whether absence of this flag
meant no watchdog reset or no driver support. Or-in the bit to fix this.

Fixes: b97cb21a4634 ("watchdog: f71808e_wdt: Fix WDTMOUT_STS register read")
Cc: stable@vger.kernel.org
Signed-off-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200611191750.28096-3-a.fatoum@pengutronix.de
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/f71808e_wdt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c
index a3c44d75d80e..c8ce80c13403 100644
--- a/drivers/watchdog/f71808e_wdt.c
+++ b/drivers/watchdog/f71808e_wdt.c
@@ -692,7 +692,8 @@ static int __init watchdog_init(int sioaddr)
 	watchdog.sioaddr = sioaddr;
 	watchdog.ident.options = WDIOC_SETTIMEOUT
 				| WDIOF_MAGICCLOSE
-				| WDIOF_KEEPALIVEPING;
+				| WDIOF_KEEPALIVEPING
+				| WDIOF_CARDRESET;
 
 	snprintf(watchdog.ident.identity,
 		sizeof(watchdog.ident.identity), "%s watchdog",

From 802141462d844f2e6a4d63a12260d79b7afc4c34 Mon Sep 17 00:00:00 2001
From: Ahmad Fatoum <a.fatoum@pengutronix.de>
Date: Thu, 11 Jun 2020 21:17:44 +0200
Subject: [PATCH 224/474] watchdog: f71808e_wdt: remove use of wrong
 watchdog_info option

The flags that should be or-ed into the watchdog_info.options by drivers
all start with WDIOF_, e.g. WDIOF_SETTIMEOUT, which indicates that the
driver's watchdog_ops has a usable set_timeout.

WDIOC_SETTIMEOUT was used instead, which expands to 0xc0045706, which
equals:

   WDIOF_FANFAULT | WDIOF_EXTERN1 | WDIOF_PRETIMEOUT | WDIOF_ALARMONLY |
   WDIOF_MAGICCLOSE | 0xc0045000

These were so far indicated to userspace on WDIOC_GETSUPPORT.
As the driver has not yet been migrated to the new watchdog kernel API,
the constant can just be dropped without substitute.

Fixes: 96cb4eb019ce ("watchdog: f71808e_wdt: new watchdog driver for Fintek F71808E and F71882FG")
Cc: stable@vger.kernel.org
Signed-off-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200611191750.28096-4-a.fatoum@pengutronix.de
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/f71808e_wdt.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c
index c8ce80c13403..8e5584c54423 100644
--- a/drivers/watchdog/f71808e_wdt.c
+++ b/drivers/watchdog/f71808e_wdt.c
@@ -690,8 +690,7 @@ static int __init watchdog_init(int sioaddr)
 	 * into the module have been registered yet.
 	 */
 	watchdog.sioaddr = sioaddr;
-	watchdog.ident.options = WDIOC_SETTIMEOUT
-				| WDIOF_MAGICCLOSE
+	watchdog.ident.options = WDIOF_MAGICCLOSE
 				| WDIOF_KEEPALIVEPING
 				| WDIOF_CARDRESET;
 

From 4f39d575844148fbf3081571a1f3b4ae04150958 Mon Sep 17 00:00:00 2001
From: Ahmad Fatoum <a.fatoum@pengutronix.de>
Date: Thu, 11 Jun 2020 21:17:45 +0200
Subject: [PATCH 225/474] watchdog: f71808e_wdt: clear watchdog timeout
 occurred flag

The flag indicating a watchdog timeout having occurred normally persists
till Power-On Reset of the Fintek Super I/O chip. The user can clear it
by writing a `1' to the bit.

The driver doesn't offer a restart method, so regular system reboot
might not reset the Super I/O and if the watchdog isn't enabled, we
won't touch the register containing the bit on the next boot.
In this case all subsequent regular reboots will be wrongly flagged
by the driver as being caused by the watchdog.

Fix this by having the flag cleared after read. This is also done by
other drivers like those for the i6300esb and mpc8xxx_wdt.

Fixes: b97cb21a4634 ("watchdog: f71808e_wdt: Fix WDTMOUT_STS register read")
Cc: stable@vger.kernel.org
Signed-off-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200611191750.28096-5-a.fatoum@pengutronix.de
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/f71808e_wdt.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c
index 8e5584c54423..26bf366aebc2 100644
--- a/drivers/watchdog/f71808e_wdt.c
+++ b/drivers/watchdog/f71808e_wdt.c
@@ -706,6 +706,13 @@ static int __init watchdog_init(int sioaddr)
 	wdt_conf = superio_inb(sioaddr, F71808FG_REG_WDT_CONF);
 	watchdog.caused_reboot = wdt_conf & BIT(F71808FG_FLAG_WDTMOUT_STS);
 
+	/*
+	 * We don't want WDTMOUT_STS to stick around till regular reboot.
+	 * Write 1 to the bit to clear it to zero.
+	 */
+	superio_outb(sioaddr, F71808FG_REG_WDT_CONF,
+		     wdt_conf | BIT(F71808FG_FLAG_WDTMOUT_STS));
+
 	superio_exit(sioaddr);
 
 	err = watchdog_set_timeout(timeout);

From 5edc8c687357b40469d90e3dab0b59b72eaabf59 Mon Sep 17 00:00:00 2001
From: Ahmad Fatoum <a.fatoum@pengutronix.de>
Date: Thu, 11 Jun 2020 21:17:46 +0200
Subject: [PATCH 226/474] watchdog: f71808e_wdt: do stricter parameter
 validation

We check the f71862fg_pin module parameter every time a watchdog device
for the f71862fg is opened, but the parameter can't change at runtime.

If we move the check to the start of init:

  - We catch userspace passing invalid, but unused, values
  - We check the condition only once
  - We simplify the code

Do so.

Signed-off-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200611191750.28096-6-a.fatoum@pengutronix.de
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/f71808e_wdt.c | 37 +++++++++++-----------------------
 1 file changed, 12 insertions(+), 25 deletions(-)

diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c
index 26bf366aebc2..9f7823819ed1 100644
--- a/drivers/watchdog/f71808e_wdt.c
+++ b/drivers/watchdog/f71808e_wdt.c
@@ -306,27 +306,6 @@ static int watchdog_keepalive(void)
 	return err;
 }
 
-static int f71862fg_pin_configure(unsigned short ioaddr)
-{
-	/* When ioaddr is non-zero the calling function has to take care of
-	   mutex handling and superio preparation! */
-
-	if (f71862fg_pin == 63) {
-		if (ioaddr) {
-			/* SPI must be disabled first to use this pin! */
-			superio_clear_bit(ioaddr, SIO_REG_ROM_ADDR_SEL, 6);
-			superio_set_bit(ioaddr, SIO_REG_MFUNCT3, 4);
-		}
-	} else if (f71862fg_pin == 56) {
-		if (ioaddr)
-			superio_set_bit(ioaddr, SIO_REG_MFUNCT1, 1);
-	} else {
-		pr_err("Invalid argument f71862fg_pin=%d\n", f71862fg_pin);
-		return -EINVAL;
-	}
-	return 0;
-}
-
 static int watchdog_start(void)
 {
 	int err;
@@ -352,9 +331,13 @@ static int watchdog_start(void)
 		break;
 
 	case f71862fg:
-		err = f71862fg_pin_configure(watchdog.sioaddr);
-		if (err)
-			goto exit_superio;
+		if (f71862fg_pin == 63) {
+			/* SPI must be disabled first to use this pin! */
+			superio_clear_bit(watchdog.sioaddr, SIO_REG_ROM_ADDR_SEL, 6);
+			superio_set_bit(watchdog.sioaddr, SIO_REG_MFUNCT3, 4);
+		} else if (f71862fg_pin == 56) {
+			superio_set_bit(watchdog.sioaddr, SIO_REG_MFUNCT1, 1);
+		}
 		break;
 
 	case f71868:
@@ -810,7 +793,6 @@ static int __init f71808e_find(int sioaddr)
 		break;
 	case SIO_F71862_ID:
 		watchdog.type = f71862fg;
-		err = f71862fg_pin_configure(0); /* validate module parameter */
 		break;
 	case SIO_F71868_ID:
 		watchdog.type = f71868;
@@ -859,6 +841,11 @@ static int __init f71808e_init(void)
 	int err = -ENODEV;
 	int i;
 
+	if (f71862fg_pin != 63 && f71862fg_pin != 56) {
+		pr_err("Invalid argument f71862fg_pin=%d\n", f71862fg_pin);
+		return -EINVAL;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(addrs); i++) {
 		err = f71808e_find(addrs[i]);
 		if (err == 0)

From bd490f8222510dea748b495a502910119060e869 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 7 Jul 2020 12:11:21 -0500
Subject: [PATCH 227/474] watchdog: Use fallthrough pseudo-keyword

Replace the existing /* fall through */ comments and its variants with
the new pseudo-keyword macro fallthrough[1]. Also, remove unnecessary
fall-through markings when it is the case.

[1] https://www.kernel.org/doc/html/latest/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-through

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200707171121.GA13472@embeddedor
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/advantechwdt.c   | 2 +-
 drivers/watchdog/alim1535_wdt.c   | 2 +-
 drivers/watchdog/alim7101_wdt.c   | 2 +-
 drivers/watchdog/ar7_wdt.c        | 3 +--
 drivers/watchdog/ath79_wdt.c      | 2 +-
 drivers/watchdog/eurotechwdt.c    | 2 +-
 drivers/watchdog/f71808e_wdt.c    | 4 ++--
 drivers/watchdog/gef_wdt.c        | 2 +-
 drivers/watchdog/geodewdt.c       | 2 +-
 drivers/watchdog/ib700wdt.c       | 2 +-
 drivers/watchdog/it8712f_wdt.c    | 2 +-
 drivers/watchdog/ixp4xx_wdt.c     | 2 +-
 drivers/watchdog/m54xx_wdt.c      | 2 +-
 drivers/watchdog/machzwd.c        | 2 +-
 drivers/watchdog/mv64x60_wdt.c    | 2 +-
 drivers/watchdog/nv_tco.c         | 2 +-
 drivers/watchdog/pc87413_wdt.c    | 2 +-
 drivers/watchdog/pcwd.c           | 2 +-
 drivers/watchdog/pcwd_pci.c       | 2 +-
 drivers/watchdog/pcwd_usb.c       | 2 +-
 drivers/watchdog/rc32434_wdt.c    | 2 +-
 drivers/watchdog/riowd.c          | 2 +-
 drivers/watchdog/sa1100_wdt.c     | 2 +-
 drivers/watchdog/sb_wdog.c        | 2 +-
 drivers/watchdog/sbc60xxwdt.c     | 2 +-
 drivers/watchdog/sbc7240_wdt.c    | 2 +-
 drivers/watchdog/sbc_fitpc2_wdt.c | 2 +-
 drivers/watchdog/sc520_wdt.c      | 2 +-
 drivers/watchdog/sch311x_wdt.c    | 2 +-
 drivers/watchdog/smsc37b787_wdt.c | 2 +-
 drivers/watchdog/w83877f_wdt.c    | 2 +-
 drivers/watchdog/w83977f_wdt.c    | 2 +-
 drivers/watchdog/wafer5823wdt.c   | 2 +-
 drivers/watchdog/watchdog_dev.c   | 2 +-
 drivers/watchdog/wdt.c            | 2 +-
 drivers/watchdog/wdt285.c         | 2 +-
 drivers/watchdog/wdt977.c         | 2 +-
 drivers/watchdog/wdt_pci.c        | 2 +-
 38 files changed, 39 insertions(+), 40 deletions(-)

diff --git a/drivers/watchdog/advantechwdt.c b/drivers/watchdog/advantechwdt.c
index 0e4c18a2aa42..554fe85da50e 100644
--- a/drivers/watchdog/advantechwdt.c
+++ b/drivers/watchdog/advantechwdt.c
@@ -177,7 +177,7 @@ static long advwdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (advwdt_set_heartbeat(new_timeout))
 			return -EINVAL;
 		advwdt_ping();
-		/* fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, p);
 	default:
diff --git a/drivers/watchdog/alim1535_wdt.c b/drivers/watchdog/alim1535_wdt.c
index 42338c7d4540..bfb9a91ca1df 100644
--- a/drivers/watchdog/alim1535_wdt.c
+++ b/drivers/watchdog/alim1535_wdt.c
@@ -220,7 +220,7 @@ static long ali_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			return -EINVAL;
 		ali_keepalive();
 	}
-		/* fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, p);
 	default:
diff --git a/drivers/watchdog/alim7101_wdt.c b/drivers/watchdog/alim7101_wdt.c
index 5af0358f4390..4ff7f5afb7aa 100644
--- a/drivers/watchdog/alim7101_wdt.c
+++ b/drivers/watchdog/alim7101_wdt.c
@@ -279,7 +279,7 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		timeout = new_timeout;
 		wdt_keepalive();
 	}
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, p);
 	default:
diff --git a/drivers/watchdog/ar7_wdt.c b/drivers/watchdog/ar7_wdt.c
index c087027ffd5d..ff37dc91057d 100644
--- a/drivers/watchdog/ar7_wdt.c
+++ b/drivers/watchdog/ar7_wdt.c
@@ -235,8 +235,7 @@ static long ar7_wdt_ioctl(struct file *file,
 		ar7_wdt_update_margin(new_margin);
 		ar7_wdt_kick(1);
 		spin_unlock(&wdt_lock);
-		/* Fall through */
-
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		if (put_user(margin, (int *)arg))
 			return -EFAULT;
diff --git a/drivers/watchdog/ath79_wdt.c b/drivers/watchdog/ath79_wdt.c
index d6dff97c280b..0f18f06a21b6 100644
--- a/drivers/watchdog/ath79_wdt.c
+++ b/drivers/watchdog/ath79_wdt.c
@@ -215,8 +215,8 @@ static long ath79_wdt_ioctl(struct file *file, unsigned int cmd,
 		err = ath79_wdt_set_timeout(t);
 		if (err)
 			break;
+		fallthrough;
 
-		/* fallthrough */
 	case WDIOC_GETTIMEOUT:
 		err = put_user(timeout, p);
 		break;
diff --git a/drivers/watchdog/eurotechwdt.c b/drivers/watchdog/eurotechwdt.c
index f5ffa7be066e..2418ebb707bd 100644
--- a/drivers/watchdog/eurotechwdt.c
+++ b/drivers/watchdog/eurotechwdt.c
@@ -286,7 +286,7 @@ static long eurwdt_ioctl(struct file *file,
 		eurwdt_timeout = time;
 		eurwdt_set_timeout(time);
 		spin_unlock(&eurwdt_lock);
-		/* fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		return put_user(eurwdt_timeout, p);
diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c
index 9f7823819ed1..f60beec1bbae 100644
--- a/drivers/watchdog/f71808e_wdt.c
+++ b/drivers/watchdog/f71808e_wdt.c
@@ -612,7 +612,7 @@ static long watchdog_ioctl(struct file *file, unsigned int cmd,
 
 		if (new_options & WDIOS_ENABLECARD)
 			return watchdog_start();
-		/* fall through */
+		fallthrough;
 
 	case WDIOC_KEEPALIVE:
 		watchdog_keepalive();
@@ -626,7 +626,7 @@ static long watchdog_ioctl(struct file *file, unsigned int cmd,
 			return -EINVAL;
 
 		watchdog_keepalive();
-		/* fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		return put_user(watchdog.timeout, uarg.i);
diff --git a/drivers/watchdog/gef_wdt.c b/drivers/watchdog/gef_wdt.c
index f6541d1b65e3..df5406aa7d25 100644
--- a/drivers/watchdog/gef_wdt.c
+++ b/drivers/watchdog/gef_wdt.c
@@ -201,7 +201,7 @@ static long gef_wdt_ioctl(struct file *file, unsigned int cmd,
 		if (get_user(timeout, (int __user *)argp))
 			return -EFAULT;
 		gef_wdt_set_timeout(timeout);
-		/* Fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		if (put_user(gef_wdt_timeout, (int __user *)argp))
diff --git a/drivers/watchdog/geodewdt.c b/drivers/watchdog/geodewdt.c
index 9914a4283cb2..83418924e30a 100644
--- a/drivers/watchdog/geodewdt.c
+++ b/drivers/watchdog/geodewdt.c
@@ -185,7 +185,7 @@ static long geodewdt_ioctl(struct file *file, unsigned int cmd,
 
 		if (geodewdt_set_heartbeat(interval))
 			return -EINVAL;
-	/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, p);
 
diff --git a/drivers/watchdog/ib700wdt.c b/drivers/watchdog/ib700wdt.c
index 2b65ea9451d1..a0ddedc362fc 100644
--- a/drivers/watchdog/ib700wdt.c
+++ b/drivers/watchdog/ib700wdt.c
@@ -214,7 +214,7 @@ static long ibwdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (ibwdt_set_heartbeat(new_margin))
 			return -EINVAL;
 		ibwdt_ping();
-		/* fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, p);
diff --git a/drivers/watchdog/it8712f_wdt.c b/drivers/watchdog/it8712f_wdt.c
index 2fed40d14007..9b89d2f09568 100644
--- a/drivers/watchdog/it8712f_wdt.c
+++ b/drivers/watchdog/it8712f_wdt.c
@@ -303,7 +303,7 @@ static long it8712f_wdt_ioctl(struct file *file, unsigned int cmd,
 
 		superio_exit();
 		it8712f_wdt_ping();
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		if (put_user(margin, p))
 			return -EFAULT;
diff --git a/drivers/watchdog/ixp4xx_wdt.c b/drivers/watchdog/ixp4xx_wdt.c
index 09886616fd21..aae29dcfaf11 100644
--- a/drivers/watchdog/ixp4xx_wdt.c
+++ b/drivers/watchdog/ixp4xx_wdt.c
@@ -136,7 +136,7 @@ static long ixp4xx_wdt_ioctl(struct file *file, unsigned int cmd,
 
 		heartbeat = time;
 		wdt_enable();
-		/* Fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		ret = put_user(heartbeat, (int *)arg);
diff --git a/drivers/watchdog/m54xx_wdt.c b/drivers/watchdog/m54xx_wdt.c
index 60ed6252e5f4..f388a769dbd3 100644
--- a/drivers/watchdog/m54xx_wdt.c
+++ b/drivers/watchdog/m54xx_wdt.c
@@ -155,7 +155,7 @@ static long m54xx_wdt_ioctl(struct file *file, unsigned int cmd,
 
 		heartbeat = time;
 		wdt_enable();
-		/* Fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		ret = put_user(heartbeat, (int *)arg);
diff --git a/drivers/watchdog/machzwd.c b/drivers/watchdog/machzwd.c
index 80ff94688487..743377c5b173 100644
--- a/drivers/watchdog/machzwd.c
+++ b/drivers/watchdog/machzwd.c
@@ -171,7 +171,7 @@ static inline void zf_set_timer(unsigned short new, unsigned char n)
 	switch (n) {
 	case WD1:
 		zf_writew(COUNTER_1, new);
-		/* fall through */
+		fallthrough;
 	case WD2:
 		zf_writeb(COUNTER_2, new > 0xff ? 0xff : new);
 	default:
diff --git a/drivers/watchdog/mv64x60_wdt.c b/drivers/watchdog/mv64x60_wdt.c
index 0bc72dd69b70..894aa63488d3 100644
--- a/drivers/watchdog/mv64x60_wdt.c
+++ b/drivers/watchdog/mv64x60_wdt.c
@@ -222,7 +222,7 @@ static long mv64x60_wdt_ioctl(struct file *file,
 		if (get_user(timeout, (int __user *)argp))
 			return -EFAULT;
 		mv64x60_wdt_set_timeout(timeout);
-		/* Fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		if (put_user(mv64x60_wdt_timeout, (int __user *)argp))
diff --git a/drivers/watchdog/nv_tco.c b/drivers/watchdog/nv_tco.c
index d7a560e348d5..d15ad8583a59 100644
--- a/drivers/watchdog/nv_tco.c
+++ b/drivers/watchdog/nv_tco.c
@@ -250,7 +250,7 @@ static long nv_tco_ioctl(struct file *file, unsigned int cmd,
 		if (tco_timer_set_heartbeat(new_heartbeat))
 			return -EINVAL;
 		tco_timer_keepalive();
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(heartbeat, p);
 	default:
diff --git a/drivers/watchdog/pc87413_wdt.c b/drivers/watchdog/pc87413_wdt.c
index 73fbfc99083b..2d4504302c9e 100644
--- a/drivers/watchdog/pc87413_wdt.c
+++ b/drivers/watchdog/pc87413_wdt.c
@@ -433,7 +433,7 @@ static long pc87413_ioctl(struct file *file, unsigned int cmd,
 			return -EINVAL;
 		timeout = new_timeout;
 		pc87413_refresh();
-		/* fall through - and return the new timeout... */
+		fallthrough;	/* and return the new timeout */
 	case WDIOC_GETTIMEOUT:
 		new_timeout = timeout * 60;
 		return put_user(new_timeout, uarg.i);
diff --git a/drivers/watchdog/pcwd.c b/drivers/watchdog/pcwd.c
index 7a0587fdc52c..e86fa7f8351d 100644
--- a/drivers/watchdog/pcwd.c
+++ b/drivers/watchdog/pcwd.c
@@ -651,7 +651,7 @@ static long pcwd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			return -EINVAL;
 
 		pcwd_keepalive();
-		/* Fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		return put_user(heartbeat, argp);
diff --git a/drivers/watchdog/pcwd_pci.c b/drivers/watchdog/pcwd_pci.c
index 81508a42a90c..54d86fcb1837 100644
--- a/drivers/watchdog/pcwd_pci.c
+++ b/drivers/watchdog/pcwd_pci.c
@@ -542,7 +542,7 @@ static long pcipcwd_ioctl(struct file *file, unsigned int cmd,
 
 		pcipcwd_keepalive();
 	}
-		/* fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		return put_user(heartbeat, p);
diff --git a/drivers/watchdog/pcwd_usb.c b/drivers/watchdog/pcwd_usb.c
index 2f44af1831d0..79efca47cebb 100644
--- a/drivers/watchdog/pcwd_usb.c
+++ b/drivers/watchdog/pcwd_usb.c
@@ -452,7 +452,7 @@ static long usb_pcwd_ioctl(struct file *file, unsigned int cmd,
 
 		usb_pcwd_keepalive(usb_pcwd_device);
 	}
-		/* fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		return put_user(heartbeat, p);
diff --git a/drivers/watchdog/rc32434_wdt.c b/drivers/watchdog/rc32434_wdt.c
index aee3c2efd565..e74802f3a32e 100644
--- a/drivers/watchdog/rc32434_wdt.c
+++ b/drivers/watchdog/rc32434_wdt.c
@@ -230,7 +230,7 @@ static long rc32434_wdt_ioctl(struct file *file, unsigned int cmd,
 			return -EFAULT;
 		if (rc32434_wdt_set(new_timeout))
 			return -EINVAL;
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return copy_to_user(argp, &timeout, sizeof(int)) ? -EFAULT : 0;
 	default:
diff --git a/drivers/watchdog/riowd.c b/drivers/watchdog/riowd.c
index 1b9a6dc8f982..7008596a575f 100644
--- a/drivers/watchdog/riowd.c
+++ b/drivers/watchdog/riowd.c
@@ -134,7 +134,7 @@ static long riowd_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			return -EINVAL;
 		riowd_timeout = (new_margin + 59) / 60;
 		riowd_writereg(p, riowd_timeout, WDTO_INDEX);
-		/* Fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		return put_user(riowd_timeout * 60, (int __user *)argp);
diff --git a/drivers/watchdog/sa1100_wdt.c b/drivers/watchdog/sa1100_wdt.c
index 9b93be00109f..27846c6bdfb0 100644
--- a/drivers/watchdog/sa1100_wdt.c
+++ b/drivers/watchdog/sa1100_wdt.c
@@ -127,7 +127,7 @@ static long sa1100dog_ioctl(struct file *file, unsigned int cmd,
 
 		pre_margin = oscr_freq * time;
 		writel_relaxed(readl_relaxed(OSCR) + pre_margin, OSMR3);
-		/*fall through*/
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		ret = put_user(pre_margin / oscr_freq, p);
diff --git a/drivers/watchdog/sb_wdog.c b/drivers/watchdog/sb_wdog.c
index da2dad00d473..504be461f992 100644
--- a/drivers/watchdog/sb_wdog.c
+++ b/drivers/watchdog/sb_wdog.c
@@ -202,7 +202,7 @@ static long sbwdog_ioctl(struct file *file, unsigned int cmd,
 		timeout = time;
 		sbwdog_set(user_dog, timeout);
 		sbwdog_pet(user_dog);
-		/* Fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		/*
diff --git a/drivers/watchdog/sbc60xxwdt.c b/drivers/watchdog/sbc60xxwdt.c
index f2cbe6d880a8..a947a63fb44a 100644
--- a/drivers/watchdog/sbc60xxwdt.c
+++ b/drivers/watchdog/sbc60xxwdt.c
@@ -265,7 +265,7 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		timeout = new_timeout;
 		wdt_keepalive();
 	}
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, p);
 	default:
diff --git a/drivers/watchdog/sbc7240_wdt.c b/drivers/watchdog/sbc7240_wdt.c
index 520b8dd77ed4..d640b26e18a6 100644
--- a/drivers/watchdog/sbc7240_wdt.c
+++ b/drivers/watchdog/sbc7240_wdt.c
@@ -195,7 +195,7 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (wdt_set_timeout(new_timeout))
 			return -EINVAL;
 	}
-	/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, (int __user *)arg);
 	default:
diff --git a/drivers/watchdog/sbc_fitpc2_wdt.c b/drivers/watchdog/sbc_fitpc2_wdt.c
index 1b20b33879c4..04483d6453d6 100644
--- a/drivers/watchdog/sbc_fitpc2_wdt.c
+++ b/drivers/watchdog/sbc_fitpc2_wdt.c
@@ -154,7 +154,7 @@ static long fitpc2_wdt_ioctl(struct file *file, unsigned int cmd,
 
 		margin = time;
 		wdt_enable();
-		/* Fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		ret = put_user(margin, (int *)arg);
diff --git a/drivers/watchdog/sc520_wdt.c b/drivers/watchdog/sc520_wdt.c
index fbe79bcc9297..e66e6b905964 100644
--- a/drivers/watchdog/sc520_wdt.c
+++ b/drivers/watchdog/sc520_wdt.c
@@ -321,7 +321,7 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 		wdt_keepalive();
 	}
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, p);
 	default:
diff --git a/drivers/watchdog/sch311x_wdt.c b/drivers/watchdog/sch311x_wdt.c
index 83949a385f62..d8b77fe10eba 100644
--- a/drivers/watchdog/sch311x_wdt.c
+++ b/drivers/watchdog/sch311x_wdt.c
@@ -295,7 +295,7 @@ static long sch311x_wdt_ioctl(struct file *file, unsigned int cmd,
 		if (sch311x_wdt_set_heartbeat(new_timeout))
 			return -EINVAL;
 		sch311x_wdt_keepalive();
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, p);
 	default:
diff --git a/drivers/watchdog/smsc37b787_wdt.c b/drivers/watchdog/smsc37b787_wdt.c
index 43de56acd767..7463df479d11 100644
--- a/drivers/watchdog/smsc37b787_wdt.c
+++ b/drivers/watchdog/smsc37b787_wdt.c
@@ -474,7 +474,7 @@ static long wb_smsc_wdt_ioctl(struct file *file,
 			return -EINVAL;
 		timeout = new_timeout;
 		wb_smsc_wdt_set_timeout(timeout);
-		/* fall through - and return the new timeout... */
+		fallthrough;	/* and return the new timeout */
 	case WDIOC_GETTIMEOUT:
 		new_timeout = timeout;
 		if (unit == UNIT_MINUTE)
diff --git a/drivers/watchdog/w83877f_wdt.c b/drivers/watchdog/w83877f_wdt.c
index 6b3b667e6f23..5772cc5d3780 100644
--- a/drivers/watchdog/w83877f_wdt.c
+++ b/drivers/watchdog/w83877f_wdt.c
@@ -289,7 +289,7 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		timeout = new_timeout;
 		wdt_keepalive();
 	}
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, p);
 	default:
diff --git a/drivers/watchdog/w83977f_wdt.c b/drivers/watchdog/w83977f_wdt.c
index 5212e68c6b01..fd64ae77780a 100644
--- a/drivers/watchdog/w83977f_wdt.c
+++ b/drivers/watchdog/w83977f_wdt.c
@@ -422,7 +422,7 @@ static long wdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			return -EINVAL;
 
 		wdt_keepalive();
-		/* Fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, uarg.i);
diff --git a/drivers/watchdog/wafer5823wdt.c b/drivers/watchdog/wafer5823wdt.c
index a6925847f76f..a8a1ed215e1e 100644
--- a/drivers/watchdog/wafer5823wdt.c
+++ b/drivers/watchdog/wafer5823wdt.c
@@ -174,7 +174,7 @@ static long wafwdt_ioctl(struct file *file, unsigned int cmd,
 		timeout = new_timeout;
 		wafwdt_stop();
 		wafwdt_start();
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, p);
 
diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index de02d90a4878..b277eebd377e 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -776,7 +776,7 @@ static long watchdog_ioctl(struct file *file, unsigned int cmd,
 		err = watchdog_ping(wdd);
 		if (err < 0)
 			break;
-		/* fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		/* timeout == 0 means that we don't know the timeout */
 		if (wdd->timeout == 0) {
diff --git a/drivers/watchdog/wdt.c b/drivers/watchdog/wdt.c
index f9054cb0f8e2..a9e40b5c633e 100644
--- a/drivers/watchdog/wdt.c
+++ b/drivers/watchdog/wdt.c
@@ -389,7 +389,7 @@ static long wdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (wdt_set_heartbeat(new_heartbeat))
 			return -EINVAL;
 		wdt_ping();
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(heartbeat, p);
 	default:
diff --git a/drivers/watchdog/wdt285.c b/drivers/watchdog/wdt285.c
index e60993d0767e..110249e5f642 100644
--- a/drivers/watchdog/wdt285.c
+++ b/drivers/watchdog/wdt285.c
@@ -168,7 +168,7 @@ static long watchdog_ioctl(struct file *file, unsigned int cmd,
 		soft_margin = new_margin;
 		reload = soft_margin * (mem_fclk_21285 / 256);
 		watchdog_ping();
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		ret = put_user(soft_margin, int_arg);
 		break;
diff --git a/drivers/watchdog/wdt977.c b/drivers/watchdog/wdt977.c
index 066a4fb4d75b..c9b8e863f70f 100644
--- a/drivers/watchdog/wdt977.c
+++ b/drivers/watchdog/wdt977.c
@@ -398,7 +398,7 @@ static long wdt977_ioctl(struct file *file, unsigned int cmd,
 			return -EINVAL;
 
 		wdt977_keepalive();
-		/* Fall through */
+		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
 		return put_user(timeout, uarg.i);
diff --git a/drivers/watchdog/wdt_pci.c b/drivers/watchdog/wdt_pci.c
index e528024faa41..c3254ba5ace6 100644
--- a/drivers/watchdog/wdt_pci.c
+++ b/drivers/watchdog/wdt_pci.c
@@ -426,7 +426,7 @@ static long wdtpci_ioctl(struct file *file, unsigned int cmd,
 		if (wdtpci_set_heartbeat(new_heartbeat))
 			return -EINVAL;
 		wdtpci_ping();
-		/* fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		return put_user(heartbeat, p);
 	default:

From 55a1b87e07fdac9194d8b0c3ded3c4d01e9234ad Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Fri, 17 Jul 2020 11:40:59 -0500
Subject: [PATCH 228/474] watchdog: scx200_wdt: Use fallthrough pseudo-keyword

Replace the existing /* fall through */ comments and its variants with
the new pseudo-keyword macro fallthrough[1].

[1] https://www.kernel.org/doc/html/v5.7-rc7/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-through

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200717164059.GA26947@embeddedor
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/scx200_wdt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/scx200_wdt.c b/drivers/watchdog/scx200_wdt.c
index c94098acb78f..7b5e18323f3f 100644
--- a/drivers/watchdog/scx200_wdt.c
+++ b/drivers/watchdog/scx200_wdt.c
@@ -186,7 +186,7 @@ static long scx200_wdt_ioctl(struct file *file, unsigned int cmd,
 		margin = new_margin;
 		scx200_wdt_update_margin();
 		scx200_wdt_ping();
-		/* Fall through */
+		fallthrough;
 	case WDIOC_GETTIMEOUT:
 		if (put_user(margin, p))
 			return -EFAULT;

From ee86a03a5dc64899edb39fe1ce21429fed98d107 Mon Sep 17 00:00:00 2001
From: Timothy Myers <timothy.myers@adtran.com>
Date: Mon, 6 Jul 2020 16:33:31 +0000
Subject: [PATCH 229/474] watchdog: booke_wdt: Add common nowayout parameter
 driver

Add the common "nowayout" parameter to booke_wdt to make this behavior
selectable at runtime and to make the implementation more consistent with
many other watchdog drivers.

Signed-off-by: Timothy Myers <timothy.myers@adtran.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
[groeck: Dropped version data, cleaned up subject line]
Link: https://lore.kernel.org/r/CH2PR19MB359059AA5C8917D8D24633FF9D690@CH2PR19MB3590.namprd19.prod.outlook.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/booke_wdt.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/watchdog/booke_wdt.c b/drivers/watchdog/booke_wdt.c
index 9d09bbfdef20..7817fb976f9c 100644
--- a/drivers/watchdog/booke_wdt.c
+++ b/drivers/watchdog/booke_wdt.c
@@ -39,6 +39,11 @@ static bool booke_wdt_enabled;
 module_param(booke_wdt_enabled, bool, 0);
 static int  booke_wdt_period = CONFIG_BOOKE_WDT_DEFAULT_TIMEOUT;
 module_param(booke_wdt_period, int, 0);
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
+MODULE_PARM_DESC(nowayout,
+		"Watchdog cannot be stopped once started (default="
+				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
 #ifdef CONFIG_PPC_FSL_BOOK3E
 
@@ -215,7 +220,6 @@ static void __exit booke_wdt_exit(void)
 static int __init booke_wdt_init(void)
 {
 	int ret = 0;
-	bool nowayout = WATCHDOG_NOWAYOUT;
 
 	pr_info("powerpc book-e watchdog driver loaded\n");
 	booke_wdt_info.firmware_version = cur_cpu_spec->pvr_value;

From cb36e29bb0e4b0c33c3d5866a0a4aebace4c99b7 Mon Sep 17 00:00:00 2001
From: Krzysztof Sobota <krzysztof.sobota@nokia.com>
Date: Fri, 17 Jul 2020 12:31:09 +0200
Subject: [PATCH 230/474] watchdog: initialize device before misc_register

When watchdog device is being registered, it calls misc_register that
makes watchdog available for systemd to open. This is a data race
scenario, because when device is open it may still have device struct
not initialized - this in turn causes a crash. This patch moves
device initialization before misc_register call and it solves the
problem printed below.

------------[ cut here ]------------
WARNING: CPU: 3 PID: 1 at lib/kobject.c:612 kobject_get+0x50/0x54
kobject: '(null)' ((ptrval)): is not initialized, yet kobject_get() is being called.
Modules linked in: k2_reset_status(O) davinci_wdt(+) sfn_platform_hwbcn(O) fsmddg_sfn(O) clk_misc_mmap(O) clk_sw_bcn(O) fsp_reset(O) cma_mod(O) slave_sup_notif(O) fpga_master(O) latency(O+) evnotify(O) enable_arm_pmu(O) xge(O) rio_mport_cdev br_netfilter bridge stp llc nvrd_checksum(O) ipv6
CPU: 3 PID: 1 Comm: systemd Tainted: G           O      4.19.113-g2579778-fsm4_k2 #1
Hardware name: Keystone
[<c02126c4>] (unwind_backtrace) from [<c020da94>] (show_stack+0x18/0x1c)
[<c020da94>] (show_stack) from [<c07f87d8>] (dump_stack+0xb4/0xe8)
[<c07f87d8>] (dump_stack) from [<c0221f70>] (__warn+0xfc/0x114)
[<c0221f70>] (__warn) from [<c0221fd8>] (warn_slowpath_fmt+0x50/0x74)
[<c0221fd8>] (warn_slowpath_fmt) from [<c07fd394>] (kobject_get+0x50/0x54)
[<c07fd394>] (kobject_get) from [<c0602ce8>] (get_device+0x1c/0x24)
[<c0602ce8>] (get_device) from [<c06961e0>] (watchdog_open+0x90/0xf0)
[<c06961e0>] (watchdog_open) from [<c06001dc>] (misc_open+0x130/0x17c)
[<c06001dc>] (misc_open) from [<c0388228>] (chrdev_open+0xec/0x1a8)
[<c0388228>] (chrdev_open) from [<c037fa98>] (do_dentry_open+0x204/0x3cc)
[<c037fa98>] (do_dentry_open) from [<c0391e2c>] (path_openat+0x330/0x1148)
[<c0391e2c>] (path_openat) from [<c0394518>] (do_filp_open+0x78/0xec)
[<c0394518>] (do_filp_open) from [<c0381100>] (do_sys_open+0x130/0x1f4)
[<c0381100>] (do_sys_open) from [<c0201000>] (ret_fast_syscall+0x0/0x28)
Exception stack(0xd2ceffa8 to 0xd2cefff0)
ffa0:                   b6f69968 00000000 ffffff9c b6ebd210 000a0001 00000000
ffc0: b6f69968 00000000 00000000 00000142 fffffffd ffffffff 00b65530 bed7bb78
ffe0: 00000142 bed7ba70 b6cc2503 b6cc41d6
---[ end trace 7b16eb105513974f ]---

------------[ cut here ]------------
WARNING: CPU: 3 PID: 1 at lib/refcount.c:153 kobject_get+0x24/0x54
refcount_t: increment on 0; use-after-free.
Modules linked in: k2_reset_status(O) davinci_wdt(+) sfn_platform_hwbcn(O) fsmddg_sfn(O) clk_misc_mmap(O) clk_sw_bcn(O) fsp_reset(O) cma_mod(O) slave_sup_notif(O) fpga_master(O) latency(O+) evnotify(O) enable_arm_pmu(O) xge(O) rio_mport_cdev br_netfilter bridge stp llc nvrd_checksum(O) ipv6
CPU: 3 PID: 1 Comm: systemd Tainted: G        W  O      4.19.113-g2579778-fsm4_k2 #1
Hardware name: Keystone
[<c02126c4>] (unwind_backtrace) from [<c020da94>] (show_stack+0x18/0x1c)
[<c020da94>] (show_stack) from [<c07f87d8>] (dump_stack+0xb4/0xe8)
[<c07f87d8>] (dump_stack) from [<c0221f70>] (__warn+0xfc/0x114)
[<c0221f70>] (__warn) from [<c0221fd8>] (warn_slowpath_fmt+0x50/0x74)
[<c0221fd8>] (warn_slowpath_fmt) from [<c07fd368>] (kobject_get+0x24/0x54)
[<c07fd368>] (kobject_get) from [<c0602ce8>] (get_device+0x1c/0x24)
[<c0602ce8>] (get_device) from [<c06961e0>] (watchdog_open+0x90/0xf0)
[<c06961e0>] (watchdog_open) from [<c06001dc>] (misc_open+0x130/0x17c)
[<c06001dc>] (misc_open) from [<c0388228>] (chrdev_open+0xec/0x1a8)
[<c0388228>] (chrdev_open) from [<c037fa98>] (do_dentry_open+0x204/0x3cc)
[<c037fa98>] (do_dentry_open) from [<c0391e2c>] (path_openat+0x330/0x1148)
[<c0391e2c>] (path_openat) from [<c0394518>] (do_filp_open+0x78/0xec)
[<c0394518>] (do_filp_open) from [<c0381100>] (do_sys_open+0x130/0x1f4)
[<c0381100>] (do_sys_open) from [<c0201000>] (ret_fast_syscall+0x0/0x28)
Exception stack(0xd2ceffa8 to 0xd2cefff0)
ffa0:                   b6f69968 00000000 ffffff9c b6ebd210 000a0001 00000000
ffc0: b6f69968 00000000 00000000 00000142 fffffffd ffffffff 00b65530 bed7bb78
ffe0: 00000142 bed7ba70 b6cc2503 b6cc41d6
---[ end trace 7b16eb1055139750 ]---

Fixes: 72139dfa2464 ("watchdog: Fix the race between the release of watchdog_core_data and cdev")
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Signed-off-by: Krzysztof Sobota <krzysztof.sobota@nokia.com>
Link: https://lore.kernel.org/r/20200717103109.14660-1-krzysztof.sobota@nokia.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/watchdog_dev.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index b277eebd377e..b7d750b24e49 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -994,6 +994,15 @@ static int watchdog_cdev_register(struct watchdog_device *wdd)
 	if (IS_ERR_OR_NULL(watchdog_kworker))
 		return -ENODEV;
 
+	device_initialize(&wd_data->dev);
+	wd_data->dev.devt = MKDEV(MAJOR(watchdog_devt), wdd->id);
+	wd_data->dev.class = &watchdog_class;
+	wd_data->dev.parent = wdd->parent;
+	wd_data->dev.groups = wdd->groups;
+	wd_data->dev.release = watchdog_core_data_release;
+	dev_set_drvdata(&wd_data->dev, wdd);
+	dev_set_name(&wd_data->dev, "watchdog%d", wdd->id);
+
 	kthread_init_work(&wd_data->work, watchdog_ping_work);
 	hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	wd_data->timer.function = watchdog_timer_expired;
@@ -1014,15 +1023,6 @@ static int watchdog_cdev_register(struct watchdog_device *wdd)
 		}
 	}
 
-	device_initialize(&wd_data->dev);
-	wd_data->dev.devt = MKDEV(MAJOR(watchdog_devt), wdd->id);
-	wd_data->dev.class = &watchdog_class;
-	wd_data->dev.parent = wdd->parent;
-	wd_data->dev.groups = wdd->groups;
-	wd_data->dev.release = watchdog_core_data_release;
-	dev_set_drvdata(&wd_data->dev, wdd);
-	dev_set_name(&wd_data->dev, "watchdog%d", wdd->id);
-
 	/* Fill in the data structures */
 	cdev_init(&wd_data->cdev, &watchdog_fops);
 

From d821ab28dfd2fa85a9aed133e9bfd368c156cc04 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Wed, 15 Jul 2020 12:09:06 +0100
Subject: [PATCH 231/474] dt-bindings: watchdog: renesas,wdt: Document r8a774e1
 support

RZ/G2H (a.k.a. R8A774E1) watchdog implementation is compatible
with R-Car Gen3, therefore add the relevant documentation.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/1594811350-14066-17-git-send-email-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml b/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml
index 572f4c912fef..6933005b52bd 100644
--- a/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml
@@ -41,6 +41,7 @@ properties:
               - renesas,r8a774a1-wdt     # RZ/G2M
               - renesas,r8a774b1-wdt     # RZ/G2N
               - renesas,r8a774c0-wdt     # RZ/G2E
+              - renesas,r8a774e1-wdt     # RZ/G2H
               - renesas,r8a7795-wdt      # R-Car H3
               - renesas,r8a7796-wdt      # R-Car M3-W
               - renesas,r8a77961-wdt     # R-Car M3-W+

From 2ab77a34d070b1611a52b50c7cfae074153d475b Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Mon, 13 Jul 2020 22:58:21 +0200
Subject: [PATCH 232/474] watchdog: Replace HTTP links with HTTPS ones

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `\bxmlns\b`:
        For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
	  If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`:
            If both the HTTP and HTTPS versions
            return 200 OK and serve the same content:
              Replace HTTP with HTTPS.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20200713205821.38223-1-grandmaster@al2klimov.de
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 Documentation/devicetree/bindings/watchdog/davinci-wdt.txt | 4 ++--
 drivers/watchdog/Kconfig                                   | 2 +-
 drivers/watchdog/dw_wdt.c                                  | 2 +-
 drivers/watchdog/nv_tco.c                                  | 2 +-
 drivers/watchdog/nv_tco.h                                  | 2 +-
 drivers/watchdog/sp5100_tco.c                              | 2 +-
 6 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/Documentation/devicetree/bindings/watchdog/davinci-wdt.txt b/Documentation/devicetree/bindings/watchdog/davinci-wdt.txt
index e60b9a13bdcb..aa10b8ec36e2 100644
--- a/Documentation/devicetree/bindings/watchdog/davinci-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/davinci-wdt.txt
@@ -11,8 +11,8 @@ Optional properties:
 	   See clock-bindings.txt
 
 Documentation:
-Davinci DM646x - http://www.ti.com/lit/ug/spruer5b/spruer5b.pdf
-Keystone - http://www.ti.com/lit/ug/sprugv5a/sprugv5a.pdf
+Davinci DM646x - https://www.ti.com/lit/ug/spruer5b/spruer5b.pdf
+Keystone - https://www.ti.com/lit/ug/sprugv5a/sprugv5a.pdf
 
 Examples:
 
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 4f4687c46d38..ab7aad5a1e69 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -1027,7 +1027,7 @@ config ADVANTECH_WDT
 	  If you are configuring a Linux kernel for the Advantech single-board
 	  computer, say `Y' here to support its built-in watchdog timer
 	  feature. More information can be found at
-	  <http://www.advantech.com.tw/products/>
+	  <https://www.advantech.com.tw/products/>
 
 config ALIM1535_WDT
 	tristate "ALi M1535 PMU Watchdog Timer"
diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c
index 4fec2c6a3c01..32d0e1781e63 100644
--- a/drivers/watchdog/dw_wdt.c
+++ b/drivers/watchdog/dw_wdt.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2010-2011 Picochip Ltd., Jamie Iles
- * http://www.picochip.com
+ * https://www.picochip.com
  *
  * This file implements a driver for the Synopsys DesignWare watchdog device
  * in the many subsystems. The watchdog has 16 different timeout periods
diff --git a/drivers/watchdog/nv_tco.c b/drivers/watchdog/nv_tco.c
index d15ad8583a59..f6902a337422 100644
--- a/drivers/watchdog/nv_tco.c
+++ b/drivers/watchdog/nv_tco.c
@@ -7,7 +7,7 @@
  *	Based off i8xx_tco.c:
  *	(c) Copyright 2000 kernel concepts <nils@kernelconcepts.de>, All Rights
  *	Reserved.
- *				http://www.kernelconcepts.de
+ *				https://www.kernelconcepts.de
  *
  *	TCO timer driver for NV chipsets
  *	based on softdog.c by Alan Cox <alan@redhat.com>
diff --git a/drivers/watchdog/nv_tco.h b/drivers/watchdog/nv_tco.h
index d325e528010f..c65f82588386 100644
--- a/drivers/watchdog/nv_tco.h
+++ b/drivers/watchdog/nv_tco.h
@@ -9,7 +9,7 @@
  *
  *	(c) Copyright 2000 kernel concepts <nils@kernelconcepts.de>, All Rights
  *	Reserved.
- *				http://www.kernelconcepts.de
+ *				https://www.kernelconcepts.de
  *
  *	Neither kernel concepts nor Nils Faerber admit liability nor provide
  *	warranty for any of this software. This material is provided
diff --git a/drivers/watchdog/sp5100_tco.c b/drivers/watchdog/sp5100_tco.c
index 93bd302ae7c5..85e9664318c9 100644
--- a/drivers/watchdog/sp5100_tco.c
+++ b/drivers/watchdog/sp5100_tco.c
@@ -7,7 +7,7 @@
  *	Based on i8xx_tco.c:
  *	(c) Copyright 2000 kernel concepts <nils@kernelconcepts.de>, All Rights
  *	Reserved.
- *				http://www.kernelconcepts.de
+ *				https://www.kernelconcepts.de
  *
  *	See AMD Publication 43009 "AMD SB700/710/750 Register Reference Guide",
  *	    AMD Publication 45482 "AMD SB800-Series Southbridges Register

From f1889c9066722f56428978ce9431a6cacabecb57 Mon Sep 17 00:00:00 2001
From: Xu Wang <vulab@iscas.ac.cn>
Date: Mon, 13 Jul 2020 05:53:48 +0000
Subject: [PATCH 233/474] watchdog: pcwd_usb: remove needless check before
 usb_free_coherent()

usb_free_coherent() is safe with NULL usb_pcwd->intr_buffer and
this check is not required.

Signed-off-by: Xu Wang <vulab@iscas.ac.cn>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200713055348.21620-1-vulab@iscas.ac.cn
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/pcwd_usb.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/watchdog/pcwd_usb.c b/drivers/watchdog/pcwd_usb.c
index 79efca47cebb..41a928eb91ed 100644
--- a/drivers/watchdog/pcwd_usb.c
+++ b/drivers/watchdog/pcwd_usb.c
@@ -585,9 +585,8 @@ static struct notifier_block usb_pcwd_notifier = {
 static inline void usb_pcwd_delete(struct usb_pcwd_private *usb_pcwd)
 {
 	usb_free_urb(usb_pcwd->intr_urb);
-	if (usb_pcwd->intr_buffer != NULL)
-		usb_free_coherent(usb_pcwd->udev, usb_pcwd->intr_size,
-				  usb_pcwd->intr_buffer, usb_pcwd->intr_dma);
+	usb_free_coherent(usb_pcwd->udev, usb_pcwd->intr_size,
+			  usb_pcwd->intr_buffer, usb_pcwd->intr_dma);
 	kfree(usb_pcwd);
 }
 

From 36a8947c6b5423b2fb867a7af87ae40eb12f4123 Mon Sep 17 00:00:00 2001
From: Woody Lin <woodylin@google.com>
Date: Wed, 8 Jul 2020 16:32:19 +0800
Subject: [PATCH 234/474] watchdog: softdog: Add options 'soft_reboot_cmd' and
 'soft_active_on_boot'

Add module parameters 'soft_reboot_cmd' and 'soft_active_on_boot' for
customizing softdog configuration; config reboot command by assigning
soft_reboot_cmd, and set soft_active_on_boot to start up softdog
timer at module initialization stage.

Signed-off-by: Woody Lin <woodylin@google.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200708083218.3157213-1-woodylin@google.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/softdog.c | 57 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 57 insertions(+)

diff --git a/drivers/watchdog/softdog.c b/drivers/watchdog/softdog.c
index 3e4885c1545e..7a1096265f18 100644
--- a/drivers/watchdog/softdog.c
+++ b/drivers/watchdog/softdog.c
@@ -20,11 +20,13 @@
 #include <linux/hrtimer.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/reboot.h>
 #include <linux/types.h>
 #include <linux/watchdog.h>
+#include <linux/workqueue.h>
 
 #define TIMER_MARGIN	60		/* Default is 60 seconds */
 static unsigned int soft_margin = TIMER_MARGIN;	/* in seconds */
@@ -49,11 +51,34 @@ module_param(soft_panic, int, 0);
 MODULE_PARM_DESC(soft_panic,
 	"Softdog action, set to 1 to panic, 0 to reboot (default=0)");
 
+static char *soft_reboot_cmd;
+module_param(soft_reboot_cmd, charp, 0000);
+MODULE_PARM_DESC(soft_reboot_cmd,
+	"Set reboot command. Emergency reboot takes place if unset");
+
+static bool soft_active_on_boot;
+module_param(soft_active_on_boot, bool, 0000);
+MODULE_PARM_DESC(soft_active_on_boot,
+	"Set to true to active Softdog on boot (default=false)");
+
 static struct hrtimer softdog_ticktock;
 static struct hrtimer softdog_preticktock;
 
+static int reboot_kthread_fn(void *data)
+{
+	kernel_restart(soft_reboot_cmd);
+	return -EPERM; /* Should not reach here */
+}
+
+static void reboot_work_fn(struct work_struct *unused)
+{
+	kthread_run(reboot_kthread_fn, NULL, "softdog_reboot");
+}
+
 static enum hrtimer_restart softdog_fire(struct hrtimer *timer)
 {
+	static bool soft_reboot_fired;
+
 	module_put(THIS_MODULE);
 	if (soft_noboot) {
 		pr_crit("Triggered - Reboot ignored\n");
@@ -62,6 +87,33 @@ static enum hrtimer_restart softdog_fire(struct hrtimer *timer)
 		panic("Software Watchdog Timer expired");
 	} else {
 		pr_crit("Initiating system reboot\n");
+		if (!soft_reboot_fired && soft_reboot_cmd != NULL) {
+			static DECLARE_WORK(reboot_work, reboot_work_fn);
+			/*
+			 * The 'kernel_restart' is a 'might-sleep' operation.
+			 * Also, executing it in system-wide workqueues blocks
+			 * any driver from using the same workqueue in its
+			 * shutdown callback function. Thus, we should execute
+			 * the 'kernel_restart' in a standalone kernel thread.
+			 * But since starting a kernel thread is also a
+			 * 'might-sleep' operation, so the 'reboot_work' is
+			 * required as a launcher of the kernel thread.
+			 *
+			 * After request the reboot, restart the timer to
+			 * schedule an 'emergency_restart' reboot after
+			 * 'TIMER_MARGIN' seconds. It's because if the softdog
+			 * hangs, it might be because of scheduling issues. And
+			 * if that is the case, both 'schedule_work' and
+			 * 'kernel_restart' may possibly be malfunctional at the
+			 * same time.
+			 */
+			soft_reboot_fired = true;
+			schedule_work(&reboot_work);
+			hrtimer_add_expires_ns(timer,
+					(u64)TIMER_MARGIN * NSEC_PER_SEC);
+
+			return HRTIMER_RESTART;
+		}
 		emergency_restart();
 		pr_crit("Reboot didn't ?????\n");
 	}
@@ -145,12 +197,17 @@ static int __init softdog_init(void)
 		softdog_preticktock.function = softdog_pretimeout;
 	}
 
+	if (soft_active_on_boot)
+		softdog_ping(&softdog_dev);
+
 	ret = watchdog_register_device(&softdog_dev);
 	if (ret)
 		return ret;
 
 	pr_info("initialized. soft_noboot=%d soft_margin=%d sec soft_panic=%d (nowayout=%d)\n",
 		soft_noboot, softdog_dev.timeout, soft_panic, nowayout);
+	pr_info("             soft_reboot_cmd=%s soft_active_on_boot=%d\n",
+		soft_reboot_cmd ?: "<not set>", soft_active_on_boot);
 
 	return 0;
 }

From fbbe35dfcf949f4d6cf987648e52a85fc0c2a23a Mon Sep 17 00:00:00 2001
From: Tero Kristo <t-kristo@ti.com>
Date: Fri, 17 Jul 2020 16:29:55 +0300
Subject: [PATCH 235/474] watchdog: use __watchdog_ping in startup

Current watchdog startup functionality does not respect the minimum hw
heartbeat setup and the last watchdog ping timeframe when watchdog is
already running and userspace process attaches to it. Fix this by using
the __watchdog_ping from the startup also. For this code path, we can
also let the __watchdog_ping handle the bookkeeping for the worker and
last keepalive times.

Signed-off-by: Tero Kristo <t-kristo@ti.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200717132958.14304-2-t-kristo@ti.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/watchdog_dev.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index b7d750b24e49..0ad1c393c00e 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -275,15 +275,18 @@ static int watchdog_start(struct watchdog_device *wdd)
 	set_bit(_WDOG_KEEPALIVE, &wd_data->status);
 
 	started_at = ktime_get();
-	if (watchdog_hw_running(wdd) && wdd->ops->ping)
-		err = wdd->ops->ping(wdd);
-	else
+	if (watchdog_hw_running(wdd) && wdd->ops->ping) {
+		err = __watchdog_ping(wdd);
+		if (err == 0)
+			set_bit(WDOG_ACTIVE, &wdd->status);
+	} else {
 		err = wdd->ops->start(wdd);
-	if (err == 0) {
-		set_bit(WDOG_ACTIVE, &wdd->status);
-		wd_data->last_keepalive = started_at;
-		wd_data->last_hw_keepalive = started_at;
-		watchdog_update_worker(wdd);
+		if (err == 0) {
+			set_bit(WDOG_ACTIVE, &wdd->status);
+			wd_data->last_keepalive = started_at;
+			wd_data->last_hw_keepalive = started_at;
+			watchdog_update_worker(wdd);
+		}
 	}
 
 	return err;

From cef9572e9af373cefd1adc9e771e89670da5da3c Mon Sep 17 00:00:00 2001
From: Tero Kristo <t-kristo@ti.com>
Date: Fri, 17 Jul 2020 16:29:56 +0300
Subject: [PATCH 236/474] watchdog: add support for adjusting last known HW
 keepalive time

Certain watchdogs require the watchdog only to be pinged within a
specific time window, pinging too early or too late cause the watchdog
to fire. In cases where this sort of watchdog has been started before
kernel comes up, we must adjust the watchdog keepalive window to match
the actually running timer, so add a new driver API for this purpose.

Signed-off-by: Tero Kristo <t-kristo@ti.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200717132958.14304-3-t-kristo@ti.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 .../watchdog/watchdog-kernel-api.rst          | 12 ++++++++
 drivers/watchdog/watchdog_dev.c               | 30 +++++++++++++++++++
 include/linux/watchdog.h                      |  2 ++
 3 files changed, 44 insertions(+)

diff --git a/Documentation/watchdog/watchdog-kernel-api.rst b/Documentation/watchdog/watchdog-kernel-api.rst
index 068a55ee0d4a..baf44e986b07 100644
--- a/Documentation/watchdog/watchdog-kernel-api.rst
+++ b/Documentation/watchdog/watchdog-kernel-api.rst
@@ -336,3 +336,15 @@ an action is taken by a preconfigured pretimeout governor preassigned to
 the watchdog device. If watchdog pretimeout governor framework is not
 enabled, watchdog_notify_pretimeout() prints a notification message to
 the kernel log buffer.
+
+To set the last known HW keepalive time for a watchdog, the following function
+should be used::
+
+  int watchdog_set_last_hw_keepalive(struct watchdog_device *wdd,
+                                     unsigned int last_ping_ms)
+
+This function must be called immediately after watchdog registration. It
+sets the last known hardware heartbeat to have happened last_ping_ms before
+current time. Calling this is only needed if the watchdog is already running
+when probe is called, and the watchdog can only be pinged after the
+min_hw_heartbeat_ms time has passed from the last ping.
diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index 0ad1c393c00e..531e74994b61 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -1138,6 +1138,36 @@ void watchdog_dev_unregister(struct watchdog_device *wdd)
 	watchdog_cdev_unregister(wdd);
 }
 
+/*
+ *	watchdog_set_last_hw_keepalive: set last HW keepalive time for watchdog
+ *	@wdd: watchdog device
+ *	@last_ping_ms: time since last HW heartbeat
+ *
+ *	Adjusts the last known HW keepalive time for a watchdog timer.
+ *	This is needed if the watchdog is already running when the probe
+ *	function is called, and it can't be pinged immediately. This
+ *	function must be called immediately after watchdog registration,
+ *	and min_hw_heartbeat_ms must be set for this to be useful.
+ */
+int watchdog_set_last_hw_keepalive(struct watchdog_device *wdd,
+				   unsigned int last_ping_ms)
+{
+	struct watchdog_core_data *wd_data;
+	ktime_t now;
+
+	if (!wdd)
+		return -EINVAL;
+
+	wd_data = wdd->wd_data;
+
+	now = ktime_get();
+
+	wd_data->last_hw_keepalive = ktime_sub(now, ms_to_ktime(last_ping_ms));
+
+	return __watchdog_ping(wdd);
+}
+EXPORT_SYMBOL_GPL(watchdog_set_last_hw_keepalive);
+
 /*
  *	watchdog_dev_init: init dev part of watchdog core
  *
diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h
index 1464ce6ffa31..9b19e6bb68b5 100644
--- a/include/linux/watchdog.h
+++ b/include/linux/watchdog.h
@@ -210,6 +210,8 @@ extern int watchdog_init_timeout(struct watchdog_device *wdd,
 extern int watchdog_register_device(struct watchdog_device *);
 extern void watchdog_unregister_device(struct watchdog_device *);
 
+int watchdog_set_last_hw_keepalive(struct watchdog_device *, unsigned int);
+
 /* devres register variant */
 int devm_watchdog_register_device(struct device *dev, struct watchdog_device *);
 

From 5527483f8f7c8edadb5ad4fe8fcb569f565369ea Mon Sep 17 00:00:00 2001
From: Tero Kristo <t-kristo@ti.com>
Date: Fri, 17 Jul 2020 16:29:57 +0300
Subject: [PATCH 237/474] watchdog: rti-wdt: attach to running watchdog during
 probe

If the RTI watchdog is running already during probe, the driver must
configure itself to match the HW. Window size and timeout is probed from
hardware, and the last keepalive ping is adjusted to match it also.

Signed-off-by: Tero Kristo <t-kristo@ti.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200717132958.14304-4-t-kristo@ti.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/rti_wdt.c | 112 +++++++++++++++++++++++++++++++++----
 1 file changed, 102 insertions(+), 10 deletions(-)

diff --git a/drivers/watchdog/rti_wdt.c b/drivers/watchdog/rti_wdt.c
index d456dd72d99a..7cbdc178ffe8 100644
--- a/drivers/watchdog/rti_wdt.c
+++ b/drivers/watchdog/rti_wdt.c
@@ -35,7 +35,11 @@
 
 #define RTIWWDRX_NMI	0xa
 
-#define RTIWWDSIZE_50P	0x50
+#define RTIWWDSIZE_50P		0x50
+#define RTIWWDSIZE_25P		0x500
+#define RTIWWDSIZE_12P5		0x5000
+#define RTIWWDSIZE_6P25		0x50000
+#define RTIWWDSIZE_3P125	0x500000
 
 #define WDENABLE_KEY	0xa98559da
 
@@ -48,7 +52,7 @@
 
 #define DWDST			BIT(1)
 
-static int heartbeat;
+static int heartbeat = DEFAULT_HEARTBEAT;
 
 /*
  * struct to hold data for each WDT device
@@ -79,11 +83,9 @@ static int rti_wdt_start(struct watchdog_device *wdd)
 	 * be petted during the open window; not too early or not too late.
 	 * The HW configuration options only allow for the open window size
 	 * to be 50% or less than that; we obviouly want to configure the open
-	 * window as large as possible so we select the 50% option. To avoid
-	 * any glitches, we accommodate 5% safety margin also, so we setup
-	 * the min_hw_hearbeat at 55% of the timeout period.
+	 * window as large as possible so we select the 50% option.
 	 */
-	wdd->min_hw_heartbeat_ms = 11 * wdd->timeout * 1000 / 20;
+	wdd->min_hw_heartbeat_ms = 500 * wdd->timeout;
 
 	/* Generate NMI when wdt expires */
 	writel_relaxed(RTIWWDRX_NMI, wdt->base + RTIWWDRXCTRL);
@@ -110,7 +112,48 @@ static int rti_wdt_ping(struct watchdog_device *wdd)
 	return 0;
 }
 
-static unsigned int rti_wdt_get_timeleft(struct watchdog_device *wdd)
+static int rti_wdt_setup_hw_hb(struct watchdog_device *wdd, u32 wsize)
+{
+	/*
+	 * RTI only supports a windowed mode, where the watchdog can only
+	 * be petted during the open window; not too early or not too late.
+	 * The HW configuration options only allow for the open window size
+	 * to be 50% or less than that.
+	 */
+	switch (wsize) {
+	case RTIWWDSIZE_50P:
+		/* 50% open window => 50% min heartbeat */
+		wdd->min_hw_heartbeat_ms = 500 * heartbeat;
+		break;
+
+	case RTIWWDSIZE_25P:
+		/* 25% open window => 75% min heartbeat */
+		wdd->min_hw_heartbeat_ms = 750 * heartbeat;
+		break;
+
+	case RTIWWDSIZE_12P5:
+		/* 12.5% open window => 87.5% min heartbeat */
+		wdd->min_hw_heartbeat_ms = 875 * heartbeat;
+		break;
+
+	case RTIWWDSIZE_6P25:
+		/* 6.5% open window => 93.5% min heartbeat */
+		wdd->min_hw_heartbeat_ms = 935 * heartbeat;
+		break;
+
+	case RTIWWDSIZE_3P125:
+		/* 3.125% open window => 96.9% min heartbeat */
+		wdd->min_hw_heartbeat_ms = 969 * heartbeat;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static unsigned int rti_wdt_get_timeleft_ms(struct watchdog_device *wdd)
 {
 	u64 timer_counter;
 	u32 val;
@@ -123,11 +166,18 @@ static unsigned int rti_wdt_get_timeleft(struct watchdog_device *wdd)
 
 	timer_counter = readl_relaxed(wdt->base + RTIDWDCNTR);
 
+	timer_counter *= 1000;
+
 	do_div(timer_counter, wdt->freq);
 
 	return timer_counter;
 }
 
+static unsigned int rti_wdt_get_timeleft(struct watchdog_device *wdd)
+{
+	return rti_wdt_get_timeleft_ms(wdd) / 1000;
+}
+
 static const struct watchdog_info rti_wdt_info = {
 	.options = WDIOF_KEEPALIVEPING,
 	.identity = "K3 RTI Watchdog",
@@ -148,6 +198,7 @@ static int rti_wdt_probe(struct platform_device *pdev)
 	struct watchdog_device *wdd;
 	struct rti_wdt_device *wdt;
 	struct clk *clk;
+	u32 last_ping = 0;
 
 	wdt = devm_kzalloc(dev, sizeof(*wdt), GFP_KERNEL);
 	if (!wdt)
@@ -169,6 +220,14 @@ static int rti_wdt_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	/*
+	 * If watchdog is running at 32k clock, it is not accurate.
+	 * Adjust frequency down in this case so that we don't pet
+	 * the watchdog too often.
+	 */
+	if (wdt->freq < 32768)
+		wdt->freq = wdt->freq * 9 / 10;
+
 	pm_runtime_enable(dev);
 	ret = pm_runtime_get_sync(dev);
 	if (ret) {
@@ -185,11 +244,8 @@ static int rti_wdt_probe(struct platform_device *pdev)
 	wdd->min_timeout = 1;
 	wdd->max_hw_heartbeat_ms = (WDT_PRELOAD_MAX << WDT_PRELOAD_SHIFT) /
 		wdt->freq * 1000;
-	wdd->timeout = DEFAULT_HEARTBEAT;
 	wdd->parent = dev;
 
-	watchdog_init_timeout(wdd, heartbeat, dev);
-
 	watchdog_set_drvdata(wdd, wdt);
 	watchdog_set_nowayout(wdd, 1);
 	watchdog_set_restart_priority(wdd, 128);
@@ -201,12 +257,48 @@ static int rti_wdt_probe(struct platform_device *pdev)
 		goto err_iomap;
 	}
 
+	if (readl(wdt->base + RTIDWDCTRL) == WDENABLE_KEY) {
+		u32 time_left_ms;
+		u64 heartbeat_ms;
+		u32 wsize;
+
+		set_bit(WDOG_HW_RUNNING, &wdd->status);
+		time_left_ms = rti_wdt_get_timeleft_ms(wdd);
+		heartbeat_ms = readl(wdt->base + RTIDWDPRLD);
+		heartbeat_ms <<= WDT_PRELOAD_SHIFT;
+		heartbeat_ms *= 1000;
+		do_div(heartbeat_ms, wdt->freq);
+		if (heartbeat_ms != heartbeat * 1000)
+			dev_warn(dev, "watchdog already running, ignoring heartbeat config!\n");
+
+		heartbeat = heartbeat_ms;
+		heartbeat /= 1000;
+
+		wsize = readl(wdt->base + RTIWWDSIZECTRL);
+		ret = rti_wdt_setup_hw_hb(wdd, wsize);
+		if (ret) {
+			dev_err(dev, "bad window size.\n");
+			goto err_iomap;
+		}
+
+		last_ping = heartbeat_ms - time_left_ms;
+		if (time_left_ms > heartbeat_ms) {
+			dev_warn(dev, "time_left > heartbeat? Assuming last ping just before now.\n");
+			last_ping = 0;
+		}
+	}
+
+	watchdog_init_timeout(wdd, heartbeat, dev);
+
 	ret = watchdog_register_device(wdd);
 	if (ret) {
 		dev_err(dev, "cannot register watchdog device\n");
 		goto err_iomap;
 	}
 
+	if (last_ping)
+		watchdog_set_last_hw_keepalive(wdd, last_ping);
+
 	return 0;
 
 err_iomap:

From d5b29c2c5ba2bd5bbdb5b744659984185d17d079 Mon Sep 17 00:00:00 2001
From: Tero Kristo <t-kristo@ti.com>
Date: Fri, 17 Jul 2020 16:29:58 +0300
Subject: [PATCH 238/474] watchdog: rti-wdt: balance pm runtime enable calls

PM runtime should be disabled in the fail path of probe and when
the driver is removed.

Fixes: 2d63908bdbfb ("watchdog: Add K3 RTI watchdog support")
Signed-off-by: Tero Kristo <t-kristo@ti.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20200717132958.14304-5-t-kristo@ti.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/rti_wdt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/watchdog/rti_wdt.c b/drivers/watchdog/rti_wdt.c
index 7cbdc178ffe8..705e8f7523e8 100644
--- a/drivers/watchdog/rti_wdt.c
+++ b/drivers/watchdog/rti_wdt.c
@@ -303,6 +303,7 @@ static int rti_wdt_probe(struct platform_device *pdev)
 
 err_iomap:
 	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 
 	return ret;
 }
@@ -313,6 +314,7 @@ static int rti_wdt_remove(struct platform_device *pdev)
 
 	watchdog_unregister_device(&wdt->wdd);
 	pm_runtime_put(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 
 	return 0;
 }

From 2342ef4e6021f5f7f2b3d4daa1ed6d1140b1378b Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 10 Jul 2020 09:37:58 +0100
Subject: [PATCH 239/474] drm/amdgpu: fix spelling mistake "Falied" -> "Failed"

There is a spelling mistake in a DRM_ERROR error message. Fix it.

This got lost in a merge, restore the fix.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 4afaa61db9cf5250b5734c2531b226e7b3a3d691)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index fe7d39bb975d..8034111acd9a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1987,7 +1987,7 @@ static int psp_suspend(void *handle)
 
 	ret = psp_tmr_terminate(psp);
 	if (ret) {
-		DRM_ERROR("Falied to terminate tmr\n");
+		DRM_ERROR("Failed to terminate tmr\n");
 		return ret;
 	}
 

From ebfbd1c2ca02f1c1bc9f8f0a7783e71efb57e4cc Mon Sep 17 00:00:00 2001
From: John Clements <john.clements@amd.com>
Date: Wed, 22 Jul 2020 09:40:11 +0800
Subject: [PATCH 240/474] drm/amdgpu: expand sienna chichlid reg access 
 support

Added dedicated 64bit reg read/write support

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/nv.c | 45 +++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index ea69ae76773e..74d02d270d34 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -97,6 +97,49 @@ static void nv_pcie_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
 }
 
+static u64 nv_pcie_rreg64(struct amdgpu_device *adev, u32 reg)
+{
+	unsigned long flags, address, data;
+	u64 r;
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
+
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
+	/* read low 32 bit */
+	WREG32(address, reg);
+	(void)RREG32(address);
+	r = RREG32(data);
+
+	/* read high 32 bit*/
+	WREG32(address, reg + 4);
+	(void)RREG32(address);
+	r |= ((u64)RREG32(data) << 32);
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+	return r;
+}
+
+static void nv_pcie_wreg64(struct amdgpu_device *adev, u32 reg, u64 v)
+{
+	unsigned long flags, address, data;
+
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
+
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
+	/* write low 32 bit */
+	WREG32(address, reg);
+	(void)RREG32(address);
+	WREG32(data, (u32)(v & 0xffffffffULL));
+	(void)RREG32(data);
+
+	/* write high 32 bit */
+	WREG32(address, reg + 4);
+	(void)RREG32(address);
+	WREG32(data, (u32)(v >> 32));
+	(void)RREG32(data);
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+}
+
 static u32 nv_didt_rreg(struct amdgpu_device *adev, u32 reg)
 {
 	unsigned long flags, address, data;
@@ -673,6 +716,8 @@ static int nv_common_early_init(void *handle)
 	adev->smc_wreg = NULL;
 	adev->pcie_rreg = &nv_pcie_rreg;
 	adev->pcie_wreg = &nv_pcie_wreg;
+	adev->pcie_rreg64 = &nv_pcie_rreg64;
+	adev->pcie_wreg64 = &nv_pcie_wreg64;
 
 	/* TODO: will add them during VCN v2 implementation */
 	adev->uvd_ctx_rreg = NULL;

From ee10e06eb00c3b371fa17a13ee2adaee4254dd54 Mon Sep 17 00:00:00 2001
From: Guchun Chen <guchun.chen@amd.com>
Date: Mon, 20 Jul 2020 11:11:13 +0800
Subject: [PATCH 241/474] drm/amdgpu: add printing after executing page
 reservation to eeprom

This will tell users if the faulty page has been written to
external eeprom device in dmesg log.

Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index e10f02ed3f65..bcce4c0be462 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1618,7 +1618,7 @@ static int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
 	data = con->eh_data;
 	save_count = data->count - control->num_recs;
 	/* only new entries are saved */
-	if (save_count > 0)
+	if (save_count > 0) {
 		if (amdgpu_ras_eeprom_process_recods(control,
 							&data->bps[control->num_recs],
 							true,
@@ -1627,6 +1627,9 @@ static int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
 			return -EIO;
 		}
 
+		dev_info(adev->dev, "Saved %d pages to EEPROM table.\n", save_count);
+	}
+
 	return 0;
 }
 

From ffa453f05be1513a2a68df0bce530db0d13480de Mon Sep 17 00:00:00 2001
From: Changfeng <Changfeng.Zhu@amd.com>
Date: Tue, 21 Jul 2020 10:38:19 +0800
Subject: [PATCH 242/474] Revert "drm/amd/powerplay: drop unnecessary message
 support check"

The below 3 messages are not supported on Renoir
SMU_MSG_PrepareMp1ForShutdown
SMU_MSG_PrepareMp1ForUnload
SMU_MSG_PrepareMp1ForReset

It needs to revert patch:
drm/amd/powerplay: drop unnecessary message support check
to avoid set mp1 state fail during gpu reset on renoir.

Signed-off-by: changfeng <Changfeng.Zhu@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 9 +++++++++
 drivers/gpu/drm/amd/powerplay/smu_cmn.h    | 2 +-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 838a369c9ec3..f778b00e49eb 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -34,6 +34,7 @@
 #include "sienna_cichlid_ppt.h"
 #include "renoir_ppt.h"
 #include "amd_pcie.h"
+#include "smu_cmn.h"
 
 /*
  * DO NOT use these for err/warn/info/debug messages.
@@ -1589,6 +1590,14 @@ int smu_set_mp1_state(struct smu_context *smu,
 		return 0;
 	}
 
+	/* some asics may not support those messages */
+	if (smu_cmn_to_asic_specific_index(smu,
+					   CMN2ASIC_MAPPING_MSG,
+					   msg) < 0) {
+		mutex_unlock(&smu->mutex);
+		return 0;
+	}
+
 	ret = smu_send_smc_msg(smu, msg, NULL);
 	if (ret)
 		dev_err(smu->adev->dev, "[PrepareMp1] Failed!\n");
diff --git a/drivers/gpu/drm/amd/powerplay/smu_cmn.h b/drivers/gpu/drm/amd/powerplay/smu_cmn.h
index 98face8c5fd6..f9e63f18b157 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_cmn.h
+++ b/drivers/gpu/drm/amd/powerplay/smu_cmn.h
@@ -25,7 +25,7 @@
 
 #include "amdgpu_smu.h"
 
-#if defined(SWSMU_CODE_LAYER_L2) || defined(SWSMU_CODE_LAYER_L3) || defined(SWSMU_CODE_LAYER_L4)
+#if defined(SWSMU_CODE_LAYER_L1) || defined(SWSMU_CODE_LAYER_L2) || defined(SWSMU_CODE_LAYER_L3) || defined(SWSMU_CODE_LAYER_L4)
 int smu_cmn_send_smc_msg_with_param(struct smu_context *smu,
 				    enum smu_message_type msg,
 				    uint32_t param,

From 3520b5e22809d1fe211a7375e7b220de85e383d7 Mon Sep 17 00:00:00 2001
From: Kenneth Feng <kenneth.feng@amd.com>
Date: Wed, 22 Jul 2020 21:27:35 +0800
Subject: [PATCH 243/474] drm/amd/powerplay: remove the dpm checking in the
 boot sequence

It's not necessary to retrieve the power features status when the
asic is booted up the first time. This patch can have the features
enablement status still checked in suspend/resume case and removed
from the first boot up sequence.

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index f778b00e49eb..6b03f750e63b 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -735,7 +735,7 @@ static int smu_smc_hw_setup(struct smu_context *smu)
 	uint32_t pcie_gen = 0, pcie_width = 0;
 	int ret;
 
-	if (smu_is_dpm_running(smu) && adev->in_suspend) {
+	if (adev->in_suspend && smu_is_dpm_running(smu)) {
 		dev_info(adev->dev, "dpm has been enabled\n");
 		return 0;
 	}

From 2f32faec004319a609982859a2b47459ae838888 Mon Sep 17 00:00:00 2001
From: Likun Gao <Likun.Gao@amd.com>
Date: Tue, 21 Jul 2020 14:01:53 +0800
Subject: [PATCH 244/474] drm/amd/powerplay: skip invalid msg when smu set mp1
 state

Some asic may not support for some message of set mp1 state.
If the return value of smu_send_smc_msg is -EINVAL, that means it failed
to send msg to smc as it can not map an valid message for the ASIC. And
with that case, smu_set_mp1_state should be skipped as those ASIC was in
fact do not support for that.

Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 6b03f750e63b..727cb9fd4aee 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -1599,6 +1599,9 @@ int smu_set_mp1_state(struct smu_context *smu,
 	}
 
 	ret = smu_send_smc_msg(smu, msg, NULL);
+	/* some asics may not support those messages */
+	if (ret == -EINVAL)
+		ret = 0;
 	if (ret)
 		dev_err(smu->adev->dev, "[PrepareMp1] Failed!\n");
 

From ef69ab6aed16094b3d840d5863ae665f21fedf58 Mon Sep 17 00:00:00 2001
From: Likun Gao <Likun.Gao@amd.com>
Date: Tue, 21 Jul 2020 13:13:39 +0800
Subject: [PATCH 245/474] drm/amd/powerplay: add msg map for mode1 reset

Mapping Mode1Reset message for sienna_cichlid.

Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
index 59da3ca2a4ca..f44fd33aeb93 100644
--- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
@@ -121,6 +121,7 @@ static struct cmn2asic_msg_mapping sienna_cichlid_message_map[SMU_MSG_MAX_COUNT]
 	MSG_MAP(PowerDownJpeg,			PPSMC_MSG_PowerDownJpeg,               1),
 	MSG_MAP(BacoAudioD3PME,			PPSMC_MSG_BacoAudioD3PME,              1),
 	MSG_MAP(ArmD3,				PPSMC_MSG_ArmD3,                       1),
+	MSG_MAP(Mode1Reset,                     PPSMC_MSG_Mode1Reset,		       1),
 };
 
 static struct cmn2asic_mapping sienna_cichlid_clk_map[SMU_CLK_COUNT] = {

From 518dcf959c68a33e61d78fec47a1d2a674d0120c Mon Sep 17 00:00:00 2001
From: Likun Gao <Likun.Gao@amd.com>
Date: Tue, 21 Jul 2020 16:39:45 +0800
Subject: [PATCH 246/474] drm/amd/powerplay: correct smu message for vf mode

Set valid_in_vf to false for the message not support in vf mode on
sienna cichlid.

Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/powerplay/sienna_cichlid_ppt.c    | 70 +++++++++----------
 1 file changed, 35 insertions(+), 35 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
index f44fd33aeb93..dcc5d25a7894 100644
--- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
@@ -74,10 +74,10 @@ static struct cmn2asic_msg_mapping sienna_cichlid_message_map[SMU_MSG_MAX_COUNT]
 	MSG_MAP(TestMessage,			PPSMC_MSG_TestMessage,                 1),
 	MSG_MAP(GetSmuVersion,			PPSMC_MSG_GetSmuVersion,               1),
 	MSG_MAP(GetDriverIfVersion,		PPSMC_MSG_GetDriverIfVersion,          1),
-	MSG_MAP(SetAllowedFeaturesMaskLow,	PPSMC_MSG_SetAllowedFeaturesMaskLow,   1),
-	MSG_MAP(SetAllowedFeaturesMaskHigh,	PPSMC_MSG_SetAllowedFeaturesMaskHigh,  1),
-	MSG_MAP(EnableAllSmuFeatures,		PPSMC_MSG_EnableAllSmuFeatures,        1),
-	MSG_MAP(DisableAllSmuFeatures,		PPSMC_MSG_DisableAllSmuFeatures,       1),
+	MSG_MAP(SetAllowedFeaturesMaskLow,	PPSMC_MSG_SetAllowedFeaturesMaskLow,   0),
+	MSG_MAP(SetAllowedFeaturesMaskHigh,	PPSMC_MSG_SetAllowedFeaturesMaskHigh,  0),
+	MSG_MAP(EnableAllSmuFeatures,		PPSMC_MSG_EnableAllSmuFeatures,        0),
+	MSG_MAP(DisableAllSmuFeatures,		PPSMC_MSG_DisableAllSmuFeatures,       0),
 	MSG_MAP(EnableSmuFeaturesLow,		PPSMC_MSG_EnableSmuFeaturesLow,        1),
 	MSG_MAP(EnableSmuFeaturesHigh,		PPSMC_MSG_EnableSmuFeaturesHigh,       1),
 	MSG_MAP(DisableSmuFeaturesLow,		PPSMC_MSG_DisableSmuFeaturesLow,       1),
@@ -85,43 +85,43 @@ static struct cmn2asic_msg_mapping sienna_cichlid_message_map[SMU_MSG_MAX_COUNT]
 	MSG_MAP(GetEnabledSmuFeaturesLow,       PPSMC_MSG_GetRunningSmuFeaturesLow,    1),
 	MSG_MAP(GetEnabledSmuFeaturesHigh,	PPSMC_MSG_GetRunningSmuFeaturesHigh,   1),
 	MSG_MAP(SetWorkloadMask,		PPSMC_MSG_SetWorkloadMask,             1),
-	MSG_MAP(SetPptLimit,			PPSMC_MSG_SetPptLimit,                 1),
-	MSG_MAP(SetDriverDramAddrHigh,		PPSMC_MSG_SetDriverDramAddrHigh,       1),
-	MSG_MAP(SetDriverDramAddrLow,		PPSMC_MSG_SetDriverDramAddrLow,        1),
-	MSG_MAP(SetToolsDramAddrHigh,		PPSMC_MSG_SetToolsDramAddrHigh,        1),
-	MSG_MAP(SetToolsDramAddrLow,		PPSMC_MSG_SetToolsDramAddrLow,         1),
-	MSG_MAP(TransferTableSmu2Dram,		PPSMC_MSG_TransferTableSmu2Dram,       1),
-	MSG_MAP(TransferTableDram2Smu,		PPSMC_MSG_TransferTableDram2Smu,       1),
-	MSG_MAP(UseDefaultPPTable,		PPSMC_MSG_UseDefaultPPTable,           1),
-	MSG_MAP(EnterBaco,			PPSMC_MSG_EnterBaco,                   1),
-	MSG_MAP(SetSoftMinByFreq,		PPSMC_MSG_SetSoftMinByFreq,            1),
-	MSG_MAP(SetSoftMaxByFreq,		PPSMC_MSG_SetSoftMaxByFreq,            1),
+	MSG_MAP(SetPptLimit,			PPSMC_MSG_SetPptLimit,                 0),
+	MSG_MAP(SetDriverDramAddrHigh,		PPSMC_MSG_SetDriverDramAddrHigh,       0),
+	MSG_MAP(SetDriverDramAddrLow,		PPSMC_MSG_SetDriverDramAddrLow,        0),
+	MSG_MAP(SetToolsDramAddrHigh,		PPSMC_MSG_SetToolsDramAddrHigh,        0),
+	MSG_MAP(SetToolsDramAddrLow,		PPSMC_MSG_SetToolsDramAddrLow,         0),
+	MSG_MAP(TransferTableSmu2Dram,		PPSMC_MSG_TransferTableSmu2Dram,       0),
+	MSG_MAP(TransferTableDram2Smu,		PPSMC_MSG_TransferTableDram2Smu,       0),
+	MSG_MAP(UseDefaultPPTable,		PPSMC_MSG_UseDefaultPPTable,           0),
+	MSG_MAP(EnterBaco,			PPSMC_MSG_EnterBaco,                   0),
+	MSG_MAP(SetSoftMinByFreq,		PPSMC_MSG_SetSoftMinByFreq,            0),
+	MSG_MAP(SetSoftMaxByFreq,		PPSMC_MSG_SetSoftMaxByFreq,            0),
 	MSG_MAP(SetHardMinByFreq,		PPSMC_MSG_SetHardMinByFreq,            1),
-	MSG_MAP(SetHardMaxByFreq,		PPSMC_MSG_SetHardMaxByFreq,            1),
+	MSG_MAP(SetHardMaxByFreq,		PPSMC_MSG_SetHardMaxByFreq,            0),
 	MSG_MAP(GetMinDpmFreq,			PPSMC_MSG_GetMinDpmFreq,               1),
 	MSG_MAP(GetMaxDpmFreq,			PPSMC_MSG_GetMaxDpmFreq,               1),
 	MSG_MAP(GetDpmFreqByIndex,		PPSMC_MSG_GetDpmFreqByIndex,           1),
-	MSG_MAP(SetGeminiMode,			PPSMC_MSG_SetGeminiMode,               1),
-	MSG_MAP(SetGeminiApertureHigh,		PPSMC_MSG_SetGeminiApertureHigh,       1),
-	MSG_MAP(SetGeminiApertureLow,		PPSMC_MSG_SetGeminiApertureLow,        1),
-	MSG_MAP(OverridePcieParameters,		PPSMC_MSG_OverridePcieParameters,      1),
-	MSG_MAP(ReenableAcDcInterrupt,		PPSMC_MSG_ReenableAcDcInterrupt,       1),
-	MSG_MAP(NotifyPowerSource,		PPSMC_MSG_NotifyPowerSource,           1),
-	MSG_MAP(SetUclkFastSwitch,		PPSMC_MSG_SetUclkFastSwitch,           1),
-	MSG_MAP(SetVideoFps,			PPSMC_MSG_SetVideoFps,                 1),
+	MSG_MAP(SetGeminiMode,			PPSMC_MSG_SetGeminiMode,               0),
+	MSG_MAP(SetGeminiApertureHigh,		PPSMC_MSG_SetGeminiApertureHigh,       0),
+	MSG_MAP(SetGeminiApertureLow,		PPSMC_MSG_SetGeminiApertureLow,        0),
+	MSG_MAP(OverridePcieParameters,		PPSMC_MSG_OverridePcieParameters,      0),
+	MSG_MAP(ReenableAcDcInterrupt,		PPSMC_MSG_ReenableAcDcInterrupt,       0),
+	MSG_MAP(NotifyPowerSource,		PPSMC_MSG_NotifyPowerSource,           0),
+	MSG_MAP(SetUclkFastSwitch,		PPSMC_MSG_SetUclkFastSwitch,           0),
+	MSG_MAP(SetVideoFps,			PPSMC_MSG_SetVideoFps,                 0),
 	MSG_MAP(PrepareMp1ForUnload,		PPSMC_MSG_PrepareMp1ForUnload,         1),
-	MSG_MAP(AllowGfxOff,			PPSMC_MSG_AllowGfxOff,                 1),
-	MSG_MAP(DisallowGfxOff,			PPSMC_MSG_DisallowGfxOff,              1),
-	MSG_MAP(GetPptLimit,			PPSMC_MSG_GetPptLimit,                 1),
+	MSG_MAP(AllowGfxOff,			PPSMC_MSG_AllowGfxOff,                 0),
+	MSG_MAP(DisallowGfxOff,			PPSMC_MSG_DisallowGfxOff,              0),
+	MSG_MAP(GetPptLimit,			PPSMC_MSG_GetPptLimit,                 0),
 	MSG_MAP(GetDcModeMaxDpmFreq,		PPSMC_MSG_GetDcModeMaxDpmFreq,         1),
-	MSG_MAP(ExitBaco,			PPSMC_MSG_ExitBaco,                    1),
-	MSG_MAP(PowerUpVcn,			PPSMC_MSG_PowerUpVcn,                  1),
-	MSG_MAP(PowerDownVcn,			PPSMC_MSG_PowerDownVcn,                1),
-	MSG_MAP(PowerUpJpeg,			PPSMC_MSG_PowerUpJpeg,                 1),
-	MSG_MAP(PowerDownJpeg,			PPSMC_MSG_PowerDownJpeg,               1),
-	MSG_MAP(BacoAudioD3PME,			PPSMC_MSG_BacoAudioD3PME,              1),
-	MSG_MAP(ArmD3,				PPSMC_MSG_ArmD3,                       1),
-	MSG_MAP(Mode1Reset,                     PPSMC_MSG_Mode1Reset,		       1),
+	MSG_MAP(ExitBaco,			PPSMC_MSG_ExitBaco,                    0),
+	MSG_MAP(PowerUpVcn,			PPSMC_MSG_PowerUpVcn,                  0),
+	MSG_MAP(PowerDownVcn,			PPSMC_MSG_PowerDownVcn,                0),
+	MSG_MAP(PowerUpJpeg,			PPSMC_MSG_PowerUpJpeg,                 0),
+	MSG_MAP(PowerDownJpeg,			PPSMC_MSG_PowerDownJpeg,               0),
+	MSG_MAP(BacoAudioD3PME,			PPSMC_MSG_BacoAudioD3PME,              0),
+	MSG_MAP(ArmD3,				PPSMC_MSG_ArmD3,                       0),
+	MSG_MAP(Mode1Reset,                     PPSMC_MSG_Mode1Reset,		       0),
 };
 
 static struct cmn2asic_mapping sienna_cichlid_clk_map[SMU_CLK_COUNT] = {

From 3da0a2dfbd3a7ada2d8388775796edf12b2c7219 Mon Sep 17 00:00:00 2001
From: Likun Gao <Likun.Gao@amd.com>
Date: Thu, 23 Jul 2020 15:26:27 +0800
Subject: [PATCH 247/474] drm/amdgpu: update golden setting for sienna_cichlid

Update golden setting for sienna_cichlid.

Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 61e89247faf3..8344c3b0b9b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3082,7 +3082,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA0_CLK_CTRL, 0xff7f0fff, 0x30000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA1_CLK_CTRL, 0xff7f0fff, 0x7e000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPF_GCR_CNTL, 0x0007ffff, 0x0000c000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000200),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_EXCEPTION_CONTROL, 0x7fff0f1f, 0x00b80000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Sienna_Cichlid, 0x1ff1ffff, 0x00000500),

From fa40a009001a30819097999d10cc3f51a0891564 Mon Sep 17 00:00:00 2001
From: James Zhu <James.Zhu@amd.com>
Date: Thu, 23 Jul 2020 11:07:52 -0400
Subject: [PATCH 248/474] drm/amdgpu/jpeg3.0: remove extra asic type check

jpeg ip block is already selected based on ASIC type during set_ip_blocks.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
index 42f1a516005e..c41e5590a701 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
@@ -49,12 +49,11 @@ static int jpeg_v3_0_set_powergating_state(void *handle,
 static int jpeg_v3_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	if (adev->asic_type == CHIP_SIENNA_CICHLID) {
-		u32 harvest = RREG32_SOC15(JPEG, 0, mmCC_UVD_HARVESTING);
+	u32 harvest = RREG32_SOC15(JPEG, 0, mmCC_UVD_HARVESTING);
+
+	if (harvest & CC_UVD_HARVESTING__UVD_DISABLE_MASK)
+		return -ENOENT;
 
-		if (harvest & CC_UVD_HARVESTING__UVD_DISABLE_MASK)
-			return -ENOENT;
-	}
 	adev->jpeg.num_jpeg_inst = 1;
 
 	jpeg_v3_0_set_dec_ring_funcs(adev);

From bbf16f530cdf0e6f95e9954ca4aa7915cd3f1d99 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Thu, 23 Jul 2020 22:34:22 -0400
Subject: [PATCH 249/474] drm/amdgpu: update dec ring test for VCN 3.0

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 910a4a32ff78..63e5547cfb16 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -1659,7 +1659,7 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_ring_vm_funcs = {
 	.emit_ib = vcn_v2_0_dec_ring_emit_ib,
 	.emit_fence = vcn_v2_0_dec_ring_emit_fence,
 	.emit_vm_flush = vcn_v2_0_dec_ring_emit_vm_flush,
-	.test_ring = amdgpu_vcn_dec_ring_test_ring,
+	.test_ring = vcn_v2_0_dec_ring_test_ring,
 	.test_ib = amdgpu_vcn_dec_ring_test_ib,
 	.insert_nop = vcn_v2_0_dec_ring_insert_nop,
 	.insert_start = vcn_v2_0_dec_ring_insert_start,

From de273b73ca6aef31c64071b90b9c76cd9f47d5d1 Mon Sep 17 00:00:00 2001
From: Changfeng <Changfeng.Zhu@amd.com>
Date: Fri, 24 Jul 2020 13:15:10 +0800
Subject: [PATCH 250/474] drm/amd/powerplay: drop unnecessary message support
 check(v2)

Take back patch:drop unnecessary message support check
Because the gpu reset fail problem on renoir can be fixed by:
drm/amd/powerplay: skip invalid msg when smu set mp1 state
It needs to remove SWSMU_CODE_LAYER_L1 in smu_cmn.h to guard a clear
code layer.

Signed-off-by: changfeng <Changfeng.Zhu@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 9 ---------
 drivers/gpu/drm/amd/powerplay/smu_cmn.h    | 2 +-
 2 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 727cb9fd4aee..2da72f333ad9 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -34,7 +34,6 @@
 #include "sienna_cichlid_ppt.h"
 #include "renoir_ppt.h"
 #include "amd_pcie.h"
-#include "smu_cmn.h"
 
 /*
  * DO NOT use these for err/warn/info/debug messages.
@@ -1590,14 +1589,6 @@ int smu_set_mp1_state(struct smu_context *smu,
 		return 0;
 	}
 
-	/* some asics may not support those messages */
-	if (smu_cmn_to_asic_specific_index(smu,
-					   CMN2ASIC_MAPPING_MSG,
-					   msg) < 0) {
-		mutex_unlock(&smu->mutex);
-		return 0;
-	}
-
 	ret = smu_send_smc_msg(smu, msg, NULL);
 	/* some asics may not support those messages */
 	if (ret == -EINVAL)
diff --git a/drivers/gpu/drm/amd/powerplay/smu_cmn.h b/drivers/gpu/drm/amd/powerplay/smu_cmn.h
index f9e63f18b157..98face8c5fd6 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_cmn.h
+++ b/drivers/gpu/drm/amd/powerplay/smu_cmn.h
@@ -25,7 +25,7 @@
 
 #include "amdgpu_smu.h"
 
-#if defined(SWSMU_CODE_LAYER_L1) || defined(SWSMU_CODE_LAYER_L2) || defined(SWSMU_CODE_LAYER_L3) || defined(SWSMU_CODE_LAYER_L4)
+#if defined(SWSMU_CODE_LAYER_L2) || defined(SWSMU_CODE_LAYER_L3) || defined(SWSMU_CODE_LAYER_L4)
 int smu_cmn_send_smc_msg_with_param(struct smu_context *smu,
 				    enum smu_message_type msg,
 				    uint32_t param,

From a486bc3c50198a7e895eef5dc3d2a94cd6186e4f Mon Sep 17 00:00:00 2001
From: Likun Gao <Likun.Gao@amd.com>
Date: Fri, 24 Jul 2020 17:24:08 +0800
Subject: [PATCH 251/474] drm/amd/powerplay: update driver if file for
 sienna_cichlid

Update sienna_cichlid driver if header and related files.
Support new smu metrics for pre & postDS frequency.

Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../inc/smu11_driver_if_sienna_cichlid.h      | 21 +++++++++++++------
 drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h |  2 +-
 .../drm/amd/powerplay/sienna_cichlid_ppt.c    | 11 +++++++---
 3 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_sienna_cichlid.h b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_sienna_cichlid.h
index b2232e24d82f..aa2708fccb6d 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_sienna_cichlid.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_sienna_cichlid.h
@@ -27,7 +27,7 @@
 // *** IMPORTANT ***
 // SMU TEAM: Always increment the interface version if 
 // any structure is changed in this file
-#define SMU11_DRIVER_IF_VERSION 0x33
+#define SMU11_DRIVER_IF_VERSION 0x34
 
 #define PPTABLE_Sienna_Cichlid_SMU_VERSION 5
 
@@ -968,9 +968,15 @@ typedef struct {
 
 typedef struct {
   uint32_t CurrClock[PPCLK_COUNT];
-  uint16_t AverageGfxclkFrequency;
-  uint16_t AverageFclkFrequency;
-  uint16_t AverageUclkFrequency  ;
+
+  uint16_t AverageGfxclkFrequencyPreDs;
+  uint16_t AverageGfxclkFrequencyPostDs;
+  uint16_t AverageFclkFrequencyPreDs;
+  uint16_t AverageFclkFrequencyPostDs;
+  uint16_t AverageUclkFrequencyPreDs  ;
+  uint16_t AverageUclkFrequencyPostDs  ;
+
+  
   uint16_t AverageGfxActivity    ;
   uint16_t AverageUclkActivity   ;
   uint8_t  CurrSocVoltageOffset  ;
@@ -988,6 +994,7 @@ typedef struct {
   uint16_t TemperatureLiquid0    ;
   uint16_t TemperatureLiquid1    ;  
   uint16_t TemperaturePlx        ;
+  uint16_t Padding16             ;
   uint32_t ThrottlerStatus       ; 
  
   uint8_t  LinkDpmLevel;
@@ -1006,8 +1013,10 @@ typedef struct {
   uint16_t AverageDclk0Frequency  ;  
   uint16_t AverageVclk1Frequency  ;
   uint16_t AverageDclk1Frequency  ;  
-  uint16_t VcnActivityPercentage ; //place holder, David N. to provide full sequence
-  uint16_t padding16_2;
+  uint16_t VcnActivityPercentage  ; //place holder, David N. to provide full sequence
+  uint8_t  PcieRate               ;
+  uint8_t  PcieWidth              ;
+
 } SmuMetrics_t;
 
 typedef struct {
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 429f5aa8924a..9504f9954fd3 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -30,7 +30,7 @@
 #define SMU11_DRIVER_IF_VERSION_NV10 0x36
 #define SMU11_DRIVER_IF_VERSION_NV12 0x33
 #define SMU11_DRIVER_IF_VERSION_NV14 0x36
-#define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x33
+#define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x34
 #define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0x2
 
 /* MP Apertures */
diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
index dcc5d25a7894..f64a1be94cb8 100644
--- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
@@ -70,6 +70,8 @@
 	FEATURE_MASK(FEATURE_DPM_FCLK_BIT)	 | \
 	FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT))
 
+#define SMU_11_0_7_GFX_BUSY_THRESHOLD 15
+
 static struct cmn2asic_msg_mapping sienna_cichlid_message_map[SMU_MSG_MAX_COUNT] = {
 	MSG_MAP(TestMessage,			PPSMC_MSG_TestMessage,                 1),
 	MSG_MAP(GetSmuVersion,			PPSMC_MSG_GetSmuVersion,               1),
@@ -443,13 +445,16 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu,
 		*value = metrics->CurrClock[PPCLK_DCEFCLK];
 		break;
 	case METRICS_AVERAGE_GFXCLK:
-		*value = metrics->AverageGfxclkFrequency;
+		if (metrics->AverageGfxActivity <= SMU_11_0_7_GFX_BUSY_THRESHOLD)
+			*value = metrics->AverageGfxclkFrequencyPostDs;
+		else
+			*value = metrics->AverageGfxclkFrequencyPreDs;
 		break;
 	case METRICS_AVERAGE_FCLK:
-		*value = metrics->AverageFclkFrequency;
+		*value = metrics->AverageFclkFrequencyPostDs;
 		break;
 	case METRICS_AVERAGE_UCLK:
-		*value = metrics->AverageUclkFrequency;
+		*value = metrics->AverageUclkFrequencyPostDs;
 		break;
 	case METRICS_AVERAGE_GFXACTIVITY:
 		*value = metrics->AverageGfxActivity;

From 68bb3c3ff9d92645488382c7261de7d477f638e9 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 27 Jul 2020 16:39:40 +0300
Subject: [PATCH 252/474] drm/amd/powerplay: off by one bugs in
 smu_cmn_to_asic_specific_index()

These tables have _COUNT number of elements so the comparisons should be
>= instead of > to prevent reading one element beyond the end of the
array.

Fixes: 8264ee69f0d8 ("drm/amd/powerplay: drop unused code")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/smu_cmn.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/smu_cmn.c b/drivers/gpu/drm/amd/powerplay/smu_cmn.c
index be4b678d0e60..5c23c44c33bd 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_cmn.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_cmn.c
@@ -166,7 +166,7 @@ int smu_cmn_to_asic_specific_index(struct smu_context *smu,
 
 	switch (type) {
 	case CMN2ASIC_MAPPING_MSG:
-		if (index > SMU_MSG_MAX_COUNT ||
+		if (index >= SMU_MSG_MAX_COUNT ||
 		    !smu->message_map)
 			return -EINVAL;
 
@@ -181,7 +181,7 @@ int smu_cmn_to_asic_specific_index(struct smu_context *smu,
 		return msg_mapping.map_to;
 
 	case CMN2ASIC_MAPPING_CLK:
-		if (index > SMU_CLK_COUNT ||
+		if (index >= SMU_CLK_COUNT ||
 		    !smu->clock_map)
 			return -EINVAL;
 
@@ -192,7 +192,7 @@ int smu_cmn_to_asic_specific_index(struct smu_context *smu,
 		return mapping.map_to;
 
 	case CMN2ASIC_MAPPING_FEATURE:
-		if (index > SMU_FEATURE_COUNT ||
+		if (index >= SMU_FEATURE_COUNT ||
 		    !smu->feature_map)
 			return -EINVAL;
 
@@ -203,7 +203,7 @@ int smu_cmn_to_asic_specific_index(struct smu_context *smu,
 		return mapping.map_to;
 
 	case CMN2ASIC_MAPPING_TABLE:
-		if (index > SMU_TABLE_COUNT ||
+		if (index >= SMU_TABLE_COUNT ||
 		    !smu->table_map)
 			return -EINVAL;
 
@@ -214,7 +214,7 @@ int smu_cmn_to_asic_specific_index(struct smu_context *smu,
 		return mapping.map_to;
 
 	case CMN2ASIC_MAPPING_PWR:
-		if (index > SMU_POWER_SOURCE_COUNT ||
+		if (index >= SMU_POWER_SOURCE_COUNT ||
 		    !smu->pwr_src_map)
 			return -EINVAL;
 

From c4e0dbcb201a79639e5e74f456d8313893a259f5 Mon Sep 17 00:00:00 2001
From: Kevin Wang <kevin1.wang@amd.com>
Date: Mon, 27 Jul 2020 09:08:22 +0800
Subject: [PATCH 253/474] drm/amd/swsmu: allow asic to handle sensor type by
 itself

1. allow asic to handle sensor type by itself.
2. if not, use smu common sensor to handle it.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 2da72f333ad9..8c624f1f33ba 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -1947,6 +1947,10 @@ int smu_read_sensor(struct smu_context *smu,
 
 	mutex_lock(&smu->mutex);
 
+	if (smu->ppt_funcs->read_sensor)
+		if (!smu->ppt_funcs->read_sensor(smu, sensor, data, size))
+			goto unlock;
+
 	switch (sensor) {
 	case AMDGPU_PP_SENSOR_STABLE_PSTATE_SCLK:
 		*((uint32_t *)data) = pstate_table->gfxclk_pstate.standard * 100;
@@ -1977,11 +1981,12 @@ int smu_read_sensor(struct smu_context *smu,
 		*size = 4;
 		break;
 	default:
-		if (smu->ppt_funcs->read_sensor)
-			ret = smu->ppt_funcs->read_sensor(smu, sensor, data, size);
+		*size = 0;
+		ret = -EOPNOTSUPP;
 		break;
 	}
 
+unlock:
 	mutex_unlock(&smu->mutex);
 
 	return ret;

From 7c146177b3368feda6dbb0e01b085c84d9774589 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Mon, 6 Jul 2020 10:54:37 -0400
Subject: [PATCH 254/474] drm/amd/display: Clean up global sync param retrieval

[Why]
This change replaces older looping code in favor of these functions.

[How]
There are built in functions for extracting global sync params
during mode validation now.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/dcn20/dcn20_resource.c | 49 ++-----------------
 .../drm/amd/display/dc/dml/display_mode_vba.c | 14 +-----
 .../drm/amd/display/dc/dml/display_mode_vba.h |  7 +--
 3 files changed, 7 insertions(+), 63 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 968a89bbcf24..2a5e7175926a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -3069,8 +3069,7 @@ void dcn20_calculate_dlg_params(
 		int pipe_cnt,
 		int vlevel)
 {
-	int i, j, pipe_idx, pipe_idx_unsplit;
-	bool visited[MAX_PIPES] = { 0 };
+	int i, pipe_idx;
 
 	/* Writeback MCIF_WB arbitration parameters */
 	dc->res_pool->funcs->set_mcif_arb_params(dc, context, pipes, pipe_cnt);
@@ -3089,55 +3088,17 @@ void dcn20_calculate_dlg_params(
 	if (context->bw_ctx.bw.dcn.clk.dispclk_khz < dc->debug.min_disp_clk_khz)
 		context->bw_ctx.bw.dcn.clk.dispclk_khz = dc->debug.min_disp_clk_khz;
 
-	/*
-	 * An artifact of dml pipe split/odm is that pipes get merged back together for
-	 * calculation. Therefore we need to only extract for first pipe in ascending index order
-	 * and copy into the other split half.
-	 */
-	for (i = 0, pipe_idx = 0, pipe_idx_unsplit = 0; i < dc->res_pool->pipe_count; i++) {
-		if (!context->res_ctx.pipe_ctx[i].stream)
-			continue;
-
-		if (!visited[pipe_idx]) {
-			display_pipe_source_params_st *src = &pipes[pipe_idx].pipe.src;
-			display_pipe_dest_params_st *dst = &pipes[pipe_idx].pipe.dest;
-
-			dst->vstartup_start = context->bw_ctx.dml.vba.VStartup[pipe_idx_unsplit];
-			dst->vupdate_offset = context->bw_ctx.dml.vba.VUpdateOffsetPix[pipe_idx_unsplit];
-			dst->vupdate_width = context->bw_ctx.dml.vba.VUpdateWidthPix[pipe_idx_unsplit];
-			dst->vready_offset = context->bw_ctx.dml.vba.VReadyOffsetPix[pipe_idx_unsplit];
-			/*
-			 * j iterates inside pipes array, unlike i which iterates inside
-			 * pipe_ctx array
-			 */
-			if (src->is_hsplit)
-				for (j = pipe_idx + 1; j < pipe_cnt; j++) {
-					display_pipe_source_params_st *src_j = &pipes[j].pipe.src;
-					display_pipe_dest_params_st *dst_j = &pipes[j].pipe.dest;
-
-					if (src_j->is_hsplit && !visited[j]
-							&& src->hsplit_grp == src_j->hsplit_grp) {
-						dst_j->vstartup_start = context->bw_ctx.dml.vba.VStartup[pipe_idx_unsplit];
-						dst_j->vupdate_offset = context->bw_ctx.dml.vba.VUpdateOffsetPix[pipe_idx_unsplit];
-						dst_j->vupdate_width = context->bw_ctx.dml.vba.VUpdateWidthPix[pipe_idx_unsplit];
-						dst_j->vready_offset = context->bw_ctx.dml.vba.VReadyOffsetPix[pipe_idx_unsplit];
-						visited[j] = true;
-					}
-				}
-			visited[pipe_idx] = true;
-			pipe_idx_unsplit++;
-		}
-		pipe_idx++;
-	}
-
 	for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) {
 		if (!context->res_ctx.pipe_ctx[i].stream)
 			continue;
+		pipes[pipe_idx].pipe.dest.vstartup_start = get_vstartup(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
+		pipes[pipe_idx].pipe.dest.vupdate_offset = get_vupdate_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
+		pipes[pipe_idx].pipe.dest.vupdate_width = get_vupdate_width(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
+		pipes[pipe_idx].pipe.dest.vready_offset = get_vready_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
 		if (context->bw_ctx.bw.dcn.clk.dppclk_khz < pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000)
 			context->bw_ctx.bw.dcn.clk.dppclk_khz = pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000;
 		context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz =
 						pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000;
-		ASSERT(visited[pipe_idx]);
 		context->res_ctx.pipe_ctx[i].pipe_dlg_param = pipes[pipe_idx].pipe.dest;
 		pipe_idx++;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
index 7916a7ea9336..b0064087b9bb 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
@@ -154,23 +154,11 @@ dml_get_pipe_attr_func(refcyc_per_meta_chunk_vblank_c_in_us, mode_lib->vba.TimeP
 dml_get_pipe_attr_func(refcyc_per_meta_chunk_flip_l_in_us, mode_lib->vba.TimePerMetaChunkFlip);
 dml_get_pipe_attr_func(refcyc_per_meta_chunk_flip_c_in_us, mode_lib->vba.TimePerChromaMetaChunkFlip);
 
+dml_get_pipe_attr_func(vstartup, mode_lib->vba.VStartup);
 dml_get_pipe_attr_func(vupdate_offset, mode_lib->vba.VUpdateOffsetPix);
 dml_get_pipe_attr_func(vupdate_width, mode_lib->vba.VUpdateWidthPix);
 dml_get_pipe_attr_func(vready_offset, mode_lib->vba.VReadyOffsetPix);
 
-unsigned int get_vstartup_calculated(
-		struct display_mode_lib *mode_lib,
-		const display_e2e_pipe_params_st *pipes,
-		unsigned int num_pipes,
-		unsigned int which_pipe)
-{
-	unsigned int which_plane;
-
-	recalculate_params(mode_lib, pipes, num_pipes);
-	which_plane = mode_lib->vba.pipe_plane[which_pipe];
-	return mode_lib->vba.VStartup[which_plane];
-}
-
 double get_total_immediate_flip_bytes(
 		struct display_mode_lib *mode_lib,
 		const display_e2e_pipe_params_st *pipes,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
index 756d8eb1221c..21e5111ea7a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
@@ -98,16 +98,11 @@ dml_get_pipe_attr_decl(refcyc_per_meta_chunk_vblank_c_in_us);
 dml_get_pipe_attr_decl(refcyc_per_meta_chunk_flip_l_in_us);
 dml_get_pipe_attr_decl(refcyc_per_meta_chunk_flip_c_in_us);
 
+dml_get_pipe_attr_decl(vstartup);
 dml_get_pipe_attr_decl(vupdate_offset);
 dml_get_pipe_attr_decl(vupdate_width);
 dml_get_pipe_attr_decl(vready_offset);
 
-unsigned int get_vstartup_calculated(
-		struct display_mode_lib *mode_lib,
-		const display_e2e_pipe_params_st *pipes,
-		unsigned int num_pipes,
-		unsigned int which_pipe);
-
 double get_total_immediate_flip_bytes(
 		struct display_mode_lib *mode_lib,
 		const display_e2e_pipe_params_st *pipes,

From 5e061a4d020380566365e8aa8f629bbd200e9708 Mon Sep 17 00:00:00 2001
From: Eryk Brol <eryk.brol@amd.com>
Date: Tue, 16 Jun 2020 16:24:11 -0400
Subject: [PATCH 255/474] drm/amd/display: Rename bytes_pp to the correct
 bits_pp

[Why]
Struct dcn_dsc_state is used for reading current state
and parameters of DSC on a pipe, the target rate parameter
uses bytes per pixel even though its reading BITS_PER_PIXEL
register.

[How]
Changing it to Bits Per Pixel for consistency.

Signed-off-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Mikita Lipski <Mikita.Lipski@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 2 +-
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 4 +++-
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c          | 2 +-
 drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h               | 2 +-
 4 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 998f729976bf..1c177c2ad1dc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -1186,7 +1186,7 @@ static ssize_t dp_dsc_bytes_per_pixel_read(struct file *f, char __user *buf,
 
 	snprintf(rd_buf_ptr, str_len,
 		"%d\n",
-		dsc_state.dsc_bytes_per_pixel);
+		dsc_state.dsc_bits_per_pixel);
 	rd_buf_ptr += str_len;
 
 	while (size) {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index da0897fe3b54..a643927e272b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -390,6 +390,8 @@ void dcn10_log_hw_state(struct dc *dc,
 	}
 	DTN_INFO("\n");
 
+	// dcn_dsc_state struct field bytes_per_pixel was renamed to bits_per_pixel
+	// TODO: Update golden log header to reflect this name change
 	DTN_INFO("DSC: CLOCK_EN  SLICE_WIDTH  Bytes_pp\n");
 	for (i = 0; i < pool->res_cap->num_dsc; i++) {
 		struct display_stream_compressor *dsc = pool->dscs[i];
@@ -400,7 +402,7 @@ void dcn10_log_hw_state(struct dc *dc,
 		dsc->inst,
 			s.dsc_clock_en,
 			s.dsc_slice_width,
-			s.dsc_bytes_per_pixel);
+			s.dsc_bits_per_pixel);
 		DTN_INFO("\n");
 	}
 	DTN_INFO("\n");
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
index ba50214d6c32..79b640e202eb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
@@ -156,7 +156,7 @@ static void dsc2_read_state(struct display_stream_compressor *dsc, struct dcn_ds
 
 	REG_GET(DSC_TOP_CONTROL, DSC_CLOCK_EN, &s->dsc_clock_en);
 	REG_GET(DSCC_PPS_CONFIG3, SLICE_WIDTH, &s->dsc_slice_width);
-	REG_GET(DSCC_PPS_CONFIG1, BITS_PER_PIXEL, &s->dsc_bytes_per_pixel);
+	REG_GET(DSCC_PPS_CONFIG1, BITS_PER_PIXEL, &s->dsc_bits_per_pixel);
 	REG_GET(DSCC_PPS_CONFIG3, SLICE_HEIGHT, &s->dsc_slice_height);
 	REG_GET(DSCC_PPS_CONFIG1, CHUNK_SIZE, &s->dsc_chunk_size);
 	REG_GET(DSCC_PPS_CONFIG2, PIC_WIDTH, &s->dsc_pic_width);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
index 5915994f9eb8..f520e13aee4c 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
@@ -55,7 +55,7 @@ struct dsc_optc_config {
 struct dcn_dsc_state {
 	uint32_t dsc_clock_en;
 	uint32_t dsc_slice_width;
-	uint32_t dsc_bytes_per_pixel;
+	uint32_t dsc_bits_per_pixel;
 	uint32_t dsc_slice_height;
 	uint32_t dsc_pic_width;
 	uint32_t dsc_pic_height;

From c6851841fc877d9e4361eeaa1e3851778fa440c4 Mon Sep 17 00:00:00 2001
From: Eryk Brol <eryk.brol@amd.com>
Date: Tue, 16 Jun 2020 16:29:19 -0400
Subject: [PATCH 256/474] drm/amd/display: Fix naming of DSC Debugfs entry

[why]
Fix naming and return bits rather than bytes per pixel for
naming consistency. Because registers return Bytes per pixel,
but DSC Config structure is expecting bits per pixel as input.
So when returning the value convert from bytes into bits.

Signed-off-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Mikita Lipski <Mikita.Lipski@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c    | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 1c177c2ad1dc..e5a6d9115949 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -35,6 +35,7 @@
 #include "dmub/dmub_srv.h"
 #include "resource.h"
 #include "dsc.h"
+#include "dc_link_dp.h"
 
 struct dmub_debugfs_trace_header {
 	uint32_t entry_count;
@@ -1150,7 +1151,7 @@ static ssize_t dp_dsc_slice_height_read(struct file *f, char __user *buf,
 	return result;
 }
 
-static ssize_t dp_dsc_bytes_per_pixel_read(struct file *f, char __user *buf,
+static ssize_t dp_dsc_bits_per_pixel_read(struct file *f, char __user *buf,
 				    size_t size, loff_t *pos)
 {
 	char *rd_buf = NULL;
@@ -1460,9 +1461,9 @@ static const struct file_operations dp_dsc_slice_height_debugfs_fops = {
 	.llseek = default_llseek
 };
 
-static const struct file_operations dp_dsc_bytes_per_pixel_debugfs_fops = {
+static const struct file_operations dp_dsc_bits_per_pixel_debugfs_fops = {
 	.owner = THIS_MODULE,
-	.read = dp_dsc_bytes_per_pixel_read,
+	.read = dp_dsc_bits_per_pixel_read,
 	.llseek = default_llseek
 };
 
@@ -1552,7 +1553,7 @@ static const struct {
 		{"dsc_clock_en", &dp_dsc_clock_en_debugfs_fops},
 		{"dsc_slice_width", &dp_dsc_slice_width_debugfs_fops},
 		{"dsc_slice_height", &dp_dsc_slice_height_debugfs_fops},
-		{"dsc_bytes_per_pixel", &dp_dsc_bytes_per_pixel_debugfs_fops},
+		{"dsc_bits_per_pixel", &dp_dsc_bits_per_pixel_debugfs_fops},
 		{"dsc_pic_width", &dp_dsc_pic_width_debugfs_fops},
 		{"dsc_pic_height", &dp_dsc_pic_height_debugfs_fops},
 		{"dsc_chunk_size", &dp_dsc_chunk_size_debugfs_fops},

From bc0cd80783ff7c2201b44d384bab4629c9cb7db9 Mon Sep 17 00:00:00 2001
From: Alvin Lee <alvin.lee2@amd.com>
Date: Tue, 14 Jul 2020 15:06:40 -0400
Subject: [PATCH 257/474] drm/amd/display: Don't compare dppclk before updating
 DTO

[Why]
In dcn3_update_clocks there are situations where dppclk is not
lowered (i.e. stays the same), but DTO still needs to be increased
before we program pipe frontend (i.e. in prepare_bandwidth). If we
don't program the new DTO value before we program the pipe,
we will underflow as soon as the pipe lock is released until the
next call to dcn3_update_clocks where the DTO is updated.

[How]
Remove dppclk check before programming new DTO value.

Signed-off-by: Alvin Lee <alvin.lee2@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c   | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
index d94fdc52be37..9133646f6d5f 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
@@ -323,9 +323,10 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base,
 			/* if clock is being raised, increase refclk before lowering DTO */
 			if (update_dppclk || update_dispclk)
 				dcn20_update_clocks_update_dentist(clk_mgr);
-			/* always update dtos unless clock is lowered and not safe to lower */
-			if (new_clocks->dppclk_khz >= dc->current_state->bw_ctx.bw.dcn.clk.dppclk_khz)
-				dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower);
+			/* There is a check inside dcn20_update_clocks_update_dpp_dto which ensures
+			 * that we do not lower dto when it is not safe to lower. We do not need to
+			 * compare the current and new dppclk before calling this function.*/
+			dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower);
 		}
 	}
 

From 3fd20292c2352660155bbc11736dd014b2fc6e98 Mon Sep 17 00:00:00 2001
From: Martin Tsai <martin.tsai@amd.com>
Date: Wed, 15 Jul 2020 11:21:43 +0800
Subject: [PATCH 258/474] drm/amd/display: Check lane status again after link
 training done

[Why]
Some monitors could suffer symbol unlock but cannot send HPD IRQ to
notic source device to handle link loss. This makes monitor stuck in
abnormal status and causes black screen.

[How]
According to the suggestion from scalar vendor, to check lane status
again after link training done. That can improve the comaptibility
from current production monitors.

Signed-off-by: Martin Tsai <martin.tsai@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/core/dc_link_dp.c  | 50 +++++++++++++++++++
 .../amd/display/include/link_service_types.h  |  2 +
 2 files changed, 52 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 5cb7b834e459..1a3dbed3becb 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1133,6 +1133,45 @@ static inline enum link_training_result perform_link_training_int(
 	return status;
 }
 
+static enum link_training_result check_link_loss_status(
+	struct dc_link *link,
+	const struct link_training_settings *link_training_setting)
+{
+	enum link_training_result status = LINK_TRAINING_SUCCESS;
+	unsigned int lane01_status_address = DP_LANE0_1_STATUS;
+	union lane_status lane_status;
+	uint8_t dpcd_buf[4] = {0};
+	uint32_t lane;
+
+	core_link_read_dpcd(
+		link,
+		lane01_status_address,
+		(uint8_t *)(dpcd_buf),
+		sizeof(dpcd_buf));
+
+	/*parse lane status*/
+	for (lane = 0; lane < link->cur_link_settings.lane_count; lane++) {
+		/*
+		 * check lanes status
+		 */
+		lane_status.raw = get_nibble_at_index(&dpcd_buf[0], lane);
+
+		if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
+			!lane_status.bits.CR_DONE_0 ||
+			!lane_status.bits.SYMBOL_LOCKED_0) {
+			/* if one of the channel equalization, clock
+			 * recovery or symbol lock is dropped
+			 * consider it as (link has been
+			 * dropped) dp sink status has changed
+			 */
+			status = LINK_TRAINING_LINK_LOSS;
+			break;
+		}
+	}
+
+	return status;
+}
+
 static void initialize_training_settings(
 	 struct dc_link *link,
 	const struct dc_link_settings *link_setting,
@@ -1372,6 +1411,9 @@ static void print_status_message(
 	case LINK_TRAINING_LQA_FAIL:
 		lt_result = "LQA failed";
 		break;
+	case LINK_TRAINING_LINK_LOSS:
+		lt_result = "Link loss";
+		break;
 	default:
 		break;
 	}
@@ -1531,6 +1573,14 @@ enum link_training_result dc_link_dp_perform_link_training(
 				status);
 	}
 
+	/* delay 5ms after Main Link output idle pattern and then check
+	 * DPCD 0202h.
+	 */
+	if (link->connector_signal != SIGNAL_TYPE_EDP && status == LINK_TRAINING_SUCCESS) {
+		msleep(5);
+		status = check_link_loss_status(link, &lt_settings);
+	}
+
 	/* 6. print status message*/
 	print_status_message(link, &lt_settings, status);
 
diff --git a/drivers/gpu/drm/amd/display/include/link_service_types.h b/drivers/gpu/drm/amd/display/include/link_service_types.h
index 4869d4562e4d..550f46e9b95f 100644
--- a/drivers/gpu/drm/amd/display/include/link_service_types.h
+++ b/drivers/gpu/drm/amd/display/include/link_service_types.h
@@ -66,6 +66,8 @@ enum link_training_result {
 	/* other failure during EQ step */
 	LINK_TRAINING_EQ_FAIL_EQ,
 	LINK_TRAINING_LQA_FAIL,
+	/* one of the CR,EQ or symbol lock is dropped */
+	LINK_TRAINING_LINK_LOSS,
 };
 
 struct link_training_settings {

From 5ce868fc474e8797bd16f19e435a538554c371ab Mon Sep 17 00:00:00 2001
From: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Date: Tue, 21 Jul 2020 13:59:52 -0400
Subject: [PATCH 259/474] drm/amd/display: Use seperate dmcub firmware for
 navy_flounder

[Why]
Currently navy_flounder is using sienna_cichlid_dmcub.bin.

[How]
Create a seperate define so navy_flounder will use its own firmware.

Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 533913bf8410..3067f54b9891 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -97,6 +97,8 @@ MODULE_FIRMWARE(FIRMWARE_RENOIR_DMUB);
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 #define FIRMWARE_SIENNA_CICHLID_DMUB "amdgpu/sienna_cichlid_dmcub.bin"
 MODULE_FIRMWARE(FIRMWARE_SIENNA_CICHLID_DMUB);
+#define FIRMWARE_NAVY_FLOUNDER_DMUB "amdgpu/navy_flounder_dmcub.bin"
+MODULE_FIRMWARE(FIRMWARE_NAVY_FLOUNDER_DMUB);
 #endif
 
 #define FIRMWARE_RAVEN_DMCU		"amdgpu/raven_dmcu.bin"
@@ -1185,10 +1187,13 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 		break;
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 	case CHIP_SIENNA_CICHLID:
-	case CHIP_NAVY_FLOUNDER:
 		dmub_asic = DMUB_ASIC_DCN30;
 		fw_name_dmub = FIRMWARE_SIENNA_CICHLID_DMUB;
 		break;
+	case CHIP_NAVY_FLOUNDER:
+		dmub_asic = DMUB_ASIC_DCN30;
+		fw_name_dmub = FIRMWARE_NAVY_FLOUNDER_DMUB;
+		break;
 #endif
 
 	default:

From 5eaec83a883b02c5e1d44d0537bb63444543d1e6 Mon Sep 17 00:00:00 2001
From: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Date: Fri, 24 Jul 2020 16:36:07 -0400
Subject: [PATCH 260/474] drm/amd/display: Use proper abm/backlight functions
 for DCN3

Use DCN21 functions instead of DCE110

Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
index 1b354c219d0a..9afee7160490 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
@@ -26,6 +26,7 @@
 #include "dce110/dce110_hw_sequencer.h"
 #include "dcn10/dcn10_hw_sequencer.h"
 #include "dcn20/dcn20_hwseq.h"
+#include "dcn21/dcn21_hwseq.h"
 #include "dcn30_hwseq.h"
 
 static const struct hw_sequencer_funcs dcn30_funcs = {
@@ -87,8 +88,8 @@ static const struct hw_sequencer_funcs dcn30_funcs = {
 	.set_flip_control_gsl = dcn20_set_flip_control_gsl,
 	.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
 	.apply_idle_power_optimizations = dcn30_apply_idle_power_optimizations,
-	.set_backlight_level = dce110_set_backlight_level,
-	.set_abm_immediate_disable = dce110_set_abm_immediate_disable,
+	.set_backlight_level = dcn21_set_backlight_level,
+	.set_abm_immediate_disable = dcn21_set_abm_immediate_disable,
 };
 
 static const struct hwseq_private_funcs dcn30_private_funcs = {

From c5892a10218214d729699ab61bad6fc109baf0ce Mon Sep 17 00:00:00 2001
From: Stylon Wang <stylon.wang@amd.com>
Date: Tue, 30 Jun 2020 17:55:29 +0800
Subject: [PATCH 261/474] drm/amd/display: Fix dmesg warning from setting abm
 level

[Why]
Setting abm level does not correctly update CRTC state. As a result
no surface update is added to dc stream state and triggers warning.

[How]
Correctly update CRTC state when setting abm level property.

CC: Stable <stable@vger.kernel.org>
Signed-off-by: Stylon Wang <stylon.wang@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 23 +++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 3067f54b9891..e6833a2d01f8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -8549,6 +8549,29 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 	if (ret)
 		goto fail;
 
+	/* Check connector changes */
+	for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) {
+		struct dm_connector_state *dm_old_con_state = to_dm_connector_state(old_con_state);
+		struct dm_connector_state *dm_new_con_state = to_dm_connector_state(new_con_state);
+
+		/* Skip connectors that are disabled or part of modeset already. */
+		if (!old_con_state->crtc && !new_con_state->crtc)
+			continue;
+
+		if (!new_con_state->crtc)
+			continue;
+
+		new_crtc_state = drm_atomic_get_crtc_state(state, new_con_state->crtc);
+		if (IS_ERR(new_crtc_state)) {
+			ret = PTR_ERR(new_crtc_state);
+			goto fail;
+		}
+
+		if (dm_old_con_state->abm_level !=
+		    dm_new_con_state->abm_level)
+			new_crtc_state->connectors_changed = true;
+	}
+
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 	if (adev->asic_type >= CHIP_NAVI10) {
 		for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {

From 6b6352dd1f96ca2464d7373557cb913f00c9e6dd Mon Sep 17 00:00:00 2001
From: Jun Lei <jun.lei@amd.com>
Date: Thu, 25 Jun 2020 13:24:12 -0400
Subject: [PATCH 262/474] drm/amd/display: Disable idle optimizations before
 programming DCN

[Why]
Programming DCN is explicitly forbidden during idle optimzations allowed
state. Existing implemenation relies on OS/DM, which is not robust. Instead
DC should sequence this.

Note that DC will not re-enter idle optimized state on its own, it is only
responsible for catching out of sequence calls. It is still DM
responsibility to sequence appropriate for optimized power, but this change
removes the requirement for DM to cover the .1% case.

[How]
 - elevate updates during idle optimized state to full updates
 - disable idle power optimizations prior to programming

Signed-off-by: Jun Lei <jun.lei@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index ef0b5941bc50..92eb1ca1634f 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1250,6 +1250,9 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 	int i, k, l;
 	struct dc_stream_state *dc_streams[MAX_STREAMS] = {0};
 
+#if defined(CONFIG_DRM_AMD_DC_DCN3_0)
+	dc_allow_idle_optimizations(dc, false);
+#endif
 
 	for (i = 0; i < context->stream_count; i++)
 		dc_streams[i] =  context->streams[i];
@@ -1838,6 +1841,11 @@ static enum surface_update_type check_update_surfaces_for_stream(
 	int i;
 	enum surface_update_type overall_type = UPDATE_TYPE_FAST;
 
+#if defined(CONFIG_DRM_AMD_DC_DCN3_0)
+	if (dc->idle_optimizations_allowed)
+		overall_type = UPDATE_TYPE_FULL;
+
+#endif
 	if (stream_status == NULL || stream_status->plane_count != surface_count)
 		overall_type = UPDATE_TYPE_FULL;
 
@@ -2306,8 +2314,14 @@ static void commit_planes_for_stream(struct dc *dc,
 		}
 	}
 
-	if (update_type == UPDATE_TYPE_FULL && dc->optimize_seamless_boot_streams == 0) {
-		dc->hwss.prepare_bandwidth(dc, context);
+	if (update_type == UPDATE_TYPE_FULL) {
+#if defined(CONFIG_DRM_AMD_DC_DCN3_0)
+		dc_allow_idle_optimizations(dc, false);
+
+#endif
+		if (dc->optimize_seamless_boot_streams == 0)
+			dc->hwss.prepare_bandwidth(dc, context);
+
 		context_clock_trace(dc, context);
 	}
 

From 471c1dd9546df81d259664ac3e2ab0e99169f755 Mon Sep 17 00:00:00 2001
From: Reza Amini <Reza.Amini@amd.com>
Date: Wed, 15 Jul 2020 11:33:23 -0400
Subject: [PATCH 263/474] drm/amd/display: Allow asic specific FSFT timing
 optimization

[Why]
Each asic can optimize best based on its capabilities

[How]
Optimizing timing for a new pixel clock

Signed-off-by: Reza Amini <Reza.Amini@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/core/dc_stream.c   | 18 ++++++-------
 drivers/gpu/drm/amd/display/dc/dc_stream.h    |  4 +--
 .../drm/amd/display/dc/dcn20/dcn20_hwseq.c    | 27 +++++++++++++++++++
 .../drm/amd/display/dc/dcn20/dcn20_hwseq.h    |  5 ++++
 .../gpu/drm/amd/display/dc/dcn20/dcn20_init.c |  3 +++
 .../gpu/drm/amd/display/dc/dcn21/dcn21_init.c |  3 +++
 .../gpu/drm/amd/display/dc/inc/hw_sequencer.h |  5 ++++
 .../amd/display/modules/freesync/freesync.c   |  5 +++-
 8 files changed, 57 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 10d69ada88e3..0257a900fe2b 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -246,20 +246,18 @@ struct dc_stream_status *dc_stream_get_status(
 
 #ifndef TRIM_FSFT
 /**
- * dc_optimize_timing() - dc to optimize timing
+ * dc_optimize_timing_for_fsft() - dc to optimize timing
  */
-bool dc_optimize_timing(
-	struct dc_crtc_timing *timing,
+bool dc_optimize_timing_for_fsft(
+	struct dc_stream_state *pStream,
 	unsigned int max_input_rate_in_khz)
 {
-	//optimization is expected to assing a value to these:
-	//timing->pix_clk_100hz
-	//timing->v_front_porch
-	//timing->v_total
-	//timing->fast_transport_output_rate_100hz;
-	timing->fast_transport_output_rate_100hz = timing->pix_clk_100hz;
+	struct dc  *dc;
 
-	return true;
+	dc = pStream->ctx->dc;
+
+	return (dc->hwss.optimize_timing_for_fsft &&
+		dc->hwss.optimize_timing_for_fsft(dc, &pStream->timing, max_input_rate_in_khz));
 }
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index e4e85a159462..633442bc7ef2 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -424,8 +424,8 @@ struct dc_stream_status *dc_stream_get_status(
 	struct dc_stream_state *dc_stream);
 
 #ifndef TRIM_FSFT
-bool dc_optimize_timing(
-	struct dc_crtc_timing *timing,
+bool dc_optimize_timing_for_fsft(
+	struct dc_stream_state *pStream,
 	unsigned int max_input_rate_in_khz);
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 7725a406c16e..66180b4332f1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -2498,3 +2498,30 @@ void dcn20_fpga_init_hw(struct dc *dc)
 		tg->funcs->tg_init(tg);
 	}
 }
+#ifndef TRIM_FSFT
+bool dcn20_optimize_timing_for_fsft(struct dc *dc,
+		struct dc_crtc_timing *timing,
+		unsigned int max_input_rate_in_khz)
+{
+	unsigned int old_v_front_porch;
+	unsigned int old_v_total;
+	unsigned int max_input_rate_in_100hz;
+	unsigned long long new_v_total;
+
+	max_input_rate_in_100hz = max_input_rate_in_khz * 10;
+	if (max_input_rate_in_100hz < timing->pix_clk_100hz)
+		return false;
+
+	old_v_total = timing->v_total;
+	old_v_front_porch = timing->v_front_porch;
+
+	timing->fast_transport_output_rate_100hz = timing->pix_clk_100hz;
+	timing->pix_clk_100hz = max_input_rate_in_100hz;
+
+	new_v_total = div_u64((unsigned long long)old_v_total * max_input_rate_in_100hz, timing->pix_clk_100hz);
+
+	timing->v_total = new_v_total;
+	timing->v_front_porch = old_v_front_porch + (timing->v_total - old_v_total);
+	return true;
+}
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h
index 63ce763f148e..83220e34c1a9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h
@@ -132,5 +132,10 @@ int dcn20_init_sys_ctx(struct dce_hwseq *hws,
 		struct dc *dc,
 		struct dc_phy_addr_space_config *pa_config);
 
+#ifndef TRIM_FSFT
+bool dcn20_optimize_timing_for_fsft(struct dc *dc,
+		struct dc_crtc_timing *timing,
+		unsigned int max_input_rate_in_khz);
+#endif
 #endif /* __DC_HWSS_DCN20_H__ */
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
index 2380392b916e..3dde6f26de47 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
@@ -88,6 +88,9 @@ static const struct hw_sequencer_funcs dcn20_funcs = {
 	.set_backlight_level = dce110_set_backlight_level,
 	.set_abm_immediate_disable = dce110_set_abm_immediate_disable,
 	.set_pipe = dce110_set_pipe,
+#ifndef TRIM_FSFT
+	.optimize_timing_for_fsft = dcn20_optimize_timing_for_fsft,
+#endif
 };
 
 static const struct hwseq_private_funcs dcn20_private_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
index 177d0dc8927a..b187f71afa65 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
@@ -92,6 +92,9 @@ static const struct hw_sequencer_funcs dcn21_funcs = {
 	.set_backlight_level = dcn21_set_backlight_level,
 	.set_abm_immediate_disable = dcn21_set_abm_immediate_disable,
 	.set_pipe = dcn21_set_pipe,
+#ifndef TRIM_FSFT
+	.optimize_timing_for_fsft = dcn20_optimize_timing_for_fsft,
+#endif
 };
 
 static const struct hwseq_private_funcs dcn21_private_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index 720ce5e458d8..3c986717dcd5 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -116,6 +116,11 @@ struct hw_sequencer_funcs {
 	void (*set_static_screen_control)(struct pipe_ctx **pipe_ctx,
 			int num_pipes,
 			const struct dc_static_screen_params *events);
+#ifndef TRIM_FSFT
+	bool (*optimize_timing_for_fsft)(struct dc *dc,
+			struct dc_crtc_timing *timing,
+			unsigned int max_input_rate_in_khz);
+#endif
 
 	/* Stream Related */
 	void (*enable_stream)(struct pipe_ctx *pipe_ctx);
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index 7a2500fbf3f2..81820f3d6b3b 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -829,10 +829,13 @@ void mod_freesync_build_vrr_infopacket(struct mod_freesync *mod_freesync,
 	switch (packet_type) {
 	case PACKET_TYPE_FS_V3:
 #ifndef TRIM_FSFT
+		// always populate with pixel rate.
 		build_vrr_infopacket_v3(
 				stream->signal, vrr,
 				stream->timing.flags.FAST_TRANSPORT,
-				stream->timing.fast_transport_output_rate_100hz,
+				(stream->timing.flags.FAST_TRANSPORT) ?
+						stream->timing.fast_transport_output_rate_100hz :
+						stream->timing.pix_clk_100hz,
 				app_tf, infopacket);
 #else
 		build_vrr_infopacket_v3(stream->signal, vrr, app_tf, infopacket);

From 8b0379a85762b516c7b46aed7dbf2a4947c00564 Mon Sep 17 00:00:00 2001
From: hersen wu <hersenxs.wu@amd.com>
Date: Sun, 19 Jul 2020 17:21:59 -0400
Subject: [PATCH 264/474] drm/amd/display: dchubbub p-state warning during
 surface planes switch

[Why]
ramp_up_dispclk_with_dpp is to change dispclk, dppclk and dprefclk
according to bandwidth requirement. call stack: rv1_update_clocks -->
update_clocks --> dcn10_prepare_bandwidth / dcn10_optimize_bandwidth
--> prepare_bandwidth / optimize_bandwidth. before change dcn hw,
prepare_bandwidth will be called first to allow enough clock,
watermark for change, after end of dcn hw change, optimize_bandwidth
is executed to lower clock to save power for new dcn hw settings.

below is sequence of commit_planes_for_stream:
step 1: prepare_bandwidth - raise clock to have enough bandwidth
step 2: lock_doublebuffer_enable
step 3: pipe_control_lock(true) - make dchubp register change will
not take effect right way
step 4: apply_ctx_for_surface - program dchubp
step 5: pipe_control_lock(false) - dchubp register change take effect
step 6: optimize_bandwidth --> dc_post_update_surfaces_to_stream
for full_date, optimize clock to save power

at end of step 1, dcn clocks (dprefclk, dispclk, dppclk) may be
changed for new dchubp configuration. but real dcn hub dchubps are
still running with old configuration until end of step 5. this need
clocks settings at step 1 should not less than that before step 1.
this is checked by two conditions: 1. if (should_set_clock(safe_to_lower
, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz) ||
new_clocks->dispclk_khz == clk_mgr_base->clks.dispclk_khz)
2. request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz

the second condition is based on new dchubp configuration. dppclk
for new dchubp may be different from dppclk before step 1.
for example, before step 1, dchubps are as below:
pipe 0: recout=(0,40,1920,980) viewport=(0,0,1920,979)
pipe 1: recout=(0,0,1920,1080) viewport=(0,0,1920,1080)
for dppclk for pipe0 need dppclk = dispclk

new dchubp pipe split configuration:
pipe 0: recout=(0,0,960,1080) viewport=(0,0,960,1080)
pipe 1: recout=(960,0,960,1080) viewport=(960,0,960,1080)
dppclk only needs dppclk = dispclk /2.

dispclk, dppclk are not lock by otg master lock. they take effect
after step 1. during this transition, dispclk are the same, but
dppclk is changed to half of previous clock for old dchubp
configuration between step 1 and step 6. This may cause p-state
warning intermittently.

[How]
for new_clocks->dispclk_khz == clk_mgr_base->clks.dispclk_khz, we
need make sure dppclk are not changed to less between step 1 and 6.
for new_clocks->dispclk_khz > clk_mgr_base->clks.dispclk_khz,
new display clock is raised, but we do not know ratio of
new_clocks->dispclk_khz and clk_mgr_base->clks.dispclk_khz,
new_clocks->dispclk_khz /2 does not guarantee equal or higher than
old dppclk. we could ignore power saving different between
dppclk = displck and dppclk = dispclk / 2 between step 1 and step 6.
as long as safe_to_lower = false, set dpclk = dispclk to simplify
condition check.

CC: Stable <stable@vger.kernel.org>
Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../display/dc/clk_mgr/dcn10/rv1_clk_mgr.c    | 69 ++++++++++++++++++-
 1 file changed, 67 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c
index 3fab9296918a..e133edc587d3 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c
@@ -85,12 +85,77 @@ static int rv1_determine_dppclk_threshold(struct clk_mgr_internal *clk_mgr, stru
 	return disp_clk_threshold;
 }
 
-static void ramp_up_dispclk_with_dpp(struct clk_mgr_internal *clk_mgr, struct dc *dc, struct dc_clocks *new_clocks)
+static void ramp_up_dispclk_with_dpp(
+		struct clk_mgr_internal *clk_mgr,
+		struct dc *dc,
+		struct dc_clocks *new_clocks,
+		bool safe_to_lower)
 {
 	int i;
 	int dispclk_to_dpp_threshold = rv1_determine_dppclk_threshold(clk_mgr, new_clocks);
 	bool request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz;
 
+	/* this function is to change dispclk, dppclk and dprefclk according to
+	 * bandwidth requirement. Its call stack is rv1_update_clocks -->
+	 * update_clocks --> dcn10_prepare_bandwidth / dcn10_optimize_bandwidth
+	 * --> prepare_bandwidth / optimize_bandwidth. before change dcn hw,
+	 * prepare_bandwidth will be called first to allow enough clock,
+	 * watermark for change, after end of dcn hw change, optimize_bandwidth
+	 * is executed to lower clock to save power for new dcn hw settings.
+	 *
+	 * below is sequence of commit_planes_for_stream:
+	 *
+	 * step 1: prepare_bandwidth - raise clock to have enough bandwidth
+	 * step 2: lock_doublebuffer_enable
+	 * step 3: pipe_control_lock(true) - make dchubp register change will
+	 * not take effect right way
+	 * step 4: apply_ctx_for_surface - program dchubp
+	 * step 5: pipe_control_lock(false) - dchubp register change take effect
+	 * step 6: optimize_bandwidth --> dc_post_update_surfaces_to_stream
+	 * for full_date, optimize clock to save power
+	 *
+	 * at end of step 1, dcn clocks (dprefclk, dispclk, dppclk) may be
+	 * changed for new dchubp configuration. but real dcn hub dchubps are
+	 * still running with old configuration until end of step 5. this need
+	 * clocks settings at step 1 should not less than that before step 1.
+	 * this is checked by two conditions: 1. if (should_set_clock(safe_to_lower
+	 * , new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz) ||
+	 * new_clocks->dispclk_khz == clk_mgr_base->clks.dispclk_khz)
+	 * 2. request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz
+	 *
+	 * the second condition is based on new dchubp configuration. dppclk
+	 * for new dchubp may be different from dppclk before step 1.
+	 * for example, before step 1, dchubps are as below:
+	 * pipe 0: recout=(0,40,1920,980) viewport=(0,0,1920,979)
+	 * pipe 1: recout=(0,0,1920,1080) viewport=(0,0,1920,1080)
+	 * for dppclk for pipe0 need dppclk = dispclk
+	 *
+	 * new dchubp pipe split configuration:
+	 * pipe 0: recout=(0,0,960,1080) viewport=(0,0,960,1080)
+	 * pipe 1: recout=(960,0,960,1080) viewport=(960,0,960,1080)
+	 * dppclk only needs dppclk = dispclk /2.
+	 *
+	 * dispclk, dppclk are not lock by otg master lock. they take effect
+	 * after step 1. during this transition, dispclk are the same, but
+	 * dppclk is changed to half of previous clock for old dchubp
+	 * configuration between step 1 and step 6. This may cause p-state
+	 * warning intermittently.
+	 *
+	 * for new_clocks->dispclk_khz == clk_mgr_base->clks.dispclk_khz, we
+	 * need make sure dppclk are not changed to less between step 1 and 6.
+	 * for new_clocks->dispclk_khz > clk_mgr_base->clks.dispclk_khz,
+	 * new display clock is raised, but we do not know ratio of
+	 * new_clocks->dispclk_khz and clk_mgr_base->clks.dispclk_khz,
+	 * new_clocks->dispclk_khz /2 does not guarantee equal or higher than
+	 * old dppclk. we could ignore power saving different between
+	 * dppclk = displck and dppclk = dispclk / 2 between step 1 and step 6.
+	 * as long as safe_to_lower = false, set dpclk = dispclk to simplify
+	 * condition check.
+	 * todo: review this change for other asic.
+	 **/
+	if (!safe_to_lower)
+		request_dpp_div = false;
+
 	/* set disp clk to dpp clk threshold */
 
 	clk_mgr->funcs->set_dispclk(clk_mgr, dispclk_to_dpp_threshold);
@@ -209,7 +274,7 @@ static void rv1_update_clocks(struct clk_mgr *clk_mgr_base,
 	/* program dispclk on = as a w/a for sleep resume clock ramping issues */
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)
 			|| new_clocks->dispclk_khz == clk_mgr_base->clks.dispclk_khz) {
-		ramp_up_dispclk_with_dpp(clk_mgr, dc, new_clocks);
+		ramp_up_dispclk_with_dpp(clk_mgr, dc, new_clocks, safe_to_lower);
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
 		send_request_to_lower = true;
 	}

From b5fe6aa2b02cdfee75f747c68f3d303fddd09af9 Mon Sep 17 00:00:00 2001
From: Wyatt Wood <wyatt.wood@amd.com>
Date: Wed, 17 Jun 2020 11:29:27 -0400
Subject: [PATCH 265/474] drm/amd/display: Use hw lock mgr

[Why]
Feature requires synchronization of dig, pipe, and cursor locking
between driver and fw.

[How]
Set flag to force psr to use hw lock mgr.

Signed-off-by: Wyatt Wood <wyatt.wood@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
index 82e67bd81f2d..5167d6b8a48d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
@@ -233,8 +233,8 @@ static bool dmub_psr_copy_settings(struct dmub_psr *dmub,
 	copy_settings_data->frame_cap_ind			= psr_context->psrFrameCaptureIndicationReq;
 	copy_settings_data->debug.bitfields.visual_confirm	= dc->dc->debug.visual_confirm == VISUAL_CONFIRM_PSR ?
 									true : false;
+	copy_settings_data->debug.bitfields.use_hw_lock_mgr	= 1;
 	copy_settings_data->init_sdp_deadline			= psr_context->sdpTransmitLineNumDeadline;
-	copy_settings_data->debug.bitfields.use_hw_lock_mgr	= 0;
 
 	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd);
 	dc_dmub_srv_cmd_execute(dc->dmub_srv);

From 76d5ef4ff10bc64f84a4b301cf8c25229048edd8 Mon Sep 17 00:00:00 2001
From: Aric Cyr <aric.cyr@amd.com>
Date: Wed, 22 Jul 2020 15:40:06 -0400
Subject: [PATCH 266/474] drm/amd/display: Fix DP Compliance tests 4.3.2.1 and
 4.3.2.2

[Why]
Test expects that we also read HPD_IRQ_VECTOR when checking for
symbol loss as well lane status.

[How]
Read bytes 0x200-0x205 instead of just 0x202-0x205

Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 1a3dbed3becb..d7d2dcd49c06 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1138,23 +1138,22 @@ static enum link_training_result check_link_loss_status(
 	const struct link_training_settings *link_training_setting)
 {
 	enum link_training_result status = LINK_TRAINING_SUCCESS;
-	unsigned int lane01_status_address = DP_LANE0_1_STATUS;
 	union lane_status lane_status;
-	uint8_t dpcd_buf[4] = {0};
+	uint8_t dpcd_buf[6] = {0};
 	uint32_t lane;
 
 	core_link_read_dpcd(
-		link,
-		lane01_status_address,
-		(uint8_t *)(dpcd_buf),
-		sizeof(dpcd_buf));
+			link,
+			DP_SINK_COUNT,
+			(uint8_t *)(dpcd_buf),
+			sizeof(dpcd_buf));
 
 	/*parse lane status*/
 	for (lane = 0; lane < link->cur_link_settings.lane_count; lane++) {
 		/*
 		 * check lanes status
 		 */
-		lane_status.raw = get_nibble_at_index(&dpcd_buf[0], lane);
+		lane_status.raw = get_nibble_at_index(&dpcd_buf[2], lane);
 
 		if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
 			!lane_status.bits.CR_DONE_0 ||

From a676a97623d399f7a2174b347d688412864d385a Mon Sep 17 00:00:00 2001
From: Huang Rui <ray.huang@amd.com>
Date: Mon, 27 Jul 2020 16:19:45 +0800
Subject: [PATCH 267/474] drm/amdgpu: skip crit temperature values on APU (v2)

It doesn't expose PPTable descriptor on APU platform. So max/min
temperature values cannot be got from APU platform.

v2: Stoney needs to skip crit temperature as well.

Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 5f20cadee343..e4dbf14320b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -3212,6 +3212,12 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 	     attr == &sensor_dev_attr_fan1_enable.dev_attr.attr))
 		return 0;
 
+	/* Skip crit temp on APU */
+	if ((adev->flags & AMD_IS_APU) && (adev->family >= AMDGPU_FAMILY_CZ) &&
+	    (attr == &sensor_dev_attr_temp1_crit.dev_attr.attr ||
+	     attr == &sensor_dev_attr_temp1_crit_hyst.dev_attr.attr))
+		return 0;
+
 	/* Skip limit attributes if DPM is not enabled */
 	if (!adev->pm.dpm_enabled &&
 	    (attr == &sensor_dev_attr_temp1_crit.dev_attr.attr ||

From 0730344ee370012574fe73c2785557d0e9180430 Mon Sep 17 00:00:00 2001
From: Jiansong Chen <Jiansong.Chen@amd.com>
Date: Tue, 28 Jul 2020 19:14:22 +0800
Subject: [PATCH 268/474] drm/amd/powerplay: update driver if version for
 navy_flounder

It's in accordance with pmfw 65.5.0 for navy_flounder.

Signed-off-by: Jiansong Chen <Jiansong.Chen@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 9504f9954fd3..6a42331aba8a 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -31,7 +31,7 @@
 #define SMU11_DRIVER_IF_VERSION_NV12 0x33
 #define SMU11_DRIVER_IF_VERSION_NV14 0x36
 #define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x34
-#define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0x2
+#define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0x3
 
 /* MP Apertures */
 #define MP0_Public			0x03800000

From 278a4b5f62be85fa62d4439b5fbdf15027e99606 Mon Sep 17 00:00:00 2001
From: Jiansong Chen <Jiansong.Chen@amd.com>
Date: Wed, 29 Jul 2020 11:58:21 +0800
Subject: [PATCH 269/474] drm/amdgpu: update GC golden setting for
 navy_flounder

Update GC golden setting for navy_flounder.

Signed-off-by: Jiansong Chen <Jiansong.Chen@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 8344c3b0b9b5..43cf3487c98a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3127,7 +3127,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_2[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA0_CLK_CTRL, 0xff7f0fff, 0x30000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA1_CLK_CTRL, 0xff7f0fff, 0x7e000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPF_GCR_CNTL, 0x0007ffff, 0x0000c000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000200),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_EXCEPTION_CONTROL, 0x7fff0f1f, 0x00b80000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Sienna_Cichlid, 0x1ff1ffff, 0x00000500),
@@ -3158,7 +3158,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_2[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER7_SELECT, 0xf0f001ff, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER8_SELECT, 0xf0f001ff, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER9_SELECT, 0xf0f001ff, 0x00000000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xffffffff, 0x010b0000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffbfffff, 0x00a00000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000003ff)
 };

From 6b6124bb4a0b05fa9ac052e14dd7c37c42ab9297 Mon Sep 17 00:00:00 2001
From: Liu ChengZhe <ChengZhe.Liu@amd.com>
Date: Fri, 24 Jul 2020 17:22:15 +0800
Subject: [PATCH 270/474] drm/amdgpu: fix PSP autoload twice in FLR

Assigning false to block->status.hw overwrites PSP's previous
hardware status, which causes the PSP to Resume operation after
hardware init.

Remove this assignment and let the PSP execute Resume operation
when it is told to.

v2: Remove the braces.
v3: Modify the description.

Signed-off-by: Liu ChengZhe <ChengZhe.Liu@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index aa5b54e5a1d7..eb7cfe87042e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2574,6 +2574,9 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 		AMD_IP_BLOCK_TYPE_IH,
 	};
 
+	for (i = 0; i < adev->num_ip_blocks; i++)
+		adev->ip_blocks[i].status.hw = false;
+
 	for (i = 0; i < ARRAY_SIZE(ip_order); i++) {
 		int j;
 		struct amdgpu_ip_block *block;
@@ -2581,7 +2584,6 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 		for (j = 0; j < adev->num_ip_blocks; j++) {
 			block = &adev->ip_blocks[j];
 
-			block->status.hw = false;
 			if (block->version->type != ip_order[i] ||
 				!block->status.valid)
 				continue;

From d392aa02db1b3ecbec49bc8bd28a132298174539 Mon Sep 17 00:00:00 2001
From: Liu ChengZhe <ChengZhe.Liu@amd.com>
Date: Fri, 24 Jul 2020 15:55:33 +0800
Subject: [PATCH 271/474] drm amdgpu: Skip tmr load for SRIOV

1. For Navi12, CHIP_SIENNA_CICHLID, skip tmr load operation;
2. Check pointer before release firmware.

v2: use CHIP_SIENNA_CICHLID instead
v3: remove local "bool ret"; fix grammer issue
v4: use my name instead of "root"
v5: fix grammer issue and indent issue

Signed-off-by: Liu ChengZhe <ChengZhe.Liu@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 35 ++++++++++++++++++++-----
 1 file changed, 29 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 8034111acd9a..7fe564275457 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -193,12 +193,18 @@ static int psp_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	psp_memory_training_fini(&adev->psp);
-	release_firmware(adev->psp.sos_fw);
-	adev->psp.sos_fw = NULL;
-	release_firmware(adev->psp.asd_fw);
-	adev->psp.asd_fw = NULL;
-	release_firmware(adev->psp.ta_fw);
-	adev->psp.ta_fw = NULL;
+	if (adev->psp.sos_fw) {
+		release_firmware(adev->psp.sos_fw);
+		adev->psp.sos_fw = NULL;
+	}
+	if (adev->psp.asd_fw) {
+		release_firmware(adev->psp.asd_fw);
+		adev->psp.asd_fw = NULL;
+	}
+	if (adev->psp.ta_fw) {
+		release_firmware(adev->psp.ta_fw);
+		adev->psp.ta_fw = NULL;
+	}
 
 	if (adev->asic_type == CHIP_NAVI10)
 		psp_sysfs_fini(adev);
@@ -409,11 +415,28 @@ static int psp_clear_vf_fw(struct psp_context *psp)
 	return ret;
 }
 
+static bool psp_skip_tmr(struct psp_context *psp)
+{
+	switch (psp->adev->asic_type) {
+	case CHIP_NAVI12:
+	case CHIP_SIENNA_CICHLID:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static int psp_tmr_load(struct psp_context *psp)
 {
 	int ret;
 	struct psp_gfx_cmd_resp *cmd;
 
+	/* For Navi12 and CHIP_SIENNA_CICHLID SRIOV, do not set up TMR.
+	 * Already set up by host driver.
+	 */
+	if (amdgpu_sriov_vf(psp->adev) && psp_skip_tmr(psp))
+		return 0;
+
 	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
 	if (!cmd)
 		return -ENOMEM;

From a15383893f798c0962ab87f7e159abba9cbe3822 Mon Sep 17 00:00:00 2001
From: Jiansong Chen <Jiansong.Chen@amd.com>
Date: Thu, 30 Jul 2020 18:09:47 +0800
Subject: [PATCH 272/474] drm/amdgpu: enable GFXOFF for navy_flounder

Enable GFXOFF for navy_flounder.

Signed-off-by: Jiansong Chen <Jiansong.Chen@amd.com>
Reviewed-by: Likun Gao <Likun.Gao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c    | 1 +
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 43cf3487c98a..65997ffaed45 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -7529,6 +7529,7 @@ static int gfx_v10_0_set_powergating_state(void *handle,
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
 	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
 		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index fd82402065e6..7b950a582a28 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1029,6 +1029,7 @@ int smu_v11_0_gfx_off_control(struct smu_context *smu, bool enable)
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
 	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
 		if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
 			return 0;
 		if (enable)

From c06f670f4701d3a19534eb7ca4f606b9771a94a3 Mon Sep 17 00:00:00 2001
From: Eric Bernstein <eric.bernstein@amd.com>
Date: Mon, 20 Jul 2020 19:18:43 -0400
Subject: [PATCH 273/474] drm/amd/display: Use parameter for call to set output
 mux

Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Chris Park <Chris.Park@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 02742cca4d84..9f8ab679616c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -3102,6 +3102,9 @@ void core_link_enable_stream(
 	struct dc *dc = pipe_ctx->stream->ctx->dc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	enum dc_status status;
+#if defined(CONFIG_DRM_AMD_DC_DCN3_0)
+	enum otg_out_mux_dest otg_out_dest = OUT_MUX_DIO;
+#endif
 	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 
 	if (!IS_DIAG_DC(dc->ctx->dce_environment) &&
@@ -3136,8 +3139,8 @@ void core_link_enable_stream(
 	pipe_ctx->stream->link->link_state_valid = true;
 
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
-		if (pipe_ctx->stream_res.tg->funcs->set_out_mux)
-					pipe_ctx->stream_res.tg->funcs->set_out_mux(pipe_ctx->stream_res.tg, OUT_MUX_DIO);
+	if (pipe_ctx->stream_res.tg->funcs->set_out_mux)
+		pipe_ctx->stream_res.tg->funcs->set_out_mux(pipe_ctx->stream_res.tg, otg_out_dest);
 #endif
 
 	if (dc_is_dvi_signal(pipe_ctx->stream->signal))

From 098214999c8f8eea8dffddb61be5742fac2c829e Mon Sep 17 00:00:00 2001
From: Igor Kravchenko <Igor.Kravchenko@amd.com>
Date: Sun, 19 Jul 2020 20:45:28 -0400
Subject: [PATCH 274/474] drm/amd/display: Read VBIOS Golden Settings Tbl

[Why]
For ver.4.4 and higher VBIOS contains default setting table.

{How]
Read Golden Settings Table from VBIOS, apply Aux tuning parameters.

Signed-off-by: Igor Kravchenko <Igor.Kravchenko@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/bios/bios_parser.c |  2 +
 .../drm/amd/display/dc/bios/bios_parser2.c    | 81 +++++++++++++++++++
 drivers/gpu/drm/amd/display/dc/core/dc_link.c |  3 +
 .../gpu/drm/amd/display/dc/dc_bios_types.h    |  4 +
 drivers/gpu/drm/amd/display/dc/dc_types.h     | 14 ++++
 .../drm/amd/display/dc/dce/dce_link_encoder.h |  4 +-
 .../amd/display/dc/dcn10/dcn10_link_encoder.h | 10 ++-
 .../amd/display/dc/dcn20/dcn20_link_encoder.c | 14 +++-
 .../amd/display/dc/dcn20/dcn20_link_encoder.h |  5 +-
 drivers/gpu/drm/amd/include/atomfirmware.h    | 54 ++++++++++++-
 10 files changed, 182 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
index 008d4d11339d..ad394aefa5d9 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -2834,6 +2834,8 @@ static const struct dc_vbios_funcs vbios_funcs = {
 	.bios_parser_destroy = bios_parser_destroy,
 
 	.get_board_layout_info = bios_get_board_layout_info,
+
+	.get_atom_dc_golden_table = NULL
 };
 
 static bool bios_parser_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index b8684131151d..f8db92fed9cf 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -2079,6 +2079,85 @@ static uint16_t bios_parser_pack_data_tables(
 	return 0;
 }
 
+static struct atom_dc_golden_table_v1 *bios_get_golden_table(
+		struct bios_parser *bp,
+		uint32_t rev_major,
+		uint32_t rev_minor,
+		uint16_t *dc_golden_table_ver)
+{
+	struct atom_display_controller_info_v4_4 *disp_cntl_tbl_4_4 = NULL;
+	uint32_t dc_golden_offset = 0;
+	*dc_golden_table_ver = 0;
+
+	if (!DATA_TABLES(dce_info))
+		return NULL;
+
+	/* ver.4.4 or higher */
+	switch (rev_major) {
+	case 4:
+		switch (rev_minor) {
+		case 4:
+			disp_cntl_tbl_4_4 = GET_IMAGE(struct atom_display_controller_info_v4_4,
+									DATA_TABLES(dce_info));
+			if (!disp_cntl_tbl_4_4)
+				return NULL;
+			dc_golden_offset = disp_cntl_tbl_4_4->dc_golden_table_offset;
+			*dc_golden_table_ver = disp_cntl_tbl_4_4->dc_golden_table_ver;
+			break;
+		}
+		break;
+	}
+
+	if (!dc_golden_offset)
+		return NULL;
+
+	if (*dc_golden_table_ver != 1)
+		return NULL;
+
+	return GET_IMAGE(struct atom_dc_golden_table_v1,
+					 dc_golden_offset);
+}
+
+static enum bp_result bios_get_atom_dc_golden_table(
+	struct dc_bios *dcb)
+{
+	struct bios_parser *bp = BP_FROM_DCB(dcb);
+	enum bp_result result = BP_RESULT_OK;
+	struct atom_dc_golden_table_v1 *atom_dc_golden_table = NULL;
+	struct atom_common_table_header *header;
+	struct atom_data_revision tbl_revision;
+	uint16_t dc_golden_table_ver = 0;
+
+	header = GET_IMAGE(struct atom_common_table_header,
+							DATA_TABLES(dce_info));
+	if (!header)
+		return BP_RESULT_UNSUPPORTED;
+
+	get_atom_data_table_revision(header, &tbl_revision);
+
+	atom_dc_golden_table = bios_get_golden_table(bp,
+			tbl_revision.major,
+			tbl_revision.minor,
+			&dc_golden_table_ver);
+
+	if (!atom_dc_golden_table)
+		return BP_RESULT_UNSUPPORTED;
+
+	dcb->golden_table.dc_golden_table_ver = dc_golden_table_ver;
+	dcb->golden_table.aux_dphy_rx_control0_val = atom_dc_golden_table->aux_dphy_rx_control0_val;
+	dcb->golden_table.aux_dphy_rx_control1_val = atom_dc_golden_table->aux_dphy_rx_control1_val;
+	dcb->golden_table.aux_dphy_tx_control_val = atom_dc_golden_table->aux_dphy_tx_control_val;
+	dcb->golden_table.dc_gpio_aux_ctrl_0_val = atom_dc_golden_table->dc_gpio_aux_ctrl_0_val;
+	dcb->golden_table.dc_gpio_aux_ctrl_1_val = atom_dc_golden_table->dc_gpio_aux_ctrl_1_val;
+	dcb->golden_table.dc_gpio_aux_ctrl_2_val = atom_dc_golden_table->dc_gpio_aux_ctrl_2_val;
+	dcb->golden_table.dc_gpio_aux_ctrl_3_val = atom_dc_golden_table->dc_gpio_aux_ctrl_3_val;
+	dcb->golden_table.dc_gpio_aux_ctrl_4_val = atom_dc_golden_table->dc_gpio_aux_ctrl_4_val;
+	dcb->golden_table.dc_gpio_aux_ctrl_5_val = atom_dc_golden_table->dc_gpio_aux_ctrl_5_val;
+
+	return result;
+}
+
+
 static const struct dc_vbios_funcs vbios_funcs = {
 	.get_connectors_number = bios_parser_get_connectors_number,
 
@@ -2128,6 +2207,8 @@ static const struct dc_vbios_funcs vbios_funcs = {
 
 	.get_board_layout_info = bios_get_board_layout_info,
 	.pack_data_tables = bios_parser_pack_data_tables,
+
+	.get_atom_dc_golden_table = bios_get_atom_dc_golden_table
 };
 
 static bool bios_parser2_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 9f8ab679616c..071c7b32b282 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -1540,6 +1540,9 @@ static bool dc_link_construct(struct dc_link *link,
 		}
 	}
 
+	if (bios->funcs->get_atom_dc_golden_table)
+		bios->funcs->get_atom_dc_golden_table(bios);
+
 	/*
 	 * TODO check if GPIO programmed correctly
 	 *
diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
index 845a3054f21f..d06d07042a12 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
@@ -133,6 +133,9 @@ struct dc_vbios_funcs {
 	uint16_t (*pack_data_tables)(
 		struct dc_bios *dcb,
 		void *dst);
+
+	enum bp_result (*get_atom_dc_golden_table)(
+			struct dc_bios *dcb);
 };
 
 struct bios_registers {
@@ -154,6 +157,7 @@ struct dc_bios {
 	struct dc_firmware_info fw_info;
 	bool fw_info_valid;
 	struct dc_vram_info vram_info;
+	struct dc_golden_table golden_table;
 };
 
 #endif /* DC_BIOS_TYPES_H */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 29fe5389f973..946ba929c6f6 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -890,6 +890,20 @@ struct dsc_dec_dpcd_caps {
 	uint32_t branch_max_line_width;
 };
 
+struct dc_golden_table {
+	uint16_t dc_golden_table_ver;
+	uint32_t aux_dphy_rx_control0_val;
+	uint32_t aux_dphy_tx_control_val;
+	uint32_t aux_dphy_rx_control1_val;
+	uint32_t dc_gpio_aux_ctrl_0_val;
+	uint32_t dc_gpio_aux_ctrl_1_val;
+	uint32_t dc_gpio_aux_ctrl_2_val;
+	uint32_t dc_gpio_aux_ctrl_3_val;
+	uint32_t dc_gpio_aux_ctrl_4_val;
+	uint32_t dc_gpio_aux_ctrl_5_val;
+};
+
+
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 enum dc_gpu_mem_alloc_type {
 	DC_MEM_ALLOC_TYPE_GART,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h
index 384389f0e2c3..66027d496778 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h
@@ -38,7 +38,8 @@
 
 #define AUX_REG_LIST(id)\
 	SRI(AUX_CONTROL, DP_AUX, id), \
-	SRI(AUX_DPHY_RX_CONTROL0, DP_AUX, id)
+	SRI(AUX_DPHY_RX_CONTROL0, DP_AUX, id), \
+	SRI(AUX_DPHY_RX_CONTROL1, DP_AUX, id)
 
 #define HPD_REG_LIST(id)\
 	SRI(DC_HPD_CONTROL, HPD, id)
@@ -107,6 +108,7 @@
 struct dce110_link_enc_aux_registers {
 	uint32_t AUX_CONTROL;
 	uint32_t AUX_DPHY_RX_CONTROL0;
+	uint32_t AUX_DPHY_RX_CONTROL1;
 };
 
 struct dce110_link_enc_hpd_registers {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
index cf59ab0034dc..04dabed5f1c5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
@@ -31,10 +31,10 @@
 #define TO_DCN10_LINK_ENC(link_encoder)\
 	container_of(link_encoder, struct dcn10_link_encoder, base)
 
-
 #define AUX_REG_LIST(id)\
 	SRI(AUX_CONTROL, DP_AUX, id), \
-	SRI(AUX_DPHY_RX_CONTROL0, DP_AUX, id)
+	SRI(AUX_DPHY_RX_CONTROL0, DP_AUX, id), \
+	SRI(AUX_DPHY_RX_CONTROL1, DP_AUX, id)
 
 #define HPD_REG_LIST(id)\
 	SRI(DC_HPD_CONTROL, HPD, id)
@@ -73,6 +73,7 @@ struct dcn10_link_enc_aux_registers {
 	uint32_t AUX_CONTROL;
 	uint32_t AUX_DPHY_RX_CONTROL0;
 	uint32_t AUX_DPHY_TX_CONTROL;
+	uint32_t AUX_DPHY_RX_CONTROL1;
 };
 
 struct dcn10_link_enc_hpd_registers {
@@ -443,7 +444,10 @@ struct dcn10_link_enc_registers {
 	type AUX_TX_PRECHARGE_LEN; \
 	type AUX_TX_PRECHARGE_SYMBOLS; \
 	type AUX_MODE_DET_CHECK_DELAY;\
-	type DPCS_DBG_CBUS_DIS
+	type DPCS_DBG_CBUS_DIS;\
+	type AUX_RX_PRECHARGE_SKIP;\
+	type AUX_RX_TIMEOUT_LEN;\
+	type AUX_RX_TIMEOUT_LEN_MUL
 
 struct dcn10_link_enc_shift {
 	DCN_LINK_ENCODER_REG_FIELD_LIST(uint8_t);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c
index 8d209dae66e6..15c2ff264ff6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c
@@ -309,7 +309,6 @@ bool dcn20_link_encoder_is_in_alt_mode(struct link_encoder *enc)
 void enc2_hw_init(struct link_encoder *enc)
 {
 	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
-
 /*
 	00 - DP_AUX_DPHY_RX_DETECTION_THRESHOLD__1to2 : 1/2
 	01 - DP_AUX_DPHY_RX_DETECTION_THRESHOLD__3to4 : 3/4
@@ -333,9 +332,18 @@ void enc2_hw_init(struct link_encoder *enc)
 	AUX_RX_PHASE_DETECT_LEN,  [21,20] = 0x3 default is 3
 	AUX_RX_DETECTION_THRESHOLD [30:28] = 1
 */
-	AUX_REG_WRITE(AUX_DPHY_RX_CONTROL0, 0x103d1110);
+	if (enc->ctx->dc_bios->golden_table.dc_golden_table_ver > 0) {
+		AUX_REG_WRITE(AUX_DPHY_RX_CONTROL0, enc->ctx->dc_bios->golden_table.aux_dphy_rx_control0_val);
 
-	AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c7a);
+		AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, enc->ctx->dc_bios->golden_table.aux_dphy_tx_control_val);
+
+		AUX_REG_WRITE(AUX_DPHY_RX_CONTROL1, enc->ctx->dc_bios->golden_table.aux_dphy_rx_control1_val);
+	} else {
+		AUX_REG_WRITE(AUX_DPHY_RX_CONTROL0, 0x103d1110);
+
+		AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c4d);
+
+	}
 
 	//AUX_DPHY_TX_REF_CONTROL'AUX_TX_REF_DIV HW default is 0x32;
 	// Set AUX_TX_REF_DIV Divider to generate 2 MHz reference from refclk
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
index db09f40075c2..bf0044f7417e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
@@ -191,7 +191,10 @@
 	LE_SF(DP_AUX0_AUX_DPHY_RX_CONTROL0, AUX_RX_DETECTION_THRESHOLD, mask_sh), \
 	LE_SF(DP_AUX0_AUX_DPHY_TX_CONTROL, AUX_TX_PRECHARGE_LEN, mask_sh),\
 	LE_SF(DP_AUX0_AUX_DPHY_TX_CONTROL, AUX_TX_PRECHARGE_SYMBOLS, mask_sh),\
-	LE_SF(DP_AUX0_AUX_DPHY_TX_CONTROL, AUX_MODE_DET_CHECK_DELAY, mask_sh)
+	LE_SF(DP_AUX0_AUX_DPHY_TX_CONTROL, AUX_MODE_DET_CHECK_DELAY, mask_sh),\
+	LE_SF(DP_AUX0_AUX_DPHY_RX_CONTROL1, AUX_RX_PRECHARGE_SKIP, mask_sh),\
+	LE_SF(DP_AUX0_AUX_DPHY_RX_CONTROL1, AUX_RX_TIMEOUT_LEN, mask_sh),\
+	LE_SF(DP_AUX0_AUX_DPHY_RX_CONTROL1, AUX_RX_TIMEOUT_LEN_MUL, mask_sh)
 
 #define UNIPHY_DCN2_REG_LIST(id) \
 	SRI(CLOCK_ENABLE, SYMCLK, id), \
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index c2544c81dfb2..3e526c394f6c 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -941,7 +941,6 @@ struct atom_display_controller_info_v4_1
   uint8_t  reserved3[8];
 };
 
-
 struct atom_display_controller_info_v4_2
 {
   struct  atom_common_table_header  table_header;
@@ -976,6 +975,59 @@ struct atom_display_controller_info_v4_2
   uint8_t  reserved3[8];
 };
 
+struct atom_display_controller_info_v4_4 {
+	struct atom_common_table_header table_header;
+	uint32_t display_caps;
+	uint32_t bootup_dispclk_10khz;
+	uint16_t dce_refclk_10khz;
+	uint16_t i2c_engine_refclk_10khz;
+	uint16_t dvi_ss_percentage;	 // in unit of 0.001%
+	uint16_t dvi_ss_rate_10hz;
+	uint16_t hdmi_ss_percentage;	 // in unit of 0.001%
+	uint16_t hdmi_ss_rate_10hz;
+	uint16_t dp_ss_percentage;	 // in unit of 0.001%
+	uint16_t dp_ss_rate_10hz;
+	uint8_t dvi_ss_mode;		 // enum of atom_spread_spectrum_mode
+	uint8_t hdmi_ss_mode;		 // enum of atom_spread_spectrum_mode
+	uint8_t dp_ss_mode;		 // enum of atom_spread_spectrum_mode
+	uint8_t ss_reserved;
+	uint8_t dfp_hardcode_mode_num;	 // DFP hardcode mode number defined in StandardVESA_TimingTable when EDID is not available
+	uint8_t dfp_hardcode_refreshrate;// DFP hardcode mode refreshrate defined in StandardVESA_TimingTable when EDID is not available
+	uint8_t vga_hardcode_mode_num;	 // VGA hardcode mode number defined in StandardVESA_TimingTable when EDID is not avablable
+	uint8_t vga_hardcode_refreshrate;// VGA hardcode mode number defined in StandardVESA_TimingTable when EDID is not avablable
+	uint16_t dpphy_refclk_10khz;
+	uint16_t hw_chip_id;
+	uint8_t dcnip_min_ver;
+	uint8_t dcnip_max_ver;
+	uint8_t max_disp_pipe_num;
+	uint8_t max_vbios_active_disp_pipum;
+	uint8_t max_ppll_num;
+	uint8_t max_disp_phy_num;
+	uint8_t max_aux_pairs;
+	uint8_t remotedisplayconfig;
+	uint32_t dispclk_pll_vco_freq;
+	uint32_t dp_ref_clk_freq;
+	uint32_t max_mclk_chg_lat;	 // Worst case blackout duration for a memory clock frequency (p-state) change, units of 100s of ns (0.1 us)
+	uint32_t max_sr_exit_lat;	 // Worst case memory self refresh exit time, units of 100ns of ns (0.1us)
+	uint32_t max_sr_enter_exit_lat;	 // Worst case memory self refresh entry followed by immediate exit time, units of 100ns of ns (0.1us)
+	uint16_t dc_golden_table_offset; // point of struct of atom_dc_golden_table_vxx
+	uint16_t dc_golden_table_ver;
+	uint32_t reserved3[3];
+};
+
+struct atom_dc_golden_table_v1
+{
+	uint32_t aux_dphy_rx_control0_val;
+	uint32_t aux_dphy_tx_control_val;
+	uint32_t aux_dphy_rx_control1_val;
+	uint32_t dc_gpio_aux_ctrl_0_val;
+	uint32_t dc_gpio_aux_ctrl_1_val;
+	uint32_t dc_gpio_aux_ctrl_2_val;
+	uint32_t dc_gpio_aux_ctrl_3_val;
+	uint32_t dc_gpio_aux_ctrl_4_val;
+	uint32_t dc_gpio_aux_ctrl_5_val;
+	uint32_t reserved[23];
+};
 
 enum dce_info_caps_def
 {

From 7c6981e7ca74be39a16a770315606d495a860275 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Fri, 26 Jun 2020 14:30:29 -0400
Subject: [PATCH 275/474] drm/amd/display: populate new dml variable

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
index b0064087b9bb..afdd4f0d9d71 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
@@ -467,7 +467,8 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 		mode_lib->vba.AudioSampleLayout[mode_lib->vba.NumberOfActivePlanes] =
 			1;
 		mode_lib->vba.DRAMClockChangeLatencyOverride = 0.0;
-		mode_lib->vba.DSCEnabled[mode_lib->vba.NumberOfActivePlanes] = dout->dsc_enable;
+		mode_lib->vba.DSCEnabled[mode_lib->vba.NumberOfActivePlanes] = dout->dsc_enable;;
+		mode_lib->vba.DSCEnable[mode_lib->vba.NumberOfActivePlanes] = dout->dsc_enable;
 		mode_lib->vba.NumberOfDSCSlices[mode_lib->vba.NumberOfActivePlanes] =
 				dout->dsc_slices;
 		mode_lib->vba.DSCInputBitPerComponent[mode_lib->vba.NumberOfActivePlanes] =

From 7edac0d3fbf58db6a807bad5c5e264bb830906aa Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Tue, 30 Jun 2020 11:16:05 -0400
Subject: [PATCH 276/474] drm/amd/display: Fix logger context

[Why&How]
use correct logger context

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Roman Li <Roman.Li@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
index 4e6e18bbef5d..72743058836d 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
@@ -71,8 +71,9 @@ enum dentist_divider_range {
 
 #define CTX \
 	clk_mgr->base.ctx
+
 #define DC_LOGGER \
-	clk_mgr->ctx->logger
+	clk_mgr->base.ctx->logger
 
 
 

From e106c96e2e0a0b9c1305d54480b60cb670d7fd1b Mon Sep 17 00:00:00 2001
From: Aric Cyr <aric.cyr@amd.com>
Date: Thu, 23 Jul 2020 13:06:23 -0400
Subject: [PATCH 277/474] drm/amd/display: AMD OUI (DPCD 0x00300) skipped on
 some sink

[Why]
Sink OUI supported cap is not set so driver skips programming it.

[How]
Revert the change the skips OUI programming if the cap is not set

Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index d7d2dcd49c06..9bc03f26efda 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -4339,22 +4339,6 @@ void dp_set_fec_enable(struct dc_link *link, bool enable)
 
 void dpcd_set_source_specific_data(struct dc_link *link)
 {
-	uint8_t dspc = 0;
-	enum dc_status ret;
-
-	ret = core_link_read_dpcd(link, DP_DOWN_STREAM_PORT_COUNT, &dspc,
-				  sizeof(dspc));
-
-	if (ret != DC_OK) {
-		DC_LOG_ERROR("Error in DP aux read transaction,"
-			     " not writing source specific data\n");
-		return;
-	}
-
-	/* Return if OUI unsupported */
-	if (!(dspc & DP_OUI_SUPPORT))
-		return;
-
 	if (!link->dc->vendor_signature.is_valid) {
 		struct dpcd_amd_signature amd_signature;
 		amd_signature.AMD_IEEE_TxSignature_byte1 = 0x0;

From bd42538f1f40a6de16eead6ab01a1c214e6894e4 Mon Sep 17 00:00:00 2001
From: "JinZe.Xu" <JinZe.Xu@amd.com>
Date: Tue, 21 Jul 2020 17:52:41 +0800
Subject: [PATCH 278/474] drm/amd/display: Use helper function to check for
 HDMI signal

[How]
Use dc_is_hdmi_signal to determine signal type.

Signed-off-by: JinZe.Xu <JinZe.Xu@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 071c7b32b282..4bd6e03a7ef3 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -3282,7 +3282,7 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx)
 			dc_is_virtual_signal(pipe_ctx->stream->signal))
 		return;
 
-	if (pipe_ctx->stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) {
+	if (dc_is_hdmi_signal(pipe_ctx->stream->signal)) {
 		core_link_set_avmute(pipe_ctx, true);
 	}
 

From ab2cf4c86b24821b6a4164a20d46961da1686634 Mon Sep 17 00:00:00 2001
From: George Shen <george.shen@amd.com>
Date: Fri, 17 Jul 2020 13:19:27 -0400
Subject: [PATCH 279/474] drm/amd/display: Change null plane state swizzle mode
 to 4kb_s

[Why]
During SetPathMode and UpdatePlanes, the plane state can be null. We default
to linear swizzle mode when plane state is null. This resulted in bandwidth
validation failing when trying to set 8K60 mode (which previously passed validation
during rebuild timing list).

[How]
Change the default swizzle mode from linear to 4kb_s and update pitch accordingly.

Signed-off-by: George Shen <george.shen@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 2a5e7175926a..790baf552695 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -2223,7 +2223,7 @@ int dcn20_populate_dml_pipes_from_context(
 		if (!res_ctx->pipe_ctx[i].plane_state) {
 			pipes[pipe_cnt].pipe.src.is_hsplit = pipes[pipe_cnt].pipe.dest.odm_combine != dm_odm_combine_mode_disabled;
 			pipes[pipe_cnt].pipe.src.source_scan = dm_horz;
-			pipes[pipe_cnt].pipe.src.sw_mode = dm_sw_linear;
+			pipes[pipe_cnt].pipe.src.sw_mode = dm_sw_4kb_s;
 			pipes[pipe_cnt].pipe.src.macro_tile_size = dm_64k_tile;
 			pipes[pipe_cnt].pipe.src.viewport_width = timing->h_addressable;
 			if (pipes[pipe_cnt].pipe.src.viewport_width > 1920)
@@ -2235,7 +2235,7 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].pipe.src.surface_width_y = pipes[pipe_cnt].pipe.src.viewport_width;
 			pipes[pipe_cnt].pipe.src.surface_height_c = pipes[pipe_cnt].pipe.src.viewport_height;
 			pipes[pipe_cnt].pipe.src.surface_width_c = pipes[pipe_cnt].pipe.src.viewport_width;
-			pipes[pipe_cnt].pipe.src.data_pitch = ((pipes[pipe_cnt].pipe.src.viewport_width + 63) / 64) * 64; /* linear sw only */
+			pipes[pipe_cnt].pipe.src.data_pitch = ((pipes[pipe_cnt].pipe.src.viewport_width + 255) / 256) * 256;
 			pipes[pipe_cnt].pipe.src.source_format = dm_444_32;
 			pipes[pipe_cnt].pipe.dest.recout_width = pipes[pipe_cnt].pipe.src.viewport_width; /*vp_width/hratio*/
 			pipes[pipe_cnt].pipe.dest.recout_height = pipes[pipe_cnt].pipe.src.viewport_height; /*vp_height/vratio*/

From d6a4e5e9fed072702a03f45584df7e74a8ba79ee Mon Sep 17 00:00:00 2001
From: Igor Kravchenko <Igor.Kravchenko@amd.com>
Date: Fri, 24 Jul 2020 11:10:40 -0400
Subject: [PATCH 280/474] drm/amd/display: Display goes blank after inst

[why]
Display goes blank after driver installation.
Aux tuning parameters must be used for 2.x only.
Wrong dc_golden_table offset was used.

[How]
Implement a new enc3_hw_init function without VBIOS constants usage to
be called for 3.x
Calculate dc_golden_table offset using sum of
base dce_info offset and golden table offset

Signed-off-by: Igor Kravchenko <Igor.Kravchenko@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/bios/bios_parser2.c    |  4 +-
 .../display/dc/dcn30/dcn30_dio_link_encoder.c | 53 ++++++++++++++++++-
 .../display/dc/dcn30/dcn30_dio_link_encoder.h |  2 +
 3 files changed, 56 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index f8db92fed9cf..078b7e344185 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -2101,7 +2101,7 @@ static struct atom_dc_golden_table_v1 *bios_get_golden_table(
 									DATA_TABLES(dce_info));
 			if (!disp_cntl_tbl_4_4)
 				return NULL;
-			dc_golden_offset = disp_cntl_tbl_4_4->dc_golden_table_offset;
+			dc_golden_offset = DATA_TABLES(dce_info) + disp_cntl_tbl_4_4->dc_golden_table_offset;
 			*dc_golden_table_ver = disp_cntl_tbl_4_4->dc_golden_table_ver;
 			break;
 		}
@@ -2115,7 +2115,7 @@ static struct atom_dc_golden_table_v1 *bios_get_golden_table(
 		return NULL;
 
 	return GET_IMAGE(struct atom_dc_golden_table_v1,
-					 dc_golden_offset);
+			dc_golden_offset);
 }
 
 static enum bp_result bios_get_atom_dc_golden_table(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.c
index c29326e9856a..2ae159e2dd6e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.c
@@ -62,7 +62,7 @@ static const struct link_encoder_funcs dcn30_link_enc_funcs = {
 	.read_state = link_enc2_read_state,
 	.validate_output_with_stream =
 			dcn30_link_encoder_validate_output_with_stream,
-	.hw_init = enc2_hw_init,
+	.hw_init = enc3_hw_init,
 	.setup = dcn10_link_encoder_setup,
 	.enable_tmds_output = dcn10_link_encoder_enable_tmds_output,
 	.enable_dp_output = dcn20_link_encoder_enable_dp_output,
@@ -203,3 +203,54 @@ void dcn30_link_encoder_construct(
 		enc10->base.features.flags.bits.HDMI_6GB_EN = 0;
 	}
 }
+
+#define AUX_REG(reg)\
+	(enc10->aux_regs->reg)
+
+#define AUX_REG_READ(reg_name) \
+		dm_read_reg(CTX, AUX_REG(reg_name))
+
+#define AUX_REG_WRITE(reg_name, val) \
+			dm_write_reg(CTX, AUX_REG(reg_name), val)
+void enc3_hw_init(struct link_encoder *enc)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+
+/*
+	00 - DP_AUX_DPHY_RX_DETECTION_THRESHOLD__1to2 : 1/2
+	01 - DP_AUX_DPHY_RX_DETECTION_THRESHOLD__3to4 : 3/4
+	02 - DP_AUX_DPHY_RX_DETECTION_THRESHOLD__7to8 : 7/8
+	03 - DP_AUX_DPHY_RX_DETECTION_THRESHOLD__15to16 : 15/16
+	04 - DP_AUX_DPHY_RX_DETECTION_THRESHOLD__31to32 : 31/32
+	05 - DP_AUX_DPHY_RX_DETECTION_THRESHOLD__63to64 : 63/64
+	06 - DP_AUX_DPHY_RX_DETECTION_THRESHOLD__127to128 : 127/128
+	07 - DP_AUX_DPHY_RX_DETECTION_THRESHOLD__255to256 : 255/256
+*/
+
+/*
+	AUX_REG_UPDATE_5(AUX_DPHY_RX_CONTROL0,
+	AUX_RX_START_WINDOW = 1 [6:4]
+	AUX_RX_RECEIVE_WINDOW = 1 default is 2 [10:8]
+	AUX_RX_HALF_SYM_DETECT_LEN  = 1 [13:12] default is 1
+	AUX_RX_TRANSITION_FILTER_EN = 1 [16] default is 1
+	AUX_RX_ALLOW_BELOW_THRESHOLD_PHASE_DETECT [17] is 0  default is 0
+	AUX_RX_ALLOW_BELOW_THRESHOLD_START [18] is 1  default is 1
+	AUX_RX_ALLOW_BELOW_THRESHOLD_STOP [19] is 1  default is 1
+	AUX_RX_PHASE_DETECT_LEN,  [21,20] = 0x3 default is 3
+	AUX_RX_DETECTION_THRESHOLD [30:28] = 1
+*/
+	AUX_REG_WRITE(AUX_DPHY_RX_CONTROL0, 0x103d1110);
+
+	AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c7a);
+
+	//AUX_DPHY_TX_REF_CONTROL'AUX_TX_REF_DIV HW default is 0x32;
+	// Set AUX_TX_REF_DIV Divider to generate 2 MHz reference from refclk
+	// 27MHz -> 0xd
+	// 100MHz -> 0x32
+	// 48MHz -> 0x18
+
+	// Set TMDS_CTL0 to 1.  This is a legacy setting.
+	REG_UPDATE(TMDS_CTL_BITS, TMDS_CTL0, 1);
+
+	dcn10_aux_initialize(enc10);
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h
index 585d1ce63db1..8e9fd59ccde8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h
@@ -73,4 +73,6 @@ void dcn30_link_encoder_construct(
 	const struct dcn10_link_enc_shift *link_shift,
 	const struct dcn10_link_enc_mask *link_mask);
 
+void enc3_hw_init(struct link_encoder *enc);
+
 #endif /* __DC_LINK_ENCODER__DCN30_H__ */

From 95a2687687f832a7f8fa32bdfe42a530796b71a2 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 30 Jul 2020 15:21:33 -0400
Subject: [PATCH 281/474] drm/amdgpu/smu: rework i2c adpater registration

The i2c init/fini functions just register the i2c adapter.
There is no need to call them during hw init/fini.  They only
need to be called once per driver init/fini.  The previous
behavior broke runtime pm because we unregistered the i2c
adapter during suspend.

Tested-by: Tom St Denis <tom.stdenis@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/amdgpu_smu.c         | 12 ++++++------
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c       | 14 --------------
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c         | 14 --------------
 drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c | 14 --------------
 4 files changed, 6 insertions(+), 48 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 8c624f1f33ba..ceef149d3410 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -579,6 +579,10 @@ static int smu_smc_table_sw_init(struct smu_context *smu)
 	if (ret)
 		return ret;
 
+	ret = smu_i2c_init(smu, &smu->adev->pm.smu_i2c);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -586,6 +590,8 @@ static int smu_smc_table_sw_fini(struct smu_context *smu)
 {
 	int ret;
 
+	smu_i2c_fini(smu, &smu->adev->pm.smu_i2c);
+
 	ret = smu_free_memory_pool(smu);
 	if (ret)
 		return ret;
@@ -844,10 +850,6 @@ static int smu_smc_hw_setup(struct smu_context *smu)
 		return ret;
 	}
 
-	ret = smu_i2c_init(smu, &adev->pm.smu_i2c);
-	if (ret)
-		return ret;
-
 	ret = smu_disable_umc_cdr_12gbps_workaround(smu);
 	if (ret) {
 		dev_err(adev->dev, "Workaround failed to disable UMC CDR feature on 12Gbps SKU!\n");
@@ -1046,8 +1048,6 @@ static int smu_smc_hw_cleanup(struct smu_context *smu)
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 
-	smu_i2c_fini(smu, &adev->pm.smu_i2c);
-
 	cancel_work_sync(&smu->throttling_logging_work);
 
 	ret = smu_disable_thermal_alert(smu);
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 3b9182c8c53f..3b2ecb52a36f 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -2080,22 +2080,11 @@ static const struct i2c_algorithm arcturus_i2c_algo = {
 	.functionality = arcturus_i2c_func,
 };
 
-static bool arcturus_i2c_adapter_is_added(struct i2c_adapter *control)
-{
-	struct amdgpu_device *adev = to_amdgpu_device(control);
-
-	return control->dev.parent == &adev->pdev->dev;
-}
-
 static int arcturus_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	int res;
 
-	/* smu_i2c_eeprom_init may be called twice in sriov */
-	if (arcturus_i2c_adapter_is_added(control))
-		return 0;
-
 	control->owner = THIS_MODULE;
 	control->class = I2C_CLASS_SPD;
 	control->dev.parent = &adev->pdev->dev;
@@ -2111,9 +2100,6 @@ static int arcturus_i2c_control_init(struct smu_context *smu, struct i2c_adapter
 
 static void arcturus_i2c_control_fini(struct smu_context *smu, struct i2c_adapter *control)
 {
-	if (!arcturus_i2c_adapter_is_added(control))
-		return;
-
 	i2c_del_adapter(control);
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 6aaf483858a0..c33bdc6747f2 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -2457,22 +2457,11 @@ static const struct i2c_algorithm navi10_i2c_algo = {
 	.functionality = navi10_i2c_func,
 };
 
-static bool navi10_i2c_adapter_is_added(struct i2c_adapter *control)
-{
-	struct amdgpu_device *adev = to_amdgpu_device(control);
-
-	return control->dev.parent == &adev->pdev->dev;
-}
-
 static int navi10_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	int res;
 
-	/* smu_i2c_eeprom_init may be called twice in sriov */
-	if (navi10_i2c_adapter_is_added(control))
-		return 0;
-
 	control->owner = THIS_MODULE;
 	control->class = I2C_CLASS_SPD;
 	control->dev.parent = &adev->pdev->dev;
@@ -2488,9 +2477,6 @@ static int navi10_i2c_control_init(struct smu_context *smu, struct i2c_adapter *
 
 static void navi10_i2c_control_fini(struct smu_context *smu, struct i2c_adapter *control)
 {
-	if (!navi10_i2c_adapter_is_added(control))
-		return;
-
 	i2c_del_adapter(control);
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
index f64a1be94cb8..f373e2d0d31c 100644
--- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
@@ -2630,22 +2630,11 @@ static const struct i2c_algorithm sienna_cichlid_i2c_algo = {
 	.functionality = sienna_cichlid_i2c_func,
 };
 
-static bool sienna_cichlid_i2c_adapter_is_added(struct i2c_adapter *control)
-{
-	struct amdgpu_device *adev = to_amdgpu_device(control);
-
-	return control->dev.parent == &adev->pdev->dev;
-}
-
 static int sienna_cichlid_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	int res;
 
-	/* smu_i2c_eeprom_init may be called twice in sriov */
-	if (sienna_cichlid_i2c_adapter_is_added(control))
-		return 0;
-
 	control->owner = THIS_MODULE;
 	control->class = I2C_CLASS_SPD;
 	control->dev.parent = &adev->pdev->dev;
@@ -2661,9 +2650,6 @@ static int sienna_cichlid_i2c_control_init(struct smu_context *smu, struct i2c_a
 
 static void sienna_cichlid_i2c_control_fini(struct smu_context *smu, struct i2c_adapter *control)
 {
-	if (!sienna_cichlid_i2c_adapter_is_added(control))
-		return;
-
 	i2c_del_adapter(control);
 }
 

From 16c24801122e2961c588562f04707b98f9c84bbb Mon Sep 17 00:00:00 2001
From: Jon Hunter <jonathanh@nvidia.com>
Date: Thu, 6 Aug 2020 13:54:31 +0100
Subject: [PATCH 282/474] rtc: max77686: Fix wake-ups for max77620

Following commit d8f090dbeafd ("rtc: max77686: Do not allow interrupt to
fire before system resume"), RTC wake-ups stopped working on Jetson TX2
and Jetson Xavier platforms. The Jetson TX2 uses the max77620 PMIC and
the Jetson Xavier uses max20024 PMIC. Both of these PMICs have the same
max77620 RTC controller.

For the max77620 RTC, the variable 'rtc_irq_from_platform' is defined as
true in the max77686 driver and because of this the IRQ passed to the
max77686 driver for RTC is the PMIC IRQ and not the parent. Hence,
following commit d8f090dbeafd ("rtc: max77686: Do not allow interrupt to
fire before system resume"), for the max77620 the RTC IRQ within the
PMIC is now getting disabled on entry to suspend and unable to wake the
system up. Fix this by only disabling interrupts on entry to suspend
in the max77686 RTC driver, if the interrupt is the parent interrupt.

Fixes: d8f090dbeafd ("rtc: max77686: Do not allow interrupt to fire before system resume")
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Tested-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Acked-by: Krzysztof Kozlowski <krzk@kernel.org>
Link: https://lore.kernel.org/r/20200806125431.699339-1-jonathanh@nvidia.com
---
 drivers/rtc/rtc-max77686.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c
index 645de5af707b..d51cc12114cb 100644
--- a/drivers/rtc/rtc-max77686.c
+++ b/drivers/rtc/rtc-max77686.c
@@ -815,13 +815,15 @@ static int max77686_rtc_suspend(struct device *dev)
 	}
 
 	/*
-	 * Main IRQ (not virtual) must be disabled during suspend because if it
-	 * happens while suspended it will be handled before resuming I2C.
+	 * If the main IRQ (not virtual) is the parent IRQ, then it must be
+	 * disabled during suspend because if it happens while suspended it
+	 * will be handled before resuming I2C.
 	 *
 	 * Since Main IRQ is shared, all its users should disable it to be sure
 	 * it won't fire while one of them is still suspended.
 	 */
-	disable_irq(info->rtc_irq);
+	if (!info->drv_data->rtc_irq_from_platform)
+		disable_irq(info->rtc_irq);
 
 	return ret;
 }
@@ -830,7 +832,8 @@ static int max77686_rtc_resume(struct device *dev)
 {
 	struct max77686_rtc_info *info = dev_get_drvdata(dev);
 
-	enable_irq(info->rtc_irq);
+	if (!info->drv_data->rtc_irq_from_platform)
+		enable_irq(info->rtc_irq);
 
 	if (device_may_wakeup(dev)) {
 		struct max77686_rtc_info *info = dev_get_drvdata(dev);

From f2e2573c0823c07dc8aac4a8e0947881af2340bd Mon Sep 17 00:00:00 2001
From: Likun Gao <Likun.Gao@amd.com>
Date: Thu, 6 Aug 2020 17:37:28 +0800
Subject: [PATCH 283/474] drm/amdgpu: use mode1 reset by default for
 sienna_cichlid

Swith default gpu reset method for sienna_cichlid to MODE1 reset.

Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/nv.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 74d02d270d34..da8024c2826e 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -362,10 +362,15 @@ nv_asic_reset_method(struct amdgpu_device *adev)
 		dev_warn(adev->dev, "Specified reset method:%d isn't supported, using AUTO instead.\n",
 				  amdgpu_reset_method);
 
-	if (smu_baco_is_support(smu))
-		return AMD_RESET_METHOD_BACO;
-	else
+	switch (adev->asic_type) {
+	case CHIP_SIENNA_CICHLID:
 		return AMD_RESET_METHOD_MODE1;
+	default:
+		if (smu_baco_is_support(smu))
+			return AMD_RESET_METHOD_BACO;
+		else
+			return AMD_RESET_METHOD_MODE1;
+	}
 }
 
 static int nv_asic_reset(struct amdgpu_device *adev)

From 2c34c960cee0dfdfe33ddf1b3835c250a9503ef6 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 3 Aug 2020 11:15:14 +0800
Subject: [PATCH 284/474] drm/amd/powerplay: update swSMU VCN/JPEG PG logics

Add lock protections and avoid unnecessary actions
if the PG state is already the same as required.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Tested-by: Matt Coffin <mcoffin13@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/amdgpu_smu.c    | 57 ++++++++++++++++++-
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c  |  4 --
 .../gpu/drm/amd/powerplay/inc/amdgpu_smu.h    |  6 +-
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c    |  8 ---
 drivers/gpu/drm/amd/powerplay/renoir_ppt.c    |  8 ---
 .../drm/amd/powerplay/sienna_cichlid_ppt.c    |  9 ---
 drivers/gpu/drm/amd/powerplay/smu_internal.h  |  2 -
 7 files changed, 60 insertions(+), 34 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index ceef149d3410..70a4e6dab166 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -133,6 +133,56 @@ int smu_get_dpm_freq_range(struct smu_context *smu,
 	return ret;
 }
 
+static int smu_dpm_set_vcn_enable(struct smu_context *smu,
+				  bool enable)
+{
+	struct smu_power_context *smu_power = &smu->smu_power;
+	struct smu_power_gate *power_gate = &smu_power->power_gate;
+	int ret = 0;
+
+	if (!smu->ppt_funcs->dpm_set_vcn_enable)
+		return 0;
+
+	mutex_lock(&power_gate->vcn_gate_lock);
+
+	if (atomic_read(&power_gate->vcn_gated) ^ enable)
+		goto out;
+
+	ret = smu->ppt_funcs->dpm_set_vcn_enable(smu, enable);
+	if (!ret)
+		atomic_set(&power_gate->vcn_gated, !enable);
+
+out:
+	mutex_unlock(&power_gate->vcn_gate_lock);
+
+	return ret;
+}
+
+static int smu_dpm_set_jpeg_enable(struct smu_context *smu,
+				   bool enable)
+{
+	struct smu_power_context *smu_power = &smu->smu_power;
+	struct smu_power_gate *power_gate = &smu_power->power_gate;
+	int ret = 0;
+
+	if (!smu->ppt_funcs->dpm_set_jpeg_enable)
+		return 0;
+
+	mutex_lock(&power_gate->jpeg_gate_lock);
+
+	if (atomic_read(&power_gate->jpeg_gated) ^ enable)
+		goto out;
+
+	ret = smu->ppt_funcs->dpm_set_jpeg_enable(smu, enable);
+	if (!ret)
+		atomic_set(&power_gate->jpeg_gated, !enable);
+
+out:
+	mutex_unlock(&power_gate->jpeg_gate_lock);
+
+	return ret;
+}
+
 /**
  * smu_dpm_set_power_gate - power gate/ungate the specific IP block
  *
@@ -649,6 +699,11 @@ static int smu_sw_init(void *handle)
 	smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
 	smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
 
+	atomic_set(&smu->smu_power.power_gate.vcn_gated, 1);
+	atomic_set(&smu->smu_power.power_gate.jpeg_gated, 1);
+	mutex_init(&smu->smu_power.power_gate.vcn_gate_lock);
+	mutex_init(&smu->smu_power.power_gate.jpeg_gate_lock);
+
 	smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT];
 	smu->workload_prority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT] = 0;
 	smu->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D] = 1;
@@ -1973,7 +2028,7 @@ int smu_read_sensor(struct smu_context *smu,
 		*size = 4;
 		break;
 	case AMDGPU_PP_SENSOR_VCN_POWER_STATE:
-		*(uint32_t *)data = smu->smu_power.power_gate.vcn_gated ? 0 : 1;
+		*(uint32_t *)data = atomic_read(&smu->smu_power.power_gate.vcn_gated) ? 0: 1;
 		*size = 4;
 		break;
 	case AMDGPU_PP_SENSOR_MIN_FAN_RPM:
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 3b2ecb52a36f..6c991de8f371 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -1849,8 +1849,6 @@ static bool arcturus_is_dpm_running(struct smu_context *smu)
 
 static int arcturus_dpm_set_vcn_enable(struct smu_context *smu, bool enable)
 {
-	struct smu_power_context *smu_power = &smu->smu_power;
-	struct smu_power_gate *power_gate = &smu_power->power_gate;
 	int ret = 0;
 
 	if (enable) {
@@ -1861,7 +1859,6 @@ static int arcturus_dpm_set_vcn_enable(struct smu_context *smu, bool enable)
 				return ret;
 			}
 		}
-		power_gate->vcn_gated = false;
 	} else {
 		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT)) {
 			ret = smu_cmn_feature_set_enabled(smu, SMU_FEATURE_VCN_PG_BIT, 0);
@@ -1870,7 +1867,6 @@ static int arcturus_dpm_set_vcn_enable(struct smu_context *smu, bool enable)
 				return ret;
 			}
 		}
-		power_gate->vcn_gated = true;
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index 28312d6dc187..074458eb5407 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -292,8 +292,10 @@ struct smu_dpm_context {
 struct smu_power_gate {
 	bool uvd_gated;
 	bool vce_gated;
-	bool vcn_gated;
-	bool jpeg_gated;
+	atomic_t vcn_gated;
+	atomic_t jpeg_gated;
+	struct mutex vcn_gate_lock;
+	struct mutex jpeg_gate_lock;
 };
 
 struct smu_power_context {
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index c33bdc6747f2..9f62af9abd23 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -785,8 +785,6 @@ static int navi10_set_default_dpm_table(struct smu_context *smu)
 
 static int navi10_dpm_set_vcn_enable(struct smu_context *smu, bool enable)
 {
-	struct smu_power_context *smu_power = &smu->smu_power;
-	struct smu_power_gate *power_gate = &smu_power->power_gate;
 	int ret = 0;
 
 	if (enable) {
@@ -796,14 +794,12 @@ static int navi10_dpm_set_vcn_enable(struct smu_context *smu, bool enable)
 			if (ret)
 				return ret;
 		}
-		power_gate->vcn_gated = false;
 	} else {
 		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT)) {
 			ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PowerDownVcn, NULL);
 			if (ret)
 				return ret;
 		}
-		power_gate->vcn_gated = true;
 	}
 
 	return ret;
@@ -811,8 +807,6 @@ static int navi10_dpm_set_vcn_enable(struct smu_context *smu, bool enable)
 
 static int navi10_dpm_set_jpeg_enable(struct smu_context *smu, bool enable)
 {
-	struct smu_power_context *smu_power = &smu->smu_power;
-	struct smu_power_gate *power_gate = &smu_power->power_gate;
 	int ret = 0;
 
 	if (enable) {
@@ -821,14 +815,12 @@ static int navi10_dpm_set_jpeg_enable(struct smu_context *smu, bool enable)
 			if (ret)
 				return ret;
 		}
-		power_gate->jpeg_gated = false;
 	} else {
 		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_JPEG_PG_BIT)) {
 			ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PowerDownJpeg, NULL);
 			if (ret)
 				return ret;
 		}
-		power_gate->jpeg_gated = true;
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index 575ae4be98a2..dbb676c482fd 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -459,8 +459,6 @@ static enum amd_pm_state_type renoir_get_current_power_state(struct smu_context
 
 static int renoir_dpm_set_vcn_enable(struct smu_context *smu, bool enable)
 {
-	struct smu_power_context *smu_power = &smu->smu_power;
-	struct smu_power_gate *power_gate = &smu_power->power_gate;
 	int ret = 0;
 
 	if (enable) {
@@ -470,14 +468,12 @@ static int renoir_dpm_set_vcn_enable(struct smu_context *smu, bool enable)
 			if (ret)
 				return ret;
 		}
-		power_gate->vcn_gated = false;
 	} else {
 		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT)) {
 			ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PowerDownVcn, NULL);
 			if (ret)
 				return ret;
 		}
-		power_gate->vcn_gated = true;
 	}
 
 	return ret;
@@ -485,8 +481,6 @@ static int renoir_dpm_set_vcn_enable(struct smu_context *smu, bool enable)
 
 static int renoir_dpm_set_jpeg_enable(struct smu_context *smu, bool enable)
 {
-	struct smu_power_context *smu_power = &smu->smu_power;
-	struct smu_power_gate *power_gate = &smu_power->power_gate;
 	int ret = 0;
 
 	if (enable) {
@@ -495,14 +489,12 @@ static int renoir_dpm_set_jpeg_enable(struct smu_context *smu, bool enable)
 			if (ret)
 				return ret;
 		}
-		power_gate->jpeg_gated = false;
 	} else {
 		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_JPEG_PG_BIT)) {
 			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownJpeg, 0, NULL);
 			if (ret)
 				return ret;
 		}
-		power_gate->jpeg_gated = true;
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
index f373e2d0d31c..3865dbed5f93 100644
--- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c
@@ -766,10 +766,7 @@ static int sienna_cichlid_set_default_dpm_table(struct smu_context *smu)
 
 static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enable)
 {
-	struct smu_power_context *smu_power = &smu->smu_power;
-	struct smu_power_gate *power_gate = &smu_power->power_gate;
 	struct amdgpu_device *adev = smu->adev;
-
 	int ret = 0;
 
 	if (enable) {
@@ -785,7 +782,6 @@ static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enabl
 					return ret;
 			}
 		}
-		power_gate->vcn_gated = false;
 	} else {
 		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_MM_DPM_PG_BIT)) {
 			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownVcn, 0, NULL);
@@ -798,7 +794,6 @@ static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enabl
 					return ret;
 			}
 		}
-		power_gate->vcn_gated = true;
 	}
 
 	return ret;
@@ -806,8 +801,6 @@ static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enabl
 
 static int sienna_cichlid_dpm_set_jpeg_enable(struct smu_context *smu, bool enable)
 {
-	struct smu_power_context *smu_power = &smu->smu_power;
-	struct smu_power_gate *power_gate = &smu_power->power_gate;
 	int ret = 0;
 
 	if (enable) {
@@ -816,14 +809,12 @@ static int sienna_cichlid_dpm_set_jpeg_enable(struct smu_context *smu, bool enab
 			if (ret)
 				return ret;
 		}
-		power_gate->jpeg_gated = false;
 	} else {
 		if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_MM_DPM_PG_BIT)) {
 			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownJpeg, 0, NULL);
 			if (ret)
 				return ret;
 		}
-		power_gate->jpeg_gated = true;
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/powerplay/smu_internal.h b/drivers/gpu/drm/amd/powerplay/smu_internal.h
index d0deaefd3feb..f1d8f247e589 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_internal.h
+++ b/drivers/gpu/drm/amd/powerplay/smu_internal.h
@@ -77,8 +77,6 @@
 #define smu_get_dal_power_level(smu, clocks)				smu_ppt_funcs(get_dal_power_level, 0, smu, clocks)
 #define smu_get_perf_level(smu, designation, level)			smu_ppt_funcs(get_perf_level, 0, smu, designation, level)
 #define smu_get_current_shallow_sleep_clocks(smu, clocks)		smu_ppt_funcs(get_current_shallow_sleep_clocks, 0, smu, clocks)
-#define smu_dpm_set_vcn_enable(smu, enable)				smu_ppt_funcs(dpm_set_vcn_enable, 0, smu, enable)
-#define smu_dpm_set_jpeg_enable(smu, enable)				smu_ppt_funcs(dpm_set_jpeg_enable, 0, smu, enable)
 #define smu_set_watermarks_table(smu, clock_ranges)			smu_ppt_funcs(set_watermarks_table, 0, smu, clock_ranges)
 #define smu_thermal_temperature_range_update(smu, range, rw)		smu_ppt_funcs(thermal_temperature_range_update, 0, smu, range, rw)
 #define smu_register_irq_handler(smu)					smu_ppt_funcs(register_irq_handler, 0, smu)

From 7fb133cf65558955b5fdac2458f9690dfd12a794 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Wed, 5 Aug 2020 17:24:41 +0800
Subject: [PATCH 285/474] drm/amd/powerplay: put VCN/JPEG into PG ungate state
 before dpm table setup(V3)

As VCN related dpm table setup needs VCN be in PG ungate state. Same logics
applies to JPEG.

V2: fix paste typo
V3: code cosmetic

Signed-off-by: Evan Quan <evan.quan@amd.com>
Tested-by: Matt Coffin <mcoffin13@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/amdgpu_smu.c   | 93 ++++++++++++++++----
 drivers/gpu/drm/amd/powerplay/smu_internal.h |  1 -
 2 files changed, 77 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 70a4e6dab166..0826625573dc 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -133,8 +133,8 @@ int smu_get_dpm_freq_range(struct smu_context *smu,
 	return ret;
 }
 
-static int smu_dpm_set_vcn_enable(struct smu_context *smu,
-				  bool enable)
+static int smu_dpm_set_vcn_enable_locked(struct smu_context *smu,
+					 bool enable)
 {
 	struct smu_power_context *smu_power = &smu->smu_power;
 	struct smu_power_gate *power_gate = &smu_power->power_gate;
@@ -143,21 +143,52 @@ static int smu_dpm_set_vcn_enable(struct smu_context *smu,
 	if (!smu->ppt_funcs->dpm_set_vcn_enable)
 		return 0;
 
-	mutex_lock(&power_gate->vcn_gate_lock);
-
 	if (atomic_read(&power_gate->vcn_gated) ^ enable)
-		goto out;
+		return 0;
 
 	ret = smu->ppt_funcs->dpm_set_vcn_enable(smu, enable);
 	if (!ret)
 		atomic_set(&power_gate->vcn_gated, !enable);
 
-out:
+	return ret;
+}
+
+static int smu_dpm_set_vcn_enable(struct smu_context *smu,
+				  bool enable)
+{
+	struct smu_power_context *smu_power = &smu->smu_power;
+	struct smu_power_gate *power_gate = &smu_power->power_gate;
+	int ret = 0;
+
+	mutex_lock(&power_gate->vcn_gate_lock);
+
+	ret = smu_dpm_set_vcn_enable_locked(smu, enable);
+
 	mutex_unlock(&power_gate->vcn_gate_lock);
 
 	return ret;
 }
 
+static int smu_dpm_set_jpeg_enable_locked(struct smu_context *smu,
+					  bool enable)
+{
+	struct smu_power_context *smu_power = &smu->smu_power;
+	struct smu_power_gate *power_gate = &smu_power->power_gate;
+	int ret = 0;
+
+	if (!smu->ppt_funcs->dpm_set_jpeg_enable)
+		return 0;
+
+	if (atomic_read(&power_gate->jpeg_gated) ^ enable)
+		return 0;
+
+	ret = smu->ppt_funcs->dpm_set_jpeg_enable(smu, enable);
+	if (!ret)
+		atomic_set(&power_gate->jpeg_gated, !enable);
+
+	return ret;
+}
+
 static int smu_dpm_set_jpeg_enable(struct smu_context *smu,
 				   bool enable)
 {
@@ -165,19 +196,10 @@ static int smu_dpm_set_jpeg_enable(struct smu_context *smu,
 	struct smu_power_gate *power_gate = &smu_power->power_gate;
 	int ret = 0;
 
-	if (!smu->ppt_funcs->dpm_set_jpeg_enable)
-		return 0;
-
 	mutex_lock(&power_gate->jpeg_gate_lock);
 
-	if (atomic_read(&power_gate->jpeg_gated) ^ enable)
-		goto out;
+	ret = smu_dpm_set_jpeg_enable_locked(smu, enable);
 
-	ret = smu->ppt_funcs->dpm_set_jpeg_enable(smu, enable);
-	if (!ret)
-		atomic_set(&power_gate->jpeg_gated, !enable);
-
-out:
 	mutex_unlock(&power_gate->jpeg_gate_lock);
 
 	return ret;
@@ -403,6 +425,45 @@ static int smu_early_init(void *handle)
 	return smu_set_funcs(adev);
 }
 
+static int smu_set_default_dpm_table(struct smu_context *smu)
+{
+	struct smu_power_context *smu_power = &smu->smu_power;
+	struct smu_power_gate *power_gate = &smu_power->power_gate;
+	int vcn_gate, jpeg_gate;
+	int ret = 0;
+
+	if (!smu->ppt_funcs->set_default_dpm_table)
+		return 0;
+
+	mutex_lock(&power_gate->vcn_gate_lock);
+	mutex_lock(&power_gate->jpeg_gate_lock);
+
+	vcn_gate = atomic_read(&power_gate->vcn_gated);
+	jpeg_gate = atomic_read(&power_gate->jpeg_gated);
+
+	ret = smu_dpm_set_vcn_enable_locked(smu, true);
+	if (ret)
+		goto err0_out;
+
+	ret = smu_dpm_set_jpeg_enable_locked(smu, true);
+	if (ret)
+		goto err1_out;
+
+	ret = smu->ppt_funcs->set_default_dpm_table(smu);
+	if (ret)
+		dev_err(smu->adev->dev,
+			"Failed to setup default dpm clock tables!\n");
+
+	smu_dpm_set_jpeg_enable_locked(smu, !jpeg_gate);
+err1_out:
+	smu_dpm_set_vcn_enable_locked(smu, !vcn_gate);
+err0_out:
+	mutex_unlock(&power_gate->jpeg_gate_lock);
+	mutex_unlock(&power_gate->vcn_gate_lock);
+
+	return ret;
+}
+
 static int smu_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
diff --git a/drivers/gpu/drm/amd/powerplay/smu_internal.h b/drivers/gpu/drm/amd/powerplay/smu_internal.h
index f1d8f247e589..264073d4e263 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_internal.h
+++ b/drivers/gpu/drm/amd/powerplay/smu_internal.h
@@ -60,7 +60,6 @@
 #define smu_disable_all_features_with_exception(smu, mask)		smu_ppt_funcs(disable_all_features_with_exception, 0, smu, mask)
 #define smu_is_dpm_running(smu)						smu_ppt_funcs(is_dpm_running, 0 , smu)
 #define smu_notify_display_change(smu)					smu_ppt_funcs(notify_display_change, 0, smu)
-#define smu_set_default_dpm_table(smu)					smu_ppt_funcs(set_default_dpm_table, 0, smu)
 #define smu_populate_umd_state_clk(smu)					smu_ppt_funcs(populate_umd_state_clk, 0, smu)
 #define smu_set_default_od8_settings(smu)				smu_ppt_funcs(set_default_od8_settings, 0, smu)
 #define smu_enable_thermal_alert(smu)					smu_ppt_funcs(enable_thermal_alert, 0, smu)

From f87812284172a9809820d10143b573d833cd3f75 Mon Sep 17 00:00:00 2001
From: Sandeep Raghuraman <sandy.8925@gmail.com>
Date: Thu, 6 Aug 2020 22:52:20 +0530
Subject: [PATCH 286/474] drm/amdgpu: Fix bug where DPM is not enabled after
 hibernate and resume

Reproducing bug report here:
After hibernating and resuming, DPM is not enabled. This remains the case
even if you test hibernate using the steps here:
https://www.kernel.org/doc/html/latest/power/basic-pm-debugging.html

I debugged the problem, and figured out that in the file hardwaremanager.c,
in the function, phm_enable_dynamic_state_management(), the check
'if (!hwmgr->pp_one_vf && smum_is_dpm_running(hwmgr) && !amdgpu_passthrough(adev) && adev->in_suspend)'
returns true for the hibernate case, and false for the suspend case.

This means that for the hibernate case, the AMDGPU driver doesn't enable DPM
(even though it should) and simply returns from that function.
In the suspend case, it goes ahead and enables DPM, even though it doesn't need to.

I debugged further, and found out that in the case of suspend, for the
CIK/Hawaii GPUs, smum_is_dpm_running(hwmgr) returns false, while in the case of
hibernate, smum_is_dpm_running(hwmgr) returns true.

For CIK, the ci_is_dpm_running() function calls the ci_is_smc_ram_running() function,
which is ultimately used to determine if DPM is currently enabled or not,
and this seems to provide the wrong answer.

I've changed the ci_is_dpm_running() function to instead use the same method that
some other AMD GPU chips do (e.g Fiji), which seems to read the voltage controller.
I've tested on my R9 390 and it seems to work correctly for both suspend and
hibernate use cases, and has been stable so far.

Bug: https://bugzilla.kernel.org/show_bug.cgi?id=208839
Signed-off-by: Sandeep Raghuraman <sandy.8925@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
index 02159ca29fa2..c18169aa59ce 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
@@ -2725,7 +2725,10 @@ static int ci_initialize_mc_reg_table(struct pp_hwmgr *hwmgr)
 
 static bool ci_is_dpm_running(struct pp_hwmgr *hwmgr)
 {
-	return ci_is_smc_ram_running(hwmgr);
+	return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device,
+					     CGS_IND_REG__SMC, FEATURE_STATUS,
+					     VOLTAGE_CONTROLLER_ON))
+		? true : false;
 }
 
 static int ci_smu_init(struct pp_hwmgr *hwmgr)

From 05487215e6b9732cc4ad0e83e465b33182200ad5 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Mon, 13 Jul 2020 18:57:32 -0700
Subject: [PATCH 287/474] KVM: x86: Don't attempt to load PDPTRs when 64-bit
 mode is enabled

Don't attempt to load PDPTRs if EFER.LME=1, i.e. if 64-bit mode is
enabled.  A recent change to reload the PDTPRs when CR0.CD or CR0.NW is
toggled botched the EFER.LME handling and sends KVM down the PDTPR path
when is_paging() is true, i.e. when the guest toggles CD/NW in 64-bit
mode.

Split the CR0 checks for 64-bit vs. 32-bit PAE into separate paths.  The
64-bit path is specifically checking state when paging is toggled on,
i.e. CR0.PG transititions from 0->1.  The PDPTR path now needs to run if
the new CR0 state has paging enabled, irrespective of whether paging was
already enabled.  Trying to shave a few cycles to make the PDPTR path an
"else if" case is a mess.

Fixes: d42e3fae6faed ("kvm: x86: Read PDPTEs on CR0.CD and CR0.NW changes")
Cc: Jim Mattson <jmattson@google.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Peter Shier <pshier@google.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20200714015732.32426-1-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 12ea77f99ff3..2db369a64f29 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -820,22 +820,22 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE))
 		return 1;
 
-	if (cr0 & X86_CR0_PG) {
 #ifdef CONFIG_X86_64
-		if (!is_paging(vcpu) && (vcpu->arch.efer & EFER_LME)) {
-			int cs_db, cs_l;
+	if ((vcpu->arch.efer & EFER_LME) && !is_paging(vcpu) &&
+	    (cr0 & X86_CR0_PG)) {
+		int cs_db, cs_l;
 
-			if (!is_pae(vcpu))
-				return 1;
-			kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
-			if (cs_l)
-				return 1;
-		} else
-#endif
-		if (is_pae(vcpu) && ((cr0 ^ old_cr0) & pdptr_bits) &&
-		    !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)))
+		if (!is_pae(vcpu))
+			return 1;
+		kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
+		if (cs_l)
 			return 1;
 	}
+#endif
+	if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) &&
+	    is_pae(vcpu) && ((cr0 ^ old_cr0) & pdptr_bits) &&
+	    !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)))
+		return 1;
 
 	if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))
 		return 1;

From 43bd9ef42b3b862c97f1f4e86bf3ace890bef924 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sun, 9 Aug 2020 13:04:56 -0400
Subject: [PATCH 288/474] x86: Expose SERIALIZE for supported cpuid

The SERIALIZE instruction is supported by Tntel processors, like
Sapphire Rapids.  SERIALIZE is a faster serializing instruction which
does not modify registers, arithmetic flags or memory, will not cause VM
exit. It's availability is indicated by CPUID.(EAX=7,ECX=0):ECX[bit 14].

Expose it in KVM supported CPUID.  This way, KVM could pass this
information to guests and they can make use of these features accordingly.

Signed-off-by: Cathy Zhang <cathy.zhang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/cpuid.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index fa873e3e6e90..3fd6eec202d7 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -370,7 +370,8 @@ void kvm_set_cpu_caps(void)
 	kvm_cpu_cap_mask(CPUID_7_EDX,
 		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
 		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
-		F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM)
+		F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) |
+		F(SERIALIZE)
 	);
 
 	/* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */

From cf99c505cf7a5b6d3deee91e3571871f20320d31 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Sat, 8 Aug 2020 20:50:52 +0800
Subject: [PATCH 289/474] MIPS: VZ: Only include loongson_regs.h for
 CPU_LOONGSON64

Only Loongson64 platform has and needs loongson_regs.h, including it
unconditionally will cause build errors.

Fixes: 7f2a83f1c2a941ebfee5 ("KVM: MIPS: Add CPUCFG emulation for Loongson-3")
Cc: stable@vger.kernel.org
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Huacai Chen <chenhc@lemote.com>
Message-Id: <1596891052-24052-1-git-send-email-chenhc@lemote.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/mips/kvm/vz.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c
index 3932f767e938..a474578ccf68 100644
--- a/arch/mips/kvm/vz.c
+++ b/arch/mips/kvm/vz.c
@@ -29,7 +29,9 @@
 #include <linux/kvm_host.h>
 
 #include "interrupt.h"
+#ifdef CONFIG_CPU_LOONGSON64
 #include "loongson_regs.h"
+#endif
 
 #include "trace.h"
 

From f40a4b0512839d07be0b03dd4097de5582fa136d Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Mon, 10 Aug 2020 09:17:49 +0800
Subject: [PATCH 290/474] MIPS: KVM: Convert a fallthrough comment to
 fallthrough

There is a fallthrough comment being forgotten,
GCC complains about it:

arch/mips/kvm/emulate.c: In function kvm_mips_emulate_load:
arch/mips/kvm/emulate.c:1936:21: error: this statement may fall through
 1936 |   vcpu->mmio_needed = 1; /* unsigned */
      |   ~~~~~~~~~~~~~~~~~~^~~
arch/mips/kvm/emulate.c:1939:2: note: here
 1939 |  case lw_op:

Just fix it.

Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Reviewed-by: Huacai Chen <chenhc@lemote.com>
Message-Id: <20200810011749.3211128-1-jiaxun.yang@flygoat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/mips/kvm/emulate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 703782355318..d70c4f8e14e2 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1935,7 +1935,7 @@ enum emulation_result kvm_mips_emulate_load(union mips_instruction inst,
 
 	case lwu_op:
 		vcpu->mmio_needed = 1;	/* unsigned */
-		/* fall through */
+		fallthrough;
 #endif
 	case lw_op:
 		run->mmio.len = 4;

From 99b48ecc8e800983b6e00a2350daaeceba1f7406 Mon Sep 17 00:00:00 2001
From: Jon Doron <arilou@gmail.com>
Date: Fri, 17 Jul 2020 15:52:38 +0300
Subject: [PATCH 291/474] x86/kvm/hyper-v: Synic default SCONTROL MSR needs to
 be enabled

Based on an analysis of the HyperV firmwares (Gen1 and Gen2) it seems
like the SCONTROL is not being set to the ENABLED state as like we have
thought.

Also from a test done by Vitaly Kuznetsov, running a nested HyperV it
was concluded that the first access to the SCONTROL MSR with a read
resulted with the value of 0x1, aka HV_SYNIC_CONTROL_ENABLE.

It's important to note that this diverges from the value states in the
HyperV TLFS of 0.

Signed-off-by: Jon Doron <arilou@gmail.com>
Message-Id: <20200717125238.1103096-2-arilou@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/hyperv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index af9cdb426dd2..814d3aee5cef 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -900,6 +900,7 @@ int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages)
 	kvm_request_apicv_update(vcpu->kvm, false, APICV_INHIBIT_REASON_HYPERV);
 	synic->active = true;
 	synic->dont_zero_synic_pages = dont_zero_synic_pages;
+	synic->control = HV_SYNIC_CONTROL_ENABLE;
 	return 0;
 }
 

From 4f88b4ccb7036ce523b3c031d1226d6eda36417b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Wed, 17 Jun 2020 16:51:44 -0500
Subject: [PATCH 292/474] drm/vmwgfx: Use struct_size() helper

Make use of the struct_size() helper instead of an open-coded version
in order to avoid any potential type mistakes.

This code was detected with the help of Coccinelle and, audited and
fixed manually.

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Roland Scheidegger <sroland@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 126f93c0b0b8..3914bfee0533 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -1969,7 +1969,7 @@ static int vmw_surface_dirty_alloc(struct vmw_resource *res)
 		num_mip = 1;
 
 	num_subres = num_layers * num_mip;
-	dirty_size = sizeof(*dirty) + num_subres * sizeof(dirty->boxes[0]);
+	dirty_size = struct_size(dirty, boxes, num_subres);
 	acc_size = ttm_round_pot(dirty_size);
 	ret = ttm_mem_global_alloc(vmw_mem_glob(res->dev_priv),
 				   acc_size, &ctx);

From 1d2c0c565bc0da25f5e899a862fb58e612b222df Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 26 Jun 2020 13:34:37 +0300
Subject: [PATCH 293/474] drm/vmwgfx: Use correct vmw_legacy_display_unit
 pointer

The "entry" pointer is an offset from the list head and it doesn't
point to a valid vmw_legacy_display_unit struct.  Presumably the
intent was to point to the last entry.

Also the "i++" wasn't used so I have removed that as well.

Fixes: d7e1958dbe4a ("drm/vmwgfx: Support older hardware.")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Signed-off-by: Roland Scheidegger <sroland@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index 16dafff5cab1..009f1742bed5 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -81,7 +81,7 @@ static int vmw_ldu_commit_list(struct vmw_private *dev_priv)
 	struct vmw_legacy_display_unit *entry;
 	struct drm_framebuffer *fb = NULL;
 	struct drm_crtc *crtc = NULL;
-	int i = 0;
+	int i;
 
 	/* If there is no display topology the host just assumes
 	 * that the guest will set the same layout as the host.
@@ -92,12 +92,11 @@ static int vmw_ldu_commit_list(struct vmw_private *dev_priv)
 			crtc = &entry->base.crtc;
 			w = max(w, crtc->x + crtc->mode.hdisplay);
 			h = max(h, crtc->y + crtc->mode.vdisplay);
-			i++;
 		}
 
 		if (crtc == NULL)
 			return 0;
-		fb = entry->base.crtc.primary->state->fb;
+		fb = crtc->primary->state->fb;
 
 		return vmw_kms_write_svga(dev_priv, w, h, fb->pitches[0],
 					  fb->format->cpp[0] * 8,

From 4437c1152ce0e57ab8f401aa696ea6291cc07ab1 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 26 Jun 2020 13:39:59 +0300
Subject: [PATCH 294/474] drm/vmwgfx: Fix two list_for_each loop exit tests

These if statements are supposed to be true if we ended the
list_for_each_entry() loops without hitting a break statement but they
don't work.

In the first loop, we increment "i" after the "if (i == unit)" condition
so we don't necessarily know that "i" is not equal to unit at the end of
the loop.

In the second loop we exit when mode is not pointing to a valid
drm_display_mode struct so it doesn't make sense to check "mode->type".

Fixes: a278724aa23c ("drm/vmwgfx: Implement fbdev on kms v2")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Signed-off-by: Roland Scheidegger <sroland@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index bbce45d142aa..6e9a6135533a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -2575,7 +2575,7 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
 		++i;
 	}
 
-	if (i != unit) {
+	if (&con->head == &dev_priv->dev->mode_config.connector_list) {
 		DRM_ERROR("Could not find initial display unit.\n");
 		ret = -EINVAL;
 		goto out_unlock;
@@ -2599,13 +2599,13 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
 			break;
 	}
 
-	if (mode->type & DRM_MODE_TYPE_PREFERRED)
-		*p_mode = mode;
-	else {
+	if (&mode->head == &con->modes) {
 		WARN_ONCE(true, "Could not find initial preferred mode.\n");
 		*p_mode = list_first_entry(&con->modes,
 					   struct drm_display_mode,
 					   head);
+	} else {
+		*p_mode = mode;
 	}
 
  out_unlock:

From 68745d1edf1700a668c15ecbed466d18f14c7e9b Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 6 Aug 2020 17:42:27 +0200
Subject: [PATCH 295/474] drm/vmwgfx/stdu: Use drm_mode_config_reset

When converting to atomic the state reset was done by directly calling
the functions, and before the modeset object was fully initialized.
This means the various ->dev pointers weren't set up.

After

commit 51f644b40b4b794b28b982fdd5d0dd8ee63f9272
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date:   Fri Jun 12 18:00:49 2020 +0200

    drm/atomic-helper: reset vblank on crtc reset

this started to oops because now we're trying to derefence
drm_crtc->dev. Fix this up by entirely switching over to
drm_mode_config_reset, called once everything is set up.

Fixes: 51f644b40b4b ("drm/atomic-helper: reset vblank on crtc reset")
Reported-by: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Tested-by: Roland Scheidegger <sroland@vmware.com>
Signed-off-by: Roland Scheidegger <sroland@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 16b385629688..cf3aafd00837 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -1738,8 +1738,6 @@ static int vmw_stdu_init(struct vmw_private *dev_priv, unsigned unit)
 	stdu->base.is_implicit = false;
 
 	/* Initialize primary plane */
-	vmw_du_plane_reset(primary);
-
 	ret = drm_universal_plane_init(dev, primary,
 				       0, &vmw_stdu_plane_funcs,
 				       vmw_primary_plane_formats,
@@ -1754,8 +1752,6 @@ static int vmw_stdu_init(struct vmw_private *dev_priv, unsigned unit)
 	drm_plane_enable_fb_damage_clips(primary);
 
 	/* Initialize cursor plane */
-	vmw_du_plane_reset(cursor);
-
 	ret = drm_universal_plane_init(dev, cursor,
 			0, &vmw_stdu_cursor_funcs,
 			vmw_cursor_plane_formats,
@@ -1769,8 +1765,6 @@ static int vmw_stdu_init(struct vmw_private *dev_priv, unsigned unit)
 
 	drm_plane_helper_add(cursor, &vmw_stdu_cursor_plane_helper_funcs);
 
-	vmw_du_connector_reset(connector);
-
 	ret = drm_connector_init(dev, connector, &vmw_stdu_connector_funcs,
 				 DRM_MODE_CONNECTOR_VIRTUAL);
 	if (ret) {
@@ -1798,7 +1792,6 @@ static int vmw_stdu_init(struct vmw_private *dev_priv, unsigned unit)
 		goto err_free_encoder;
 	}
 
-	vmw_du_crtc_reset(crtc);
 	ret = drm_crtc_init_with_planes(dev, crtc, &stdu->base.primary,
 					&stdu->base.cursor,
 					&vmw_stdu_crtc_funcs, NULL);
@@ -1894,6 +1887,8 @@ int vmw_kms_stdu_init_display(struct vmw_private *dev_priv)
 		}
 	}
 
+	drm_mode_config_reset(dev);
+
 	DRM_INFO("Screen Target Display device initialized\n");
 
 	return 0;

From 1338441cf166e2ef789af5915b961d4e13a4ec31 Mon Sep 17 00:00:00 2001
From: Roland Scheidegger <sroland@vmware.com>
Date: Fri, 7 Aug 2020 22:03:42 +0200
Subject: [PATCH 296/474] drm/vmwgfx/sou: Use drm_mode_config_reset

Same problem as in stdu, same fix.

Fixes: 51f644b40b4b ("drm/atomic-helper: reset vblank on crtc reset")
Acked-by: Charmaine Lee <charmainel@vmware.com>
Reviewed-by: Zack Rusin <zackr@vmware.com>
Signed-off-by: Roland Scheidegger <sroland@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index 32a22e4eddb1..4bf0f5ec4fc2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -859,8 +859,6 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit)
 	sou->base.is_implicit = false;
 
 	/* Initialize primary plane */
-	vmw_du_plane_reset(primary);
-
 	ret = drm_universal_plane_init(dev, &sou->base.primary,
 				       0, &vmw_sou_plane_funcs,
 				       vmw_primary_plane_formats,
@@ -875,8 +873,6 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit)
 	drm_plane_enable_fb_damage_clips(primary);
 
 	/* Initialize cursor plane */
-	vmw_du_plane_reset(cursor);
-
 	ret = drm_universal_plane_init(dev, &sou->base.cursor,
 			0, &vmw_sou_cursor_funcs,
 			vmw_cursor_plane_formats,
@@ -890,7 +886,6 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit)
 
 	drm_plane_helper_add(cursor, &vmw_sou_cursor_plane_helper_funcs);
 
-	vmw_du_connector_reset(connector);
 	ret = drm_connector_init(dev, connector, &vmw_sou_connector_funcs,
 				 DRM_MODE_CONNECTOR_VIRTUAL);
 	if (ret) {
@@ -918,8 +913,6 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit)
 		goto err_free_encoder;
 	}
 
-
-	vmw_du_crtc_reset(crtc);
 	ret = drm_crtc_init_with_planes(dev, crtc, &sou->base.primary,
 					&sou->base.cursor,
 					&vmw_screen_object_crtc_funcs, NULL);
@@ -973,6 +966,8 @@ int vmw_kms_sou_init_display(struct vmw_private *dev_priv)
 
 	dev_priv->active_display_unit = vmw_du_screen_object;
 
+	drm_mode_config_reset(dev);
+
 	DRM_INFO("Screen Objects Display Unit initialized\n");
 
 	return 0;

From 981243371a5d832af5bc572071172e955d02fe88 Mon Sep 17 00:00:00 2001
From: Roland Scheidegger <sroland@vmware.com>
Date: Fri, 7 Aug 2020 22:04:33 +0200
Subject: [PATCH 297/474] drm/vmwgfx/ldu: Use drm_mode_config_reset

Same problem as in stdu, same fix.

Fixes: 51f644b40b4b ("drm/atomic-helper: reset vblank on crtc reset")
Acked-by: Charmaine Lee <charmainel@vmware.com>
Reviewed-by: Zack Rusin <zackr@vmware.com>
Signed-off-by: Roland Scheidegger <sroland@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index 009f1742bed5..c4017c7a24db 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -387,8 +387,6 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit)
 	ldu->base.is_implicit = true;
 
 	/* Initialize primary plane */
-	vmw_du_plane_reset(primary);
-
 	ret = drm_universal_plane_init(dev, &ldu->base.primary,
 				       0, &vmw_ldu_plane_funcs,
 				       vmw_primary_plane_formats,
@@ -402,8 +400,6 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit)
 	drm_plane_helper_add(primary, &vmw_ldu_primary_plane_helper_funcs);
 
 	/* Initialize cursor plane */
-	vmw_du_plane_reset(cursor);
-
 	ret = drm_universal_plane_init(dev, &ldu->base.cursor,
 			0, &vmw_ldu_cursor_funcs,
 			vmw_cursor_plane_formats,
@@ -417,7 +413,6 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit)
 
 	drm_plane_helper_add(cursor, &vmw_ldu_cursor_plane_helper_funcs);
 
-	vmw_du_connector_reset(connector);
 	ret = drm_connector_init(dev, connector, &vmw_legacy_connector_funcs,
 				 DRM_MODE_CONNECTOR_VIRTUAL);
 	if (ret) {
@@ -445,7 +440,6 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit)
 		goto err_free_encoder;
 	}
 
-	vmw_du_crtc_reset(crtc);
 	ret = drm_crtc_init_with_planes(dev, crtc, &ldu->base.primary,
 					&ldu->base.cursor,
 					&vmw_legacy_crtc_funcs, NULL);
@@ -520,6 +514,8 @@ int vmw_kms_ldu_init_display(struct vmw_private *dev_priv)
 
 	dev_priv->active_display_unit = vmw_du_legacy;
 
+	drm_mode_config_reset(dev);
+
 	DRM_INFO("Legacy Display Unit initialized\n");
 
 	return 0;

From 1ae96fce3e4dfe769515350b7f142b3bca1e0bb6 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 5 Aug 2020 12:31:55 +0100
Subject: [PATCH 298/474] drm/vmwgfx: fix spelling mistake "Cound" -> "Could"

There is a spelling mistake in a DRM_ERROR message. Fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Roland Scheidegger <sroland@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 4284c4bd444d..e67e2e8f6e6f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -3037,7 +3037,7 @@ static int vmw_cmd_dx_bind_streamoutput(struct vmw_private *dev_priv,
 	res = vmw_dx_streamoutput_lookup(vmw_context_res_man(ctx_node->ctx),
 					 cmd->body.soid);
 	if (IS_ERR(res)) {
-		DRM_ERROR("Cound not find streamoutput to bind.\n");
+		DRM_ERROR("Could not find streamoutput to bind.\n");
 		return PTR_ERR(res);
 	}
 

From e97644ebcdc83854e6e29e96285b25042445c28c Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 10 Aug 2020 11:04:01 +0100
Subject: [PATCH 299/474] drm/vmwgfx: fix spelling mistake "Cant" -> "Can't"

There is a spelling mistake in a DRM_ERROR message. Fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Roland Scheidegger <sroland@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 6e9a6135533a..312ed0881a99 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -186,7 +186,7 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf,
 		/* TODO handle none page aligned offsets */
 		/* TODO handle more dst & src != 0 */
 		/* TODO handle more then one copy */
-		DRM_ERROR("Cant snoop dma request for cursor!\n");
+		DRM_ERROR("Can't snoop dma request for cursor!\n");
 		DRM_ERROR("(%u, %u, %u) (%u, %u, %u) (%ux%ux%u) %u %u\n",
 			  box->srcx, box->srcy, box->srcz,
 			  box->x, box->y, box->z,

From 60e5da629a7c29e0987f6f02ec20b14c4ee0645e Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Sun, 9 Aug 2020 07:30:06 +0200
Subject: [PATCH 300/474] sections.h: dereference_function_descriptor() returns
 void pointer

The function dereference_function_descriptor() takes on hppa64, ppc64
and ia64 a pointer to a function descriptor and returns a (void) pointer
to the dereferenced function.
To make cross-arch coding easier, on all other architectures the
dereference_function_descriptor() macro should return a void pointer
too.

Signed-off-by: Helge Deller <deller@gmx.de>
---
 include/asm-generic/sections.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index 66397ed10acb..d16302d3eb59 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -60,8 +60,8 @@ extern __visible const void __nosave_begin, __nosave_end;
 
 /* Function descriptor handling (if any).  Override in asm/sections.h */
 #ifndef dereference_function_descriptor
-#define dereference_function_descriptor(p) (p)
-#define dereference_kernel_function_descriptor(p) (p)
+#define dereference_function_descriptor(p) ((void *)(p))
+#define dereference_kernel_function_descriptor(p) ((void *)(p))
 #endif
 
 /* random extra sections (if any).  Override

From 875102ea4b7700330a33c0db71555d91dafa9c82 Mon Sep 17 00:00:00 2001
From: Oscar Carter <oscar.carter@gmx.com>
Date: Sat, 4 Jul 2020 17:50:57 +0200
Subject: [PATCH 301/474] parisc/kernel/ftrace: Remove function callback casts

In an effort to enable -Wcast-function-type in the top-level Makefile to
support Control Flow Integrity builds, remove all the function callback
casts.

Co-developed-by: Helge Deller <deller@gmx.de>
Signed-off-by: Oscar Carter <oscar.carter@gmx.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/ftrace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index 1df0f67ed667..4bab21c71055 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -64,7 +64,8 @@ void notrace __hot ftrace_function_trampoline(unsigned long parent,
 				function_trace_op, regs);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	if (ftrace_graph_return != (trace_func_graph_ret_t) ftrace_stub ||
+	if (dereference_function_descriptor(ftrace_graph_return) !=
+	    dereference_function_descriptor(ftrace_stub) ||
 	    ftrace_graph_entry != ftrace_graph_entry_stub) {
 		unsigned long *parent_rp;
 

From e792415c5d3e0eb52527cce228a72e4392f8cae2 Mon Sep 17 00:00:00 2001
From: Xingxing Su <suxingxing@loongson.cn>
Date: Tue, 11 Aug 2020 07:18:37 -0400
Subject: [PATCH 302/474] KVM: MIPS/VZ: Fix build error caused by 'kvm_run'
 cleanup

Commit c34b26b98caca48ec9ee9 ("KVM: MIPS: clean up redundant 'kvm_run'
parameters") remove the 'kvm_run' parameter in kvm_vz_gpsi_lwc2.

The following build error:

arch/mips/kvm/vz.c: In function 'kvm_trap_vz_handle_gpsi':
arch/mips/kvm/vz.c:1243:43: error: 'run' undeclared (first use in this function)
   er = kvm_vz_gpsi_lwc2(inst, opc, cause, run, vcpu);
                                           ^~~
arch/mips/kvm/vz.c:1243:43: note: each undeclared identifier is reported only
once for each function it appears in
scripts/Makefile.build:283: recipe for target 'arch/mips/kvm/vz.o' failed
make[2]: *** [arch/mips/kvm/vz.o] Error 1
scripts/Makefile.build:500: recipe for target 'arch/mips/kvm' failed
make[1]: *** [arch/mips/kvm] Error 2
Makefile:1785: recipe for target 'arch/mips' failed
make: *** [arch/mips] Error 2

Signed-off-by: Xingxing Su <suxingxing@loongson.cn>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/mips/kvm/vz.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c
index a474578ccf68..c299e5d6d69c 100644
--- a/arch/mips/kvm/vz.c
+++ b/arch/mips/kvm/vz.c
@@ -1144,7 +1144,6 @@ static enum emulation_result kvm_vz_gpsi_cache(union mips_instruction inst,
 #ifdef CONFIG_CPU_LOONGSON64
 static enum emulation_result kvm_vz_gpsi_lwc2(union mips_instruction inst,
 					      u32 *opc, u32 cause,
-					      struct kvm_run *run,
 					      struct kvm_vcpu *vcpu)
 {
 	unsigned int rs, rd;
@@ -1242,7 +1241,7 @@ static enum emulation_result kvm_trap_vz_handle_gpsi(u32 cause, u32 *opc,
 #endif
 #ifdef CONFIG_CPU_LOONGSON64
 	case lwc2_op:
-		er = kvm_vz_gpsi_lwc2(inst, opc, cause, run, vcpu);
+		er = kvm_vz_gpsi_lwc2(inst, opc, cause, vcpu);
 		break;
 #endif
 	case spec3_op:

From 3bc6e3dc5a54d5842938c6f1ed78dd1add379af7 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Sun, 14 Jun 2020 10:50:42 +0200
Subject: [PATCH 303/474] parisc: Whitespace cleanups in atomic.h

Fix whitespace indenting and drop trailing backslashes.

Cc: <stable@vger.kernel.org> # 4.19+
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/include/asm/atomic.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 6dd4171c9530..90e8267fc509 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -34,13 +34,13 @@ extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
 /* Can't use raw_spin_lock_irq because of #include problems, so
  * this is the substitute */
 #define _atomic_spin_lock_irqsave(l,f) do {	\
-	arch_spinlock_t *s = ATOMIC_HASH(l);		\
+	arch_spinlock_t *s = ATOMIC_HASH(l);	\
 	local_irq_save(f);			\
 	arch_spin_lock(s);			\
 } while(0)
 
 #define _atomic_spin_unlock_irqrestore(l,f) do {	\
-	arch_spinlock_t *s = ATOMIC_HASH(l);			\
+	arch_spinlock_t *s = ATOMIC_HASH(l);		\
 	arch_spin_unlock(s);				\
 	local_irq_restore(f);				\
 } while(0)
@@ -85,7 +85,7 @@ static __inline__ void atomic_##op(int i, atomic_t *v)			\
 	_atomic_spin_lock_irqsave(v, flags);				\
 	v->counter c_op i;						\
 	_atomic_spin_unlock_irqrestore(v, flags);			\
-}									\
+}
 
 #define ATOMIC_OP_RETURN(op, c_op)					\
 static __inline__ int atomic_##op##_return(int i, atomic_t *v)		\
@@ -150,7 +150,7 @@ static __inline__ void atomic64_##op(s64 i, atomic64_t *v)		\
 	_atomic_spin_lock_irqsave(v, flags);				\
 	v->counter c_op i;						\
 	_atomic_spin_unlock_irqrestore(v, flags);			\
-}									\
+}
 
 #define ATOMIC64_OP_RETURN(op, c_op)					\
 static __inline__ s64 atomic64_##op##_return(s64 i, atomic64_t *v)	\

From 5b24993c21cbf2de11aff077a48c5cb0505a0450 Mon Sep 17 00:00:00 2001
From: Sven Schnelle <svens@stackframe.org>
Date: Tue, 11 Aug 2020 18:19:19 +0200
Subject: [PATCH 304/474] parisc: mask out enable and reserved bits from sba
 imask

When using kexec the SBA IOMMU IBASE might still have the RE
bit set. This triggers a WARN_ON when trying to write back the
IBASE register later, and it also makes some mask calculations fail.

Cc: <stable@vger.kernel.org>
Signed-off-by: Sven Schnelle <svens@stackframe.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/parisc/sba_iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 7e112829d250..00785fa81ff7 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -1270,7 +1270,7 @@ sba_ioc_init_pluto(struct parisc_device *sba, struct ioc *ioc, int ioc_num)
 	** (one that doesn't overlap memory or LMMIO space) in the
 	** IBASE and IMASK registers.
 	*/
-	ioc->ibase = READ_REG(ioc->ioc_hpa + IOC_IBASE);
+	ioc->ibase = READ_REG(ioc->ioc_hpa + IOC_IBASE) & ~0x1fffffULL;
 	iova_space_size = ~(READ_REG(ioc->ioc_hpa + IOC_IMASK) & 0xFFFFFFFFUL) + 1;
 
 	if ((ioc->ibase < 0xfed00000UL) && ((ioc->ibase + iova_space_size) > 0xfee00000UL)) {

From 62975d27d647a40c58d3b96c29b911fc4f33c310 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <ckoenig.leichtzumerken@gmail.com>
Date: Wed, 12 Aug 2020 13:03:49 +1000
Subject: [PATCH 305/474] drm/ttm: revert "drm/ttm: make TT creation purely
 optional v3"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 2ddef17678bc2ea1d20517dd2b4ed4aa967ffa8b.

As it turned out VMWGFX needs a much wider audit to fix this.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200811092400.188124-1-christian.koenig@amd.com
---
 drivers/gpu/drm/ttm/ttm_bo.c      | 37 +++++++++++++++++++++++--------
 drivers/gpu/drm/ttm/ttm_bo_util.c |  7 ++----
 drivers/gpu/drm/ttm/ttm_bo_vm.c   |  5 -----
 drivers/gpu/drm/ttm/ttm_tt.c      |  4 +---
 4 files changed, 31 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index f297fd5e02d4..cc6a4e7551e3 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -287,11 +287,12 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 	 */
 
 	if (!(new_man->flags & TTM_MEMTYPE_FLAG_FIXED)) {
-		bool zero = !(old_man->flags & TTM_MEMTYPE_FLAG_FIXED);
-
-		ret = ttm_tt_create(bo, zero);
-		if (ret)
-			goto out_err;
+		if (bo->ttm == NULL) {
+			bool zero = !(old_man->flags & TTM_MEMTYPE_FLAG_FIXED);
+			ret = ttm_tt_create(bo, zero);
+			if (ret)
+				goto out_err;
+		}
 
 		ret = ttm_tt_set_placement_caching(bo->ttm, mem->placement);
 		if (ret)
@@ -652,8 +653,13 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo,
 	placement.num_busy_placement = 0;
 	bdev->driver->evict_flags(bo, &placement);
 
-	if (!placement.num_placement && !placement.num_busy_placement)
-		return ttm_bo_pipeline_gutting(bo);
+	if (!placement.num_placement && !placement.num_busy_placement) {
+		ret = ttm_bo_pipeline_gutting(bo);
+		if (ret)
+			return ret;
+
+		return ttm_tt_create(bo, false);
+	}
 
 	evict_mem = bo->mem;
 	evict_mem.mm_node = NULL;
@@ -1192,8 +1198,13 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	/*
 	 * Remove the backing store if no placement is given.
 	 */
-	if (!placement->num_placement && !placement->num_busy_placement)
-		return ttm_bo_pipeline_gutting(bo);
+	if (!placement->num_placement && !placement->num_busy_placement) {
+		ret = ttm_bo_pipeline_gutting(bo);
+		if (ret)
+			return ret;
+
+		return ttm_tt_create(bo, false);
+	}
 
 	/*
 	 * Check whether we need to move buffer.
@@ -1210,6 +1221,14 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 		ttm_flag_masked(&bo->mem.placement, new_flags,
 				~TTM_PL_MASK_MEMTYPE);
 	}
+	/*
+	 * We might need to add a TTM.
+	 */
+	if (bo->mem.mem_type == TTM_PL_SYSTEM && bo->ttm == NULL) {
+		ret = ttm_tt_create(bo, true);
+		if (ret)
+			return ret;
+	}
 	return 0;
 }
 EXPORT_SYMBOL(ttm_bo_validate);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 7fb3e0bcbab4..e6c8bd254055 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -531,15 +531,12 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo,
 		.interruptible = false,
 		.no_wait_gpu = false
 	};
-	struct ttm_tt *ttm;
+	struct ttm_tt *ttm = bo->ttm;
 	pgprot_t prot;
 	int ret;
 
-	ret = ttm_tt_create(bo, true);
-	if (ret)
-		return ret;
+	BUG_ON(!ttm);
 
-	ttm = bo->ttm;
 	ret = ttm_tt_populate(ttm, &ctx);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index dd60b96b7522..33526c5df0e8 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -351,11 +351,6 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 
 		};
 
-		if (ttm_tt_create(bo, true)) {
-			ret = VM_FAULT_OOM;
-			goto out_io_unlock;
-		}
-
 		ttm = bo->ttm;
 		if (ttm_tt_populate(bo->ttm, &ctx)) {
 			ret = VM_FAULT_OOM;
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 9d1c7177384c..3437711ddb43 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -50,9 +50,6 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc)
 
 	dma_resv_assert_held(bo->base.resv);
 
-	if (bo->ttm)
-		return 0;
-
 	if (bdev->need_dma32)
 		page_flags |= TTM_PAGE_FLAG_DMA32;
 
@@ -70,6 +67,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc)
 		page_flags |= TTM_PAGE_FLAG_SG;
 		break;
 	default:
+		bo->ttm = NULL;
 		pr_err("Illegal buffer object type\n");
 		return -EINVAL;
 	}

From 985b30dbe2cf58c27dd81da85410439ced8ce6d7 Mon Sep 17 00:00:00 2001
From: Liam Beguin <lvb@xiphos.com>
Date: Mon, 29 Jun 2020 22:42:10 -0400
Subject: [PATCH 306/474] rtc: pcf2127: add pca2129 device id

The PCA2129 is the automotive grade version of the PCF2129.
add it to the list of compatibles.

Signed-off-by: Liam Beguin <lvb@xiphos.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Reviewed-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Link: https://lore.kernel.org/r/20200630024211.12782-2-liambeguin@gmail.com
---
 Documentation/devicetree/bindings/rtc/trivial-rtc.yaml | 2 ++
 drivers/rtc/rtc-pcf2127.c                              | 3 +++
 2 files changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
index 18cb456752f6..c7d14de214c4 100644
--- a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
@@ -52,6 +52,8 @@ properties:
       - nxp,pcf2127
       # Real-time clock
       - nxp,pcf2129
+      # Real-time clock
+      - nxp,pca2129
       # Real-time Clock Module
       - pericom,pt7c4338
       # I2C bus SERIAL INTERFACE REAL-TIME CLOCK IC
diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 9c5670776c68..4accee09bfad 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -553,6 +553,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 static const struct of_device_id pcf2127_of_match[] = {
 	{ .compatible = "nxp,pcf2127" },
 	{ .compatible = "nxp,pcf2129" },
+	{ .compatible = "nxp,pca2129" },
 	{}
 };
 MODULE_DEVICE_TABLE(of, pcf2127_of_match);
@@ -664,6 +665,7 @@ static int pcf2127_i2c_probe(struct i2c_client *client,
 static const struct i2c_device_id pcf2127_i2c_id[] = {
 	{ "pcf2127", 1 },
 	{ "pcf2129", 0 },
+	{ "pca2129", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, pcf2127_i2c_id);
@@ -729,6 +731,7 @@ static int pcf2127_spi_probe(struct spi_device *spi)
 static const struct spi_device_id pcf2127_spi_id[] = {
 	{ "pcf2127", 1 },
 	{ "pcf2129", 0 },
+	{ "pca2129", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(spi, pcf2127_spi_id);

From 8a914bac44be33623cfcf27688b18b6f81a5c7d5 Mon Sep 17 00:00:00 2001
From: Liam Beguin <lvb@xiphos.com>
Date: Mon, 29 Jun 2020 22:42:11 -0400
Subject: [PATCH 307/474] rtc: pcf2127: add alarm support

Add alarm support for the pcf2127 RTC chip family.
Tested on pca2129.

Signed-off-by: Liam Beguin <lvb@xiphos.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Reviewed-by: Bruno Thomsen <bruno.thomsen@gmail.com>
Link: https://lore.kernel.org/r/20200630024211.12782-3-liambeguin@gmail.com
---
 drivers/rtc/rtc-pcf2127.c | 134 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 134 insertions(+)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 4accee09bfad..4e99c45a87d7 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -20,6 +20,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_irq.h>
 #include <linux/regmap.h>
 #include <linux/watchdog.h>
 
@@ -28,7 +29,9 @@
 #define PCF2127_BIT_CTRL1_TSF1			BIT(4)
 /* Control register 2 */
 #define PCF2127_REG_CTRL2		0x01
+#define PCF2127_BIT_CTRL2_AIE			BIT(1)
 #define PCF2127_BIT_CTRL2_TSIE			BIT(2)
+#define PCF2127_BIT_CTRL2_AF			BIT(4)
 #define PCF2127_BIT_CTRL2_TSF2			BIT(5)
 /* Control register 3 */
 #define PCF2127_REG_CTRL3		0x02
@@ -46,6 +49,12 @@
 #define PCF2127_REG_DW			0x07
 #define PCF2127_REG_MO			0x08
 #define PCF2127_REG_YR			0x09
+/* Alarm registers */
+#define PCF2127_REG_ALARM_SC		0x0A
+#define PCF2127_REG_ALARM_MN		0x0B
+#define PCF2127_REG_ALARM_HR		0x0C
+#define PCF2127_REG_ALARM_DM		0x0D
+#define PCF2127_REG_ALARM_DW		0x0E
 /* Watchdog registers */
 #define PCF2127_REG_WD_CTL		0x10
 #define PCF2127_BIT_WD_CTL_TF0			BIT(0)
@@ -324,6 +333,114 @@ static const struct watchdog_ops pcf2127_watchdog_ops = {
 	.set_timeout = pcf2127_wdt_set_timeout,
 };
 
+/* Alarm */
+static int pcf2127_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
+	unsigned int buf[5], ctrl2;
+	int ret;
+
+	ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL2, &ctrl2);
+	if (ret)
+		return ret;
+
+	ret = pcf2127_wdt_active_ping(&pcf2127->wdd);
+	if (ret)
+		return ret;
+
+	ret = regmap_bulk_read(pcf2127->regmap, PCF2127_REG_ALARM_SC, buf,
+			       sizeof(buf));
+	if (ret)
+		return ret;
+
+	alrm->enabled = ctrl2 & PCF2127_BIT_CTRL2_AIE;
+	alrm->pending = ctrl2 & PCF2127_BIT_CTRL2_AF;
+
+	alrm->time.tm_sec = bcd2bin(buf[0] & 0x7F);
+	alrm->time.tm_min = bcd2bin(buf[1] & 0x7F);
+	alrm->time.tm_hour = bcd2bin(buf[2] & 0x3F);
+	alrm->time.tm_mday = bcd2bin(buf[3] & 0x3F);
+	alrm->time.tm_wday = buf[4] & 0x07;
+
+	return 0;
+}
+
+static int pcf2127_rtc_alarm_irq_enable(struct device *dev, u32 enable)
+{
+	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
+	int ret;
+
+	ret = regmap_update_bits(pcf2127->regmap, PCF2127_REG_CTRL2,
+				 PCF2127_BIT_CTRL2_AIE,
+				 enable ? PCF2127_BIT_CTRL2_AIE : 0);
+	if (ret)
+		return ret;
+
+	return pcf2127_wdt_active_ping(&pcf2127->wdd);
+}
+
+static int pcf2127_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
+	uint8_t buf[5];
+	int ret;
+
+	ret = regmap_update_bits(pcf2127->regmap, PCF2127_REG_CTRL2,
+				 PCF2127_BIT_CTRL2_AF, 0);
+	if (ret)
+		return ret;
+
+	ret = pcf2127_wdt_active_ping(&pcf2127->wdd);
+	if (ret)
+		return ret;
+
+	buf[0] = bin2bcd(alrm->time.tm_sec);
+	buf[1] = bin2bcd(alrm->time.tm_min);
+	buf[2] = bin2bcd(alrm->time.tm_hour);
+	buf[3] = bin2bcd(alrm->time.tm_mday);
+	buf[4] = (alrm->time.tm_wday & 0x07);
+
+	ret = regmap_bulk_write(pcf2127->regmap, PCF2127_REG_ALARM_SC, buf,
+				sizeof(buf));
+	if (ret)
+		return ret;
+
+	return pcf2127_rtc_alarm_irq_enable(dev, alrm->enabled);
+}
+
+static irqreturn_t pcf2127_rtc_irq(int irq, void *dev)
+{
+	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
+	unsigned int ctrl2 = 0;
+	int ret = 0;
+
+	ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL2, &ctrl2);
+	if (ret)
+		return IRQ_NONE;
+
+	if (ctrl2 & PCF2127_BIT_CTRL2_AF) {
+		regmap_write(pcf2127->regmap, PCF2127_REG_CTRL2,
+			     ctrl2 & ~PCF2127_BIT_CTRL2_AF);
+
+		rtc_update_irq(pcf2127->rtc, 1, RTC_IRQF | RTC_AF);
+	}
+
+	ret = pcf2127_wdt_active_ping(&pcf2127->wdd);
+	if (ret)
+		return IRQ_NONE;
+
+	return IRQ_HANDLED;
+}
+
+static const struct rtc_class_ops pcf2127_rtc_alrm_ops = {
+	.ioctl            = pcf2127_rtc_ioctl,
+	.read_time        = pcf2127_rtc_read_time,
+	.set_time         = pcf2127_rtc_set_time,
+	.read_alarm       = pcf2127_rtc_read_alarm,
+	.set_alarm        = pcf2127_rtc_set_alarm,
+	.alarm_irq_enable = pcf2127_rtc_alarm_irq_enable,
+};
+
 /* sysfs interface */
 
 static ssize_t timestamp0_store(struct device *dev,
@@ -419,6 +536,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 			const char *name, bool has_nvmem)
 {
 	struct pcf2127 *pcf2127;
+	int alarm_irq = 0;
 	u32 wdd_timeout;
 	int ret = 0;
 
@@ -441,6 +559,22 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 	pcf2127->rtc->range_max = RTC_TIMESTAMP_END_2099;
 	pcf2127->rtc->set_start_time = true; /* Sets actual start to 1970 */
 
+	alarm_irq = of_irq_get_byname(dev->of_node, "alarm");
+	if (alarm_irq >= 0) {
+		ret = devm_request_irq(dev, alarm_irq, pcf2127_rtc_irq,
+				       IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+				       dev_name(dev), dev);
+		if (ret) {
+			dev_err(dev, "failed to request alarm irq\n");
+			return ret;
+		}
+	}
+
+	if (alarm_irq >= 0 || device_property_read_bool(dev, "wakeup-source")) {
+		device_init_wakeup(dev, true);
+		pcf2127->rtc->ops = &pcf2127_rtc_alrm_ops;
+	}
+
 	pcf2127->wdd.parent = dev;
 	pcf2127->wdd.info = &pcf2127_wdt_info;
 	pcf2127->wdd.ops = &pcf2127_watchdog_ops;

From 27006416be16b7887fb94b3b445f32453defb3f1 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 12 Aug 2020 10:51:14 +0200
Subject: [PATCH 308/474] rtc: pcf2127: fix alarm handling

Fix multiple issues when handling alarms:
 - Use threaded interrupt to avoid scheduling when atomic
 - Stop matching on week day as it may not be set correctly
 - Avoid parsing the DT interrupt and use what is provided by the i2c or
   spi subsystem
 - Avoid returning IRQ_NONE in case of error in the interrupt handler
 - Never write WDTF as specified in the datasheet
 - Set uie_unsupported, as for the pcf85063, setting alarms every seconds
   is not working correctly and confuses the RTC.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20200812085114.474903-1-alexandre.belloni@bootlin.com
---
 drivers/rtc/rtc-pcf2127.c | 39 ++++++++++++++++++++-------------------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 4e99c45a87d7..ed6316992cbb 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -33,6 +33,7 @@
 #define PCF2127_BIT_CTRL2_TSIE			BIT(2)
 #define PCF2127_BIT_CTRL2_AF			BIT(4)
 #define PCF2127_BIT_CTRL2_TSF2			BIT(5)
+#define PCF2127_BIT_CTRL2_WDTF			BIT(6)
 /* Control register 3 */
 #define PCF2127_REG_CTRL3		0x02
 #define PCF2127_BIT_CTRL3_BLIE			BIT(0)
@@ -55,6 +56,7 @@
 #define PCF2127_REG_ALARM_HR		0x0C
 #define PCF2127_REG_ALARM_DM		0x0D
 #define PCF2127_REG_ALARM_DW		0x0E
+#define PCF2127_BIT_ALARM_AE			BIT(7)
 /* Watchdog registers */
 #define PCF2127_REG_WD_CTL		0x10
 #define PCF2127_BIT_WD_CTL_TF0			BIT(0)
@@ -360,7 +362,6 @@ static int pcf2127_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	alrm->time.tm_min = bcd2bin(buf[1] & 0x7F);
 	alrm->time.tm_hour = bcd2bin(buf[2] & 0x3F);
 	alrm->time.tm_mday = bcd2bin(buf[3] & 0x3F);
-	alrm->time.tm_wday = buf[4] & 0x07;
 
 	return 0;
 }
@@ -398,7 +399,7 @@ static int pcf2127_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	buf[1] = bin2bcd(alrm->time.tm_min);
 	buf[2] = bin2bcd(alrm->time.tm_hour);
 	buf[3] = bin2bcd(alrm->time.tm_mday);
-	buf[4] = (alrm->time.tm_wday & 0x07);
+	buf[4] = PCF2127_BIT_ALARM_AE; /* Do not match on week day */
 
 	ret = regmap_bulk_write(pcf2127->regmap, PCF2127_REG_ALARM_SC, buf,
 				sizeof(buf));
@@ -418,17 +419,16 @@ static irqreturn_t pcf2127_rtc_irq(int irq, void *dev)
 	if (ret)
 		return IRQ_NONE;
 
-	if (ctrl2 & PCF2127_BIT_CTRL2_AF) {
-		regmap_write(pcf2127->regmap, PCF2127_REG_CTRL2,
-			     ctrl2 & ~PCF2127_BIT_CTRL2_AF);
-
-		rtc_update_irq(pcf2127->rtc, 1, RTC_IRQF | RTC_AF);
-	}
-
-	ret = pcf2127_wdt_active_ping(&pcf2127->wdd);
-	if (ret)
+	if (!(ctrl2 & PCF2127_BIT_CTRL2_AF))
 		return IRQ_NONE;
 
+	regmap_write(pcf2127->regmap, PCF2127_REG_CTRL2,
+		     ctrl2 & ~(PCF2127_BIT_CTRL2_AF | PCF2127_BIT_CTRL2_WDTF));
+
+	rtc_update_irq(pcf2127->rtc, 1, RTC_IRQF | RTC_AF);
+
+	pcf2127_wdt_active_ping(&pcf2127->wdd);
+
 	return IRQ_HANDLED;
 }
 
@@ -533,10 +533,9 @@ static const struct attribute_group pcf2127_attr_group = {
 };
 
 static int pcf2127_probe(struct device *dev, struct regmap *regmap,
-			const char *name, bool has_nvmem)
+			 int alarm_irq, const char *name, bool has_nvmem)
 {
 	struct pcf2127 *pcf2127;
-	int alarm_irq = 0;
 	u32 wdd_timeout;
 	int ret = 0;
 
@@ -558,12 +557,13 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 	pcf2127->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	pcf2127->rtc->range_max = RTC_TIMESTAMP_END_2099;
 	pcf2127->rtc->set_start_time = true; /* Sets actual start to 1970 */
+	pcf2127->rtc->uie_unsupported = 1;
 
-	alarm_irq = of_irq_get_byname(dev->of_node, "alarm");
 	if (alarm_irq >= 0) {
-		ret = devm_request_irq(dev, alarm_irq, pcf2127_rtc_irq,
-				       IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-				       dev_name(dev), dev);
+		ret = devm_request_threaded_irq(dev, alarm_irq, NULL,
+						pcf2127_rtc_irq,
+						IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+						dev_name(dev), dev);
 		if (ret) {
 			dev_err(dev, "failed to request alarm irq\n");
 			return ret;
@@ -792,7 +792,7 @@ static int pcf2127_i2c_probe(struct i2c_client *client,
 		return PTR_ERR(regmap);
 	}
 
-	return pcf2127_probe(&client->dev, regmap,
+	return pcf2127_probe(&client->dev, regmap, client->irq,
 			     pcf2127_i2c_driver.driver.name, id->driver_data);
 }
 
@@ -858,7 +858,8 @@ static int pcf2127_spi_probe(struct spi_device *spi)
 		return PTR_ERR(regmap);
 	}
 
-	return pcf2127_probe(&spi->dev, regmap, pcf2127_spi_driver.driver.name,
+	return pcf2127_probe(&spi->dev, regmap, spi->irq,
+			     pcf2127_spi_driver.driver.name,
 			     spi_get_device_id(spi)->driver_data);
 }
 

From e96ebd589debd9a6a793608c4ec7019c38785dea Mon Sep 17 00:00:00 2001
From: John David Anglin <dave.anglin@bell.net>
Date: Thu, 30 Jul 2020 08:59:12 -0400
Subject: [PATCH 309/474] parisc: Implement __smp_store_release and
 __smp_load_acquire barriers

This patch implements the __smp_store_release and __smp_load_acquire barriers
using ordered stores and loads.  This avoids the sync instruction present in
the generic implementation.

Cc: <stable@vger.kernel.org> # 4.14+
Signed-off-by: Dave Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/include/asm/barrier.h | 61 +++++++++++++++++++++++++++++++
 1 file changed, 61 insertions(+)

diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h
index dbaaca84f27f..640d46edf32e 100644
--- a/arch/parisc/include/asm/barrier.h
+++ b/arch/parisc/include/asm/barrier.h
@@ -26,6 +26,67 @@
 #define __smp_rmb()	mb()
 #define __smp_wmb()	mb()
 
+#define __smp_store_release(p, v)					\
+do {									\
+	typeof(p) __p = (p);						\
+        union { typeof(*p) __val; char __c[1]; } __u =			\
+                { .__val = (__force typeof(*p)) (v) };			\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile("stb,ma %0,0(%1)"				\
+				: : "r"(*(__u8 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile("sth,ma %0,0(%1)"				\
+				: : "r"(*(__u16 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile("stw,ma %0,0(%1)"				\
+				: : "r"(*(__u32 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		if (IS_ENABLED(CONFIG_64BIT))				\
+			asm volatile("std,ma %0,0(%1)"			\
+				: : "r"(*(__u64 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	}								\
+} while (0)
+
+#define __smp_load_acquire(p)						\
+({									\
+	union { typeof(*p) __val; char __c[1]; } __u;			\
+	typeof(p) __p = (p);						\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile("ldb,ma 0(%1),%0"				\
+				: "=r"(*(__u8 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile("ldh,ma 0(%1),%0"				\
+				: "=r"(*(__u16 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile("ldw,ma 0(%1),%0"				\
+				: "=r"(*(__u32 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		if (IS_ENABLED(CONFIG_64BIT))				\
+			asm volatile("ldd,ma 0(%1),%0"			\
+				: "=r"(*(__u64 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	}								\
+	__u.__val;							\
+})
 #include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */

From 24fb33d40d60bd7d196400e7d5b26ff566fd98b7 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 12 Aug 2020 05:15:18 +0100
Subject: [PATCH 310/474] fix breakage in do_rmdir()

syzbot reported and bisected a use-after-free due to the recent init
cleanups.

The putname() should happen only after we'd *not* branched to retry,
same as it's done in do_unlinkat().

Reported-by: syzbot+bbeb1c88016c7db4aa24@syzkaller.appspotmail.com
Fixes: e24ab0ef689d "fs: push the getname from do_rmdir into the callers"
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/namei.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/namei.c b/fs/namei.c
index fde8fe086c09..9fa10c614de7 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3770,11 +3770,11 @@ long do_rmdir(int dfd, struct filename *name)
 	mnt_drop_write(path.mnt);
 exit1:
 	path_put(&path);
-	putname(name);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
 		goto retry;
 	}
+	putname(name);
 	return error;
 }
 

From 5b32af91b5de6f95ad99e4eaaf57777376af124f Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 11 Aug 2020 18:30:14 -0700
Subject: [PATCH 311/474] percpu: return number of released bytes from
 pcpu_free_area()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Patch series "mm: memcg accounting of percpu memory", v3.

This patchset adds percpu memory accounting to memory cgroups.  It's based
on the rework of the slab controller and reuses concepts and features
introduced for the per-object slab accounting.

Percpu memory is becoming more and more widely used by various subsystems,
and the total amount of memory controlled by the percpu allocator can make
a good part of the total memory.

As an example, bpf maps can consume a lot of percpu memory, and they are
created by a user.  Also, some cgroup internals (e.g.  memory controller
statistics) can be quite large.  On a machine with many CPUs and big
number of cgroups they can consume hundreds of megabytes.

So the lack of memcg accounting is creating a breach in the memory
isolation.  Similar to the slab memory, percpu memory should be accounted
by default.

Percpu allocations by their nature are scattered over multiple pages, so
they can't be tracked on the per-page basis.  So the per-object tracking
introduced by the new slab controller is reused.

The patchset implements charging of percpu allocations, adds memcg-level
statistics, enables accounting for percpu allocations made by memory
cgroup internals and provides some basic tests.

To implement the accounting of percpu memory without a significant memory
and performance overhead the following approach is used: all accounted
allocations are placed into a separate percpu chunk (or chunks).  These
chunks are similar to default chunks, except that they do have an attached
vector of pointers to obj_cgroup objects, which is big enough to save a
pointer for each allocated object.  On the allocation, if the allocation
has to be accounted (__GFP_ACCOUNT is passed, the allocating process
belongs to a non-root memory cgroup, etc), the memory cgroup is getting
charged and if the maximum limit is not exceeded the allocation is
performed using a memcg-aware chunk.  Otherwise -ENOMEM is returned or the
allocation is forced over the limit, depending on gfp (as any other kernel
memory allocation).  The memory cgroup information is saved in the
obj_cgroup vector at the corresponding offset.  On the release time the
memcg information is restored from the vector and the cgroup is getting
uncharged.  Unaccounted allocations (at this point the absolute majority
of all percpu allocations) are performed in the old way, so no additional
overhead is expected.

To avoid pinning dying memory cgroups by outstanding allocations,
obj_cgroup API is used instead of directly saving memory cgroup pointers.
obj_cgroup is basically a pointer to a memory cgroup with a standalone
reference counter.  The trick is that it can be atomically swapped to
point at the parent cgroup, so that the original memory cgroup can be
released prior to all objects, which has been charged to it.  Because all
charges and statistics are fully recursive, it's perfectly correct to
uncharge the parent cgroup instead.  This scheme is used in the slab
memory accounting, and percpu memory can just follow the scheme.

This patch (of 5):

To implement accounting of percpu memory we need the information about the
size of freed object.  Return it from pcpu_free_area().

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Dennis Zhou <dennis@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tobin C. Harding <tobin@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Waiman Long <longman@redhat.com>
cC: Michal Koutnýutny@suse.com>
Cc: Bixuan Cui <cuibixuan@huawei.com>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Link: http://lkml.kernel.org/r/20200623184515.4132564-1-guro@fb.com
Link: http://lkml.kernel.org/r/20200608230819.832349-1-guro@fb.com
Link: http://lkml.kernel.org/r/20200608230819.832349-2-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/percpu.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/mm/percpu.c b/mm/percpu.c
index b626766160ce..5e9eefdce21f 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1211,11 +1211,14 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits,
  *
  * This function determines the size of an allocation to free using
  * the boundary bitmap and clears the allocation map.
+ *
+ * RETURNS:
+ * Number of freed bytes.
  */
-static void pcpu_free_area(struct pcpu_chunk *chunk, int off)
+static int pcpu_free_area(struct pcpu_chunk *chunk, int off)
 {
 	struct pcpu_block_md *chunk_md = &chunk->chunk_md;
-	int bit_off, bits, end, oslot;
+	int bit_off, bits, end, oslot, freed;
 
 	lockdep_assert_held(&pcpu_lock);
 	pcpu_stats_area_dealloc(chunk);
@@ -1230,8 +1233,10 @@ static void pcpu_free_area(struct pcpu_chunk *chunk, int off)
 	bits = end - bit_off;
 	bitmap_clear(chunk->alloc_map, bit_off, bits);
 
+	freed = bits * PCPU_MIN_ALLOC_SIZE;
+
 	/* update metadata */
-	chunk->free_bytes += bits * PCPU_MIN_ALLOC_SIZE;
+	chunk->free_bytes += freed;
 
 	/* update first free bit */
 	chunk_md->first_free = min(chunk_md->first_free, bit_off);
@@ -1239,6 +1244,8 @@ static void pcpu_free_area(struct pcpu_chunk *chunk, int off)
 	pcpu_block_update_hint_free(chunk, bit_off, bits);
 
 	pcpu_chunk_relocate(chunk, oslot);
+
+	return freed;
 }
 
 static void pcpu_init_md_block(struct pcpu_block_md *block, int nr_bits)

From 3c7be18ac9a06bc67196bfdabb7c21e1bbacdc13 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 11 Aug 2020 18:30:17 -0700
Subject: [PATCH 312/474] mm: memcg/percpu: account percpu memory to memory
 cgroups
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Percpu memory is becoming more and more widely used by various subsystems,
and the total amount of memory controlled by the percpu allocator can make
a good part of the total memory.

As an example, bpf maps can consume a lot of percpu memory, and they are
created by a user.  Also, some cgroup internals (e.g.  memory controller
statistics) can be quite large.  On a machine with many CPUs and big
number of cgroups they can consume hundreds of megabytes.

So the lack of memcg accounting is creating a breach in the memory
isolation.  Similar to the slab memory, percpu memory should be accounted
by default.

To implement the perpcu accounting it's possible to take the slab memory
accounting as a model to follow.  Let's introduce two types of percpu
chunks: root and memcg.  What makes memcg chunks different is an
additional space allocated to store memcg membership information.  If
__GFP_ACCOUNT is passed on allocation, a memcg chunk should be be used.
If it's possible to charge the corresponding size to the target memory
cgroup, allocation is performed, and the memcg ownership data is recorded.
System-wide allocations are performed using root chunks, so there is no
additional memory overhead.

To implement a fast reparenting of percpu memory on memcg removal, we
don't store mem_cgroup pointers directly: instead we use obj_cgroup API,
introduced for slab accounting.

[akpm@linux-foundation.org: fix CONFIG_MEMCG_KMEM=n build errors and warning]
[akpm@linux-foundation.org: move unreachable code, per Roman]
[cuibixuan@huawei.com: mm/percpu: fix 'defined but not used' warning]
  Link: http://lkml.kernel.org/r/6d41b939-a741-b521-a7a2-e7296ec16219@huawei.com

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Bixuan Cui <cuibixuan@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Dennis Zhou <dennis@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Tobin C. Harding <tobin@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Waiman Long <longman@redhat.com>
Cc: Bixuan Cui <cuibixuan@huawei.com>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Link: http://lkml.kernel.org/r/20200623184515.4132564-3-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/percpu-internal.h |  55 ++++++++++++-
 mm/percpu-km.c       |   5 +-
 mm/percpu-stats.c    |  36 +++++----
 mm/percpu-vm.c       |   5 +-
 mm/percpu.c          | 185 ++++++++++++++++++++++++++++++++++++++-----
 5 files changed, 246 insertions(+), 40 deletions(-)

diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index 0468ba500bd4..18b768ac7dca 100644
--- a/mm/percpu-internal.h
+++ b/mm/percpu-internal.h
@@ -5,6 +5,25 @@
 #include <linux/types.h>
 #include <linux/percpu.h>
 
+/*
+ * There are two chunk types: root and memcg-aware.
+ * Chunks of each type have separate slots list.
+ *
+ * Memcg-aware chunks have an attached vector of obj_cgroup pointers, which is
+ * used to store memcg membership data of a percpu object.  Obj_cgroups are
+ * ref-counted pointers to a memory cgroup with an ability to switch dynamically
+ * to the parent memory cgroup.  This allows to reclaim a deleted memory cgroup
+ * without reclaiming of all outstanding objects, which hold a reference at it.
+ */
+enum pcpu_chunk_type {
+	PCPU_CHUNK_ROOT,
+#ifdef CONFIG_MEMCG_KMEM
+	PCPU_CHUNK_MEMCG,
+#endif
+	PCPU_NR_CHUNK_TYPES,
+	PCPU_FAIL_ALLOC = PCPU_NR_CHUNK_TYPES
+};
+
 /*
  * pcpu_block_md is the metadata block struct.
  * Each chunk's bitmap is split into a number of full blocks.
@@ -54,6 +73,9 @@ struct pcpu_chunk {
 	int			end_offset;	/* additional area required to
 						   have the region end page
 						   aligned */
+#ifdef CONFIG_MEMCG_KMEM
+	struct obj_cgroup	**obj_cgroups;	/* vector of object cgroups */
+#endif
 
 	int			nr_pages;	/* # of pages served by this chunk */
 	int			nr_populated;	/* # of populated pages */
@@ -63,7 +85,7 @@ struct pcpu_chunk {
 
 extern spinlock_t pcpu_lock;
 
-extern struct list_head *pcpu_slot;
+extern struct list_head *pcpu_chunk_lists;
 extern int pcpu_nr_slots;
 extern int pcpu_nr_empty_pop_pages;
 
@@ -106,6 +128,37 @@ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk)
 	return pcpu_nr_pages_to_map_bits(chunk->nr_pages);
 }
 
+#ifdef CONFIG_MEMCG_KMEM
+static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk)
+{
+	if (chunk->obj_cgroups)
+		return PCPU_CHUNK_MEMCG;
+	return PCPU_CHUNK_ROOT;
+}
+
+static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type)
+{
+	return chunk_type == PCPU_CHUNK_MEMCG;
+}
+
+#else
+static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk)
+{
+	return PCPU_CHUNK_ROOT;
+}
+
+static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type)
+{
+	return false;
+}
+#endif
+
+static inline struct list_head *pcpu_chunk_list(enum pcpu_chunk_type chunk_type)
+{
+	return &pcpu_chunk_lists[pcpu_nr_slots *
+				 pcpu_is_memcg_chunk(chunk_type)];
+}
+
 #ifdef CONFIG_PERCPU_STATS
 
 #include <linux/spinlock.h>
diff --git a/mm/percpu-km.c b/mm/percpu-km.c
index 20d2b69a13b0..35c9941077ee 100644
--- a/mm/percpu-km.c
+++ b/mm/percpu-km.c
@@ -44,7 +44,8 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
 	/* nada */
 }
 
-static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
+static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type,
+					    gfp_t gfp)
 {
 	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;
 	struct pcpu_chunk *chunk;
@@ -52,7 +53,7 @@ static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
 	unsigned long flags;
 	int i;
 
-	chunk = pcpu_alloc_chunk(gfp);
+	chunk = pcpu_alloc_chunk(type, gfp);
 	if (!chunk)
 		return NULL;
 
diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c
index 32558063c3f9..c8400a2adbc2 100644
--- a/mm/percpu-stats.c
+++ b/mm/percpu-stats.c
@@ -34,11 +34,15 @@ static int find_max_nr_alloc(void)
 {
 	struct pcpu_chunk *chunk;
 	int slot, max_nr_alloc;
+	enum pcpu_chunk_type type;
 
 	max_nr_alloc = 0;
-	for (slot = 0; slot < pcpu_nr_slots; slot++)
-		list_for_each_entry(chunk, &pcpu_slot[slot], list)
-			max_nr_alloc = max(max_nr_alloc, chunk->nr_alloc);
+	for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
+		for (slot = 0; slot < pcpu_nr_slots; slot++)
+			list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot],
+					    list)
+				max_nr_alloc = max(max_nr_alloc,
+						   chunk->nr_alloc);
 
 	return max_nr_alloc;
 }
@@ -129,6 +133,9 @@ static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk,
 	P("cur_min_alloc", cur_min_alloc);
 	P("cur_med_alloc", cur_med_alloc);
 	P("cur_max_alloc", cur_max_alloc);
+#ifdef CONFIG_MEMCG_KMEM
+	P("memcg_aware", pcpu_is_memcg_chunk(pcpu_chunk_type(chunk)));
+#endif
 	seq_putc(m, '\n');
 }
 
@@ -137,6 +144,7 @@ static int percpu_stats_show(struct seq_file *m, void *v)
 	struct pcpu_chunk *chunk;
 	int slot, max_nr_alloc;
 	int *buffer;
+	enum pcpu_chunk_type type;
 
 alloc_buffer:
 	spin_lock_irq(&pcpu_lock);
@@ -202,18 +210,18 @@ static int percpu_stats_show(struct seq_file *m, void *v)
 		chunk_map_stats(m, pcpu_reserved_chunk, buffer);
 	}
 
-	for (slot = 0; slot < pcpu_nr_slots; slot++) {
-		list_for_each_entry(chunk, &pcpu_slot[slot], list) {
-			if (chunk == pcpu_first_chunk) {
-				seq_puts(m, "Chunk: <- First Chunk\n");
-				chunk_map_stats(m, chunk, buffer);
-
-
-			} else {
-				seq_puts(m, "Chunk:\n");
-				chunk_map_stats(m, chunk, buffer);
+	for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) {
+		for (slot = 0; slot < pcpu_nr_slots; slot++) {
+			list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot],
+					    list) {
+				if (chunk == pcpu_first_chunk) {
+					seq_puts(m, "Chunk: <- First Chunk\n");
+					chunk_map_stats(m, chunk, buffer);
+				} else {
+					seq_puts(m, "Chunk:\n");
+					chunk_map_stats(m, chunk, buffer);
+				}
 			}
-
 		}
 	}
 
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index a2b395acef89..e46f7a6917f9 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -328,12 +328,13 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
 	pcpu_free_pages(chunk, pages, page_start, page_end);
 }
 
-static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
+static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type,
+					    gfp_t gfp)
 {
 	struct pcpu_chunk *chunk;
 	struct vm_struct **vms;
 
-	chunk = pcpu_alloc_chunk(gfp);
+	chunk = pcpu_alloc_chunk(type, gfp);
 	if (!chunk)
 		return NULL;
 
diff --git a/mm/percpu.c b/mm/percpu.c
index 5e9eefdce21f..dc1a213293aa 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -37,9 +37,14 @@
  * takes care of normal allocations.
  *
  * The allocator organizes chunks into lists according to free size and
- * tries to allocate from the fullest chunk first.  Each chunk is managed
- * by a bitmap with metadata blocks.  The allocation map is updated on
- * every allocation and free to reflect the current state while the boundary
+ * memcg-awareness.  To make a percpu allocation memcg-aware the __GFP_ACCOUNT
+ * flag should be passed.  All memcg-aware allocations are sharing one set
+ * of chunks and all unaccounted allocations and allocations performed
+ * by processes belonging to the root memory cgroup are using the second set.
+ *
+ * The allocator tries to allocate from the fullest chunk first. Each chunk
+ * is managed by a bitmap with metadata blocks.  The allocation map is updated
+ * on every allocation and free to reflect the current state while the boundary
  * map is only updated on allocation.  Each metadata block contains
  * information to help mitigate the need to iterate over large portions
  * of the bitmap.  The reverse mapping from page to chunk is stored in
@@ -81,6 +86,7 @@
 #include <linux/kmemleak.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/memcontrol.h>
 
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
@@ -160,7 +166,7 @@ struct pcpu_chunk *pcpu_reserved_chunk __ro_after_init;
 DEFINE_SPINLOCK(pcpu_lock);	/* all internal data structures */
 static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop, map ext */
 
-struct list_head *pcpu_slot __ro_after_init; /* chunk list slots */
+struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */
 
 /* chunks which need their map areas extended, protected by pcpu_lock */
 static LIST_HEAD(pcpu_map_extend_chunks);
@@ -500,6 +506,9 @@ static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot,
 			      bool move_front)
 {
 	if (chunk != pcpu_reserved_chunk) {
+		struct list_head *pcpu_slot;
+
+		pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk));
 		if (move_front)
 			list_move(&chunk->list, &pcpu_slot[slot]);
 		else
@@ -1341,6 +1350,10 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 		panic("%s: Failed to allocate %zu bytes\n", __func__,
 		      alloc_size);
 
+#ifdef CONFIG_MEMCG_KMEM
+	/* first chunk isn't memcg-aware */
+	chunk->obj_cgroups = NULL;
+#endif
 	pcpu_init_md_blocks(chunk);
 
 	/* manage populated page bitmap */
@@ -1380,7 +1393,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 	return chunk;
 }
 
-static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp)
+static struct pcpu_chunk *pcpu_alloc_chunk(enum pcpu_chunk_type type, gfp_t gfp)
 {
 	struct pcpu_chunk *chunk;
 	int region_bits;
@@ -1408,6 +1421,16 @@ static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp)
 	if (!chunk->md_blocks)
 		goto md_blocks_fail;
 
+#ifdef CONFIG_MEMCG_KMEM
+	if (pcpu_is_memcg_chunk(type)) {
+		chunk->obj_cgroups =
+			pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) *
+					sizeof(struct obj_cgroup *), gfp);
+		if (!chunk->obj_cgroups)
+			goto objcg_fail;
+	}
+#endif
+
 	pcpu_init_md_blocks(chunk);
 
 	/* init metadata */
@@ -1415,6 +1438,10 @@ static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp)
 
 	return chunk;
 
+#ifdef CONFIG_MEMCG_KMEM
+objcg_fail:
+	pcpu_mem_free(chunk->md_blocks);
+#endif
 md_blocks_fail:
 	pcpu_mem_free(chunk->bound_map);
 bound_map_fail:
@@ -1429,6 +1456,9 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk)
 {
 	if (!chunk)
 		return;
+#ifdef CONFIG_MEMCG_KMEM
+	pcpu_mem_free(chunk->obj_cgroups);
+#endif
 	pcpu_mem_free(chunk->md_blocks);
 	pcpu_mem_free(chunk->bound_map);
 	pcpu_mem_free(chunk->alloc_map);
@@ -1505,7 +1535,8 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
 			       int page_start, int page_end, gfp_t gfp);
 static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
 				  int page_start, int page_end);
-static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp);
+static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type,
+					    gfp_t gfp);
 static void pcpu_destroy_chunk(struct pcpu_chunk *chunk);
 static struct page *pcpu_addr_to_page(void *addr);
 static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai);
@@ -1547,6 +1578,77 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 	return pcpu_get_page_chunk(pcpu_addr_to_page(addr));
 }
 
+#ifdef CONFIG_MEMCG_KMEM
+static enum pcpu_chunk_type pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp,
+						     struct obj_cgroup **objcgp)
+{
+	struct obj_cgroup *objcg;
+
+	if (!memcg_kmem_enabled() || !(gfp & __GFP_ACCOUNT) ||
+	    memcg_kmem_bypass())
+		return PCPU_CHUNK_ROOT;
+
+	objcg = get_obj_cgroup_from_current();
+	if (!objcg)
+		return PCPU_CHUNK_ROOT;
+
+	if (obj_cgroup_charge(objcg, gfp, size * num_possible_cpus())) {
+		obj_cgroup_put(objcg);
+		return PCPU_FAIL_ALLOC;
+	}
+
+	*objcgp = objcg;
+	return PCPU_CHUNK_MEMCG;
+}
+
+static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg,
+				       struct pcpu_chunk *chunk, int off,
+				       size_t size)
+{
+	if (!objcg)
+		return;
+
+	if (chunk) {
+		chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg;
+	} else {
+		obj_cgroup_uncharge(objcg, size * num_possible_cpus());
+		obj_cgroup_put(objcg);
+	}
+}
+
+static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
+{
+	struct obj_cgroup *objcg;
+
+	if (!pcpu_is_memcg_chunk(pcpu_chunk_type(chunk)))
+		return;
+
+	objcg = chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT];
+	chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = NULL;
+
+	obj_cgroup_uncharge(objcg, size * num_possible_cpus());
+
+	obj_cgroup_put(objcg);
+}
+
+#else /* CONFIG_MEMCG_KMEM */
+static enum pcpu_chunk_type
+pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp)
+{
+	return PCPU_CHUNK_ROOT;
+}
+
+static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg,
+				       struct pcpu_chunk *chunk, int off,
+				       size_t size)
+{
+}
+
+static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
 /**
  * pcpu_alloc - the percpu allocator
  * @size: size of area to allocate in bytes
@@ -1568,6 +1670,9 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 	gfp_t pcpu_gfp;
 	bool is_atomic;
 	bool do_warn;
+	enum pcpu_chunk_type type;
+	struct list_head *pcpu_slot;
+	struct obj_cgroup *objcg = NULL;
 	static int warn_limit = 10;
 	struct pcpu_chunk *chunk, *next;
 	const char *err;
@@ -1602,16 +1707,23 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 		return NULL;
 	}
 
+	type = pcpu_memcg_pre_alloc_hook(size, gfp, &objcg);
+	if (unlikely(type == PCPU_FAIL_ALLOC))
+		return NULL;
+	pcpu_slot = pcpu_chunk_list(type);
+
 	if (!is_atomic) {
 		/*
 		 * pcpu_balance_workfn() allocates memory under this mutex,
 		 * and it may wait for memory reclaim. Allow current task
 		 * to become OOM victim, in case of memory pressure.
 		 */
-		if (gfp & __GFP_NOFAIL)
+		if (gfp & __GFP_NOFAIL) {
 			mutex_lock(&pcpu_alloc_mutex);
-		else if (mutex_lock_killable(&pcpu_alloc_mutex))
+		} else if (mutex_lock_killable(&pcpu_alloc_mutex)) {
+			pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size);
 			return NULL;
+		}
 	}
 
 	spin_lock_irqsave(&pcpu_lock, flags);
@@ -1666,7 +1778,7 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 	}
 
 	if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
-		chunk = pcpu_create_chunk(pcpu_gfp);
+		chunk = pcpu_create_chunk(type, pcpu_gfp);
 		if (!chunk) {
 			err = "failed to allocate new chunk";
 			goto fail;
@@ -1723,6 +1835,8 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 	trace_percpu_alloc_percpu(reserved, is_atomic, size, align,
 			chunk->base_addr, off, ptr);
 
+	pcpu_memcg_post_alloc_hook(objcg, chunk, off, size);
+
 	return ptr;
 
 fail_unlock:
@@ -1744,6 +1858,9 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 	} else {
 		mutex_unlock(&pcpu_alloc_mutex);
 	}
+
+	pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size);
+
 	return NULL;
 }
 
@@ -1803,8 +1920,8 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
 }
 
 /**
- * pcpu_balance_workfn - manage the amount of free chunks and populated pages
- * @work: unused
+ * __pcpu_balance_workfn - manage the amount of free chunks and populated pages
+ * @type: chunk type
  *
  * Reclaim all fully free chunks except for the first one.  This is also
  * responsible for maintaining the pool of empty populated pages.  However,
@@ -1813,11 +1930,12 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
  * allocation causes the failure as it is possible that requests can be
  * serviced from already backed regions.
  */
-static void pcpu_balance_workfn(struct work_struct *work)
+static void __pcpu_balance_workfn(enum pcpu_chunk_type type)
 {
 	/* gfp flags passed to underlying allocators */
 	const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
 	LIST_HEAD(to_free);
+	struct list_head *pcpu_slot = pcpu_chunk_list(type);
 	struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1];
 	struct pcpu_chunk *chunk, *next;
 	int slot, nr_to_pop, ret;
@@ -1915,7 +2033,7 @@ static void pcpu_balance_workfn(struct work_struct *work)
 
 	if (nr_to_pop) {
 		/* ran out of chunks to populate, create a new one and retry */
-		chunk = pcpu_create_chunk(gfp);
+		chunk = pcpu_create_chunk(type, gfp);
 		if (chunk) {
 			spin_lock_irq(&pcpu_lock);
 			pcpu_chunk_relocate(chunk, -1);
@@ -1927,6 +2045,20 @@ static void pcpu_balance_workfn(struct work_struct *work)
 	mutex_unlock(&pcpu_alloc_mutex);
 }
 
+/**
+ * pcpu_balance_workfn - manage the amount of free chunks and populated pages
+ * @work: unused
+ *
+ * Call __pcpu_balance_workfn() for each chunk type.
+ */
+static void pcpu_balance_workfn(struct work_struct *work)
+{
+	enum pcpu_chunk_type type;
+
+	for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
+		__pcpu_balance_workfn(type);
+}
+
 /**
  * free_percpu - free percpu area
  * @ptr: pointer to area to free
@@ -1941,8 +2073,9 @@ void free_percpu(void __percpu *ptr)
 	void *addr;
 	struct pcpu_chunk *chunk;
 	unsigned long flags;
-	int off;
+	int size, off;
 	bool need_balance = false;
+	struct list_head *pcpu_slot;
 
 	if (!ptr)
 		return;
@@ -1956,7 +2089,11 @@ void free_percpu(void __percpu *ptr)
 	chunk = pcpu_chunk_addr_search(addr);
 	off = addr - chunk->base_addr;
 
-	pcpu_free_area(chunk, off);
+	size = pcpu_free_area(chunk, off);
+
+	pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk));
+
+	pcpu_memcg_free_hook(chunk, off, size);
 
 	/* if there are more than one fully free chunks, wake up grim reaper */
 	if (chunk->free_bytes == pcpu_unit_size) {
@@ -2267,6 +2404,7 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	int map_size;
 	unsigned long tmp_addr;
 	size_t alloc_size;
+	enum pcpu_chunk_type type;
 
 #define PCPU_SETUP_BUG_ON(cond)	do {					\
 	if (unlikely(cond)) {						\
@@ -2384,13 +2522,18 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	 * empty chunks.
 	 */
 	pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2;
-	pcpu_slot = memblock_alloc(pcpu_nr_slots * sizeof(pcpu_slot[0]),
-				   SMP_CACHE_BYTES);
-	if (!pcpu_slot)
+	pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots *
+					  sizeof(pcpu_chunk_lists[0]) *
+					  PCPU_NR_CHUNK_TYPES,
+					  SMP_CACHE_BYTES);
+	if (!pcpu_chunk_lists)
 		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      pcpu_nr_slots * sizeof(pcpu_slot[0]));
-	for (i = 0; i < pcpu_nr_slots; i++)
-		INIT_LIST_HEAD(&pcpu_slot[i]);
+		      pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]) *
+		      PCPU_NR_CHUNK_TYPES);
+
+	for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
+		for (i = 0; i < pcpu_nr_slots; i++)
+			INIT_LIST_HEAD(&pcpu_chunk_list(type)[i]);
 
 	/*
 	 * The end of the static region needs to be aligned with the

From 772616b031f06e05846488b01dab46a7c832da13 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 11 Aug 2020 18:30:21 -0700
Subject: [PATCH 313/474] mm: memcg/percpu: per-memcg percpu memory statistics
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Percpu memory can represent a noticeable chunk of the total memory
consumption, especially on big machines with many CPUs.  Let's track
percpu memory usage for each memcg and display it in memory.stat.

A percpu allocation is usually scattered over multiple pages (and nodes),
and can be significantly smaller than a page.  So let's add a byte-sized
counter on the memcg level: MEMCG_PERCPU_B.  Byte-sized vmstat infra
created for slabs can be perfectly reused for percpu case.

[guro@fb.com: v3]
  Link: http://lkml.kernel.org/r/20200623184515.4132564-4-guro@fb.com

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Dennis Zhou <dennis@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Tobin C. Harding <tobin@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Waiman Long <longman@redhat.com>
Cc: Bixuan Cui <cuibixuan@huawei.com>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Link: http://lkml.kernel.org/r/20200608230819.832349-4-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/admin-guide/cgroup-v2.rst |  4 ++++
 include/linux/memcontrol.h              |  8 ++++++++
 mm/memcontrol.c                         |  4 +++-
 mm/percpu.c                             | 10 ++++++++++
 4 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index fa4018afa5a4..6be43781ec7f 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1274,6 +1274,10 @@ PAGE_SIZE multiple when read back.
 		Amount of memory used for storing in-kernel data
 		structures.
 
+	  percpu
+		Amount of memory used for storing per-cpu kernel
+		data structures.
+
 	  sock
 		Amount of memory used in network transmission buffers
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1bb49b600310..2c2d301eac33 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -32,6 +32,7 @@ struct kmem_cache;
 enum memcg_stat_item {
 	MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS,
 	MEMCG_SOCK,
+	MEMCG_PERCPU_B,
 	MEMCG_NR_STAT,
 };
 
@@ -339,6 +340,13 @@ struct mem_cgroup {
 
 extern struct mem_cgroup *root_mem_cgroup;
 
+static __always_inline bool memcg_stat_item_in_bytes(int idx)
+{
+	if (idx == MEMCG_PERCPU_B)
+		return true;
+	return vmstat_item_in_bytes(idx);
+}
+
 static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 {
 	return (memcg == root_mem_cgroup);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8d9ceea7fe4d..36d5300f9b69 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -781,7 +781,7 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
 	if (mem_cgroup_disabled())
 		return;
 
-	if (vmstat_item_in_bytes(idx))
+	if (memcg_stat_item_in_bytes(idx))
 		threshold <<= PAGE_SHIFT;
 
 	x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
@@ -1488,6 +1488,8 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 	seq_buf_printf(&s, "slab %llu\n",
 		       (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE_B) +
 			     memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE_B)));
+	seq_buf_printf(&s, "percpu %llu\n",
+		       (u64)memcg_page_state(memcg, MEMCG_PERCPU_B));
 	seq_buf_printf(&s, "sock %llu\n",
 		       (u64)memcg_page_state(memcg, MEMCG_SOCK) *
 		       PAGE_SIZE);
diff --git a/mm/percpu.c b/mm/percpu.c
index dc1a213293aa..f4709629e6de 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1610,6 +1610,11 @@ static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg,
 
 	if (chunk) {
 		chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg;
+
+		rcu_read_lock();
+		mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
+				size * num_possible_cpus());
+		rcu_read_unlock();
 	} else {
 		obj_cgroup_uncharge(objcg, size * num_possible_cpus());
 		obj_cgroup_put(objcg);
@@ -1628,6 +1633,11 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
 
 	obj_cgroup_uncharge(objcg, size * num_possible_cpus());
 
+	rcu_read_lock();
+	mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
+			-(size * num_possible_cpus()));
+	rcu_read_unlock();
+
 	obj_cgroup_put(objcg);
 }
 

From 3e38e0aaca9eafb12b1c4b731d1c10975cbe7974 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 11 Aug 2020 18:30:25 -0700
Subject: [PATCH 314/474] mm: memcg: charge memcg percpu memory to the parent
 cgroup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Memory cgroups are using large chunks of percpu memory to store vmstat
data.  Yet this memory is not accounted at all, so in the case when there
are many (dying) cgroups, it's not exactly clear where all the memory is.

Because the size of memory cgroup internal structures can dramatically
exceed the size of object or page which is pinning it in the memory, it's
not a good idea to simply ignore it.  It actually breaks the isolation
between cgroups.

Let's account the consumed percpu memory to the parent cgroup.

[guro@fb.com: add WARN_ON_ONCE()s, per Johannes]
  Link: http://lkml.kernel.org/r/20200811170611.GB1507044@carbon.DHCP.thefacebook.com

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Dennis Zhou <dennis@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Tobin C. Harding <tobin@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Waiman Long <longman@redhat.com>
Cc: Bixuan Cui <cuibixuan@huawei.com>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Link: http://lkml.kernel.org/r/20200623184515.4132564-5-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memcontrol.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 36d5300f9b69..f1fd265b9f9e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5131,13 +5131,18 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return 1;
 
-	pn->lruvec_stat_local = alloc_percpu(struct lruvec_stat);
+	/* We charge the parent cgroup, never the current task */
+	WARN_ON_ONCE(!current->active_memcg);
+
+	pn->lruvec_stat_local = alloc_percpu_gfp(struct lruvec_stat,
+						 GFP_KERNEL_ACCOUNT);
 	if (!pn->lruvec_stat_local) {
 		kfree(pn);
 		return 1;
 	}
 
-	pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat);
+	pn->lruvec_stat_cpu = alloc_percpu_gfp(struct lruvec_stat,
+					       GFP_KERNEL_ACCOUNT);
 	if (!pn->lruvec_stat_cpu) {
 		free_percpu(pn->lruvec_stat_local);
 		kfree(pn);
@@ -5211,11 +5216,16 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 		goto fail;
 	}
 
-	memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu);
+	/* We charge the parent cgroup, never the current task */
+	WARN_ON_ONCE(!current->active_memcg);
+
+	memcg->vmstats_local = alloc_percpu_gfp(struct memcg_vmstats_percpu,
+						GFP_KERNEL_ACCOUNT);
 	if (!memcg->vmstats_local)
 		goto fail;
 
-	memcg->vmstats_percpu = alloc_percpu(struct memcg_vmstats_percpu);
+	memcg->vmstats_percpu = alloc_percpu_gfp(struct memcg_vmstats_percpu,
+						 GFP_KERNEL_ACCOUNT);
 	if (!memcg->vmstats_percpu)
 		goto fail;
 
@@ -5264,7 +5274,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	struct mem_cgroup *memcg;
 	long error = -ENOMEM;
 
+	memalloc_use_memcg(parent);
 	memcg = mem_cgroup_alloc();
+	memalloc_unuse_memcg();
 	if (IS_ERR(memcg))
 		return ERR_CAST(memcg);
 

From 90631e1dea55bfc14a8ee8c594aa136b243d4c88 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 11 Aug 2020 18:30:29 -0700
Subject: [PATCH 315/474] kselftests: cgroup: add perpcu memory accounting test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a simple test to check the percpu memory accounting.  The test creates
a cgroup tree with 1000 child cgroups and checks values of memory.current
and memory.stat::percpu.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Tobin C. Harding <tobin@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Waiman Long <longman@redhat.com>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Bixuan Cui <cuibixuan@huawei.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Link: http://lkml.kernel.org/r/20200608230819.832349-6-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/cgroup/test_kmem.c | 70 +++++++++++++++++++++-
 1 file changed, 69 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index 5224dae216e5..0941aa16157e 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -18,6 +18,15 @@
 #include "cgroup_util.h"
 
 
+/*
+ * Memory cgroup charging and vmstat data aggregation is performed using
+ * percpu batches 32 pages big (look at MEMCG_CHARGE_BATCH). So the maximum
+ * discrepancy between charge and vmstat entries is number of cpus multiplied
+ * by 32 pages multiplied by 2.
+ */
+#define MAX_VMSTAT_ERROR (4096 * 32 * 2 * get_nprocs())
+
+
 static int alloc_dcache(const char *cgroup, void *arg)
 {
 	unsigned long i;
@@ -180,7 +189,7 @@ static int test_kmem_memcg_deletion(const char *root)
 		goto cleanup;
 
 	sum = slab + anon + file + kernel_stack;
-	if (abs(sum - current) < 4096 * 32 * 2 * get_nprocs()) {
+	if (abs(sum - current) < MAX_VMSTAT_ERROR) {
 		ret = KSFT_PASS;
 	} else {
 		printf("memory.current = %ld\n", current);
@@ -331,6 +340,64 @@ static int test_kmem_dead_cgroups(const char *root)
 	return ret;
 }
 
+/*
+ * This test creates a sub-tree with 1000 memory cgroups.
+ * Then it checks that the memory.current on the parent level
+ * is greater than 0 and approximates matches the percpu value
+ * from memory.stat.
+ */
+static int test_percpu_basic(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent, *child;
+	long current, percpu;
+	int i;
+
+	parent = cg_name(root, "percpu_basic_test");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	for (i = 0; i < 1000; i++) {
+		child = cg_name_indexed(parent, "child", i);
+		if (!child)
+			return -1;
+
+		if (cg_create(child))
+			goto cleanup_children;
+
+		free(child);
+	}
+
+	current = cg_read_long(parent, "memory.current");
+	percpu = cg_read_key_long(parent, "memory.stat", "percpu ");
+
+	if (current > 0 && percpu > 0 && abs(current - percpu) <
+	    MAX_VMSTAT_ERROR)
+		ret = KSFT_PASS;
+	else
+		printf("memory.current %ld\npercpu %ld\n",
+		       current, percpu);
+
+cleanup_children:
+	for (i = 0; i < 1000; i++) {
+		child = cg_name_indexed(parent, "child", i);
+		cg_destroy(child);
+		free(child);
+	}
+
+cleanup:
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
 #define T(x) { x, #x }
 struct kmem_test {
 	int (*fn)(const char *root);
@@ -341,6 +408,7 @@ struct kmem_test {
 	T(test_kmem_proc_kpagecgroup),
 	T(test_kmem_kernel_stacks),
 	T(test_kmem_dead_cgroups),
+	T(test_percpu_basic),
 };
 #undef T
 

From 8ca39e6874f812a393bb66d9fdbb7598d5f0451c Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Tue, 11 Aug 2020 18:30:32 -0700
Subject: [PATCH 316/474] mm/hugetlb: add mempolicy check in the reservation
 routine

In the reservation routine, we only check whether the cpuset meets the
memory allocation requirements.  But we ignore the mempolicy of MPOL_BIND
case.  If someone mmap hugetlb succeeds, but the subsequent memory
allocation may fail due to mempolicy restrictions and receives the SIGBUS
signal.  This can be reproduced by the follow steps.

 1) Compile the test case.
    cd tools/testing/selftests/vm/
    gcc map_hugetlb.c -o map_hugetlb

 2) Pre-allocate huge pages. Suppose there are 2 numa nodes in the
    system. Each node will pre-allocate one huge page.
    echo 2 > /proc/sys/vm/nr_hugepages

 3) Run test case(mmap 4MB). We receive the SIGBUS signal.
    numactl --membind=3D0 ./map_hugetlb 4

With this patch applied, the mmap will fail in the step 3) and throw
"mmap: Cannot allocate memory".

[akpm@linux-foundation.org: include sched.h for `current']

Reported-by: Jianchao Guo <guojianchao@bytedance.com>
Suggested-by: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michel Lespinasse <walken@google.com>
Cc: Baoquan He <bhe@redhat.com>
Link: http://lkml.kernel.org/r/20200728034938.14993-1-songmuchun@bytedance.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mempolicy.h | 16 +++++++++++++++-
 mm/hugetlb.c              | 22 ++++++++++++++++++----
 mm/mempolicy.c            |  2 +-
 3 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index ea9c15b60a96..5f1648c23e29 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -6,7 +6,7 @@
 #ifndef _LINUX_MEMPOLICY_H
 #define _LINUX_MEMPOLICY_H 1
 
-
+#include <linux/sched.h>
 #include <linux/mmzone.h>
 #include <linux/dax.h>
 #include <linux/slab.h>
@@ -152,6 +152,15 @@ extern int huge_node(struct vm_area_struct *vma,
 extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
 extern bool mempolicy_nodemask_intersects(struct task_struct *tsk,
 				const nodemask_t *mask);
+extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy);
+
+static inline nodemask_t *policy_nodemask_current(gfp_t gfp)
+{
+	struct mempolicy *mpol = get_task_policy(current);
+
+	return policy_nodemask(gfp, mpol);
+}
+
 extern unsigned int mempolicy_slab_node(void);
 
 extern enum zone_type policy_zone;
@@ -281,5 +290,10 @@ static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
 static inline void mpol_put_task_policy(struct task_struct *task)
 {
 }
+
+static inline nodemask_t *policy_nodemask_current(gfp_t gfp)
+{
+	return NULL;
+}
 #endif /* CONFIG_NUMA */
 #endif
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e52c878940bb..dffafb5bf2ed 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3458,13 +3458,21 @@ static int __init default_hugepagesz_setup(char *s)
 }
 __setup("default_hugepagesz=", default_hugepagesz_setup);
 
-static unsigned int cpuset_mems_nr(unsigned int *array)
+static unsigned int allowed_mems_nr(struct hstate *h)
 {
 	int node;
 	unsigned int nr = 0;
+	nodemask_t *mpol_allowed;
+	unsigned int *array = h->free_huge_pages_node;
+	gfp_t gfp_mask = htlb_alloc_mask(h);
 
-	for_each_node_mask(node, cpuset_current_mems_allowed)
-		nr += array[node];
+	mpol_allowed = policy_nodemask_current(gfp_mask);
+
+	for_each_node_mask(node, cpuset_current_mems_allowed) {
+		if (!mpol_allowed ||
+		    (mpol_allowed && node_isset(node, *mpol_allowed)))
+			nr += array[node];
+	}
 
 	return nr;
 }
@@ -3643,12 +3651,18 @@ static int hugetlb_acct_memory(struct hstate *h, long delta)
 	 * we fall back to check against current free page availability as
 	 * a best attempt and hopefully to minimize the impact of changing
 	 * semantics that cpuset has.
+	 *
+	 * Apart from cpuset, we also have memory policy mechanism that
+	 * also determines from which node the kernel will allocate memory
+	 * in a NUMA system. So similar to cpuset, we also should consider
+	 * the memory policy of the current task. Similar to the description
+	 * above.
 	 */
 	if (delta > 0) {
 		if (gather_surplus_pages(h, delta) < 0)
 			goto out;
 
-		if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
+		if (delta > allowed_mems_nr(h)) {
 			return_unused_surplus_pages(h, delta);
 			goto out;
 		}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index b9e85d467352..7af44d7cdd11 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1890,7 +1890,7 @@ static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
  * Return a nodemask representing a mempolicy for filtering nodes for
  * page allocation
  */
-static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
+nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
 {
 	/* Lower zones don't get a nodemask applied for MPOL_BIND */
 	if (unlikely(policy->mode == MPOL_BIND) &&

From ccc5dc67340c109e624e07e02790e9fbdec900d6 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:30:36 -0700
Subject: [PATCH 317/474] mm/vmscan: make active/inactive ratio as 1:1 for anon
 lru

Patch series "workingset protection/detection on the anonymous LRU list", v7.

* PROBLEM
In current implementation, newly created or swap-in anonymous page is
started on the active list.  Growing the active list results in
rebalancing active/inactive list so old pages on the active list are
demoted to the inactive list.  Hence, hot page on the active list isn't
protected at all.

Following is an example of this situation.

Assume that 50 hot pages on active list and system can contain total 100
pages.  Numbers denote the number of pages on active/inactive list (active
| inactive).  (h) stands for hot pages and (uo) stands for used-once
pages.

1. 50 hot pages on active list
50(h) | 0

2. workload: 50 newly created (used-once) pages
50(uo) | 50(h)

3. workload: another 50 newly created (used-once) pages
50(uo) | 50(uo), swap-out 50(h)

As we can see, hot pages are swapped-out and it would cause swap-in later.

* SOLUTION
Since this is what we want to avoid, this patchset implements workingset
protection.  Like as the file LRU list, newly created or swap-in anonymous
page is started on the inactive list.  Also, like as the file LRU list, if
enough reference happens, the page will be promoted.  This simple
modification changes the above example as following.

1. 50 hot pages on active list
50(h) | 0

2. workload: 50 newly created (used-once) pages
50(h) | 50(uo)

3. workload: another 50 newly created (used-once) pages
50(h) | 50(uo), swap-out 50(uo)

hot pages remains in the active list. :)

* EXPERIMENT
I tested this scenario on my test bed and confirmed that this problem
happens on current implementation. I also checked that it is fixed by
this patchset.

* SUBJECT
workingset detection

* PROBLEM
Later part of the patchset implements the workingset detection for the
anonymous LRU list.  There is a corner case that workingset protection
could cause thrashing.  If we can avoid thrashing by workingset detection,
we can get the better performance.

Following is an example of thrashing due to the workingset protection.

1. 50 hot pages on active list
50(h) | 0

2. workload: 50 newly created (will be hot) pages
50(h) | 50(wh)

3. workload: another 50 newly created (used-once) pages
50(h) | 50(uo), swap-out 50(wh)

4. workload: 50 (will be hot) pages
50(h) | 50(wh), swap-in 50(wh)

5. workload: another 50 newly created (used-once) pages
50(h) | 50(uo), swap-out 50(wh)

6. repeat 4, 5

Without workingset detection, this kind of workload cannot be promoted and
thrashing happens forever.

* SOLUTION
Therefore, this patchset implements workingset detection.  All the
infrastructure for workingset detecion is already implemented, so there is
not much work to do.  First, extend workingset detection code to deal with
the anonymous LRU list.  Then, make swap cache handles the exceptional
value for the shadow entry.  Lastly, install/retrieve the shadow value
into/from the swap cache and check the refault distance.

* EXPERIMENT
I made a test program to imitates above scenario and confirmed that
problem exists.  Then, I checked that this patchset fixes it.

My test setup is a virtual machine with 8 cpus and 6100MB memory.  But,
the amount of the memory that the test program can use is about 280 MB.
This is because the system uses large ram-backed swap and large ramdisk to
capture the trace.

Test scenario is like as below.

1. allocate cold memory (512MB)
2. allocate hot-1 memory (96MB)
3. activate hot-1 memory (96MB)
4. allocate another hot-2 memory (96MB)
5. access cold memory (128MB)
6. access hot-2 memory (96MB)
7. repeat 5, 6

Since hot-1 memory (96MB) is on the active list, the inactive list can
contains roughly 190MB pages.  hot-2 memory's re-access interval (96+128
MB) is more 190MB, so it cannot be promoted without workingset detection
and swap-in/out happens repeatedly.  With this patchset, workingset
detection works and promotion happens.  Therefore, swap-in/out occurs
less.

Here is the result. (average of 5 runs)

type swap-in swap-out
base 863240 989945
patch 681565 809273

As we can see, patched kernel do less swap-in/out.

* OVERALL TEST (ebizzy using modified random function)
ebizzy is the test program that main thread allocates lots of memory and
child threads access them randomly during the given times.  Swap-in will
happen if allocated memory is larger than the system memory.

The random function that represents the zipf distribution is used to make
hot/cold memory.  Hot/cold ratio is controlled by the parameter.  If the
parameter is high, hot memory is accessed much larger than cold one.  If
the parameter is low, the number of access on each memory would be
similar.  I uses various parameters in order to show the effect of
patchset on various hot/cold ratio workload.

My test setup is a virtual machine with 8 cpus, 1024 MB memory and 5120 MB
ram swap.

Result format is as following.

param: 1-1024-0.1
- 1 (number of thread)
- 1024 (allocated memory size, MB)
- 0.1 (zipf distribution alpha,
0.1 works like as roughly uniform random,
1.3 works like as small portion of memory is hot and the others are cold)

pswpin: smaller is better
std: standard deviation
improvement: negative is better

* single thread
           param        pswpin       std       improvement
      base 1-1024.0-0.1 14101983.40   79441.19
      prot 1-1024.0-0.1 14065875.80  136413.01  (   -0.26 )
    detect 1-1024.0-0.1 13910435.60  100804.82  (   -1.36 )
      base 1-1024.0-0.7 7998368.80   43469.32
      prot 1-1024.0-0.7 7622245.80   88318.74  (   -4.70 )
    detect 1-1024.0-0.7 7618515.20   59742.07  (   -4.75 )
      base 1-1024.0-1.3 1017400.80   38756.30
      prot 1-1024.0-1.3  940464.60   29310.69  (   -7.56 )
    detect 1-1024.0-1.3  945511.40   24579.52  (   -7.07 )
      base 1-1280.0-0.1 22895541.40   50016.08
      prot 1-1280.0-0.1 22860305.40   51952.37  (   -0.15 )
    detect 1-1280.0-0.1 22705565.20   93380.35  (   -0.83 )
      base 1-1280.0-0.7 13717645.60   46250.65
      prot 1-1280.0-0.7 12935355.80   64754.43  (   -5.70 )
    detect 1-1280.0-0.7 13040232.00   63304.00  (   -4.94 )
      base 1-1280.0-1.3 1654251.40    4159.68
      prot 1-1280.0-1.3 1522680.60   33673.50  (   -7.95 )
    detect 1-1280.0-1.3 1599207.00   70327.89  (   -3.33 )
      base 1-1536.0-0.1 31621775.40   31156.28
      prot 1-1536.0-0.1 31540355.20   62241.36  (   -0.26 )
    detect 1-1536.0-0.1 31420056.00  123831.27  (   -0.64 )
      base 1-1536.0-0.7 19620760.60   60937.60
      prot 1-1536.0-0.7 18337839.60   56102.58  (   -6.54 )
    detect 1-1536.0-0.7 18599128.00   75289.48  (   -5.21 )
      base 1-1536.0-1.3 2378142.40   20994.43
      prot 1-1536.0-1.3 2166260.60   48455.46  (   -8.91 )
    detect 1-1536.0-1.3 2183762.20   16883.24  (   -8.17 )
      base 1-1792.0-0.1 40259714.80   90750.70
      prot 1-1792.0-0.1 40053917.20   64509.47  (   -0.51 )
    detect 1-1792.0-0.1 39949736.40  104989.64  (   -0.77 )
      base 1-1792.0-0.7 25704884.40   69429.68
      prot 1-1792.0-0.7 23937389.00   79945.60  (   -6.88 )
    detect 1-1792.0-0.7 24271902.00   35044.30  (   -5.57 )
      base 1-1792.0-1.3 3129497.00   32731.86
      prot 1-1792.0-1.3 2796994.40   19017.26  (  -10.62 )
    detect 1-1792.0-1.3 2886840.40   33938.82  (   -7.75 )
      base 1-2048.0-0.1 48746924.40   50863.88
      prot 1-2048.0-0.1 48631954.40   24537.30  (   -0.24 )
    detect 1-2048.0-0.1 48509419.80   27085.34  (   -0.49 )
      base 1-2048.0-0.7 32046424.40   78624.22
      prot 1-2048.0-0.7 29764182.20   86002.26  (   -7.12 )
    detect 1-2048.0-0.7 30250315.80  101282.14  (   -5.60 )
      base 1-2048.0-1.3 3916723.60   24048.55
      prot 1-2048.0-1.3 3490781.60   33292.61  (  -10.87 )
    detect 1-2048.0-1.3 3585002.20   44942.04  (   -8.47 )

* multi thread
           param        pswpin       std       improvement
      base 8-1024.0-0.1 16219822.60  329474.01
      prot 8-1024.0-0.1 15959494.00  654597.45  (   -1.61 )
    detect 8-1024.0-0.1 15773790.80  502275.25  (   -2.75 )
      base 8-1024.0-0.7 9174107.80  537619.33
      prot 8-1024.0-0.7 8571915.00  385230.08  (   -6.56 )
    detect 8-1024.0-0.7 8489484.20  364683.00  (   -7.46 )
      base 8-1024.0-1.3 1108495.60   83555.98
      prot 8-1024.0-1.3 1038906.20   63465.20  (   -6.28 )
    detect 8-1024.0-1.3  941817.80   32648.80  (  -15.04 )
      base 8-1280.0-0.1 25776114.20  450480.45
      prot 8-1280.0-0.1 25430847.00  465627.07  (   -1.34 )
    detect 8-1280.0-0.1 25282555.00  465666.55  (   -1.91 )
      base 8-1280.0-0.7 15218968.00  702007.69
      prot 8-1280.0-0.7 13957947.80  492643.86  (   -8.29 )
    detect 8-1280.0-0.7 14158331.20  238656.02  (   -6.97 )
      base 8-1280.0-1.3 1792482.80   30512.90
      prot 8-1280.0-1.3 1577686.40   34002.62  (  -11.98 )
    detect 8-1280.0-1.3 1556133.00   22944.79  (  -13.19 )
      base 8-1536.0-0.1 33923761.40  575455.85
      prot 8-1536.0-0.1 32715766.20  300633.51  (   -3.56 )
    detect 8-1536.0-0.1 33158477.40  117764.51  (   -2.26 )
      base 8-1536.0-0.7 20628907.80  303851.34
      prot 8-1536.0-0.7 19329511.20  341719.31  (   -6.30 )
    detect 8-1536.0-0.7 20013934.00  385358.66  (   -2.98 )
      base 8-1536.0-1.3 2588106.40  130769.20
      prot 8-1536.0-1.3 2275222.40   89637.06  (  -12.09 )
    detect 8-1536.0-1.3 2365008.40  124412.55  (   -8.62 )
      base 8-1792.0-0.1 43328279.20  946469.12
      prot 8-1792.0-0.1 41481980.80  525690.89  (   -4.26 )
    detect 8-1792.0-0.1 41713944.60  406798.93  (   -3.73 )
      base 8-1792.0-0.7 27155647.40  536253.57
      prot 8-1792.0-0.7 24989406.80  502734.52  (   -7.98 )
    detect 8-1792.0-0.7 25524806.40  263237.87  (   -6.01 )
      base 8-1792.0-1.3 3260372.80  137907.92
      prot 8-1792.0-1.3 2879187.80   63597.26  (  -11.69 )
    detect 8-1792.0-1.3 2892962.20   33229.13  (  -11.27 )
      base 8-2048.0-0.1 50583989.80  710121.48
      prot 8-2048.0-0.1 49599984.40  228782.42  (   -1.95 )
    detect 8-2048.0-0.1 50578596.00  660971.66  (   -0.01 )
      base 8-2048.0-0.7 33765479.60  812659.55
      prot 8-2048.0-0.7 30767021.20  462907.24  (   -8.88 )
    detect 8-2048.0-0.7 32213068.80  211884.24  (   -4.60 )
      base 8-2048.0-1.3 3941675.80   28436.45
      prot 8-2048.0-1.3 3538742.40   76856.08  (  -10.22 )
    detect 8-2048.0-1.3 3579397.80   58630.95  (   -9.19 )

As we can see, all the cases show improvement.  Especially, test case with
zipf distribution 1.3 show more improvements.  It means that if there is a
hot/cold tendency in anon pages, this patchset works better.

This patch (of 6):

Current implementation of LRU management for anonymous page has some
problems.  Most important one is that it doesn't protect the workingset,
that is, pages on the active LRU list.  Although, this problem will be
fixed in the following patchset, the preparation is required and this
patch does it.

What following patch does is to implement workingset protection.  After
the following patchset, newly created or swap-in pages will start their
lifetime on the inactive list.  If inactive list is too small, there is
not enough chance to be referenced and the page cannot become the
workingset.

In order to provide the newly anonymous or swap-in pages enough chance to
be referenced again, this patch makes active/inactive LRU ratio as 1:1.

This is just a temporary measure.  Later patch in the series introduces
workingset detection for anonymous LRU that will be used to better decide
if pages should start on the active and inactive list.  Afterwards this
patch is effectively reverted.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Matthew Wilcox <willy@infradead.org>
Link: http://lkml.kernel.org/r/1595490560-15117-1-git-send-email-iamjoonsoo.kim@lge.com
Link: http://lkml.kernel.org/r/1595490560-15117-2-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/vmscan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 72da290b171b..e34fc04b7045 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2208,7 +2208,7 @@ static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru)
 	active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru);
 
 	gb = (inactive + active) >> (30 - PAGE_SHIFT);
-	if (gb)
+	if (gb && is_file_lru(inactive_lru))
 		inactive_ratio = int_sqrt(10 * gb);
 	else
 		inactive_ratio = 1;

From b518154e59aab3ad0780a169c5cc84bd4ee4357e Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:30:40 -0700
Subject: [PATCH 318/474] mm/vmscan: protect the workingset on anonymous LRU

In current implementation, newly created or swap-in anonymous page is
started on active list.  Growing active list results in rebalancing
active/inactive list so old pages on active list are demoted to inactive
list.  Hence, the page on active list isn't protected at all.

Following is an example of this situation.

Assume that 50 hot pages on active list.  Numbers denote the number of
pages on active/inactive list (active | inactive).

1. 50 hot pages on active list
50(h) | 0

2. workload: 50 newly created (used-once) pages
50(uo) | 50(h)

3. workload: another 50 newly created (used-once) pages
50(uo) | 50(uo), swap-out 50(h)

This patch tries to fix this issue.  Like as file LRU, newly created or
swap-in anonymous pages will be inserted to the inactive list.  They are
promoted to active list if enough reference happens.  This simple
modification changes the above example as following.

1. 50 hot pages on active list
50(h) | 0

2. workload: 50 newly created (used-once) pages
50(h) | 50(uo)

3. workload: another 50 newly created (used-once) pages
50(h) | 50(uo), swap-out 50(uo)

As you can see, hot pages on active list would be protected.

Note that, this implementation has a drawback that the page cannot be
promoted and will be swapped-out if re-access interval is greater than the
size of inactive list but less than the size of total(active+inactive).
To solve this potential issue, following patch will apply workingset
detection similar to the one that's already applied to file LRU.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Link: http://lkml.kernel.org/r/1595490560-15117-3-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h    |  2 +-
 kernel/events/uprobes.c |  2 +-
 mm/huge_memory.c        |  2 +-
 mm/khugepaged.c         |  2 +-
 mm/memory.c             |  9 ++++-----
 mm/migrate.c            |  2 +-
 mm/swap.c               | 13 +++++++------
 mm/swapfile.c           |  2 +-
 mm/userfaultfd.c        |  2 +-
 mm/vmscan.c             |  4 +---
 10 files changed, 19 insertions(+), 21 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7eb59bc552a5..51ec9cdb92c0 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -352,7 +352,7 @@ extern void deactivate_page(struct page *page);
 extern void mark_page_lazyfree(struct page *page);
 extern void swap_setup(void);
 
-extern void lru_cache_add_active_or_unevictable(struct page *page,
+extern void lru_cache_add_inactive_or_unevictable(struct page *page,
 						struct vm_area_struct *vma);
 
 /* linux/mm/vmscan.c */
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 25de10c904e6..49047d479c57 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -184,7 +184,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	if (new_page) {
 		get_page(new_page);
 		page_add_new_anon_rmap(new_page, vma, addr, false);
-		lru_cache_add_active_or_unevictable(new_page, vma);
+		lru_cache_add_inactive_or_unevictable(new_page, vma);
 	} else
 		/* no new page, just dec_mm_counter for old_page */
 		dec_mm_counter(mm, MM_ANONPAGES);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 206f52b36ffb..863c495776d7 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -640,7 +640,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 		entry = mk_huge_pmd(page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		page_add_new_anon_rmap(page, vma, haddr, true);
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
 		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
 		add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index b52bd46ad146..15a9af791014 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1173,7 +1173,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	spin_lock(pmd_ptl);
 	BUG_ON(!pmd_none(*pmd));
 	page_add_new_anon_rmap(new_page, vma, address, true);
-	lru_cache_add_active_or_unevictable(new_page, vma);
+	lru_cache_add_inactive_or_unevictable(new_page, vma);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache_pmd(vma, address, pmd);
diff --git a/mm/memory.c b/mm/memory.c
index c39a13b09602..6fe8b5b22c57 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2715,7 +2715,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		 */
 		ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
 		page_add_new_anon_rmap(new_page, vma, vmf->address, false);
-		lru_cache_add_active_or_unevictable(new_page, vma);
+		lru_cache_add_inactive_or_unevictable(new_page, vma);
 		/*
 		 * We call the notify macro here because, when using secondary
 		 * mmu page tables (such as kvm shadow page tables), we want the
@@ -3266,10 +3266,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	/* ksm created a completely new copy */
 	if (unlikely(page != swapcache && swapcache)) {
 		page_add_new_anon_rmap(page, vma, vmf->address, false);
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
 		do_page_add_anon_rmap(page, vma, vmf->address, exclusive);
-		activate_page(page);
 	}
 
 	swap_free(entry);
@@ -3414,7 +3413,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 
 	inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 	page_add_new_anon_rmap(page, vma, vmf->address, false);
-	lru_cache_add_active_or_unevictable(page, vma);
+	lru_cache_add_inactive_or_unevictable(page, vma);
 setpte:
 	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
 
@@ -3672,7 +3671,7 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page)
 	if (write && !(vma->vm_flags & VM_SHARED)) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 		page_add_new_anon_rmap(page, vma, vmf->address, false);
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
 		inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
 		page_add_file_rmap(page, false);
diff --git a/mm/migrate.c b/mm/migrate.c
index d179657f8685..819e55130134 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2830,7 +2830,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 	inc_mm_counter(mm, MM_ANONPAGES);
 	page_add_new_anon_rmap(page, vma, addr, false);
 	if (!is_zone_device_page(page))
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 	get_page(page);
 
 	if (flush) {
diff --git a/mm/swap.c b/mm/swap.c
index de257c0a89b1..9285e60c7d6e 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -476,23 +476,24 @@ void lru_cache_add(struct page *page)
 EXPORT_SYMBOL(lru_cache_add);
 
 /**
- * lru_cache_add_active_or_unevictable
+ * lru_cache_add_inactive_or_unevictable
  * @page:  the page to be added to LRU
  * @vma:   vma in which page is mapped for determining reclaimability
  *
- * Place @page on the active or unevictable LRU list, depending on its
+ * Place @page on the inactive or unevictable LRU list, depending on its
  * evictability.  Note that if the page is not evictable, it goes
  * directly back onto it's zone's unevictable list, it does NOT use a
  * per cpu pagevec.
  */
-void lru_cache_add_active_or_unevictable(struct page *page,
+void lru_cache_add_inactive_or_unevictable(struct page *page,
 					 struct vm_area_struct *vma)
 {
+	bool unevictable;
+
 	VM_BUG_ON_PAGE(PageLRU(page), page);
 
-	if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED))
-		SetPageActive(page);
-	else if (!TestSetPageMlocked(page)) {
+	unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED;
+	if (unlikely(unevictable) && !TestSetPageMlocked(page)) {
 		/*
 		 * We use the irq-unsafe __mod_zone_page_stat because this
 		 * counter is not modified from interrupt context, and the pte
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6c26916e95fd..82183432fdd0 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1915,7 +1915,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		page_add_anon_rmap(page, vma, addr, false);
 	} else { /* ksm created a completely new copy */
 		page_add_new_anon_rmap(page, vma, addr, false);
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 	}
 	swap_free(entry);
 	/*
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index b80419320c7d..9a3d451402d7 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -123,7 +123,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 
 	inc_mm_counter(dst_mm, MM_ANONPAGES);
 	page_add_new_anon_rmap(page, dst_vma, dst_addr, false);
-	lru_cache_add_active_or_unevictable(page, dst_vma);
+	lru_cache_add_inactive_or_unevictable(page, dst_vma);
 
 	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e34fc04b7045..783cd7fdc61a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -998,8 +998,6 @@ static enum page_references page_check_references(struct page *page,
 		return PAGEREF_RECLAIM;
 
 	if (referenced_ptes) {
-		if (PageSwapBacked(page))
-			return PAGEREF_ACTIVATE;
 		/*
 		 * All mapped pages start out with page table
 		 * references from the instantiating fault, so we need
@@ -1022,7 +1020,7 @@ static enum page_references page_check_references(struct page *page,
 		/*
 		 * Activate file-backed executable pages after first usage.
 		 */
-		if (vm_flags & VM_EXEC)
+		if ((vm_flags & VM_EXEC) && !PageSwapBacked(page))
 			return PAGEREF_ACTIVATE;
 
 		return PAGEREF_KEEP;

From 170b04b7ae49634df103810dad67b22cf8a99aa6 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:30:43 -0700
Subject: [PATCH 319/474] mm/workingset: prepare the workingset detection
 infrastructure for anon LRU

To prepare the workingset detection for anon LRU, this patch splits
workingset event counters for refault, activate and restore into anon and
file variants, as well as the refaults counter in struct lruvec.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Link: http://lkml.kernel.org/r/1595490560-15117-4-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 16 +++++++++++-----
 mm/memcontrol.c        | 16 +++++++++++-----
 mm/vmscan.c            | 15 ++++++++++-----
 mm/vmstat.c            |  9 ++++++---
 mm/workingset.c        |  8 +++++---
 5 files changed, 43 insertions(+), 21 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 635a96cd9b1f..efbd95dd3bbf 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -173,9 +173,15 @@ enum node_stat_item {
 	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
 	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
 	WORKINGSET_NODES,
-	WORKINGSET_REFAULT,
-	WORKINGSET_ACTIVATE,
-	WORKINGSET_RESTORE,
+	WORKINGSET_REFAULT_BASE,
+	WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE,
+	WORKINGSET_REFAULT_FILE,
+	WORKINGSET_ACTIVATE_BASE,
+	WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE,
+	WORKINGSET_ACTIVATE_FILE,
+	WORKINGSET_RESTORE_BASE,
+	WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE,
+	WORKINGSET_RESTORE_FILE,
 	WORKINGSET_NODERECLAIM,
 	NR_ANON_MAPPED,	/* Mapped anonymous pages */
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
@@ -277,8 +283,8 @@ struct lruvec {
 	unsigned long			file_cost;
 	/* Non-resident age, driven by LRU movement */
 	atomic_long_t			nonresident_age;
-	/* Refaults at the time of last reclaim cycle */
-	unsigned long			refaults;
+	/* Refaults at the time of last reclaim cycle, anon=0, file=1 */
+	unsigned long			refaults[2];
 	/* Various lruvec state flags (enum lruvec_flags) */
 	unsigned long			flags;
 #ifdef CONFIG_MEMCG
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f1fd265b9f9e..c6c579217855 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1530,12 +1530,18 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGMAJFAULT),
 		       memcg_events(memcg, PGMAJFAULT));
 
-	seq_buf_printf(&s, "workingset_refault %lu\n",
-		       memcg_page_state(memcg, WORKINGSET_REFAULT));
-	seq_buf_printf(&s, "workingset_activate %lu\n",
-		       memcg_page_state(memcg, WORKINGSET_ACTIVATE));
+	seq_buf_printf(&s, "workingset_refault_anon %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_REFAULT_ANON));
+	seq_buf_printf(&s, "workingset_refault_file %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_REFAULT_FILE));
+	seq_buf_printf(&s, "workingset_activate_anon %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_ACTIVATE_ANON));
+	seq_buf_printf(&s, "workingset_activate_file %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_ACTIVATE_FILE));
 	seq_buf_printf(&s, "workingset_restore %lu\n",
-		       memcg_page_state(memcg, WORKINGSET_RESTORE));
+		       memcg_page_state(memcg, WORKINGSET_RESTORE_ANON));
+	seq_buf_printf(&s, "workingset_restore %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_RESTORE_FILE));
 	seq_buf_printf(&s, "workingset_nodereclaim %lu\n",
 		       memcg_page_state(memcg, WORKINGSET_NODERECLAIM));
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 783cd7fdc61a..017f323318a3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2683,7 +2683,10 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 	if (!sc->force_deactivate) {
 		unsigned long refaults;
 
-		if (inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
+		refaults = lruvec_page_state(target_lruvec,
+				WORKINGSET_ACTIVATE_ANON);
+		if (refaults != target_lruvec->refaults[0] ||
+			inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
 			sc->may_deactivate |= DEACTIVATE_ANON;
 		else
 			sc->may_deactivate &= ~DEACTIVATE_ANON;
@@ -2694,8 +2697,8 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 		 * rid of any stale active pages quickly.
 		 */
 		refaults = lruvec_page_state(target_lruvec,
-					     WORKINGSET_ACTIVATE);
-		if (refaults != target_lruvec->refaults ||
+				WORKINGSET_ACTIVATE_FILE);
+		if (refaults != target_lruvec->refaults[1] ||
 		    inactive_is_low(target_lruvec, LRU_INACTIVE_FILE))
 			sc->may_deactivate |= DEACTIVATE_FILE;
 		else
@@ -2972,8 +2975,10 @@ static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat)
 	unsigned long refaults;
 
 	target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
-	refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE);
-	target_lruvec->refaults = refaults;
+	refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON);
+	target_lruvec->refaults[0] = refaults;
+	refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE);
+	target_lruvec->refaults[1] = refaults;
 }
 
 /*
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 2b866cbab11d..fef03463a0cf 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1167,9 +1167,12 @@ const char * const vmstat_text[] = {
 	"nr_isolated_anon",
 	"nr_isolated_file",
 	"workingset_nodes",
-	"workingset_refault",
-	"workingset_activate",
-	"workingset_restore",
+	"workingset_refault_anon",
+	"workingset_refault_file",
+	"workingset_activate_anon",
+	"workingset_activate_file",
+	"workingset_restore_anon",
+	"workingset_restore_file",
 	"workingset_nodereclaim",
 	"nr_anon_pages",
 	"nr_mapped",
diff --git a/mm/workingset.c b/mm/workingset.c
index b199726924dd..941bbaa6c262 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/memcontrol.h>
+#include <linux/mm_inline.h>
 #include <linux/writeback.h>
 #include <linux/shmem_fs.h>
 #include <linux/pagemap.h>
@@ -280,6 +281,7 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
  */
 void workingset_refault(struct page *page, void *shadow)
 {
+	bool file = page_is_file_lru(page);
 	struct mem_cgroup *eviction_memcg;
 	struct lruvec *eviction_lruvec;
 	unsigned long refault_distance;
@@ -346,7 +348,7 @@ void workingset_refault(struct page *page, void *shadow)
 	memcg = page_memcg(page);
 	lruvec = mem_cgroup_lruvec(memcg, pgdat);
 
-	inc_lruvec_state(lruvec, WORKINGSET_REFAULT);
+	inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file);
 
 	/*
 	 * Compare the distance to the existing workingset size. We
@@ -366,7 +368,7 @@ void workingset_refault(struct page *page, void *shadow)
 
 	SetPageActive(page);
 	workingset_age_nonresident(lruvec, hpage_nr_pages(page));
-	inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE);
+	inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file);
 
 	/* Page was active prior to eviction */
 	if (workingset) {
@@ -375,7 +377,7 @@ void workingset_refault(struct page *page, void *shadow)
 		spin_lock_irq(&page_pgdat(page)->lru_lock);
 		lru_note_cost_page(page);
 		spin_unlock_irq(&page_pgdat(page)->lru_lock);
-		inc_lruvec_state(lruvec, WORKINGSET_RESTORE);
+		inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file);
 	}
 out:
 	rcu_read_unlock();

From 3852f6768ede542ed48b9077bedf482c7ecb6327 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:30:47 -0700
Subject: [PATCH 320/474] mm/swapcache: support to handle the shadow entries

Workingset detection for anonymous page will be implemented in the
following patch and it requires to store the shadow entries into the
swapcache.  This patch implements an infrastructure to store the shadow
entry in the swapcache.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: http://lkml.kernel.org/r/1595490560-15117-5-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h | 17 +++++++++----
 mm/shmem.c           |  3 ++-
 mm/swap_state.c      | 57 +++++++++++++++++++++++++++++++++++++++-----
 mm/swapfile.c        |  2 ++
 mm/vmscan.c          |  2 +-
 5 files changed, 69 insertions(+), 12 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 51ec9cdb92c0..8a4c592698a9 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -414,9 +414,13 @@ extern struct address_space *swapper_spaces[];
 extern unsigned long total_swapcache_pages(void);
 extern void show_swap_cache_info(void);
 extern int add_to_swap(struct page *page);
-extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t);
-extern void __delete_from_swap_cache(struct page *, swp_entry_t entry);
+extern int add_to_swap_cache(struct page *page, swp_entry_t entry,
+			gfp_t gfp, void **shadowp);
+extern void __delete_from_swap_cache(struct page *page,
+			swp_entry_t entry, void *shadow);
 extern void delete_from_swap_cache(struct page *);
+extern void clear_shadow_from_swap_cache(int type, unsigned long begin,
+				unsigned long end);
 extern void free_page_and_swap_cache(struct page *);
 extern void free_pages_and_swap_cache(struct page **, int);
 extern struct page *lookup_swap_cache(swp_entry_t entry,
@@ -570,13 +574,13 @@ static inline int add_to_swap(struct page *page)
 }
 
 static inline int add_to_swap_cache(struct page *page, swp_entry_t entry,
-							gfp_t gfp_mask)
+					gfp_t gfp_mask, void **shadowp)
 {
 	return -1;
 }
 
 static inline void __delete_from_swap_cache(struct page *page,
-							swp_entry_t entry)
+					swp_entry_t entry, void *shadow)
 {
 }
 
@@ -584,6 +588,11 @@ static inline void delete_from_swap_cache(struct page *page)
 {
 }
 
+static inline void clear_shadow_from_swap_cache(int type, unsigned long begin,
+				unsigned long end)
+{
+}
+
 static inline int page_swapcount(struct page *page)
 {
 	return 0;
diff --git a/mm/shmem.c b/mm/shmem.c
index eb6b36d89722..49bde088a7ea 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1434,7 +1434,8 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 		list_add(&info->swaplist, &shmem_swaplist);
 
 	if (add_to_swap_cache(page, swap,
-			__GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN) == 0) {
+			__GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN,
+			NULL) == 0) {
 		spin_lock_irq(&info->lock);
 		shmem_recalc_inode(inode);
 		info->swapped++;
diff --git a/mm/swap_state.c b/mm/swap_state.c
index e82f4f8b1f63..a29b33c7c236 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -110,12 +110,14 @@ void show_swap_cache_info(void)
  * add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
  * but sets SwapCache flag and private instead of mapping and index.
  */
-int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp)
+int add_to_swap_cache(struct page *page, swp_entry_t entry,
+			gfp_t gfp, void **shadowp)
 {
 	struct address_space *address_space = swap_address_space(entry);
 	pgoff_t idx = swp_offset(entry);
 	XA_STATE_ORDER(xas, &address_space->i_pages, idx, compound_order(page));
 	unsigned long i, nr = hpage_nr_pages(page);
+	void *old;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageSwapCache(page), page);
@@ -125,16 +127,25 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp)
 	SetPageSwapCache(page);
 
 	do {
+		unsigned long nr_shadows = 0;
+
 		xas_lock_irq(&xas);
 		xas_create_range(&xas);
 		if (xas_error(&xas))
 			goto unlock;
 		for (i = 0; i < nr; i++) {
 			VM_BUG_ON_PAGE(xas.xa_index != idx + i, page);
+			old = xas_load(&xas);
+			if (xa_is_value(old)) {
+				nr_shadows++;
+				if (shadowp)
+					*shadowp = old;
+			}
 			set_page_private(page + i, entry.val + i);
 			xas_store(&xas, page);
 			xas_next(&xas);
 		}
+		address_space->nrexceptional -= nr_shadows;
 		address_space->nrpages += nr;
 		__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
 		ADD_CACHE_INFO(add_total, nr);
@@ -154,7 +165,8 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp)
  * This must be called only on pages that have
  * been verified to be in the swap cache.
  */
-void __delete_from_swap_cache(struct page *page, swp_entry_t entry)
+void __delete_from_swap_cache(struct page *page,
+			swp_entry_t entry, void *shadow)
 {
 	struct address_space *address_space = swap_address_space(entry);
 	int i, nr = hpage_nr_pages(page);
@@ -166,12 +178,14 @@ void __delete_from_swap_cache(struct page *page, swp_entry_t entry)
 	VM_BUG_ON_PAGE(PageWriteback(page), page);
 
 	for (i = 0; i < nr; i++) {
-		void *entry = xas_store(&xas, NULL);
+		void *entry = xas_store(&xas, shadow);
 		VM_BUG_ON_PAGE(entry != page, entry);
 		set_page_private(page + i, 0);
 		xas_next(&xas);
 	}
 	ClearPageSwapCache(page);
+	if (shadow)
+		address_space->nrexceptional += nr;
 	address_space->nrpages -= nr;
 	__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
 	ADD_CACHE_INFO(del_total, nr);
@@ -208,7 +222,7 @@ int add_to_swap(struct page *page)
 	 * Add it to the swap cache.
 	 */
 	err = add_to_swap_cache(page, entry,
-			__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
+			__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN, NULL);
 	if (err)
 		/*
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
@@ -246,13 +260,44 @@ void delete_from_swap_cache(struct page *page)
 	struct address_space *address_space = swap_address_space(entry);
 
 	xa_lock_irq(&address_space->i_pages);
-	__delete_from_swap_cache(page, entry);
+	__delete_from_swap_cache(page, entry, NULL);
 	xa_unlock_irq(&address_space->i_pages);
 
 	put_swap_page(page, entry);
 	page_ref_sub(page, hpage_nr_pages(page));
 }
 
+void clear_shadow_from_swap_cache(int type, unsigned long begin,
+				unsigned long end)
+{
+	unsigned long curr = begin;
+	void *old;
+
+	for (;;) {
+		unsigned long nr_shadows = 0;
+		swp_entry_t entry = swp_entry(type, curr);
+		struct address_space *address_space = swap_address_space(entry);
+		XA_STATE(xas, &address_space->i_pages, curr);
+
+		xa_lock_irq(&address_space->i_pages);
+		xas_for_each(&xas, old, end) {
+			if (!xa_is_value(old))
+				continue;
+			xas_store(&xas, NULL);
+			nr_shadows++;
+		}
+		address_space->nrexceptional -= nr_shadows;
+		xa_unlock_irq(&address_space->i_pages);
+
+		/* search the next swapcache until we meet end */
+		curr >>= SWAP_ADDRESS_SPACE_SHIFT;
+		curr++;
+		curr <<= SWAP_ADDRESS_SPACE_SHIFT;
+		if (curr > end)
+			break;
+	}
+}
+
 /* 
  * If we are the only user, then try to free up the swap cache. 
  * 
@@ -429,7 +474,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	__SetPageSwapBacked(page);
 
 	/* May fail (-ENOMEM) if XArray node allocation failed. */
-	if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK)) {
+	if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK, NULL)) {
 		put_swap_page(page, entry);
 		goto fail_unlock;
 	}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 82183432fdd0..e653eea1eb88 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -696,6 +696,7 @@ static void add_to_avail_list(struct swap_info_struct *p)
 static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
 			    unsigned int nr_entries)
 {
+	unsigned long begin = offset;
 	unsigned long end = offset + nr_entries - 1;
 	void (*swap_slot_free_notify)(struct block_device *, unsigned long);
 
@@ -721,6 +722,7 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
 			swap_slot_free_notify(si->bdev, offset);
 		offset++;
 	}
+	clear_shadow_from_swap_cache(si->type, begin, end);
 }
 
 static void set_cluster_next(struct swap_info_struct *si, unsigned long next)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 017f323318a3..e84c4dd08c4e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -896,7 +896,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	if (PageSwapCache(page)) {
 		swp_entry_t swap = { .val = page_private(page) };
 		mem_cgroup_swapout(page, swap);
-		__delete_from_swap_cache(page, swap);
+		__delete_from_swap_cache(page, swap, NULL);
 		xa_unlock_irqrestore(&mapping->i_pages, flags);
 		put_swap_page(page, swap);
 		workingset_eviction(page, target_memcg);

From aae466b0052e1888edd1d7f473d4310d64936196 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:30:50 -0700
Subject: [PATCH 321/474] mm/swap: implement workingset detection for anonymous
 LRU

This patch implements workingset detection for anonymous LRU.  All the
infrastructure is implemented by the previous patches so this patch just
activates the workingset detection by installing/retrieving the shadow
entry and adding refault calculation.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Link: http://lkml.kernel.org/r/1595490560-15117-6-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h |  6 ++++++
 mm/memory.c          | 11 ++++-------
 mm/swap_state.c      | 23 ++++++++++++++++++-----
 mm/vmscan.c          |  7 ++++---
 mm/workingset.c      | 15 +++++++++++----
 5 files changed, 43 insertions(+), 19 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 8a4c592698a9..661046994db4 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -414,6 +414,7 @@ extern struct address_space *swapper_spaces[];
 extern unsigned long total_swapcache_pages(void);
 extern void show_swap_cache_info(void);
 extern int add_to_swap(struct page *page);
+extern void *get_shadow_from_swap_cache(swp_entry_t entry);
 extern int add_to_swap_cache(struct page *page, swp_entry_t entry,
 			gfp_t gfp, void **shadowp);
 extern void __delete_from_swap_cache(struct page *page,
@@ -573,6 +574,11 @@ static inline int add_to_swap(struct page *page)
 	return 0;
 }
 
+static inline void *get_shadow_from_swap_cache(swp_entry_t entry)
+{
+	return NULL;
+}
+
 static inline int add_to_swap_cache(struct page *page, swp_entry_t entry,
 					gfp_t gfp_mask, void **shadowp)
 {
diff --git a/mm/memory.c b/mm/memory.c
index 6fe8b5b22c57..de311fc7639e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3098,6 +3098,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	int locked;
 	int exclusive = 0;
 	vm_fault_t ret = 0;
+	void *shadow = NULL;
 
 	if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte))
 		goto out;
@@ -3149,13 +3150,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 					goto out_page;
 				}
 
-				/*
-				 * XXX: Move to lru_cache_add() when it
-				 * supports new vs putback
-				 */
-				spin_lock_irq(&page_pgdat(page)->lru_lock);
-				lru_note_cost_page(page);
-				spin_unlock_irq(&page_pgdat(page)->lru_lock);
+				shadow = get_shadow_from_swap_cache(entry);
+				if (shadow)
+					workingset_refault(page, shadow);
 
 				lru_cache_add(page);
 				swap_readpage(page, true);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index a29b33c7c236..b73aabdfd35a 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -106,6 +106,20 @@ void show_swap_cache_info(void)
 	printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10));
 }
 
+void *get_shadow_from_swap_cache(swp_entry_t entry)
+{
+	struct address_space *address_space = swap_address_space(entry);
+	pgoff_t idx = swp_offset(entry);
+	struct page *page;
+
+	page = find_get_entry(address_space, idx);
+	if (xa_is_value(page))
+		return page;
+	if (page)
+		put_page(page);
+	return NULL;
+}
+
 /*
  * add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
  * but sets SwapCache flag and private instead of mapping and index.
@@ -406,6 +420,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 {
 	struct swap_info_struct *si;
 	struct page *page;
+	void *shadow = NULL;
 
 	*new_page_allocated = false;
 
@@ -474,7 +489,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	__SetPageSwapBacked(page);
 
 	/* May fail (-ENOMEM) if XArray node allocation failed. */
-	if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK, NULL)) {
+	if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow)) {
 		put_swap_page(page, entry);
 		goto fail_unlock;
 	}
@@ -484,10 +499,8 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		goto fail_unlock;
 	}
 
-	/* XXX: Move to lru_cache_add() when it supports new vs putback */
-	spin_lock_irq(&page_pgdat(page)->lru_lock);
-	lru_note_cost_page(page);
-	spin_unlock_irq(&page_pgdat(page)->lru_lock);
+	if (shadow)
+		workingset_refault(page, shadow);
 
 	/* Caller will initiate read into locked page */
 	SetPageWorkingset(page);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e84c4dd08c4e..66d73fea80e4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -854,6 +854,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 {
 	unsigned long flags;
 	int refcount;
+	void *shadow = NULL;
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(mapping != page_mapping(page));
@@ -896,13 +897,13 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	if (PageSwapCache(page)) {
 		swp_entry_t swap = { .val = page_private(page) };
 		mem_cgroup_swapout(page, swap);
-		__delete_from_swap_cache(page, swap, NULL);
+		if (reclaimed && !mapping_exiting(mapping))
+			shadow = workingset_eviction(page, target_memcg);
+		__delete_from_swap_cache(page, swap, shadow);
 		xa_unlock_irqrestore(&mapping->i_pages, flags);
 		put_swap_page(page, swap);
-		workingset_eviction(page, target_memcg);
 	} else {
 		void (*freepage)(struct page *);
-		void *shadow = NULL;
 
 		freepage = mapping->a_ops->freepage;
 		/*
diff --git a/mm/workingset.c b/mm/workingset.c
index 941bbaa6c262..8cbe4e3cbe5c 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -353,15 +353,22 @@ void workingset_refault(struct page *page, void *shadow)
 	/*
 	 * Compare the distance to the existing workingset size. We
 	 * don't activate pages that couldn't stay resident even if
-	 * all the memory was available to the page cache. Whether
-	 * cache can compete with anon or not depends on having swap.
+	 * all the memory was available to the workingset. Whether
+	 * workingset competition needs to consider anon or not depends
+	 * on having swap.
 	 */
 	workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE);
+	if (!file) {
+		workingset_size += lruvec_page_state(eviction_lruvec,
+						     NR_INACTIVE_FILE);
+	}
 	if (mem_cgroup_get_nr_swap_pages(memcg) > 0) {
-		workingset_size += lruvec_page_state(eviction_lruvec,
-						     NR_INACTIVE_ANON);
 		workingset_size += lruvec_page_state(eviction_lruvec,
 						     NR_ACTIVE_ANON);
+		if (file) {
+			workingset_size += lruvec_page_state(eviction_lruvec,
+						     NR_INACTIVE_ANON);
+		}
 	}
 	if (refault_distance > workingset_size)
 		goto out;

From 4002570c5c585c4c9a889e45dd104ed663257eec Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:30:54 -0700
Subject: [PATCH 322/474] mm/vmscan: restore active/inactive ratio for
 anonymous LRU

Now that workingset detection is implemented for anonymous LRU, we don't
need large inactive list to allow detecting frequently accessed pages
before they are reclaimed, anymore.  This effectively reverts the
temporary measure put in by commit "mm/vmscan: make active/inactive ratio
as 1:1 for anon lru".

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Link: http://lkml.kernel.org/r/1595490560-15117-7-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/vmscan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 66d73fea80e4..846b7e9b8d2e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2207,7 +2207,7 @@ static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru)
 	active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru);
 
 	gb = (inactive + active) >> (30 - PAGE_SHIFT);
-	if (gb && is_file_lru(inactive_lru))
+	if (gb)
 		inactive_ratio = int_sqrt(10 * gb);
 	else
 		inactive_ratio = 1;

From 471e78cc7687337abd10626196f5addb30b01824 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Koutn=C3=BD?= <mkoutny@suse.com>
Date: Tue, 11 Aug 2020 18:30:57 -0700
Subject: [PATCH 323/474] /proc/PID/smaps: consistent whitespace output format
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The keys in smaps output are padded to fixed width with spaces.  All
except for THPeligible that uses tabs (only since commit c06306696f83
("mm: thp: fix false negative of shmem vma's THP eligibility")).

Unify the output formatting to save time debugging some naïve parsers.
(Part of the unification is also aligning FilePmdMapped with others.)

Signed-off-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Yang Shi <yang.shi@linux.alibaba.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Link: http://lkml.kernel.org/r/20200728083207.17531-1-mkoutny@suse.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/task_mmu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index dbda4499a859..5066b0251ed8 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -786,7 +786,7 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss,
 	SEQ_PUT_DEC(" kB\nLazyFree:       ", mss->lazyfree);
 	SEQ_PUT_DEC(" kB\nAnonHugePages:  ", mss->anonymous_thp);
 	SEQ_PUT_DEC(" kB\nShmemPmdMapped: ", mss->shmem_thp);
-	SEQ_PUT_DEC(" kB\nFilePmdMapped: ", mss->file_thp);
+	SEQ_PUT_DEC(" kB\nFilePmdMapped:  ", mss->file_thp);
 	SEQ_PUT_DEC(" kB\nShared_Hugetlb: ", mss->shared_hugetlb);
 	seq_put_decimal_ull_width(m, " kB\nPrivate_Hugetlb: ",
 				  mss->private_hugetlb >> 10, 7);
@@ -816,7 +816,7 @@ static int show_smap(struct seq_file *m, void *v)
 
 	__show_smap(m, &mss, false);
 
-	seq_printf(m, "THPeligible:		%d\n",
+	seq_printf(m, "THPeligible:    %d\n",
 		   transparent_hugepage_enabled(vma));
 
 	if (arch_pkeys_enabled())

From facdaa917c4d5a376d09d25865f5a863f906234a Mon Sep 17 00:00:00 2001
From: Nitin Gupta <nigupta@nvidia.com>
Date: Tue, 11 Aug 2020 18:31:00 -0700
Subject: [PATCH 324/474] mm: proactive compaction
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For some applications, we need to allocate almost all memory as hugepages.
However, on a running system, higher-order allocations can fail if the
memory is fragmented.  Linux kernel currently does on-demand compaction as
we request more hugepages, but this style of compaction incurs very high
latency.  Experiments with one-time full memory compaction (followed by
hugepage allocations) show that kernel is able to restore a highly
fragmented memory state to a fairly compacted memory state within <1 sec
for a 32G system.  Such data suggests that a more proactive compaction can
help us allocate a large fraction of memory as hugepages keeping
allocation latencies low.

For a more proactive compaction, the approach taken here is to define a
new sysctl called 'vm.compaction_proactiveness' which dictates bounds for
external fragmentation which kcompactd tries to maintain.

The tunable takes a value in range [0, 100], with a default of 20.

Note that a previous version of this patch [1] was found to introduce too
many tunables (per-order extfrag{low, high}), but this one reduces them to
just one sysctl.  Also, the new tunable is an opaque value instead of
asking for specific bounds of "external fragmentation", which would have
been difficult to estimate.  The internal interpretation of this opaque
value allows for future fine-tuning.

Currently, we use a simple translation from this tunable to [low, high]
"fragmentation score" thresholds (low=100-proactiveness, high=low+10%).
The score for a node is defined as weighted mean of per-zone external
fragmentation.  A zone's present_pages determines its weight.

To periodically check per-node score, we reuse per-node kcompactd threads,
which are woken up every 500 milliseconds to check the same.  If a node's
score exceeds its high threshold (as derived from user-provided
proactiveness value), proactive compaction is started until its score
reaches its low threshold value.  By default, proactiveness is set to 20,
which implies threshold values of low=80 and high=90.

This patch is largely based on ideas from Michal Hocko [2].  See also the
LWN article [3].

Performance data
================

System: x64_64, 1T RAM, 80 CPU threads.
Kernel: 5.6.0-rc3 + this patch

echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/enabled
echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/defrag

Before starting the driver, the system was fragmented from a userspace
program that allocates all memory and then for each 2M aligned section,
frees 3/4 of base pages using munmap.  The workload is mainly anonymous
userspace pages, which are easy to move around.  I intentionally avoided
unmovable pages in this test to see how much latency we incur when
hugepage allocations hit direct compaction.

1. Kernel hugepage allocation latencies

With the system in such a fragmented state, a kernel driver then allocates
as many hugepages as possible and measures allocation latency:

(all latency values are in microseconds)

- With vanilla 5.6.0-rc3

  percentile latency
  –––––––––– –––––––
	   5    7894
	  10    9496
	  25   12561
	  30   15295
	  40   18244
	  50   21229
	  60   27556
	  75   30147
	  80   31047
	  90   32859
	  95   33799

Total 2M hugepages allocated = 383859 (749G worth of hugepages out of 762G
total free => 98% of free memory could be allocated as hugepages)

- With 5.6.0-rc3 + this patch, with proactiveness=20

sysctl -w vm.compaction_proactiveness=20

  percentile latency
  –––––––––– –––––––
	   5       2
	  10       2
	  25       3
	  30       3
	  40       3
	  50       4
	  60       4
	  75       4
	  80       4
	  90       5
	  95     429

Total 2M hugepages allocated = 384105 (750G worth of hugepages out of 762G
total free => 98% of free memory could be allocated as hugepages)

2. JAVA heap allocation

In this test, we first fragment memory using the same method as for (1).

Then, we start a Java process with a heap size set to 700G and request the
heap to be allocated with THP hugepages.  We also set THP to madvise to
allow hugepage backing of this heap.

/usr/bin/time
 java -Xms700G -Xmx700G -XX:+UseTransparentHugePages -XX:+AlwaysPreTouch

The above command allocates 700G of Java heap using hugepages.

- With vanilla 5.6.0-rc3

17.39user 1666.48system 27:37.89elapsed

- With 5.6.0-rc3 + this patch, with proactiveness=20

8.35user 194.58system 3:19.62elapsed

Elapsed time remains around 3:15, as proactiveness is further increased.

Note that proactive compaction happens throughout the runtime of these
workloads.  The situation of one-time compaction, sufficient to supply
hugepages for following allocation stream, can probably happen for more
extreme proactiveness values, like 80 or 90.

In the above Java workload, proactiveness is set to 20.  The test starts
with a node's score of 80 or higher, depending on the delay between the
fragmentation step and starting the benchmark, which gives more-or-less
time for the initial round of compaction.  As t he benchmark consumes
hugepages, node's score quickly rises above the high threshold (90) and
proactive compaction starts again, which brings down the score to the low
threshold level (80).  Repeat.

bpftrace also confirms proactive compaction running 20+ times during the
runtime of this Java benchmark.  kcompactd threads consume 100% of one of
the CPUs while it tries to bring a node's score within thresholds.

Backoff behavior
================

Above workloads produce a memory state which is easy to compact.  However,
if memory is filled with unmovable pages, proactive compaction should
essentially back off.  To test this aspect:

- Created a kernel driver that allocates almost all memory as hugepages
  followed by freeing first 3/4 of each hugepage.
- Set proactiveness=40
- Note that proactive_compact_node() is deferred maximum number of times
  with HPAGE_FRAG_CHECK_INTERVAL_MSEC of wait between each check
  (=> ~30 seconds between retries).

[1] https://patchwork.kernel.org/patch/11098289/
[2] https://lore.kernel.org/linux-mm/20161230131412.GI13301@dhcp22.suse.cz/
[3] https://lwn.net/Articles/817905/

Signed-off-by: Nitin Gupta <nigupta@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Oleksandr Natalenko <oleksandr@redhat.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Khalid Aziz <khalid.aziz@oracle.com>
Reviewed-by: Oleksandr Natalenko <oleksandr@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Nitin Gupta <ngupta@nitingupta.dev>
Cc: Oleksandr Natalenko <oleksandr@redhat.com>
Link: http://lkml.kernel.org/r/20200616204527.19185-1-nigupta@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/admin-guide/sysctl/vm.rst |  15 ++
 include/linux/compaction.h              |   2 +
 kernel/sysctl.c                         |   9 ++
 mm/compaction.c                         | 183 +++++++++++++++++++++++-
 mm/internal.h                           |   1 +
 mm/vmstat.c                             |  18 +++
 6 files changed, 223 insertions(+), 5 deletions(-)

diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
index d997cc3c26d0..4b9d2e8e9142 100644
--- a/Documentation/admin-guide/sysctl/vm.rst
+++ b/Documentation/admin-guide/sysctl/vm.rst
@@ -119,6 +119,21 @@ all zones are compacted such that free memory is available in contiguous
 blocks where possible. This can be important for example in the allocation of
 huge pages although processes will also directly compact memory as required.
 
+compaction_proactiveness
+========================
+
+This tunable takes a value in the range [0, 100] with a default value of
+20. This tunable determines how aggressively compaction is done in the
+background. Setting it to 0 disables proactive compaction.
+
+Note that compaction has a non-trivial system-wide impact as pages
+belonging to different processes are moved around, which could also lead
+to latency spikes in unsuspecting applications. The kernel employs
+various heuristics to avoid wasting CPU cycles if it detects that
+proactive compaction is not being effective.
+
+Be careful when setting it to extreme values like 100, as that may
+cause excessive background compaction activity.
 
 compact_unevictable_allowed
 ===========================
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 6fa0eea3f530..7a242d46454e 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -85,11 +85,13 @@ static inline unsigned long compact_gap(unsigned int order)
 
 #ifdef CONFIG_COMPACTION
 extern int sysctl_compact_memory;
+extern int sysctl_compaction_proactiveness;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void *buffer, size_t *length, loff_t *ppos);
 extern int sysctl_extfrag_threshold;
 extern int sysctl_compact_unevictable_allowed;
 
+extern int extfrag_for_order(struct zone *zone, unsigned int order);
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
 		unsigned int order, unsigned int alloc_flags,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index f785de3caac0..ab72e52f8a7b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2851,6 +2851,15 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0200,
 		.proc_handler	= sysctl_compaction_handler,
 	},
+	{
+		.procname	= "compaction_proactiveness",
+		.data		= &sysctl_compaction_proactiveness,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &one_hundred,
+	},
 	{
 		.procname	= "extfrag_threshold",
 		.data		= &sysctl_extfrag_threshold,
diff --git a/mm/compaction.c b/mm/compaction.c
index 86375605faa9..544a98811c82 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -50,6 +50,24 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 #define pageblock_start_pfn(pfn)	block_start_pfn(pfn, pageblock_order)
 #define pageblock_end_pfn(pfn)		block_end_pfn(pfn, pageblock_order)
 
+/*
+ * Fragmentation score check interval for proactive compaction purposes.
+ */
+static const int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500;
+
+/*
+ * Page order with-respect-to which proactive compaction
+ * calculates external fragmentation, which is used as
+ * the "fragmentation score" of a node/zone.
+ */
+#if defined CONFIG_TRANSPARENT_HUGEPAGE
+#define COMPACTION_HPAGE_ORDER	HPAGE_PMD_ORDER
+#elif defined HUGETLB_PAGE_ORDER
+#define COMPACTION_HPAGE_ORDER	HUGETLB_PAGE_ORDER
+#else
+#define COMPACTION_HPAGE_ORDER	(PMD_SHIFT - PAGE_SHIFT)
+#endif
+
 static unsigned long release_freepages(struct list_head *freelist)
 {
 	struct page *page, *next;
@@ -1857,6 +1875,76 @@ static inline bool is_via_compact_memory(int order)
 	return order == -1;
 }
 
+static bool kswapd_is_running(pg_data_t *pgdat)
+{
+	return pgdat->kswapd && (pgdat->kswapd->state == TASK_RUNNING);
+}
+
+/*
+ * A zone's fragmentation score is the external fragmentation wrt to the
+ * COMPACTION_HPAGE_ORDER scaled by the zone's size. It returns a value
+ * in the range [0, 100].
+ *
+ * The scaling factor ensures that proactive compaction focuses on larger
+ * zones like ZONE_NORMAL, rather than smaller, specialized zones like
+ * ZONE_DMA32. For smaller zones, the score value remains close to zero,
+ * and thus never exceeds the high threshold for proactive compaction.
+ */
+static int fragmentation_score_zone(struct zone *zone)
+{
+	unsigned long score;
+
+	score = zone->present_pages *
+			extfrag_for_order(zone, COMPACTION_HPAGE_ORDER);
+	return div64_ul(score, zone->zone_pgdat->node_present_pages + 1);
+}
+
+/*
+ * The per-node proactive (background) compaction process is started by its
+ * corresponding kcompactd thread when the node's fragmentation score
+ * exceeds the high threshold. The compaction process remains active till
+ * the node's score falls below the low threshold, or one of the back-off
+ * conditions is met.
+ */
+static int fragmentation_score_node(pg_data_t *pgdat)
+{
+	unsigned long score = 0;
+	int zoneid;
+
+	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+		struct zone *zone;
+
+		zone = &pgdat->node_zones[zoneid];
+		score += fragmentation_score_zone(zone);
+	}
+
+	return score;
+}
+
+static int fragmentation_score_wmark(pg_data_t *pgdat, bool low)
+{
+	int wmark_low;
+
+	/*
+	 * Cap the low watermak to avoid excessive compaction
+	 * activity in case a user sets the proactivess tunable
+	 * close to 100 (maximum).
+	 */
+	wmark_low = max(100 - sysctl_compaction_proactiveness, 5);
+	return low ? wmark_low : min(wmark_low + 10, 100);
+}
+
+static bool should_proactive_compact_node(pg_data_t *pgdat)
+{
+	int wmark_high;
+
+	if (!sysctl_compaction_proactiveness || kswapd_is_running(pgdat))
+		return false;
+
+	wmark_high = fragmentation_score_wmark(pgdat, false);
+	return fragmentation_score_node(pgdat) > wmark_high;
+}
+
 static enum compact_result __compact_finished(struct compact_control *cc)
 {
 	unsigned int order;
@@ -1883,6 +1971,25 @@ static enum compact_result __compact_finished(struct compact_control *cc)
 			return COMPACT_PARTIAL_SKIPPED;
 	}
 
+	if (cc->proactive_compaction) {
+		int score, wmark_low;
+		pg_data_t *pgdat;
+
+		pgdat = cc->zone->zone_pgdat;
+		if (kswapd_is_running(pgdat))
+			return COMPACT_PARTIAL_SKIPPED;
+
+		score = fragmentation_score_zone(cc->zone);
+		wmark_low = fragmentation_score_wmark(pgdat, true);
+
+		if (score > wmark_low)
+			ret = COMPACT_CONTINUE;
+		else
+			ret = COMPACT_SUCCESS;
+
+		goto out;
+	}
+
 	if (is_via_compact_memory(cc->order))
 		return COMPACT_CONTINUE;
 
@@ -1941,6 +2048,7 @@ static enum compact_result __compact_finished(struct compact_control *cc)
 		}
 	}
 
+out:
 	if (cc->contended || fatal_signal_pending(current))
 		ret = COMPACT_CONTENDED;
 
@@ -2421,6 +2529,41 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 	return rc;
 }
 
+/*
+ * Compact all zones within a node till each zone's fragmentation score
+ * reaches within proactive compaction thresholds (as determined by the
+ * proactiveness tunable).
+ *
+ * It is possible that the function returns before reaching score targets
+ * due to various back-off conditions, such as, contention on per-node or
+ * per-zone locks.
+ */
+static void proactive_compact_node(pg_data_t *pgdat)
+{
+	int zoneid;
+	struct zone *zone;
+	struct compact_control cc = {
+		.order = -1,
+		.mode = MIGRATE_SYNC_LIGHT,
+		.ignore_skip_hint = true,
+		.whole_zone = true,
+		.gfp_mask = GFP_KERNEL,
+		.proactive_compaction = true,
+	};
+
+	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+		zone = &pgdat->node_zones[zoneid];
+		if (!populated_zone(zone))
+			continue;
+
+		cc.zone = zone;
+
+		compact_zone(&cc, NULL);
+
+		VM_BUG_ON(!list_empty(&cc.freepages));
+		VM_BUG_ON(!list_empty(&cc.migratepages));
+	}
+}
 
 /* Compact all zones within a node */
 static void compact_node(int nid)
@@ -2467,6 +2610,13 @@ static void compact_nodes(void)
 /* The written value is actually unused, all memory is compacted */
 int sysctl_compact_memory;
 
+/*
+ * Tunable for proactive compaction. It determines how
+ * aggressively the kernel should compact memory in the
+ * background. It takes values in the range [0, 100].
+ */
+int __read_mostly sysctl_compaction_proactiveness = 20;
+
 /*
  * This is the entry point for compacting all nodes via
  * /proc/sys/vm/compact_memory
@@ -2646,6 +2796,7 @@ static int kcompactd(void *p)
 {
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
+	unsigned int proactive_defer = 0;
 
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
@@ -2661,12 +2812,34 @@ static int kcompactd(void *p)
 		unsigned long pflags;
 
 		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
-		wait_event_freezable(pgdat->kcompactd_wait,
-				kcompactd_work_requested(pgdat));
+		if (wait_event_freezable_timeout(pgdat->kcompactd_wait,
+			kcompactd_work_requested(pgdat),
+			msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC))) {
 
-		psi_memstall_enter(&pflags);
-		kcompactd_do_work(pgdat);
-		psi_memstall_leave(&pflags);
+			psi_memstall_enter(&pflags);
+			kcompactd_do_work(pgdat);
+			psi_memstall_leave(&pflags);
+			continue;
+		}
+
+		/* kcompactd wait timeout */
+		if (should_proactive_compact_node(pgdat)) {
+			unsigned int prev_score, score;
+
+			if (proactive_defer) {
+				proactive_defer--;
+				continue;
+			}
+			prev_score = fragmentation_score_node(pgdat);
+			proactive_compact_node(pgdat);
+			score = fragmentation_score_node(pgdat);
+			/*
+			 * Defer proactive compaction if the fragmentation
+			 * score did not go down i.e. no progress made.
+			 */
+			proactive_defer = score < prev_score ?
+					0 : 1 << COMPACT_MAX_DEFER_SHIFT;
+		}
 	}
 
 	return 0;
diff --git a/mm/internal.h b/mm/internal.h
index 9886db20d94f..42cf0b610847 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -239,6 +239,7 @@ struct compact_control {
 	bool no_set_skip_hint;		/* Don't mark blocks for skipping */
 	bool ignore_block_suitable;	/* Scan blocks considered unsuitable */
 	bool direct_compaction;		/* False from kcompactd or /proc/... */
+	bool proactive_compaction;	/* kcompactd proactive compaction */
 	bool whole_zone;		/* Whole zone should/has been scanned */
 	bool contended;			/* Signal lock or sched contention */
 	bool rescan;			/* Rescanning the same pageblock */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index fef03463a0cf..f183aa37994e 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1096,6 +1096,24 @@ static int __fragmentation_index(unsigned int order, struct contig_page_info *in
 	return 1000 - div_u64( (1000+(div_u64(info->free_pages * 1000ULL, requested))), info->free_blocks_total);
 }
 
+/*
+ * Calculates external fragmentation within a zone wrt the given order.
+ * It is defined as the percentage of pages found in blocks of size
+ * less than 1 << order. It returns values in range [0, 100].
+ */
+int extfrag_for_order(struct zone *zone, unsigned int order)
+{
+	struct contig_page_info info;
+
+	fill_contig_page_info(zone, order, &info);
+	if (info.free_pages == 0)
+		return 0;
+
+	return div_u64((info.free_pages -
+			(info.free_blocks_suitable << order)) * 100,
+			info.free_pages);
+}
+
 /* Same as __fragmentation index but allocs contig_page_info on stack */
 int fragmentation_index(struct zone *zone, unsigned int order)
 {

From 25788738eb9ce46fe6a0fd84a3ceef5c795d41f0 Mon Sep 17 00:00:00 2001
From: Nitin Gupta <nigupta@nvidia.com>
Date: Tue, 11 Aug 2020 18:31:04 -0700
Subject: [PATCH 325/474] mm: fix compile error due to COMPACTION_HPAGE_ORDER

Fix compile error when COMPACTION_HPAGE_ORDER is assigned to
HUGETLB_PAGE_ORDER.  The correct way to check if this constant is defined
is to check for CONFIG_HUGETLBFS.

Reported-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Nitin Gupta <nigupta@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Link: http://lkml.kernel.org/r/20200623064544.25766-1-nigupta@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/compaction.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 544a98811c82..ed8ea1511634 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -62,7 +62,7 @@ static const int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500;
  */
 #if defined CONFIG_TRANSPARENT_HUGEPAGE
 #define COMPACTION_HPAGE_ORDER	HPAGE_PMD_ORDER
-#elif defined HUGETLB_PAGE_ORDER
+#elif defined CONFIG_HUGETLBFS
 #define COMPACTION_HPAGE_ORDER	HUGETLB_PAGE_ORDER
 #else
 #define COMPACTION_HPAGE_ORDER	(PMD_SHIFT - PAGE_SHIFT)

From d34c0a7599ea8c301bc471dfa1eb2bf2db6752d1 Mon Sep 17 00:00:00 2001
From: Nitin Gupta <nigupta@nvidia.com>
Date: Tue, 11 Aug 2020 18:31:07 -0700
Subject: [PATCH 326/474] mm: use unsigned types for fragmentation score

Proactive compaction uses per-node/zone "fragmentation score" which is
always in range [0, 100], so use unsigned type of these scores as well as
for related constants.

Signed-off-by: Nitin Gupta <nigupta@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Link: http://lkml.kernel.org/r/20200618010319.13159-1-nigupta@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h |  4 ++--
 kernel/sysctl.c            |  2 +-
 mm/compaction.c            | 18 +++++++++---------
 mm/vmstat.c                |  2 +-
 4 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 7a242d46454e..25a521d299c1 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -85,13 +85,13 @@ static inline unsigned long compact_gap(unsigned int order)
 
 #ifdef CONFIG_COMPACTION
 extern int sysctl_compact_memory;
-extern int sysctl_compaction_proactiveness;
+extern unsigned int sysctl_compaction_proactiveness;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void *buffer, size_t *length, loff_t *ppos);
 extern int sysctl_extfrag_threshold;
 extern int sysctl_compact_unevictable_allowed;
 
-extern int extfrag_for_order(struct zone *zone, unsigned int order);
+extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order);
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
 		unsigned int order, unsigned int alloc_flags,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ab72e52f8a7b..287862f91717 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2854,7 +2854,7 @@ static struct ctl_table vm_table[] = {
 	{
 		.procname	= "compaction_proactiveness",
 		.data		= &sysctl_compaction_proactiveness,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(sysctl_compaction_proactiveness),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
diff --git a/mm/compaction.c b/mm/compaction.c
index ed8ea1511634..b7d433f1706a 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -53,7 +53,7 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 /*
  * Fragmentation score check interval for proactive compaction purposes.
  */
-static const int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500;
+static const unsigned int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500;
 
 /*
  * Page order with-respect-to which proactive compaction
@@ -1890,7 +1890,7 @@ static bool kswapd_is_running(pg_data_t *pgdat)
  * ZONE_DMA32. For smaller zones, the score value remains close to zero,
  * and thus never exceeds the high threshold for proactive compaction.
  */
-static int fragmentation_score_zone(struct zone *zone)
+static unsigned int fragmentation_score_zone(struct zone *zone)
 {
 	unsigned long score;
 
@@ -1906,9 +1906,9 @@ static int fragmentation_score_zone(struct zone *zone)
  * the node's score falls below the low threshold, or one of the back-off
  * conditions is met.
  */
-static int fragmentation_score_node(pg_data_t *pgdat)
+static unsigned int fragmentation_score_node(pg_data_t *pgdat)
 {
-	unsigned long score = 0;
+	unsigned int score = 0;
 	int zoneid;
 
 	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
@@ -1921,17 +1921,17 @@ static int fragmentation_score_node(pg_data_t *pgdat)
 	return score;
 }
 
-static int fragmentation_score_wmark(pg_data_t *pgdat, bool low)
+static unsigned int fragmentation_score_wmark(pg_data_t *pgdat, bool low)
 {
-	int wmark_low;
+	unsigned int wmark_low;
 
 	/*
 	 * Cap the low watermak to avoid excessive compaction
 	 * activity in case a user sets the proactivess tunable
 	 * close to 100 (maximum).
 	 */
-	wmark_low = max(100 - sysctl_compaction_proactiveness, 5);
-	return low ? wmark_low : min(wmark_low + 10, 100);
+	wmark_low = max(100U - sysctl_compaction_proactiveness, 5U);
+	return low ? wmark_low : min(wmark_low + 10, 100U);
 }
 
 static bool should_proactive_compact_node(pg_data_t *pgdat)
@@ -2615,7 +2615,7 @@ int sysctl_compact_memory;
  * aggressively the kernel should compact memory in the
  * background. It takes values in the range [0, 100].
  */
-int __read_mostly sysctl_compaction_proactiveness = 20;
+unsigned int __read_mostly sysctl_compaction_proactiveness = 20;
 
 /*
  * This is the entry point for compacting all nodes via
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f183aa37994e..3bb034c99887 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1101,7 +1101,7 @@ static int __fragmentation_index(unsigned int order, struct contig_page_info *in
  * It is defined as the percentage of pages found in blocks of size
  * less than 1 << order. It returns values in range [0, 100].
  */
-int extfrag_for_order(struct zone *zone, unsigned int order)
+unsigned int extfrag_for_order(struct zone *zone, unsigned int order)
 {
 	struct contig_page_info info;
 

From 860b32729a21e0565585a9e2ecea2e5244d65acd Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@linux.alibaba.com>
Date: Tue, 11 Aug 2020 18:31:10 -0700
Subject: [PATCH 327/474] mm/compaction: correct the comments of
 compact_defer_shift

There is no compact_defer_limit. It should be compact_defer_shift in
use. and add compact_order_failed explanation.

Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Link: http://lkml.kernel.org/r/3bd60e1b-a74e-050d-ade4-6e8f54e00b92@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 1 +
 mm/compaction.c        | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index efbd95dd3bbf..8379432f4f2f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -536,6 +536,7 @@ struct zone {
 	 * On compaction failure, 1<<compact_defer_shift compactions
 	 * are skipped before trying again. The number attempted since
 	 * last failure is tracked with compact_considered.
+	 * compact_order_failed is the minimum compaction failed order.
 	 */
 	unsigned int		compact_considered;
 	unsigned int		compact_defer_shift;
diff --git a/mm/compaction.c b/mm/compaction.c
index b7d433f1706a..5e8f2e22b73e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -154,7 +154,7 @@ EXPORT_SYMBOL(__ClearPageMovable);
 
 /*
  * Compaction is deferred when compaction fails to result in a page
- * allocation success. 1 << compact_defer_limit compactions are skipped up
+ * allocation success. 1 << compact_defer_shift, compactions are skipped up
  * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
  */
 void defer_compaction(struct zone *zone, int order)

From f6e92f404834698df0a7c4e1d8e07b3771cd6e46 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 11 Aug 2020 18:31:13 -0700
Subject: [PATCH 328/474] mm: mempolicy: fix kerneldoc of
 numa_map_to_online_node()

Fix W=1 compile warnings (invalid kerneldoc):

    mm/mempolicy.c:137: warning: Function parameter or member 'node' not described in 'numa_map_to_online_node'
    mm/mempolicy.c:137: warning: Excess function parameter 'nid' description in 'numa_map_to_online_node'

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20200728171109.28687-3-krzk@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/mempolicy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 7af44d7cdd11..92030ead2506 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -129,7 +129,7 @@ static struct mempolicy preferred_node_policy[MAX_NUMNODES];
 
 /**
  * numa_map_to_online_node - Find closest online node
- * @nid: Node id to start the search
+ * @node: Node id to start the search
  *
  * Lookup the next closest node by distance if @nid is not online.
  */

From 4605f057aace9291e80bf9982cc7c8babc917f56 Mon Sep 17 00:00:00 2001
From: Wenchao Hao <haowenchao22@gmail.com>
Date: Tue, 11 Aug 2020 18:31:16 -0700
Subject: [PATCH 329/474] mm/mempolicy.c: check parameters first in
 kernel_get_mempolicy

Previous implementatoin calls untagged_addr() before error check, while if
the error check failed and return EINVAL, the untagged_addr() call is just
useless work.

Signed-off-by: Wenchao Hao <haowenchao22@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20200801090825.5597-1-haowenchao22@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/mempolicy.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 92030ead2506..25b7e412c20b 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1632,11 +1632,11 @@ static int kernel_get_mempolicy(int __user *policy,
 	int pval;
 	nodemask_t nodes;
 
-	addr = untagged_addr(addr);
-
 	if (nmask != NULL && maxnode < nr_node_ids)
 		return -EINVAL;
 
+	addr = untagged_addr(addr);
+
 	err = do_get_mempolicy(&pval, &nodes, addr, flags);
 
 	if (err)

From f3f3416c2234c0a9372316bec5c48cbd58b565c5 Mon Sep 17 00:00:00 2001
From: Yanfei Xu <yanfei.xu@windriver.com>
Date: Tue, 11 Aug 2020 18:31:19 -0700
Subject: [PATCH 330/474] include/linux/mempolicy.h: fix typo

Change "interlave" to "interleave".

Signed-off-by: Yanfei Xu <yanfei.xu@windriver.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20200810063454.9357-1-yanfei.xu@windriver.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mempolicy.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 5f1648c23e29..5f1c74df264d 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -28,7 +28,7 @@ struct mm_struct;
  * the process policy is used. Interrupts ignore the memory policy
  * of the current process.
  *
- * Locking policy for interlave:
+ * Locking policy for interleave:
  * In process context there is no locking because only the process accesses
  * its own state. All vma manipulation is somewhat protected by a down_read on
  * mmap_lock.

From 9066e5cfb73cdbcdbb49e87999482ab615e9fc76 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Tue, 11 Aug 2020 18:31:22 -0700
Subject: [PATCH 331/474] mm, oom: make the calculation of oom badness more
 accurate

Recently we found an issue on our production environment that when memcg
oom is triggered the oom killer doesn't chose the process with largest
resident memory but chose the first scanned process.  Note that all
processes in this memcg have the same oom_score_adj, so the oom killer
should chose the process with largest resident memory.

Bellow is part of the oom info, which is enough to analyze this issue.
[7516987.983223] memory: usage 16777216kB, limit 16777216kB, failcnt 52843037
[7516987.983224] memory+swap: usage 16777216kB, limit 9007199254740988kB, failcnt 0
[7516987.983225] kmem: usage 301464kB, limit 9007199254740988kB, failcnt 0
[...]
[7516987.983293] [ pid ]   uid  tgid total_vm      rss pgtables_bytes swapents oom_score_adj name
[7516987.983510] [ 5740]     0  5740      257        1    32768        0          -998 pause
[7516987.983574] [58804]     0 58804     4594      771    81920        0          -998 entry_point.bas
[7516987.983577] [58908]     0 58908     7089      689    98304        0          -998 cron
[7516987.983580] [58910]     0 58910    16235     5576   163840        0          -998 supervisord
[7516987.983590] [59620]     0 59620    18074     1395   188416        0          -998 sshd
[7516987.983594] [59622]     0 59622    18680     6679   188416        0          -998 python
[7516987.983598] [59624]     0 59624  1859266     5161   548864        0          -998 odin-agent
[7516987.983600] [59625]     0 59625   707223     9248   983040        0          -998 filebeat
[7516987.983604] [59627]     0 59627   416433    64239   774144        0          -998 odin-log-agent
[7516987.983607] [59631]     0 59631   180671    15012   385024        0          -998 python3
[7516987.983612] [61396]     0 61396   791287     3189   352256        0          -998 client
[7516987.983615] [61641]     0 61641  1844642    29089   946176        0          -998 client
[7516987.983765] [ 9236]     0  9236     2642      467    53248        0          -998 php_scanner
[7516987.983911] [42898]     0 42898    15543      838   167936        0          -998 su
[7516987.983915] [42900]  1000 42900     3673      867    77824        0          -998 exec_script_vr2
[7516987.983918] [42925]  1000 42925    36475    19033   335872        0          -998 python
[7516987.983921] [57146]  1000 57146     3673      848    73728        0          -998 exec_script_J2p
[7516987.983925] [57195]  1000 57195   186359    22958   491520        0          -998 python2
[7516987.983928] [58376]  1000 58376   275764    14402   290816        0          -998 rosmaster
[7516987.983931] [58395]  1000 58395   155166     4449   245760        0          -998 rosout
[7516987.983935] [58406]  1000 58406 18285584  3967322 37101568        0          -998 data_sim
[7516987.984221] oom-kill:constraint=CONSTRAINT_MEMCG,nodemask=(null),cpuset=3aa16c9482ae3a6f6b78bda68a55d32c87c99b985e0f11331cddf05af6c4d753,mems_allowed=0-1,oom_memcg=/kubepods/podf1c273d3-9b36-11ea-b3df-246e9693c184,task_memcg=/kubepods/podf1c273d3-9b36-11ea-b3df-246e9693c184/1f246a3eeea8f70bf91141eeaf1805346a666e225f823906485ea0b6c37dfc3d,task=pause,pid=5740,uid=0
[7516987.984254] Memory cgroup out of memory: Killed process 5740 (pause) total-vm:1028kB, anon-rss:4kB, file-rss:0kB, shmem-rss:0kB
[7516988.092344] oom_reaper: reaped process 5740 (pause), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB

We can find that the first scanned process 5740 (pause) was killed, but
its rss is only one page.  That is because, when we calculate the oom
badness in oom_badness(), we always ignore the negtive point and convert
all of these negtive points to 1.  Now as oom_score_adj of all the
processes in this targeted memcg have the same value -998, the points of
these processes are all negtive value.  As a result, the first scanned
process will be killed.

The oom_socre_adj (-998) in this memcg is set by kubelet, because it is a
a Guaranteed pod, which has higher priority to prevent from being killed
by system oom.

To fix this issue, we should make the calculation of oom point more
accurate.  We can achieve it by convert the chosen_point from 'unsigned
long' to 'long'.

[cai@lca.pw: reported a issue in the previous version]
[mhocko@suse.com: fixed the issue reported by Cai]
[mhocko@suse.com: add the comment in proc_oom_score()]
[laoar.shao@gmail.com: v3]
  Link: http://lkml.kernel.org/r/1594396651-9931-1-git-send-email-laoar.shao@gmail.com

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Qian Cai <cai@lca.pw>
Link: http://lkml.kernel.org/r/1594309987-9919-1-git-send-email-laoar.shao@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/base.c      | 11 ++++++++++-
 include/linux/oom.h |  4 ++--
 mm/oom_kill.c       | 22 ++++++++++------------
 3 files changed, 22 insertions(+), 15 deletions(-)

diff --git a/fs/proc/base.c b/fs/proc/base.c
index a333caeca291..617db4e0faa0 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -551,8 +551,17 @@ static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
 {
 	unsigned long totalpages = totalram_pages() + total_swap_pages;
 	unsigned long points = 0;
+	long badness;
+
+	badness = oom_badness(task, totalpages);
+	/*
+	 * Special case OOM_SCORE_ADJ_MIN for all others scale the
+	 * badness value into [0, 2000] range which we have been
+	 * exporting for a long time so userspace might depend on it.
+	 */
+	if (badness != LONG_MIN)
+		points = (1000 + badness * 1000 / (long)totalpages) * 2 / 3;
 
-	points = oom_badness(task, totalpages) * 1000 / totalpages;
 	seq_printf(m, "%lu\n", points);
 
 	return 0;
diff --git a/include/linux/oom.h b/include/linux/oom.h
index c696c265f019..f022f581ac29 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -48,7 +48,7 @@ struct oom_control {
 	/* Used by oom implementation, do not set */
 	unsigned long totalpages;
 	struct task_struct *chosen;
-	unsigned long chosen_points;
+	long chosen_points;
 
 	/* Used to print the constraint info. */
 	enum oom_constraint constraint;
@@ -107,7 +107,7 @@ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm)
 
 bool __oom_reap_task_mm(struct mm_struct *mm);
 
-extern unsigned long oom_badness(struct task_struct *p,
+long oom_badness(struct task_struct *p,
 		unsigned long totalpages);
 
 extern bool out_of_memory(struct oom_control *oc);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d30ce75f23fb..48e0db54d838 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -196,17 +196,17 @@ static bool is_dump_unreclaim_slabs(void)
  * predictable as possible.  The goal is to return the highest value for the
  * task consuming the most memory to avoid subsequent oom failures.
  */
-unsigned long oom_badness(struct task_struct *p, unsigned long totalpages)
+long oom_badness(struct task_struct *p, unsigned long totalpages)
 {
 	long points;
 	long adj;
 
 	if (oom_unkillable_task(p))
-		return 0;
+		return LONG_MIN;
 
 	p = find_lock_task_mm(p);
 	if (!p)
-		return 0;
+		return LONG_MIN;
 
 	/*
 	 * Do not even consider tasks which are explicitly marked oom
@@ -218,7 +218,7 @@ unsigned long oom_badness(struct task_struct *p, unsigned long totalpages)
 			test_bit(MMF_OOM_SKIP, &p->mm->flags) ||
 			in_vfork(p)) {
 		task_unlock(p);
-		return 0;
+		return LONG_MIN;
 	}
 
 	/*
@@ -233,11 +233,7 @@ unsigned long oom_badness(struct task_struct *p, unsigned long totalpages)
 	adj *= totalpages / 1000;
 	points += adj;
 
-	/*
-	 * Never return 0 for an eligible task regardless of the root bonus and
-	 * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
-	 */
-	return points > 0 ? points : 1;
+	return points;
 }
 
 static const char * const oom_constraint_text[] = {
@@ -310,7 +306,7 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc)
 static int oom_evaluate_task(struct task_struct *task, void *arg)
 {
 	struct oom_control *oc = arg;
-	unsigned long points;
+	long points;
 
 	if (oom_unkillable_task(task))
 		goto next;
@@ -336,12 +332,12 @@ static int oom_evaluate_task(struct task_struct *task, void *arg)
 	 * killed first if it triggers an oom, then select it.
 	 */
 	if (oom_task_origin(task)) {
-		points = ULONG_MAX;
+		points = LONG_MAX;
 		goto select;
 	}
 
 	points = oom_badness(task, oc->totalpages);
-	if (!points || points < oc->chosen_points)
+	if (points == LONG_MIN || points < oc->chosen_points)
 		goto next;
 
 select:
@@ -365,6 +361,8 @@ static int oom_evaluate_task(struct task_struct *task, void *arg)
  */
 static void select_bad_process(struct oom_control *oc)
 {
+	oc->chosen_points = LONG_MIN;
+
 	if (is_memcg_oom(oc))
 		mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc);
 	else {

From de3f32e1424ca5c751d4cd78cbed6d17ca261c24 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Tue, 11 Aug 2020 18:31:25 -0700
Subject: [PATCH 332/474] doc, mm: sync up oom_score_adj documentation

There are at least two notes in the oom section.  The 3% discount for root
processes is gone since d46078b28889 ("mm, oom: remove 3% bonus for
CAP_SYS_ADMIN processes").

Likewise children of the selected oom victim are not sacrificed since
bbbe48029720 ("mm, oom: remove 'prefer children over parent' heuristic")

Drop both of them.

Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: David Rientjes <rientjes@google.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Link: http://lkml.kernel.org/r/20200709062603.18480-1-mhocko@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/filesystems/proc.rst | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index e024a9efffd8..eb96a440a064 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -1633,9 +1633,6 @@ may allocate from based on an estimation of its current memory and swap use.
 For example, if a task is using all allowed memory, its badness score will be
 1000.  If it is using half of its allowed memory, its score will be 500.
 
-There is an additional factor included in the badness score: the current memory
-and swap usage is discounted by 3% for root processes.
-
 The amount of "allowed" memory depends on the context in which the oom killer
 was called.  If it is due to the memory assigned to the allocating task's cpuset
 being exhausted, the allowed memory represents the set of mems assigned to that
@@ -1671,11 +1668,6 @@ The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
 value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
 requires CAP_SYS_RESOURCE.
 
-Caveat: when a parent task is selected, the oom killer will sacrifice any first
-generation children with separate address spaces instead, if possible.  This
-avoids servers and important system daemons from being killed and loses the
-minimal amount of work.
-
 
 3.2 /proc/<pid>/oom_score - Display current oom-killer score
 -------------------------------------------------------------

From b1aa7c9377bdff904efa0fbde1f96e1769730d8a Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Tue, 11 Aug 2020 18:31:28 -0700
Subject: [PATCH 333/474] doc, mm: clarify /proc/<pid>/oom_score value range

The exported value includes oom_score_adj so the range is no [0, 1000] as
described in the previous section but rather [0, 2000].  Mention that fact
explicitly.

Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: David Rientjes <rientjes@google.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Link: http://lkml.kernel.org/r/20200709062603.18480-2-mhocko@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/filesystems/proc.rst | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index eb96a440a064..533c79e8d2cd 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -1676,6 +1676,9 @@ This file can be used to check the current score used by the oom-killer for
 any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which
 process should be killed in an out-of-memory situation.
 
+Please note that the exported value includes oom_score_adj so it is
+effectively in range [0,2000].
+
 
 3.3  /proc/<pid>/io - Display the IO accounting fields
 -------------------------------------------------------

From 619b5b469bcab84ea3bee1d8d04451c781d23feb Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Tue, 11 Aug 2020 18:31:32 -0700
Subject: [PATCH 334/474] mm, oom: show process exiting information in
 __oom_kill_process()

When the OOM killer finds a victim and tryies to kill it, if the victim is
already exiting, the task mm will be NULL and no process will be killed.
But the dump_header() has been already executed, so it will be strange to
dump so much information without killing a process.  We'd better show some
helpful information to indicate why this happens.

Suggested-by: David Rientjes <rientjes@google.com>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Qian Cai <cai@lca.pw>
Link: http://lkml.kernel.org/r/20200721010127.17238-1-laoar.shao@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/oom_kill.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 48e0db54d838..e90f25d6385d 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -861,6 +861,8 @@ static void __oom_kill_process(struct task_struct *victim, const char *message)
 
 	p = find_lock_task_mm(victim);
 	if (!p) {
+		pr_info("%s: OOM victim %d (%s) is already exiting. Skip killing the task\n",
+			message, task_pid_nr(victim), victim->comm);
 		put_task_struct(victim);
 		return;
 	} else if (victim != p) {

From 15568299b7d9988063afce60731df605ab236e2a Mon Sep 17 00:00:00 2001
From: Mike Kravetz <mike.kravetz@oracle.com>
Date: Tue, 11 Aug 2020 18:31:35 -0700
Subject: [PATCH 335/474] hugetlbfs: prevent filesystem stacking of hugetlbfs

syzbot found issues with having hugetlbfs on a union/overlay as reported
in [1].  Due to the limitations (no write) and special functionality of
hugetlbfs, it does not work well in filesystem stacking.  There are no
know use cases for hugetlbfs stacking.  Rather than making modifications
to get hugetlbfs working in such environments, simply prevent stacking.

[1] https://lore.kernel.org/linux-mm/000000000000b4684e05a2968ca6@google.com/

Reported-by: syzbot+d6ec23007e951dadf3de@syzkaller.appspotmail.com
Suggested-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Miklos Szeredi <mszeredi@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Colin Walters <walters@verbum.org>
Link: http://lkml.kernel.org/r/80f869aa-810d-ef6c-8888-b46cee135907@oracle.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/hugetlbfs/inode.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 523954d00dff..b5c109703daa 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1364,6 +1364,12 @@ hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_magic = HUGETLBFS_MAGIC;
 	sb->s_op = &hugetlbfs_ops;
 	sb->s_time_gran = 1;
+
+	/*
+	 * Due to the special and limited functionality of hugetlbfs, it does
+	 * not work well as a stacking filesystem.
+	 */
+	sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
 	sb->s_root = d_make_root(hugetlbfs_get_root(sb, ctx));
 	if (!sb->s_root)
 		goto out_free;

From 34ae204f18519f0920bd50a644abd6fefc8dbfcf Mon Sep 17 00:00:00 2001
From: Mike Kravetz <mike.kravetz@oracle.com>
Date: Tue, 11 Aug 2020 18:31:38 -0700
Subject: [PATCH 336/474] hugetlbfs: remove call to huge_pte_alloc without
 i_mmap_rwsem

Commit c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing
synchronization") requires callers of huge_pte_alloc to hold i_mmap_rwsem
in at least read mode.  This is because the explicit locking in
huge_pmd_share (called by huge_pte_alloc) was removed.  When restructuring
the code, the call to huge_pte_alloc in the else block at the beginning of
hugetlb_fault was missed.

Unfortunately, that else clause is exercised when there is no page table
entry.  This will likely lead to a call to huge_pmd_share.  If
huge_pmd_share thinks pmd sharing is possible, it will traverse the
mapping tree (i_mmap) without holding i_mmap_rwsem.  If someone else is
modifying the tree, bad things such as addressing exceptions or worse
could happen.

Simply remove the else clause.  It should have been removed previously.
The code following the else will call huge_pte_alloc with the appropriate
locking.

To prevent this type of issue in the future, add routines to assert that
i_mmap_rwsem is held, and call these routines in huge pmd sharing
routines.

Fixes: c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization")
Suggested-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A.Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Prakash Sangappa <prakash.sangappa@oracle.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/e670f327-5cf9-1959-96e4-6dc7cc30d3d5@oracle.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fs.h      | 10 ++++++++++
 include/linux/hugetlb.h |  8 +++++---
 mm/hugetlb.c            | 15 +++++++--------
 mm/rmap.c               |  2 +-
 4 files changed, 23 insertions(+), 12 deletions(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 011af396aa17..7c69dd7c6160 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -518,6 +518,16 @@ static inline void i_mmap_unlock_read(struct address_space *mapping)
 	up_read(&mapping->i_mmap_rwsem);
 }
 
+static inline void i_mmap_assert_locked(struct address_space *mapping)
+{
+	lockdep_assert_held(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_assert_write_locked(struct address_space *mapping)
+{
+	lockdep_assert_held_write(&mapping->i_mmap_rwsem);
+}
+
 /*
  * Might pages of this file be mapped into userspace?
  */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 50650d0d01b9..a520bf26e5d8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -164,7 +164,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 			unsigned long addr, unsigned long sz);
 pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz);
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
+int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
+				unsigned long *addr, pte_t *ptep);
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end);
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
@@ -203,8 +204,9 @@ static inline struct address_space *hugetlb_page_mapping_lock_write(
 	return NULL;
 }
 
-static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr,
-					pte_t *ptep)
+static inline int huge_pmd_unshare(struct mm_struct *mm,
+					struct vm_area_struct *vma,
+					unsigned long *addr, pte_t *ptep)
 {
 	return 0;
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index dffafb5bf2ed..8a18f1234e80 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3967,7 +3967,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			continue;
 
 		ptl = huge_pte_lock(h, mm, ptep);
-		if (huge_pmd_unshare(mm, &address, ptep)) {
+		if (huge_pmd_unshare(mm, vma, &address, ptep)) {
 			spin_unlock(ptl);
 			/*
 			 * We just unmapped a page of PMDs by clearing a PUD.
@@ -4554,10 +4554,6 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
 				VM_FAULT_SET_HINDEX(hstate_index(h));
-	} else {
-		ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
-		if (!ptep)
-			return VM_FAULT_OOM;
 	}
 
 	/*
@@ -5034,7 +5030,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		if (!ptep)
 			continue;
 		ptl = huge_pte_lock(h, mm, ptep);
-		if (huge_pmd_unshare(mm, &address, ptep)) {
+		if (huge_pmd_unshare(mm, vma, &address, ptep)) {
 			pages++;
 			spin_unlock(ptl);
 			shared_pmd = true;
@@ -5415,12 +5411,14 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
  * returns: 1 successfully unmapped a shared pte page
  *	    0 the underlying pte page is not shared, or it is the last user
  */
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
+					unsigned long *addr, pte_t *ptep)
 {
 	pgd_t *pgd = pgd_offset(mm, *addr);
 	p4d_t *p4d = p4d_offset(pgd, *addr);
 	pud_t *pud = pud_offset(p4d, *addr);
 
+	i_mmap_assert_write_locked(vma->vm_file->f_mapping);
 	BUG_ON(page_count(virt_to_page(ptep)) == 0);
 	if (page_count(virt_to_page(ptep)) == 1)
 		return 0;
@@ -5438,7 +5436,8 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	return NULL;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
+				unsigned long *addr, pte_t *ptep)
 {
 	return 0;
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 5fe2dedce1fc..6cce9ef06753 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1469,7 +1469,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 * do this outside rmap routines.
 			 */
 			VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
-			if (huge_pmd_unshare(mm, &address, pvmw.pte)) {
+			if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
 				/*
 				 * huge_pmd_unshare unmapped an entire PMD
 				 * page.  There is no way of knowing exactly

From 0744f2807a4ffb111a31c0769878ec8b125b5241 Mon Sep 17 00:00:00 2001
From: Ralph Campbell <rcampbell@nvidia.com>
Date: Tue, 11 Aug 2020 18:31:41 -0700
Subject: [PATCH 337/474] mm/migrate: optimize migrate_vma_setup() for holes

Patch series "mm/migrate: optimize migrate_vma_setup() for holes".

A simple optimization for migrate_vma_*() when the source vma is not an
anonymous vma and a new test case to exercise it.

This patch (of 2):

When migrating system memory to device private memory, if the source
address range is a valid VMA range and there is no memory or a zero page,
the source PFN array is marked as valid but with no PFN.

This lets the device driver allocate private memory and clear it, then
insert the new device private struct page into the CPU's page tables when
migrate_vma_pages() is called.  migrate_vma_pages() only inserts the new
page if the VMA is an anonymous range.

There is no point in telling the device driver to allocate device private
memory and then not migrate the page.  Instead, mark the source PFN array
entries as not migrating to avoid this overhead.

[rcampbell@nvidia.com: v2]
  Link: http://lkml.kernel.org/r/20200710194840.7602-2-rcampbell@nvidia.com

Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: "Bharata B Rao" <bharata@linux.ibm.com>
Cc: Shuah Khan <shuah@kernel.org>
Link: http://lkml.kernel.org/r/20200710194840.7602-1-rcampbell@nvidia.com
Link: http://lkml.kernel.org/r/20200709165711.26584-1-rcampbell@nvidia.com
Link: http://lkml.kernel.org/r/20200709165711.26584-2-rcampbell@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/migrate.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index 819e55130134..b52f30113366 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2168,6 +2168,16 @@ static int migrate_vma_collect_hole(unsigned long start,
 	struct migrate_vma *migrate = walk->private;
 	unsigned long addr;
 
+	/* Only allow populating anonymous memory. */
+	if (!vma_is_anonymous(walk->vma)) {
+		for (addr = start; addr < end; addr += PAGE_SIZE) {
+			migrate->src[migrate->npages] = 0;
+			migrate->dst[migrate->npages] = 0;
+			migrate->npages++;
+		}
+		return 0;
+	}
+
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
 		migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE;
 		migrate->dst[migrate->npages] = 0;
@@ -2260,8 +2270,10 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 		pte = *ptep;
 
 		if (pte_none(pte)) {
-			mpfn = MIGRATE_PFN_MIGRATE;
-			migrate->cpages++;
+			if (vma_is_anonymous(vma)) {
+				mpfn = MIGRATE_PFN_MIGRATE;
+				migrate->cpages++;
+			}
 			goto next;
 		}
 

From b0fc0f3fca80cf8ea8631eaec6b922bca4c4c2dd Mon Sep 17 00:00:00 2001
From: Ralph Campbell <rcampbell@nvidia.com>
Date: Tue, 11 Aug 2020 18:31:45 -0700
Subject: [PATCH 338/474] mm/migrate: add migrate-shared test for
 migrate_vma_*()

Add a migrate_vma_*() self test for mmap(MAP_SHARED) to verify that
!vma_anonymous() ranges won't be migrated.

Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: "Bharata B Rao" <bharata@linux.ibm.com>
Cc: Shuah Khan <shuah@kernel.org>
Link: http://lkml.kernel.org/r/20200710194840.7602-3-rcampbell@nvidia.com
Link: http://lkml.kernel.org/r/20200709165711.26584-3-rcampbell@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/hmm-tests.c | 35 ++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c
index 91d38a29956b..93fc5cadce61 100644
--- a/tools/testing/selftests/vm/hmm-tests.c
+++ b/tools/testing/selftests/vm/hmm-tests.c
@@ -941,6 +941,41 @@ TEST_F(hmm, migrate_fault)
 	hmm_buffer_free(buffer);
 }
 
+/*
+ * Migrate anonymous shared memory to device private memory.
+ */
+TEST_F(hmm, migrate_shared)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_SHARED | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Migrate memory to device. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages);
+	ASSERT_EQ(ret, -ENOENT);
+
+	hmm_buffer_free(buffer);
+}
+
 /*
  * Try to migrate various memory types to device private memory.
  */

From 4958e4d86ecb011a81f5d80ce2023ef9f10692d8 Mon Sep 17 00:00:00 2001
From: Yang Shi <yang.shi@linux.alibaba.com>
Date: Tue, 11 Aug 2020 18:31:48 -0700
Subject: [PATCH 339/474] mm: thp: remove debug_cow switch

Since commit 3917c80280c93a7123f ("thp: change CoW semantics for
anon-THP"), the CoW page fault of THP has been rewritten, debug_cow is not
used anymore.  So, just remove it.

Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: http://lkml.kernel.org/r/1592270980-116062-1-git-send-email-yang.shi@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h |  7 -------
 mm/huge_memory.c        | 21 ---------------------
 2 files changed, 28 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 17c4c4975145..467302056e17 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -181,13 +181,6 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
 #define transparent_hugepage_use_zero_page()				\
 	(transparent_hugepage_flags &					\
 	 (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
-#ifdef CONFIG_DEBUG_VM
-#define transparent_hugepage_debug_cow()				\
-	(transparent_hugepage_flags &					\
-	 (1<<TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG))
-#else /* CONFIG_DEBUG_VM */
-#define transparent_hugepage_debug_cow() 0
-#endif /* CONFIG_DEBUG_VM */
 
 extern unsigned long thp_get_unmapped_area(struct file *filp,
 		unsigned long addr, unsigned long len, unsigned long pgoff,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 863c495776d7..2ccff8472cd4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -303,24 +303,6 @@ static ssize_t hpage_pmd_size_show(struct kobject *kobj,
 static struct kobj_attribute hpage_pmd_size_attr =
 	__ATTR_RO(hpage_pmd_size);
 
-#ifdef CONFIG_DEBUG_VM
-static ssize_t debug_cow_show(struct kobject *kobj,
-				struct kobj_attribute *attr, char *buf)
-{
-	return single_hugepage_flag_show(kobj, attr, buf,
-				TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
-}
-static ssize_t debug_cow_store(struct kobject *kobj,
-			       struct kobj_attribute *attr,
-			       const char *buf, size_t count)
-{
-	return single_hugepage_flag_store(kobj, attr, buf, count,
-				 TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
-}
-static struct kobj_attribute debug_cow_attr =
-	__ATTR(debug_cow, 0644, debug_cow_show, debug_cow_store);
-#endif /* CONFIG_DEBUG_VM */
-
 static struct attribute *hugepage_attr[] = {
 	&enabled_attr.attr,
 	&defrag_attr.attr,
@@ -328,9 +310,6 @@ static struct attribute *hugepage_attr[] = {
 	&hpage_pmd_size_attr.attr,
 #ifdef CONFIG_SHMEM
 	&shmem_enabled_attr.attr,
-#endif
-#ifdef CONFIG_DEBUG_VM
-	&debug_cow_attr.attr,
 #endif
 	NULL,
 };

From 1a5bae25e3cf95c4e83a97f87a6b5280d9acbb22 Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Tue, 11 Aug 2020 18:31:51 -0700
Subject: [PATCH 340/474] mm/vmstat: add events for THP migration without split

Add following new vmstat events which will help in validating THP
migration without split.  Statistics reported through these new VM events
will help in performance debugging.

1. THP_MIGRATION_SUCCESS
2. THP_MIGRATION_FAILURE
3. THP_MIGRATION_SPLIT

In addition, these new events also update normal page migration statistics
appropriately via PGMIGRATE_SUCCESS and PGMIGRATE_FAILURE.  While here,
this updates current trace event 'mm_migrate_pages' to accommodate now
available THP statistics.

[akpm@linux-foundation.org: s/hpage_nr_pages/thp_nr_pages/]
[ziy@nvidia.com: v2]
  Link: http://lkml.kernel.org/r/C5E3C65C-8253-4638-9D3C-71A61858BB8B@nvidia.com
[anshuman.khandual@arm.com: s/thp_nr_pages/hpage_nr_pages/]
  Link: http://lkml.kernel.org/r/1594287583-16568-1-git-send-email-anshuman.khandual@arm.com

Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Zi Yan <ziy@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Link: http://lkml.kernel.org/r/1594080415-27924-1-git-send-email-anshuman.khandual@arm.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/vm/page_migration.rst | 27 +++++++++++++++
 include/linux/vm_event_item.h       |  3 ++
 include/trace/events/migrate.h      | 17 ++++++++--
 mm/migrate.c                        | 52 ++++++++++++++++++++++++-----
 mm/vmstat.c                         |  3 ++
 5 files changed, 91 insertions(+), 11 deletions(-)

diff --git a/Documentation/vm/page_migration.rst b/Documentation/vm/page_migration.rst
index 1d6cd7db4e43..68883ac485fa 100644
--- a/Documentation/vm/page_migration.rst
+++ b/Documentation/vm/page_migration.rst
@@ -253,5 +253,32 @@ which are function pointers of struct address_space_operations.
      PG_isolated is alias with PG_reclaim flag so driver shouldn't use the flag
      for own purpose.
 
+Monitoring Migration
+=====================
+
+The following events (counters) can be used to monitor page migration.
+
+1. PGMIGRATE_SUCCESS: Normal page migration success. Each count means that a
+   page was migrated. If the page was a non-THP page, then this counter is
+   increased by one. If the page was a THP, then this counter is increased by
+   the number of THP subpages. For example, migration of a single 2MB THP that
+   has 4KB-size base pages (subpages) will cause this counter to increase by
+   512.
+
+2. PGMIGRATE_FAIL: Normal page migration failure. Same counting rules as for
+   _SUCCESS, above: this will be increased by the number of subpages, if it was
+   a THP.
+
+3. THP_MIGRATION_SUCCESS: A THP was migrated without being split.
+
+4. THP_MIGRATION_FAIL: A THP could not be migrated nor it could be split.
+
+5. THP_MIGRATION_SPLIT: A THP was migrated, but not as such: first, the THP had
+   to be split. After splitting, a migration retry was used for it's sub-pages.
+
+THP_MIGRATION_* events also update the appropriate PGMIGRATE_SUCCESS or
+PGMIGRATE_FAIL events. For example, a THP migration failure will cause both
+THP_MIGRATION_FAIL and PGMIGRATE_FAIL to increase.
+
 Christoph Lameter, May 8, 2006.
 Minchan Kim, Mar 28, 2016.
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 24fc7c3ae7d6..2e6ca53b9bbd 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -56,6 +56,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #endif
 #ifdef CONFIG_MIGRATION
 		PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
+		THP_MIGRATION_SUCCESS,
+		THP_MIGRATION_FAIL,
+		THP_MIGRATION_SPLIT,
 #endif
 #ifdef CONFIG_COMPACTION
 		COMPACTMIGRATE_SCANNED, COMPACTFREE_SCANNED,
diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h
index 705b33d1e395..4d434398d64d 100644
--- a/include/trace/events/migrate.h
+++ b/include/trace/events/migrate.h
@@ -46,13 +46,18 @@ MIGRATE_REASON
 TRACE_EVENT(mm_migrate_pages,
 
 	TP_PROTO(unsigned long succeeded, unsigned long failed,
-		 enum migrate_mode mode, int reason),
+		 unsigned long thp_succeeded, unsigned long thp_failed,
+		 unsigned long thp_split, enum migrate_mode mode, int reason),
 
-	TP_ARGS(succeeded, failed, mode, reason),
+	TP_ARGS(succeeded, failed, thp_succeeded, thp_failed,
+		thp_split, mode, reason),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,		succeeded)
 		__field(	unsigned long,		failed)
+		__field(	unsigned long,		thp_succeeded)
+		__field(	unsigned long,		thp_failed)
+		__field(	unsigned long,		thp_split)
 		__field(	enum migrate_mode,	mode)
 		__field(	int,			reason)
 	),
@@ -60,13 +65,19 @@ TRACE_EVENT(mm_migrate_pages,
 	TP_fast_assign(
 		__entry->succeeded	= succeeded;
 		__entry->failed		= failed;
+		__entry->thp_succeeded	= thp_succeeded;
+		__entry->thp_failed	= thp_failed;
+		__entry->thp_split	= thp_split;
 		__entry->mode		= mode;
 		__entry->reason		= reason;
 	),
 
-	TP_printk("nr_succeeded=%lu nr_failed=%lu mode=%s reason=%s",
+	TP_printk("nr_succeeded=%lu nr_failed=%lu nr_thp_succeeded=%lu nr_thp_failed=%lu nr_thp_split=%lu mode=%s reason=%s",
 		__entry->succeeded,
 		__entry->failed,
+		__entry->thp_succeeded,
+		__entry->thp_failed,
+		__entry->thp_split,
 		__print_symbolic(__entry->mode, MIGRATE_MODE),
 		__print_symbolic(__entry->reason, MIGRATE_REASON))
 );
diff --git a/mm/migrate.c b/mm/migrate.c
index b52f30113366..5ea275878383 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1418,22 +1418,35 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 		enum migrate_mode mode, int reason)
 {
 	int retry = 1;
+	int thp_retry = 1;
 	int nr_failed = 0;
 	int nr_succeeded = 0;
+	int nr_thp_succeeded = 0;
+	int nr_thp_failed = 0;
+	int nr_thp_split = 0;
 	int pass = 0;
+	bool is_thp = false;
 	struct page *page;
 	struct page *page2;
 	int swapwrite = current->flags & PF_SWAPWRITE;
-	int rc;
+	int rc, nr_subpages;
 
 	if (!swapwrite)
 		current->flags |= PF_SWAPWRITE;
 
-	for(pass = 0; pass < 10 && retry; pass++) {
+	for (pass = 0; pass < 10 && (retry || thp_retry); pass++) {
 		retry = 0;
+		thp_retry = 0;
 
 		list_for_each_entry_safe(page, page2, from, lru) {
 retry:
+			/*
+			 * THP statistics is based on the source huge page.
+			 * Capture required information that might get lost
+			 * during migration.
+			 */
+			is_thp = PageTransHuge(page);
+			nr_subpages = hpage_nr_pages(page);
 			cond_resched();
 
 			if (PageHuge(page))
@@ -1464,15 +1477,30 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 					unlock_page(page);
 					if (!rc) {
 						list_safe_reset_next(page, page2, lru);
+						nr_thp_split++;
 						goto retry;
 					}
 				}
+				if (is_thp) {
+					nr_thp_failed++;
+					nr_failed += nr_subpages;
+					goto out;
+				}
 				nr_failed++;
 				goto out;
 			case -EAGAIN:
+				if (is_thp) {
+					thp_retry++;
+					break;
+				}
 				retry++;
 				break;
 			case MIGRATEPAGE_SUCCESS:
+				if (is_thp) {
+					nr_thp_succeeded++;
+					nr_succeeded += nr_subpages;
+					break;
+				}
 				nr_succeeded++;
 				break;
 			default:
@@ -1482,19 +1510,27 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 				 * removed from migration page list and not
 				 * retried in the next outer loop.
 				 */
+				if (is_thp) {
+					nr_thp_failed++;
+					nr_failed += nr_subpages;
+					break;
+				}
 				nr_failed++;
 				break;
 			}
 		}
 	}
-	nr_failed += retry;
+	nr_failed += retry + thp_retry;
+	nr_thp_failed += thp_retry;
 	rc = nr_failed;
 out:
-	if (nr_succeeded)
-		count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
-	if (nr_failed)
-		count_vm_events(PGMIGRATE_FAIL, nr_failed);
-	trace_mm_migrate_pages(nr_succeeded, nr_failed, mode, reason);
+	count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
+	count_vm_events(PGMIGRATE_FAIL, nr_failed);
+	count_vm_events(THP_MIGRATION_SUCCESS, nr_thp_succeeded);
+	count_vm_events(THP_MIGRATION_FAIL, nr_thp_failed);
+	count_vm_events(THP_MIGRATION_SPLIT, nr_thp_split);
+	trace_mm_migrate_pages(nr_succeeded, nr_failed, nr_thp_succeeded,
+			       nr_thp_failed, nr_thp_split, mode, reason);
 
 	if (!swapwrite)
 		current->flags &= ~PF_SWAPWRITE;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 3bb034c99887..727a26d1ec1d 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1277,6 +1277,9 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_MIGRATION
 	"pgmigrate_success",
 	"pgmigrate_fail",
+	"thp_migration_success",
+	"thp_migration_fail",
+	"thp_migration_split",
 #endif
 #ifdef CONFIG_COMPACTION
 	"compact_migrate_scanned",

From 835832ba01bb444c7e45139e4b807527c119dafc Mon Sep 17 00:00:00 2001
From: Jianqun Xu <jay.xu@rock-chips.com>
Date: Tue, 11 Aug 2020 18:31:54 -0700
Subject: [PATCH 341/474] mm/cma.c: fix NULL pointer dereference when cma could
 not be activated

In some case the cma area could not be activated, but the cma_alloc be
used under this case, then the kernel will crash caused by NULL pointer
dereference.

Add bitmap valid check in cma_alloc to avoid this issue.

Signed-off-by: Jianqun Xu <jay.xu@rock-chips.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Link: http://lkml.kernel.org/r/20200615010123.15596-1-jay.xu@rock-chips.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/cma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/cma.c b/mm/cma.c
index 26ecff818881..3a18f8d8ea5e 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -425,7 +425,7 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align,
 	struct page *page = NULL;
 	int ret = -ENOMEM;
 
-	if (!cma || !cma->count)
+	if (!cma || !cma->count || !cma->bitmap)
 		return NULL;
 
 	pr_debug("%s(cma %p, count %zu, align %d)\n", __func__, (void *)cma,

From 18e98e56f4407b8c766b6f6d9f2850fd2a081e4d Mon Sep 17 00:00:00 2001
From: Barry Song <song.bao.hua@hisilicon.com>
Date: Tue, 11 Aug 2020 18:31:57 -0700
Subject: [PATCH 342/474] mm: cma: fix the name of CMA areas

Patch series "mm: fix the names of general cma and hugetlb cma", v2.

The current code of CMA can only work when users pass a const string as
name parameter.  we need to fix the way to handle names in CMA.  On the
other hand, to avoid name conflicts after enabling CMA_DEBUGFS, each
hugetlb should get a different CMA name.

This patch (of 2):

If users give a name saved in stack, the current code will generate magic
pointer.  if users don't give a name(NULL), kasprintf() will always return
NULL as we are at the early stage.  that means cma_init_reserved_mem()
will return -ENOMEM if users set name parameter as NULL.

[natechancellor@gmail.com: return cma->name directly in cma_get_name]
  Link: https://github.com/ClangBuiltLinux/linux/issues/1063
  Link: http://lkml.kernel.org/r/20200623015840.621964-1-natechancellor@gmail.com

Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/20200616223131.33828-2-song.bao.hua@hisilicon.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/cma.c | 15 +++++++--------
 mm/cma.h |  4 +++-
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/mm/cma.c b/mm/cma.c
index 3a18f8d8ea5e..aa2df0bd49c3 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -52,7 +52,7 @@ unsigned long cma_get_size(const struct cma *cma)
 
 const char *cma_get_name(const struct cma *cma)
 {
-	return cma->name ? cma->name : "(undefined)";
+	return cma->name;
 }
 
 static unsigned long cma_bitmap_aligned_mask(const struct cma *cma,
@@ -202,13 +202,12 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
 	 * subsystems (like slab allocator) are available.
 	 */
 	cma = &cma_areas[cma_area_count];
-	if (name) {
-		cma->name = name;
-	} else {
-		cma->name = kasprintf(GFP_KERNEL, "cma%d\n", cma_area_count);
-		if (!cma->name)
-			return -ENOMEM;
-	}
+
+	if (name)
+		snprintf(cma->name, CMA_MAX_NAME, name);
+	else
+		snprintf(cma->name, CMA_MAX_NAME,  "cma%d\n", cma_area_count);
+
 	cma->base_pfn = PFN_DOWN(base);
 	cma->count = size >> PAGE_SHIFT;
 	cma->order_per_bit = order_per_bit;
diff --git a/mm/cma.h b/mm/cma.h
index 6698fa63279b..20f6e24bc477 100644
--- a/mm/cma.h
+++ b/mm/cma.h
@@ -4,6 +4,8 @@
 
 #include <linux/debugfs.h>
 
+#define CMA_MAX_NAME 64
+
 struct cma {
 	unsigned long   base_pfn;
 	unsigned long   count;
@@ -15,7 +17,7 @@ struct cma {
 	spinlock_t mem_head_lock;
 	struct debugfs_u32_array dfs_bitmap;
 #endif
-	const char *name;
+	char name[CMA_MAX_NAME];
 };
 
 extern struct cma cma_areas[MAX_CMA_AREAS];

From 29d0f41d232393482ced6a233126832df3429ad2 Mon Sep 17 00:00:00 2001
From: Barry Song <song.bao.hua@hisilicon.com>
Date: Tue, 11 Aug 2020 18:32:00 -0700
Subject: [PATCH 343/474] mm: hugetlb: fix the name of hugetlb CMA

Once we enable CMA_DEBUGFS, we will get the below errors: directory
'cma-hugetlb' with parent 'cma' already present.

We should have different names for different CMA areas.

Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/20200616223131.33828-3-song.bao.hua@hisilicon.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/hugetlb.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8a18f1234e80..6b6b0d5cc642 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5707,12 +5707,14 @@ void __init hugetlb_cma_reserve(int order)
 	reserved = 0;
 	for_each_node_state(nid, N_ONLINE) {
 		int res;
+		char name[20];
 
 		size = min(per_node, hugetlb_cma_size - reserved);
 		size = round_up(size, PAGE_SIZE << order);
 
+		snprintf(name, 20, "hugetlb%d", nid);
 		res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order,
-						 0, false, "hugetlb",
+						 0, false, name,
 						 &hugetlb_cma[nid], nid);
 		if (res) {
 			pr_warn("hugetlb_cma: reservation failed: err %d, node %d",

From 3a5139f1c5bb76d69756fb8f13fffa173e261153 Mon Sep 17 00:00:00 2001
From: Mike Kravetz <mike.kravetz@oracle.com>
Date: Tue, 11 Aug 2020 18:32:03 -0700
Subject: [PATCH 344/474] cma: don't quit at first error when activating
 reserved areas

The routine cma_init_reserved_areas is designed to activate all
reserved cma areas.  It quits when it first encounters an error.
This can leave some areas in a state where they are reserved but
not activated.  There is no feedback to code which performed the
reservation.  Attempting to allocate memory from areas in such a
state will result in a BUG.

Modify cma_init_reserved_areas to always attempt to activate all
areas.  The called routine, cma_activate_area is responsible for
leaving the area in a valid state.  No one is making active use
of returned error codes, so change the routine to void.

How to reproduce:  This example uses kernelcore, hugetlb and cma
as an easy way to reproduce.  However, this is a more general cma
issue.

Two node x86 VM 16GB total, 8GB per node
Kernel command line parameters, kernelcore=4G hugetlb_cma=8G
Related boot time messages,
  hugetlb_cma: reserve 8192 MiB, up to 4096 MiB per node
  cma: Reserved 4096 MiB at 0x0000000100000000
  hugetlb_cma: reserved 4096 MiB on node 0
  cma: Reserved 4096 MiB at 0x0000000300000000
  hugetlb_cma: reserved 4096 MiB on node 1
  cma: CMA area hugetlb could not be activated

 # echo 8 > /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages

  BUG: kernel NULL pointer dereference, address: 0000000000000000
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 0 P4D 0
  Oops: 0000 [#1] SMP PTI
  ...
  Call Trace:
    bitmap_find_next_zero_area_off+0x51/0x90
    cma_alloc+0x1a5/0x310
    alloc_fresh_huge_page+0x78/0x1a0
    alloc_pool_huge_page+0x6f/0xf0
    set_max_huge_pages+0x10c/0x250
    nr_hugepages_store_common+0x92/0x120
    ? __kmalloc+0x171/0x270
    kernfs_fop_write+0xc1/0x1a0
    vfs_write+0xc7/0x1f0
    ksys_write+0x5f/0xe0
    do_syscall_64+0x4d/0x90
    entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: c64be2bb1c6e ("drivers: add Contiguous Memory Allocator")
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Barry Song <song.bao.hua@hisilicon.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200730163123.6451-1-mike.kravetz@oracle.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/cma.c | 23 +++++++++--------------
 1 file changed, 9 insertions(+), 14 deletions(-)

diff --git a/mm/cma.c b/mm/cma.c
index aa2df0bd49c3..7f415d7cda9f 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -93,17 +93,15 @@ static void cma_clear_bitmap(struct cma *cma, unsigned long pfn,
 	mutex_unlock(&cma->lock);
 }
 
-static int __init cma_activate_area(struct cma *cma)
+static void __init cma_activate_area(struct cma *cma)
 {
 	unsigned long base_pfn = cma->base_pfn, pfn = base_pfn;
 	unsigned i = cma->count >> pageblock_order;
 	struct zone *zone;
 
 	cma->bitmap = bitmap_zalloc(cma_bitmap_maxno(cma), GFP_KERNEL);
-	if (!cma->bitmap) {
-		cma->count = 0;
-		return -ENOMEM;
-	}
+	if (!cma->bitmap)
+		goto out_error;
 
 	WARN_ON_ONCE(!pfn_valid(pfn));
 	zone = page_zone(pfn_to_page(pfn));
@@ -133,25 +131,22 @@ static int __init cma_activate_area(struct cma *cma)
 	spin_lock_init(&cma->mem_head_lock);
 #endif
 
-	return 0;
+	return;
 
 not_in_zone:
-	pr_err("CMA area %s could not be activated\n", cma->name);
 	bitmap_free(cma->bitmap);
+out_error:
 	cma->count = 0;
-	return -EINVAL;
+	pr_err("CMA area %s could not be activated\n", cma->name);
+	return;
 }
 
 static int __init cma_init_reserved_areas(void)
 {
 	int i;
 
-	for (i = 0; i < cma_area_count; i++) {
-		int ret = cma_activate_area(&cma_areas[i]);
-
-		if (ret)
-			return ret;
-	}
+	for (i = 0; i < cma_area_count; i++)
+		cma_activate_area(&cma_areas[i]);
 
 	return 0;
 }

From af161bee93332a1ff10ba029f41936d21850ae82 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 11 Aug 2020 18:32:06 -0700
Subject: [PATCH 345/474] include/linux/sched/mm.h: optimize
 current_gfp_context()

The current_gfp_context() converts a number of PF_MEMALLOC_* per-process
flags into the corresponding GFP_* flags for memory allocation.  In that
function, current->flags is accessed 3 times.  That may lead to duplicated
access of the same memory location.

This is not usually a problem with minimal debug config options on as the
compiler can optimize away the duplicated memory accesses.  With most of
the debug config options on, however, that may not be the case.  For
example, the x86-64 object size of the __need_fs_reclaim() in a debug
kernel that calls current_gfp_context() was 309 bytes.  With this patch
applied, the object size is reduced to 202 bytes.  This is a saving of 107
bytes and will probably be slightly faster too.

Use READ_ONCE() to access current->flags to prevent the compiler from
possibly accessing current->flags multiple times.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Michel Lespinasse <walken@google.com>
Link: http://lkml.kernel.org/r/20200618212936.9776-1-longman@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched/mm.h | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 85023ddc2dc2..f889e332912f 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -178,14 +178,16 @@ static inline bool in_vfork(struct task_struct *tsk)
  */
 static inline gfp_t current_gfp_context(gfp_t flags)
 {
-	if (unlikely(current->flags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) {
+	unsigned int pflags = READ_ONCE(current->flags);
+
+	if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) {
 		/*
 		 * NOIO implies both NOIO and NOFS and it is a weaker context
 		 * so always make sure it makes precedence
 		 */
-		if (current->flags & PF_MEMALLOC_NOIO)
+		if (pflags & PF_MEMALLOC_NOIO)
 			flags &= ~(__GFP_IO | __GFP_FS);
-		else if (current->flags & PF_MEMALLOC_NOFS)
+		else if (pflags & PF_MEMALLOC_NOFS)
 			flags &= ~__GFP_FS;
 	}
 	return flags;

From d49653f35adff8c778e7c5fbd4dbdf929594eca8 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 11 Aug 2020 18:32:09 -0700
Subject: [PATCH 346/474] mm: mmu_notifier: fix and extend kerneldoc

Fix W=1 compile warnings (invalid kerneldoc):

    mm/mmu_notifier.c:187: warning: Function parameter or member 'interval_sub' not described in 'mmu_interval_read_bgin'
    mm/mmu_notifier.c:708: warning: Function parameter or member 'subscription' not described in 'mmu_notifier_registr'
    mm/mmu_notifier.c:708: warning: Excess function parameter 'mn' description in 'mmu_notifier_register'
    mm/mmu_notifier.c:880: warning: Function parameter or member 'subscription' not described in 'mmu_notifier_put'
    mm/mmu_notifier.c:880: warning: Excess function parameter 'mn' description in 'mmu_notifier_put'
    mm/mmu_notifier.c:982: warning: Function parameter or member 'ops' not described in 'mmu_interval_notifier_insert'

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: http://lkml.kernel.org/r/20200728171109.28687-4-krzk@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/mmu_notifier.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 352bb9f3ecc0..4fc918163dd3 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -166,7 +166,7 @@ static void mn_itree_inv_end(struct mmu_notifier_subscriptions *subscriptions)
 /**
  * mmu_interval_read_begin - Begin a read side critical section against a VA
  *                           range
- * interval_sub: The interval subscription
+ * @interval_sub: The interval subscription
  *
  * mmu_iterval_read_begin()/mmu_iterval_read_retry() implement a
  * collision-retry scheme similar to seqcount for the VA range under
@@ -686,7 +686,7 @@ EXPORT_SYMBOL_GPL(__mmu_notifier_register);
 
 /**
  * mmu_notifier_register - Register a notifier on a mm
- * @mn: The notifier to attach
+ * @subscription: The notifier to attach
  * @mm: The mm to attach the notifier to
  *
  * Must not hold mmap_lock nor any other VM related lock when calling
@@ -856,7 +856,7 @@ static void mmu_notifier_free_rcu(struct rcu_head *rcu)
 
 /**
  * mmu_notifier_put - Release the reference on the notifier
- * @mn: The notifier to act on
+ * @subscription: The notifier to act on
  *
  * This function must be paired with each mmu_notifier_get(), it releases the
  * reference obtained by the get. If this is the last reference then process
@@ -965,7 +965,8 @@ static int __mmu_interval_notifier_insert(
  * @interval_sub: Interval subscription to register
  * @start: Starting virtual address to monitor
  * @length: Length of the range to monitor
- * @mm : mm_struct to attach to
+ * @mm: mm_struct to attach to
+ * @ops: Interval notifier operations to be called on matching events
  *
  * This function subscribes the interval notifier for notifications from the
  * mm.  Upon return the ops related to mmu_interval_notifier will be called

From fe124c95df9e2acf202910b0510300e37afe074b Mon Sep 17 00:00:00 2001
From: Daniel Jordan <daniel.m.jordan@oracle.com>
Date: Tue, 11 Aug 2020 18:32:12 -0700
Subject: [PATCH 347/474] x86/mm: use max memory block size on bare metal

Some of our servers spend significant time at kernel boot initializing
memory block sysfs directories and then creating symlinks between them and
the corresponding nodes.  The slowness happens because the machines get
stuck with the smallest supported memory block size on x86 (128M), which
results in 16,288 directories to cover the 2T of installed RAM.  The
search for each memory block is noticeable even with commit 4fb6eabf1037
("drivers/base/memory.c: cache memory blocks in xarray to accelerate
lookup").

Commit 078eb6aa50dc ("x86/mm/memory_hotplug: determine block size based on
the end of boot memory") chooses the block size based on alignment with
memory end.  That addresses hotplug failures in qemu guests, but for bare
metal systems whose memory end isn't aligned to even the smallest size, it
leaves them at 128M.

Make kernels that aren't running on a hypervisor use the largest supported
size (2G) to minimize overhead on big machines.  Kernel boot goes 7%
faster on the aforementioned servers, shaving off half a second.

[daniel.m.jordan@oracle.com: v3]
  Link: http://lkml.kernel.org/r/20200714205450.945834-1-daniel.m.jordan@oracle.com

Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Sistare <steven.sistare@oracle.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20200609225451.3542648-1-daniel.m.jordan@oracle.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/mm/init_64.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 3b246ae40c8f..a4ac13cc3fdc 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1452,6 +1452,15 @@ static unsigned long probe_memory_block_size(void)
 		goto done;
 	}
 
+	/*
+	 * Use max block size to minimize overhead on bare metal, where
+	 * alignment for memory hotplug isn't a concern.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		bz = MAX_BLOCK_SIZE;
+		goto done;
+	}
+
 	/* Find the largest allowed block size that aligns to memory end */
 	for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
 		if (IS_ALIGNED(boot_mem_end, bz))

From d622ecec5f57ee7e27fbc6db222d8cbaf3c59478 Mon Sep 17 00:00:00 2001
From: Jia He <justin.he@arm.com>
Date: Tue, 11 Aug 2020 18:32:16 -0700
Subject: [PATCH 348/474] mm/memory_hotplug: introduce default dummy
 memory_add_physaddr_to_nid()

This is to introduce a general dummy helper.  memory_add_physaddr_to_nid()
is a fallback option to get the nid in case NUMA_NO_NID is detected.

After this patch, arm64/sh/s390 can simply use the general dummy version.
PowerPC/x86/ia64 will still use their specific version.

This is the preparation to set a fallback value for dev_dax->target_node.

Signed-off-by: Jia He <justin.he@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Chuhong Yuan <hslester96@gmail.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Jonathan Cameron <Jonathan.Cameron@Huawei.com>
Cc: Kaly Xin <Kaly.Xin@arm.com>
Link: http://lkml.kernel.org/r/20200710031619.18762-2-justin.he@arm.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/mm/numa.c | 10 ----------
 arch/ia64/mm/numa.c  |  2 --
 arch/sh/mm/init.c    |  9 ---------
 arch/x86/mm/numa.c   |  1 -
 mm/memory_hotplug.c  | 10 ++++++++++
 5 files changed, 10 insertions(+), 22 deletions(-)

diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index aafcee3e3f7e..73f8b49d485c 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -461,13 +461,3 @@ void __init arm64_numa_init(void)
 
 	numa_init(dummy_numa_init);
 }
-
-/*
- * We hope that we will be hotplugging memory on nodes we already know about,
- * such that acpi_get_node() succeeds and we never fall back to this...
- */
-int memory_add_physaddr_to_nid(u64 addr)
-{
-	pr_warn("Unknown node for memory at 0x%llx, assuming node 0\n", addr);
-	return 0;
-}
diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c
index 5e1015eb6d0d..f34964271101 100644
--- a/arch/ia64/mm/numa.c
+++ b/arch/ia64/mm/numa.c
@@ -106,7 +106,5 @@ int memory_add_physaddr_to_nid(u64 addr)
 		return 0;
 	return nid;
 }
-
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
 #endif
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 613de8096335..cd1379360f08 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -425,15 +425,6 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return ret;
 }
 
-#ifdef CONFIG_NUMA
-int memory_add_physaddr_to_nid(u64 addr)
-{
-	/* Node 0 for now.. */
-	return 0;
-}
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-#endif
-
 void arch_remove_memory(int nid, u64 start, u64 size,
 			struct vmem_altmap *altmap)
 {
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index b05f45e5e8e2..aa76ec2d359b 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -929,5 +929,4 @@ int memory_add_physaddr_to_nid(u64 start)
 		nid = numa_meminfo.blk[0].nid;
 	return nid;
 }
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ac6961abaa10..6289a909ea36 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -350,6 +350,16 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
 	return err;
 }
 
+#ifdef CONFIG_NUMA
+int __weak memory_add_physaddr_to_nid(u64 start)
+{
+	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
+			start);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+#endif
+
 /* find the smallest valid pfn in the range [start_pfn, end_pfn) */
 static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
 				     unsigned long start_pfn,

From b4223a510e2ab1bf0f971d50af7c1431014b25ad Mon Sep 17 00:00:00 2001
From: Jia He <justin.he@arm.com>
Date: Tue, 11 Aug 2020 18:32:20 -0700
Subject: [PATCH 349/474] mm/memory_hotplug: fix unpaired
 mem_hotplug_begin/done

When check_memblock_offlined_cb() returns failed rc(e.g. the memblock is
online at that time), mem_hotplug_begin/done is unpaired in such case.

Therefore a warning:
 Call Trace:
  percpu_up_write+0x33/0x40
  try_remove_memory+0x66/0x120
  ? _cond_resched+0x19/0x30
  remove_memory+0x2b/0x40
  dev_dax_kmem_remove+0x36/0x72 [kmem]
  device_release_driver_internal+0xf0/0x1c0
  device_release_driver+0x12/0x20
  bus_remove_device+0xe1/0x150
  device_del+0x17b/0x3e0
  unregister_dev_dax+0x29/0x60
  devm_action_release+0x15/0x20
  release_nodes+0x19a/0x1e0
  devres_release_all+0x3f/0x50
  device_release_driver_internal+0x100/0x1c0
  driver_detach+0x4c/0x8f
  bus_remove_driver+0x5c/0xd0
  driver_unregister+0x31/0x50
  dax_pmem_exit+0x10/0xfe0 [dax_pmem]

Fixes: f1037ec0cc8a ("mm/memory_hotplug: fix remove_memory() lockdep splat")
Signed-off-by: Jia He <justin.he@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Cc: <stable@vger.kernel.org>	[5.6+]
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chuhong Yuan <hslester96@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@Huawei.com>
Cc: Kaly Xin <Kaly.Xin@arm.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/20200710031619.18762-3-justin.he@arm.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memory_hotplug.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 6289a909ea36..ce3d858319bd 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1757,7 +1757,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
 	 */
 	rc = walk_memory_blocks(start, size, NULL, check_memblock_offlined_cb);
 	if (rc)
-		goto done;
+		return rc;
 
 	/* remove memmap entry */
 	firmware_map_remove(start, start + size, "System RAM");
@@ -1781,9 +1781,8 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
 
 	try_offline_node(nid);
 
-done:
 	mem_hotplug_done();
-	return rc;
+	return 0;
 }
 
 /**

From de1193f0be66f88e2c6d0fd965137668fc2ec4a5 Mon Sep 17 00:00:00 2001
From: Charan Teja Reddy <charante@codeaurora.org>
Date: Tue, 11 Aug 2020 18:32:24 -0700
Subject: [PATCH 350/474] mm, memory_hotplug: update pcp lists everytime
 onlining a memory block

When onlining a first memory block in a zone, pcp lists are not updated
thus pcp struct will have the default setting of ->high = 0,->batch = 1.

This means till the second memory block in a zone(if it have) is onlined
the pcp lists of this zone will not contain any pages because pcp's
->count is always greater than ->high thus free_pcppages_bulk() is called
to free batch size(=1) pages every time system wants to add a page to the
pcp list through free_unref_page().

To put this in a word, system is not using benefits offered by the pcp
lists when there is a single onlineable memory block in a zone.  Correct
this by always updating the pcp lists when memory block is onlined.

Fixes: 1f522509c77a ("mem-hotplug: avoid multiple zones sharing same boot strapping boot_pageset")
Signed-off-by: Charan Teja Reddy <charante@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Link: http://lkml.kernel.org/r/1596372896-15336-1-git-send-email-charante@codeaurora.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memory_hotplug.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ce3d858319bd..0a9e1972fbe7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -854,8 +854,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 	node_states_set_node(nid, &arg);
 	if (need_zonelists_rebuild)
 		build_all_zonelists(NULL);
-	else
-		zone_pcp_update(zone);
+	zone_pcp_update(zone);
 
 	init_per_zone_wmark_min();
 

From 1067b261cc973d68c29de54ef0587c56786e6bd5 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:27 -0700
Subject: [PATCH 351/474] mm: drop duplicated words in <linux/pgtable.h>

Drop the doubled words "used" and "by".

Drop the repeated acronym "TLB" and make several other fixes around it.
(capital letters, spellos)

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Link: http://lkml.kernel.org/r/2bb6e13e-44df-4920-52d9-4d3539945f73@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pgtable.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 53e97da1e8e2..a124c21e3204 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -804,7 +804,7 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
 
 /*
  * No-op macros that just return the current protection value. Defined here
- * because these macros can be used used even if CONFIG_MMU is not defined.
+ * because these macros can be used even if CONFIG_MMU is not defined.
  */
 
 #ifndef pgprot_nx
@@ -1234,7 +1234,7 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
  * Technically a PTE can be PROTNONE even when not doing NUMA balancing but
  * the only case the kernel cares is for NUMA balancing and is only ever set
  * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked
- * _PAGE_PROTNONE so by by default, implement the helper as "always no". It
+ * _PAGE_PROTNONE so by default, implement the helper as "always no". It
  * is the responsibility of the caller to distinguish between PROT_NONE
  * protections and NUMA hinting fault protections.
  */
@@ -1318,10 +1318,10 @@ static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 /*
  * ARCHes with special requirements for evicting THP backing TLB entries can
  * implement this. Otherwise also, it can help optimize normal TLB flush in
- * THP regime. stock flush_tlb_range() typically has optimization to nuke the
- * entire TLB TLB if flush span is greater than a threshold, which will
- * likely be true for a single huge page. Thus a single thp flush will
- * invalidate the entire TLB which is not desitable.
+ * THP regime. Stock flush_tlb_range() typically has optimization to nuke the
+ * entire TLB if flush span is greater than a threshold, which will
+ * likely be true for a single huge page. Thus a single THP flush will
+ * invalidate the entire TLB which is not desirable.
  * e.g. see arch/arc: flush_pmd_tlb_range
  */
 #define flush_pmd_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)

From 11192337206d2211bce3ba4ec1575439b6045654 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:30 -0700
Subject: [PATCH 352/474] mm: drop duplicated words in <linux/mm.h>

Drop the doubled words "to" and "the".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Link: http://lkml.kernel.org/r/d9fae8d6-0d60-4d52-9385-3199ee98de49@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f6a82f9bccd7..f97b10117d44 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -479,7 +479,7 @@ static inline bool fault_flag_allow_retry_first(unsigned int flags)
 	{ FAULT_FLAG_INTERRUPTIBLE,	"INTERRUPTIBLE" }
 
 /*
- * vm_fault is filled by the the pagefault handler and passed to the vma's
+ * vm_fault is filled by the pagefault handler and passed to the vma's
  * ->fault function. The vma's ->fault is responsible for returning a bitmask
  * of VM_FAULT_xxx flags that give details about how the fault was handled.
  *
@@ -2599,7 +2599,7 @@ extern unsigned long stack_guard_gap;
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
 
-/* CONFIG_STACK_GROWSUP still needs to to grow downwards at some places */
+/* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */
 extern int expand_downwards(struct vm_area_struct *vma,
 		unsigned long address);
 #if VM_GROWSUP

From 3ecabd31341fb4307f156a2bf4467c3f8fa9101b Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:33 -0700
Subject: [PATCH 353/474] include/linux/highmem.h: fix duplicated words in a
 comment

Change the doubled word "is" in a comment to "it is".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/ad605959-0083-4794-8d31-6b073300dd6f@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/highmem.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index d6e82e3de027..14e6202ce47f 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -73,7 +73,7 @@ static inline void kunmap(struct page *page)
  * no global lock is needed and because the kmap code must perform a global TLB
  * invalidation when the kmap pool wraps.
  *
- * However when holding an atomic kmap is is not legal to sleep, so atomic
+ * However when holding an atomic kmap it is not legal to sleep, so atomic
  * kmaps are appropriate for short, tight code paths only.
  *
  * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap

From c82f16b52cb3b50ac1b47e6c590e3dddefc5a97c Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:36 -0700
Subject: [PATCH 354/474] include/linux/frontswap.h: drop duplicated word in a
 comment

Drop the doubled word "in" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Link: http://lkml.kernel.org/r/3af7ed91-ad62-8445-40a4-9e07a64b9523@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/frontswap.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
index 6d775984905b..b07d88c92bb2 100644
--- a/include/linux/frontswap.h
+++ b/include/linux/frontswap.h
@@ -10,7 +10,7 @@
 /*
  * Return code to denote that requested number of
  * frontswap pages are unused(moved to page cache).
- * Used in in shmem_unuse and try_to_unuse.
+ * Used in shmem_unuse and try_to_unuse.
  */
 #define FRONTSWAP_PAGES_UNUSED	2
 

From 0845f83122d93ae3bafa7ea10209de2148a3b9bc Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:40 -0700
Subject: [PATCH 355/474] include/linux/memcontrol.h: drop duplicate word and
 fix spello

Drop the doubled word "for" in a comment.
Fix spello of "incremented".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Chris Down <chris@chrisdown.name>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Link: http://lkml.kernel.org/r/b04aa2e4-7c95-12f0-599d-43d07fb28134@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 2c2d301eac33..385237e4cb44 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -65,8 +65,8 @@ struct mem_cgroup_id {
 
 /*
  * Per memcg event counter is incremented at every pagein/pageout. With THP,
- * it will be incremated by the number of pages. This counter is used for
- * for trigger some periodic events. This is straightforward and better
+ * it will be incremented by the number of pages. This counter is used
+ * to trigger some periodic events. This is straightforward and better
  * than using jiffies etc. to handle periodic memcg event.
  */
 enum mem_cgroup_events_target {

From c56771b3095d4f1af82847081b6781fc03a13904 Mon Sep 17 00:00:00 2001
From: Arvind Sankar <nivedita@alum.mit.edu>
Date: Tue, 11 Aug 2020 18:32:43 -0700
Subject: [PATCH 356/474] sh/mm: drop unused MAX_PHYSADDR_BITS

The macro is not used anywhere, so remove the definition.

Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Link: http://lkml.kernel.org/r/20200723231544.17274-3-nivedita@alum.mit.edu
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/sh/include/asm/sparsemem.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/sh/include/asm/sparsemem.h b/arch/sh/include/asm/sparsemem.h
index 4eb899751e45..084706bb8cca 100644
--- a/arch/sh/include/asm/sparsemem.h
+++ b/arch/sh/include/asm/sparsemem.h
@@ -5,11 +5,9 @@
 #ifdef __KERNEL__
 /*
  * SECTION_SIZE_BITS		2^N: how big each section will be
- * MAX_PHYSADDR_BITS		2^N: how much physical address space we have
- * MAX_PHYSMEM_BITS		2^N: how much memory we can have in that space
+ * MAX_PHYSMEM_BITS		2^N: how much physical address space we have
  */
 #define SECTION_SIZE_BITS	26
-#define MAX_PHYSADDR_BITS	32
 #define MAX_PHYSMEM_BITS	32
 
 #endif

From 6f8c00ff5aa88c847af9af35131d72fae480b566 Mon Sep 17 00:00:00 2001
From: Arvind Sankar <nivedita@alum.mit.edu>
Date: Tue, 11 Aug 2020 18:32:46 -0700
Subject: [PATCH 357/474] sparc: drop unused MAX_PHYSADDR_BITS

The macro is not used anywhere, so remove the definition.

Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Link: http://lkml.kernel.org/r/20200723231544.17274-4-nivedita@alum.mit.edu
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/sparc/include/asm/sparsemem.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/sparc/include/asm/sparsemem.h b/arch/sparc/include/asm/sparsemem.h
index 1dd1b61432db..aa9a676bc341 100644
--- a/arch/sparc/include/asm/sparsemem.h
+++ b/arch/sparc/include/asm/sparsemem.h
@@ -7,7 +7,6 @@
 #include <asm/page.h>
 
 #define SECTION_SIZE_BITS       30
-#define MAX_PHYSADDR_BITS       MAX_PHYS_ADDRESS_BITS
 #define MAX_PHYSMEM_BITS        MAX_PHYS_ADDRESS_BITS
 
 #endif /* !(__KERNEL__) */

From a1c1dbeb2e1a995c374d4954b36269070725f3a0 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:49 -0700
Subject: [PATCH 358/474] mm/compaction.c: delete duplicated word

Drop the repeated word "a".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-2-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/compaction.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 5e8f2e22b73e..b89581bf859c 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1477,7 +1477,7 @@ static void isolate_freepages(struct compact_control *cc)
 	 * this pfn aligned down to the pageblock boundary, because we do
 	 * block_start_pfn -= pageblock_nr_pages in the for loop.
 	 * For ending point, take care when isolating in last pageblock of a
-	 * a zone which ends in the middle of a pageblock.
+	 * zone which ends in the middle of a pageblock.
 	 * The low boundary is the end of the pageblock the migration scanner
 	 * is using.
 	 */

From ce89fddfe0b73e99b2edd8cfd21afd461258a2df Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:53 -0700
Subject: [PATCH 359/474] mm/filemap.c: delete duplicated word

Drop the repeated word "the".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-3-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/filemap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index f2bb5ff0293d..8e75bce0346d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2885,7 +2885,7 @@ static struct page *do_read_cache_page(struct address_space *mapping,
 	 * Case a, the page will be up to date when the page is unlocked.
 	 *    There is no need to serialise on the page lock here as the page
 	 *    is pinned so the lock gives no additional protection. Even if the
-	 *    the page is truncated, the data is still valid if PageUptodate as
+	 *    page is truncated, the data is still valid if PageUptodate as
 	 *    it's a race vs truncate race.
 	 * Case b, the page will not be up to date
 	 * Case c, the page may be truncated but in itself, the data may still

From 0cb80a2fb5bcd10f8aa7747e35511b52053232ae Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:56 -0700
Subject: [PATCH 360/474] mm/hmm.c: delete duplicated word

Drop the repeated word "pages".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-4-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/hmm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/hmm.c b/mm/hmm.c
index 0809baee49d0..bb279319bf40 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -249,7 +249,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		swp_entry_t entry = pte_to_swp_entry(pte);
 
 		/*
-		 * Never fault in device private pages pages, but just report
+		 * Never fault in device private pages, but just report
 		 * the PFN even if not present.
 		 */
 		if (hmm_is_device_private_entry(range, entry)) {

From 9e7ee40097ec654d5b9c7803b8e6dc560d17bbe3 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:32:59 -0700
Subject: [PATCH 361/474] mm/hugetlb.c: delete duplicated words

Drop the repeated word "the" in two places.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-5-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/hugetlb.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6b6b0d5cc642..b66bf74e999e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -133,7 +133,7 @@ void hugepage_put_subpool(struct hugepage_subpool *spool)
 /*
  * Subpool accounting for allocating and reserving pages.
  * Return -ENOMEM if there are not enough resources to satisfy the
- * the request.  Otherwise, return the number of pages by which the
+ * request.  Otherwise, return the number of pages by which the
  * global pools must be adjusted (upward).  The returned value may
  * only be different than the passed value (delta) in the case where
  * a subpool minimum size must be maintained.
@@ -2167,7 +2167,7 @@ static void return_unused_surplus_pages(struct hstate *h,
 	 * evenly across all nodes with memory. Iterate across these nodes
 	 * until we can no longer free unreserved surplus pages. This occurs
 	 * when the nodes with surplus pages have no free pages.
-	 * free_pool_huge_page() will balance the the freed pages across the
+	 * free_pool_huge_page() will balance the freed pages across the
 	 * on-line nodes with memory and will handle the hstate accounting.
 	 *
 	 * Note that we decrement resv_huge_pages as we free the pages.  If

From ac5ddd0fcea9bfee1d48884e7fa94e706d213aac Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:02 -0700
Subject: [PATCH 362/474] mm/memcontrol.c: delete duplicated words

Drop the repeated word "down".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-6-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memcontrol.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c6c579217855..d59fd9af6e63 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2422,7 +2422,7 @@ static void high_work_func(struct work_struct *work)
  *
  * - MEMCG_DELAY_PRECISION_SHIFT: Extra precision bits while translating the
  *   overage ratio to a delay.
- * - MEMCG_DELAY_SCALING_SHIFT: The number of bits to scale down down the
+ * - MEMCG_DELAY_SCALING_SHIFT: The number of bits to scale down the
  *   proposed penalty in order to reduce to a reasonable number of jiffies, and
  *   to produce a reasonable delay curve.
  *

From a1a0aea592c1ef05283bc7af8d66ac3de87b2e07 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:05 -0700
Subject: [PATCH 363/474] mm/memory.c: delete duplicated words

Drop the repeated word "to" in two places.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-7-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memory.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index de311fc7639e..325bb575e7ec 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1800,7 +1800,7 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
  * @pfn: source kernel pfn
  * @pgprot: pgprot flags for the inserted page
  *
- * This is exactly like vmf_insert_pfn(), except that it allows drivers to
+ * This is exactly like vmf_insert_pfn(), except that it allows drivers
  * to override pgprot on a per-page basis.
  *
  * This only makes sense for IO mappings, and it makes no sense for
@@ -1936,7 +1936,7 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
  * @pfn: source kernel pfn
  * @pgprot: pgprot flags for the inserted page
  *
- * This is exactly like vmf_insert_mixed(), except that it allows drivers to
+ * This is exactly like vmf_insert_mixed(), except that it allows drivers
  * to override pgprot on a per-page basis.
  *
  * Typically this function should be used by drivers to set caching- and

From eaf444deed482f908395defa4d9b67ce55b72208 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:08 -0700
Subject: [PATCH 364/474] mm/migrate.c: delete duplicated word

Drop the repeated word "and".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-8-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/migrate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index 5ea275878383..52896b4921a7 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2667,7 +2667,7 @@ static void migrate_vma_unmap(struct migrate_vma *migrate)
 
 /**
  * migrate_vma_setup() - prepare to migrate a range of memory
- * @args: contains the vma, start, and and pfns arrays for the migration
+ * @args: contains the vma, start, and pfns arrays for the migration
  *
  * Returns: negative errno on failures, 0 when 0 or more pages were migrated
  * without an error.

From c08b342c214c4473b329f828cdc516d2f50a192f Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:11 -0700
Subject: [PATCH 365/474] mm/nommu.c: delete duplicated words

Drop the repeated word "that" in two places.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-9-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/nommu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/nommu.c b/mm/nommu.c
index 340ae7774c13..75a327149af1 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1762,8 +1762,8 @@ EXPORT_SYMBOL_GPL(access_process_vm);
  * @newsize: The proposed filesize of the inode
  *
  * Check the shared mappings on an inode on behalf of a shrinking truncate to
- * make sure that that any outstanding VMAs aren't broken and then shrink the
- * vm_regions that extend that beyond so that do_mmap() doesn't
+ * make sure that any outstanding VMAs aren't broken and then shrink the
+ * vm_regions that extend beyond so that do_mmap() doesn't
  * automatically grant mappings that are too large.
  */
 int nommu_shrink_inode_mappings(struct inode *inode, size_t size,

From 047b9967d59940f9f64ed13d02e98e9ca7cb5ffb Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:14 -0700
Subject: [PATCH 366/474] mm/page_alloc.c: delete or fix duplicated words

Drop the repeated word "them" and "that".
Change "the the" to "to the".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-10-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 167732f4d124..d80c9bac489c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4282,7 +4282,7 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 	/*
 	 * If an allocation failed after direct reclaim, it could be because
 	 * pages are pinned on the per-cpu lists or in high alloc reserves.
-	 * Shrink them them and try again
+	 * Shrink them and try again
 	 */
 	if (!page && !drained) {
 		unreserve_highatomic_pageblock(ac, false);
@@ -6192,7 +6192,7 @@ static int zone_batchsize(struct zone *zone)
  * locking.
  *
  * Any new users of pcp->batch and pcp->high should ensure they can cope with
- * those fields changing asynchronously (acording the the above rule).
+ * those fields changing asynchronously (acording to the above rule).
  *
  * mutex_is_locked(&pcp_batch_high_lock) required when calling this function
  * outside of boot time (or some other assurance that no concurrent updaters
@@ -8203,7 +8203,7 @@ void *__init alloc_large_system_hash(const char *tablename,
  * race condition. So you can't expect this function should be exact.
  *
  * Returns a page without holding a reference. If the caller wants to
- * dereference that page (e.g., dumping), it has to make sure that that it
+ * dereference that page (e.g., dumping), it has to make sure that it
  * cannot get removed (e.g., via memory unplug) concurrently.
  *
  */

From af44c12fe7c9704c4d185446a8ffdea18792017d Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:17 -0700
Subject: [PATCH 367/474] mm/shmem.c: delete duplicated word

Drop the repeated word "the".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-11-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/shmem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 49bde088a7ea..271548ca20f3 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1686,7 +1686,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
  * Swap in the page pointed to by *pagep.
  * Caller has to make sure that *pagep contains a valid swapped page.
  * Returns 0 and the page in pagep if success. On failure, returns the
- * the error code and NULL in *pagep.
+ * error code and NULL in *pagep.
  */
 static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 			     struct page **pagep, enum sgp_type sgp,

From 081a06fa29906643c62ea9477bc374c23417e6f9 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:19 -0700
Subject: [PATCH 368/474] mm/slab_common.c: delete duplicated word

Drop the repeated word "and".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-12-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/slab_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/slab_common.c b/mm/slab_common.c
index a513f3237155..f9ccd5dc13f3 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -419,7 +419,7 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
 	/*
 	 * On destruction, SLAB_TYPESAFE_BY_RCU kmem_caches are put on the
 	 * @slab_caches_to_rcu_destroy list.  The slab pages are freed
-	 * through RCU and and the associated kmem_cache are dereferenced
+	 * through RCU and the associated kmem_cache are dereferenced
 	 * while freeing the pages, so the kmem_caches should be freed only
 	 * after the pending RCU operations are finished.  As rcu_barrier()
 	 * is a pretty slow operation, we batch all pending destructions

From 5ce1be0e40fe64cbf540ba54dd10824a8cef99e1 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:23 -0700
Subject: [PATCH 369/474] mm/usercopy.c: delete duplicated word

Drop the repeated word "the".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-13-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/usercopy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/usercopy.c b/mm/usercopy.c
index 660717a1ea5c..b3de3c4eefba 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -43,7 +43,7 @@ static noinline int check_stack_object(const void *obj, unsigned long len)
 
 	/*
 	 * Reject: object partially overlaps the stack (passing the
-	 * the check above means at least one end is within the stack,
+	 * check above means at least one end is within the stack,
 	 * so if this check fails, the other end is outside the stack).
 	 */
 	if (obj < stack || stackend < obj + len)

From 1eba09c15decaf4e390aba0cd409e8a4e821c2a8 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:26 -0700
Subject: [PATCH 370/474] mm/vmscan.c: delete or fix duplicated words

Drop the repeated word "marked".
Change "time time" to "same time".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-14-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/vmscan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 846b7e9b8d2e..738115ed75e2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2798,7 +2798,7 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			set_bit(PGDAT_DIRTY, &pgdat->flags);
 
 		/*
-		 * If kswapd scans pages marked marked for immediate
+		 * If kswapd scans pages marked for immediate
 		 * reclaim and under writeback (nr_immediate), it
 		 * implies that pages are cycling through the LRU
 		 * faster than they are written so also forcibly stall.
@@ -3373,7 +3373,7 @@ static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx)
 	/*
 	 * Check for watermark boosts top-down as the higher zones
 	 * are more likely to be boosted. Both watermarks and boosts
-	 * should not be checked at the time time as reclaim would
+	 * should not be checked at the same time as reclaim would
 	 * start prematurely when there is no boosting and a lower
 	 * zone is balanced.
 	 */

From b6aa2c83428d49f1331d89a9e3d77850ee0696ba Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:28 -0700
Subject: [PATCH 371/474] mm/zpool.c: delete duplicated word and fix grammar

Drop the repeated word "if".
Fix subject/verb agreement.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-15-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/zpool.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/mm/zpool.c b/mm/zpool.c
index 863669212070..3744a2d1a624 100644
--- a/mm/zpool.c
+++ b/mm/zpool.c
@@ -239,15 +239,15 @@ const char *zpool_get_type(struct zpool *zpool)
 }
 
 /**
- * zpool_malloc_support_movable() - Check if the zpool support
- * allocate movable memory
+ * zpool_malloc_support_movable() - Check if the zpool supports
+ *	allocating movable memory
  * @zpool:	The zpool to check
  *
- * This returns if the zpool support allocate movable memory.
+ * This returns if the zpool supports allocating movable memory.
  *
  * Implementations must guarantee this to be thread-safe.
  *
- * Returns: true if if the zpool support allocate movable memory, false if not
+ * Returns: true if the zpool supports allocating movable memory, false if not
  */
 bool zpool_malloc_support_movable(struct zpool *zpool)
 {

From b956b5ac28cd709567f10c0ef67e65898ded2e45 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:31 -0700
Subject: [PATCH 372/474] mm/zsmalloc.c: fix duplicated words

Change "as as" to "as a".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200801173822.14973-16-rdunlap@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/zsmalloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 952a01e45c6a..c36fdff9a371 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -79,7 +79,7 @@
 
 /*
  * Object location (<PFN>, <obj_idx>) is encoded as
- * as single (unsigned long) handle value.
+ * a single (unsigned long) handle value.
  *
  * Note that object index <obj_idx> starts from 0.
  *

From bfe00c5bbd9ee37b99c281429556c335271d027b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 11 Aug 2020 18:33:34 -0700
Subject: [PATCH 373/474] syscalls: use uaccess_kernel in addr_limit_user_check

Patch series "clean up address limit helpers", v2.

In preparation for eventually phasing out direct use of set_fs(), this
series removes the segment_eq() arch helper that is only used to implement
or duplicate the uaccess_kernel() API, and then adds descriptive helpers
to force the kernel address limit.

This patch (of 6):

Use the uaccess_kernel helper instead of duplicating it.

[hch@lst.de: arm: don't call addr_limit_user_check for nommu]
  Link: http://lkml.kernel.org/r/20200721045834.GA9613@lst.de

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Link: http://lkml.kernel.org/r/20200714105505.935079-1-hch@lst.de
Link: http://lkml.kernel.org/r/20200710135706.537715-1-hch@lst.de
Link: http://lkml.kernel.org/r/20200710135706.537715-2-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/kernel/signal.c | 2 ++
 include/linux/syscalls.h | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index ab2568996ddb..c9dc912b83f0 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -713,7 +713,9 @@ struct page *get_signal_page(void)
 /* Defer to generic check */
 asmlinkage void addr_limit_check_failed(void)
 {
+#ifdef CONFIG_MMU
 	addr_limit_user_check();
+#endif
 }
 
 #ifdef CONFIG_DEBUG_RSEQ
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a2429d336593..dc2b827c81e5 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -263,7 +263,7 @@ static inline void addr_limit_user_check(void)
 		return;
 #endif
 
-	if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS),
+	if (CHECK_DATA_CORRUPTION(uaccess_kernel(),
 				  "Invalid address limit on user-mode return"))
 		force_sig(SIGKILL);
 

From 9af0f90aea46081566bf2014b6dfeb87b792005c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 11 Aug 2020 18:33:38 -0700
Subject: [PATCH 374/474] nds32: use uaccess_kernel in show_regs

Use the uaccess_kernel helper instead of duplicating it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Greentime Hu <green.hu@gmail.com>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Link: http://lkml.kernel.org/r/20200710135706.537715-3-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/nds32/kernel/process.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/nds32/kernel/process.c b/arch/nds32/kernel/process.c
index e85bbbadc0e7..e01ad5d17224 100644
--- a/arch/nds32/kernel/process.c
+++ b/arch/nds32/kernel/process.c
@@ -121,7 +121,7 @@ void show_regs(struct pt_regs *regs)
 		regs->uregs[3], regs->uregs[2], regs->uregs[1], regs->uregs[0]);
 	pr_info("  IRQs o%s  Segment %s\n",
 		interrupts_enabled(regs) ? "n" : "ff",
-		segment_eq(get_fs(), KERNEL_DS)? "kernel" : "user");
+		uaccess_kernel() ? "kernel" : "user");
 }
 
 EXPORT_SYMBOL(show_regs);

From efbfc62e1d9ce835fd3ea5f25db1844e1496ced6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 11 Aug 2020 18:33:41 -0700
Subject: [PATCH 375/474] riscv: include <asm/pgtable.h> in <asm/uaccess.h>

To ensure TASK_SIZE is defined for USER_DS.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Palmer Dabbelt <palmerdabbelt@google.com>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Link: http://lkml.kernel.org/r/20200710135706.537715-4-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/riscv/include/asm/uaccess.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 8ce9d607b53d..22de922d6ecb 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -8,6 +8,8 @@
 #ifndef _ASM_RISCV_UACCESS_H
 #define _ASM_RISCV_UACCESS_H
 
+#include <asm/pgtable.h>		/* for TASK_SIZE */
+
 /*
  * User space memory access functions
  */

From 428e2976a5bf7e7f5554286d7a5a33b8147b106a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 11 Aug 2020 18:33:44 -0700
Subject: [PATCH 376/474] uaccess: remove segment_eq

segment_eq is only used to implement uaccess_kernel.  Just open code
uaccess_kernel in the arch uaccess headers and remove one layer of
indirection.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Greentime Hu <green.hu@gmail.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Link: http://lkml.kernel.org/r/20200710135706.537715-5-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/include/asm/uaccess.h      | 2 +-
 arch/arc/include/asm/segment.h        | 3 +--
 arch/arm/include/asm/uaccess.h        | 4 ++--
 arch/arm64/include/asm/uaccess.h      | 2 +-
 arch/csky/include/asm/segment.h       | 2 +-
 arch/h8300/include/asm/segment.h      | 2 +-
 arch/ia64/include/asm/uaccess.h       | 2 +-
 arch/m68k/include/asm/segment.h       | 2 +-
 arch/microblaze/include/asm/uaccess.h | 2 +-
 arch/mips/include/asm/uaccess.h       | 2 +-
 arch/nds32/include/asm/uaccess.h      | 2 +-
 arch/nios2/include/asm/uaccess.h      | 2 +-
 arch/openrisc/include/asm/uaccess.h   | 2 +-
 arch/parisc/include/asm/uaccess.h     | 2 +-
 arch/powerpc/include/asm/uaccess.h    | 3 +--
 arch/riscv/include/asm/uaccess.h      | 4 +---
 arch/s390/include/asm/uaccess.h       | 2 +-
 arch/sh/include/asm/segment.h         | 3 +--
 arch/sparc/include/asm/uaccess_32.h   | 2 +-
 arch/sparc/include/asm/uaccess_64.h   | 2 +-
 arch/x86/include/asm/uaccess.h        | 2 +-
 arch/xtensa/include/asm/uaccess.h     | 2 +-
 include/asm-generic/uaccess.h         | 4 ++--
 include/linux/uaccess.h               | 2 --
 24 files changed, 25 insertions(+), 32 deletions(-)

diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index 1fe2b56cb861..1b6f25efa247 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -20,7 +20,7 @@
 #define get_fs()  (current_thread_info()->addr_limit)
 #define set_fs(x) (current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 /*
  * Is a address valid? This does a straightforward calculation rather
diff --git a/arch/arc/include/asm/segment.h b/arch/arc/include/asm/segment.h
index 6a2a5be5026d..871f8ab11bfd 100644
--- a/arch/arc/include/asm/segment.h
+++ b/arch/arc/include/asm/segment.h
@@ -14,8 +14,7 @@ typedef unsigned long mm_segment_t;
 
 #define KERNEL_DS		MAKE_MM_SEG(0)
 #define USER_DS			MAKE_MM_SEG(TASK_SIZE)
-
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 #endif /* __ASSEMBLY__ */
 #endif /* __ASMARC_SEGMENT_H */
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index b5fdd30252f8..a13d90206472 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -76,7 +76,7 @@ static inline void set_fs(mm_segment_t fs)
 	modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
 }
 
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 /*
  * We use 33-bit arithmetic here.  Success returns zero, failure returns
@@ -267,7 +267,7 @@ extern int __put_user_8(void *, unsigned long long);
  */
 #define USER_DS			KERNEL_DS
 
-#define segment_eq(a, b)		(1)
+#define uaccess_kernel()	(true)
 #define __addr_ok(addr)		((void)(addr), 1)
 #define __range_ok(addr, size)	((void)(addr), 0)
 #define get_fs()		(KERNEL_DS)
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 8d7c466f809b..991dd5f031e4 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -50,7 +50,7 @@ static inline void set_fs(mm_segment_t fs)
 				CONFIG_ARM64_UAO));
 }
 
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 /*
  * Test whether a block of memory is a valid user space address.
diff --git a/arch/csky/include/asm/segment.h b/arch/csky/include/asm/segment.h
index db2640d5f575..79ede9b1a646 100644
--- a/arch/csky/include/asm/segment.h
+++ b/arch/csky/include/asm/segment.h
@@ -13,6 +13,6 @@ typedef struct {
 #define USER_DS			((mm_segment_t) { 0x80000000UL })
 #define get_fs()		(current_thread_info()->addr_limit)
 #define set_fs(x)		(current_thread_info()->addr_limit = (x))
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 #endif /* __ASM_CSKY_SEGMENT_H */
diff --git a/arch/h8300/include/asm/segment.h b/arch/h8300/include/asm/segment.h
index a407978f9f9f..37950725d9b9 100644
--- a/arch/h8300/include/asm/segment.h
+++ b/arch/h8300/include/asm/segment.h
@@ -33,7 +33,7 @@ static inline mm_segment_t get_fs(void)
 	return USER_DS;
 }
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h
index 8aa473a4b0f4..179243c3dfc7 100644
--- a/arch/ia64/include/asm/uaccess.h
+++ b/arch/ia64/include/asm/uaccess.h
@@ -50,7 +50,7 @@
 #define get_fs()  (current_thread_info()->addr_limit)
 #define set_fs(x) (current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 /*
  * When accessing user memory, we need to make sure the entire area really is in
diff --git a/arch/m68k/include/asm/segment.h b/arch/m68k/include/asm/segment.h
index c6686559e9b7..2b5e68a71ef7 100644
--- a/arch/m68k/include/asm/segment.h
+++ b/arch/m68k/include/asm/segment.h
@@ -52,7 +52,7 @@ static inline void set_fs(mm_segment_t val)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
 #endif
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 6723c56ec378..304b04ffea2f 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -41,7 +41,7 @@
 # define get_fs()	(current_thread_info()->addr_limit)
 # define set_fs(val)	(current_thread_info()->addr_limit = (val))
 
-# define segment_eq(a, b)	((a).seg == (b).seg)
+# define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 #ifndef CONFIG_MMU
 
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index 62b298c50905..61fc01f177a6 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -72,7 +72,7 @@ extern u64 __ua_limit;
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 /*
  * eva_kernel_access() - determine whether kernel memory access on an EVA system
diff --git a/arch/nds32/include/asm/uaccess.h b/arch/nds32/include/asm/uaccess.h
index 3a9219f53ee0..010ba5f1d7dd 100644
--- a/arch/nds32/include/asm/uaccess.h
+++ b/arch/nds32/include/asm/uaccess.h
@@ -44,7 +44,7 @@ static inline void set_fs(mm_segment_t fs)
 	current_thread_info()->addr_limit = fs;
 }
 
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 #define __range_ok(addr, size) (size <= get_fs() && addr <= (get_fs() -size))
 
diff --git a/arch/nios2/include/asm/uaccess.h b/arch/nios2/include/asm/uaccess.h
index e83f831a76f9..a741abbed6fb 100644
--- a/arch/nios2/include/asm/uaccess.h
+++ b/arch/nios2/include/asm/uaccess.h
@@ -30,7 +30,7 @@
 #define get_fs()		(current_thread_info()->addr_limit)
 #define set_fs(seg)		(current_thread_info()->addr_limit = (seg))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define __access_ok(addr, len)			\
 	(((signed long)(((long)get_fs().seg) &	\
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index 17c24f14615f..48b691530d3e 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -43,7 +43,7 @@
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 /* Ensure that the range from addr to addr+size is all within the process'
  * address space
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index ebbb9ffe038c..ed2cd4fb479b 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -14,7 +14,7 @@
 #define KERNEL_DS	((mm_segment_t){0})
 #define USER_DS 	((mm_segment_t){1})
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 64c04ab09112..00699903f1ef 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -38,8 +38,7 @@ static inline void set_fs(mm_segment_t fs)
 	set_thread_flag(TIF_FSCHECK);
 }
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
-
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #define user_addr_max()	(get_fs().seg)
 
 #ifdef __powerpc64__
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 22de922d6ecb..f56c66b3f5fe 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -64,11 +64,9 @@ static inline void set_fs(mm_segment_t fs)
 	current_thread_info()->addr_limit = fs;
 }
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
-
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #define user_addr_max()	(get_fs().seg)
 
-
 /**
  * access_ok: - Checks if a user space pointer is valid
  * @addr: User space pointer to start of block to check
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 324438889fe1..f09444d6aeab 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -32,7 +32,7 @@
 #define USER_DS_SACF	(3)
 
 #define get_fs()        (current->thread.mm_segment)
-#define segment_eq(a,b) (((a) & 2) == ((b) & 2))
+#define uaccess_kernel() ((get_fs() & 2) == KERNEL_DS)
 
 void set_fs(mm_segment_t fs);
 
diff --git a/arch/sh/include/asm/segment.h b/arch/sh/include/asm/segment.h
index 33d1d28057cb..02e54a3335d6 100644
--- a/arch/sh/include/asm/segment.h
+++ b/arch/sh/include/asm/segment.h
@@ -24,8 +24,7 @@ typedef struct {
 #define USER_DS		KERNEL_DS
 #endif
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
-
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index d6d8413eca83..0a2d3ebc4bb8 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -28,7 +28,7 @@
 #define get_fs()	(current->thread.current_ds)
 #define set_fs(val)	((current->thread.current_ds) = (val))
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 /* We have there a nice not-mapped page at PAGE_OFFSET - PAGE_SIZE, so that this test
  * can be fairly lightweight.
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index bf9d330073b2..698cf69f74e9 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -32,7 +32,7 @@
 
 #define get_fs() ((mm_segment_t){(current_thread_info()->current_ds)})
 
-#define segment_eq(a, b)  ((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define set_fs(val)								\
 do {										\
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 2f3e8f2a958f..ecefaffd15d4 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -33,7 +33,7 @@ static inline void set_fs(mm_segment_t fs)
 	set_thread_flag(TIF_FSCHECK);
 }
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #define user_addr_max() (current->thread.addr_limit.seg)
 
 /*
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index e57f0d0a88d8..b9758119feca 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -35,7 +35,7 @@
 #define get_fs()	(current->thread.current_ds)
 #define set_fs(val)	(current->thread.current_ds = (val))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define __kernel_ok (uaccess_kernel())
 #define __user_ok(addr, size) \
diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index e935318804f8..ba68ee4dabfa 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -86,8 +86,8 @@ static inline void set_fs(mm_segment_t fs)
 }
 #endif
 
-#ifndef segment_eq
-#define segment_eq(a, b) ((a).seg == (b).seg)
+#ifndef uaccess_kernel
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #endif
 
 #define access_ok(addr, size) __access_ok((unsigned long)(addr),(size))
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 0a76ddc07d59..5c62d0c6f15b 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -6,8 +6,6 @@
 #include <linux/sched.h>
 #include <linux/thread_info.h>
 
-#define uaccess_kernel() segment_eq(get_fs(), KERNEL_DS)
-
 #include <asm/uaccess.h>
 
 /*

From 3d13f313ce4c34c524ccc37986fe77172f601ff3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 11 Aug 2020 18:33:47 -0700
Subject: [PATCH 377/474] uaccess: add force_uaccess_{begin,end} helpers

Add helpers to wrap the get_fs/set_fs magic for undoing any damange done
by set_fs(KERNEL_DS).  There is no real functional benefit, but this
documents the intent of these calls better, and will allow stubbing the
functions out easily for kernels builds that do not allow address space
overrides in the future.

[hch@lst.de: drop two incorrect hunks, fix a commit log typo]
  Link: http://lkml.kernel.org/r/20200714105505.935079-6-hch@lst.de

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Greentime Hu <green.hu@gmail.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Link: http://lkml.kernel.org/r/20200710135706.537715-6-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/kernel/sdei.c         |  2 +-
 arch/m68k/include/asm/tlbflush.h |  6 +++---
 arch/mips/kernel/unaligned.c     | 27 +++++++++++++--------------
 arch/nds32/mm/alignment.c        |  7 +++----
 arch/sh/kernel/traps_32.c        | 12 +++++-------
 drivers/firmware/arm_sdei.c      |  5 ++---
 include/linux/uaccess.h          | 18 ++++++++++++++++++
 kernel/events/callchain.c        |  5 ++---
 kernel/events/core.c             |  5 ++---
 kernel/kthread.c                 |  5 ++---
 kernel/stacktrace.c              |  5 ++---
 mm/maccess.c                     | 22 ++++++++++------------
 12 files changed, 63 insertions(+), 56 deletions(-)

diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index dab88260b137..7689f2031c0c 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -180,7 +180,7 @@ static __kprobes unsigned long _sdei_handler(struct pt_regs *regs,
 
 	/*
 	 * We didn't take an exception to get here, set PAN. UAO will be cleared
-	 * by sdei_event_handler()s set_fs(USER_DS) call.
+	 * by sdei_event_handler()s force_uaccess_begin() call.
 	 */
 	__uaccess_enable_hw_pan();
 
diff --git a/arch/m68k/include/asm/tlbflush.h b/arch/m68k/include/asm/tlbflush.h
index 191e75a6bb24..5337bc2c262f 100644
--- a/arch/m68k/include/asm/tlbflush.h
+++ b/arch/m68k/include/asm/tlbflush.h
@@ -85,10 +85,10 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
 	if (vma->vm_mm == current->active_mm) {
-		mm_segment_t old_fs = get_fs();
-		set_fs(USER_DS);
+		mm_segment_t old_fs = force_uaccess_begin();
+
 		__flush_tlb_one(addr);
-		set_fs(old_fs);
+		force_uaccess_end(old_fs);
 	}
 }
 
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index 0adce604fa44..126a5f3f4e4c 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -191,17 +191,16 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 			 * memory, so we need to "switch" the address limit to
 			 * user space, so that address check can work properly.
 			 */
-			seg = get_fs();
-			set_fs(USER_DS);
+			seg = force_uaccess_begin();
 			switch (insn.spec3_format.func) {
 			case lhe_op:
 				if (!access_ok(addr, 2)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				LoadHWE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				compute_return_epc(regs);
@@ -209,12 +208,12 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 				break;
 			case lwe_op:
 				if (!access_ok(addr, 4)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				LoadWE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				compute_return_epc(regs);
@@ -222,12 +221,12 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 				break;
 			case lhue_op:
 				if (!access_ok(addr, 2)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				LoadHWUE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				compute_return_epc(regs);
@@ -235,35 +234,35 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 				break;
 			case she_op:
 				if (!access_ok(addr, 2)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				compute_return_epc(regs);
 				value = regs->regs[insn.spec3_format.rt];
 				StoreHWE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				break;
 			case swe_op:
 				if (!access_ok(addr, 4)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				compute_return_epc(regs);
 				value = regs->regs[insn.spec3_format.rt];
 				StoreWE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				break;
 			default:
-				set_fs(seg);
+				force_uaccess_end(seg);
 				goto sigill;
 			}
-			set_fs(seg);
+			force_uaccess_end(seg);
 		}
 #endif
 		break;
diff --git a/arch/nds32/mm/alignment.c b/arch/nds32/mm/alignment.c
index c8b9061a2ee3..1eb7ded6992b 100644
--- a/arch/nds32/mm/alignment.c
+++ b/arch/nds32/mm/alignment.c
@@ -512,7 +512,7 @@ int do_unaligned_access(unsigned long addr, struct pt_regs *regs)
 {
 	unsigned long inst;
 	int ret = -EFAULT;
-	mm_segment_t seg = get_fs();
+	mm_segment_t seg;
 
 	inst = get_inst(regs->ipc);
 
@@ -520,13 +520,12 @@ int do_unaligned_access(unsigned long addr, struct pt_regs *regs)
 	      "Faulting addr: 0x%08lx, pc: 0x%08lx [inst: 0x%08lx ]\n", addr,
 	      regs->ipc, inst);
 
-	set_fs(USER_DS);
-
+	seg = force_uaccess_begin();
 	if (inst & NDS32_16BIT_INSTRUCTION)
 		ret = do_16((inst >> 16) & 0xffff, regs);
 	else
 		ret = do_32(inst, regs);
-	set_fs(seg);
+	force_uaccess_end(seg);
 
 	return ret;
 }
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index 058c6181bb30..b62ad0ba2395 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -482,8 +482,6 @@ asmlinkage void do_address_error(struct pt_regs *regs,
 	error_code = lookup_exception_vector();
 #endif
 
-	oldfs = get_fs();
-
 	if (user_mode(regs)) {
 		int si_code = BUS_ADRERR;
 		unsigned int user_action;
@@ -491,13 +489,13 @@ asmlinkage void do_address_error(struct pt_regs *regs,
 		local_irq_enable();
 		inc_unaligned_user_access();
 
-		set_fs(USER_DS);
+		oldfs = force_uaccess_begin();
 		if (copy_from_user(&instruction, (insn_size_t *)(regs->pc & ~1),
 				   sizeof(instruction))) {
-			set_fs(oldfs);
+			force_uaccess_end(oldfs);
 			goto uspace_segv;
 		}
-		set_fs(oldfs);
+		force_uaccess_end(oldfs);
 
 		/* shout about userspace fixups */
 		unaligned_fixups_notify(current, instruction, regs);
@@ -520,11 +518,11 @@ asmlinkage void do_address_error(struct pt_regs *regs,
 			goto uspace_segv;
 		}
 
-		set_fs(USER_DS);
+		oldfs = force_uaccess_begin();
 		tmp = handle_unaligned_access(instruction, regs,
 					      &user_mem_access, 0,
 					      address);
-		set_fs(oldfs);
+		force_uaccess_end(oldfs);
 
 		if (tmp == 0)
 			return; /* sorted */
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index e7e36aab2386..b4b9ce97f415 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -1136,15 +1136,14 @@ int sdei_event_handler(struct pt_regs *regs,
 	 * access kernel memory.
 	 * Do the same here because this doesn't come via the same entry code.
 	*/
-	orig_addr_limit = get_fs();
-	set_fs(USER_DS);
+	orig_addr_limit = force_uaccess_begin();
 
 	err = arg->callback(event_num, regs, arg->callback_arg);
 	if (err)
 		pr_err_ratelimited("event %u on CPU %u failed with error: %d\n",
 				   event_num, smp_processor_id(), err);
 
-	set_fs(orig_addr_limit);
+	force_uaccess_end(orig_addr_limit);
 
 	return err;
 }
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 5c62d0c6f15b..94b285411659 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -8,6 +8,24 @@
 
 #include <asm/uaccess.h>
 
+/*
+ * Force the uaccess routines to be wired up for actual userspace access,
+ * overriding any possible set_fs(KERNEL_DS) still lingering around.  Undone
+ * using force_uaccess_end below.
+ */
+static inline mm_segment_t force_uaccess_begin(void)
+{
+	mm_segment_t fs = get_fs();
+
+	set_fs(USER_DS);
+	return fs;
+}
+
+static inline void force_uaccess_end(mm_segment_t oldfs)
+{
+	set_fs(oldfs);
+}
+
 /*
  * Architectures should provide two primitives (raw_copy_{to,from}_user())
  * and get rid of their private instances of copy_{to,from}_user() and
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index c6ce894e4ce9..58cbe357fb2b 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -217,10 +217,9 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 			if (add_mark)
 				perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
 
-			fs = get_fs();
-			set_fs(USER_DS);
+			fs = force_uaccess_begin();
 			perf_callchain_user(&ctx, regs);
-			set_fs(fs);
+			force_uaccess_end(fs);
 		}
 	}
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d1f0a7e5b182..6961333ebad5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6453,10 +6453,9 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
 
 		/* Data. */
 		sp = perf_user_stack_pointer(regs);
-		fs = get_fs();
-		set_fs(USER_DS);
+		fs = force_uaccess_begin();
 		rem = __output_copy_user(handle, (void *) sp, dump_size);
-		set_fs(fs);
+		force_uaccess_end(fs);
 		dyn_size = dump_size - rem;
 
 		perf_output_skip(handle, rem);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index b2807e7be772..3edaa380dc7b 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -1258,8 +1258,7 @@ void kthread_use_mm(struct mm_struct *mm)
 	if (active_mm != mm)
 		mmdrop(active_mm);
 
-	to_kthread(tsk)->oldfs = get_fs();
-	set_fs(USER_DS);
+	to_kthread(tsk)->oldfs = force_uaccess_begin();
 }
 EXPORT_SYMBOL_GPL(kthread_use_mm);
 
@@ -1274,7 +1273,7 @@ void kthread_unuse_mm(struct mm_struct *mm)
 	WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD));
 	WARN_ON_ONCE(!tsk->mm);
 
-	set_fs(to_kthread(tsk)->oldfs);
+	force_uaccess_end(to_kthread(tsk)->oldfs);
 
 	task_lock(tsk);
 	sync_mm_rss(mm);
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 2af66e449aa6..946f44a9e86a 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -233,10 +233,9 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size)
 	if (current->flags & PF_KTHREAD)
 		return 0;
 
-	fs = get_fs();
-	set_fs(USER_DS);
+	fs = force_uaccess_begin();
 	arch_stack_walk_user(consume_entry, &c, task_pt_regs(current));
-	set_fs(fs);
+	force_uaccess_end(fs);
 
 	return c.len;
 }
diff --git a/mm/maccess.c b/mm/maccess.c
index f98ff91e32c6..3bd70405f2d8 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -205,15 +205,14 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)
 long copy_from_user_nofault(void *dst, const void __user *src, size_t size)
 {
 	long ret = -EFAULT;
-	mm_segment_t old_fs = get_fs();
+	mm_segment_t old_fs = force_uaccess_begin();
 
-	set_fs(USER_DS);
 	if (access_ok(src, size)) {
 		pagefault_disable();
 		ret = __copy_from_user_inatomic(dst, src, size);
 		pagefault_enable();
 	}
-	set_fs(old_fs);
+	force_uaccess_end(old_fs);
 
 	if (ret)
 		return -EFAULT;
@@ -233,15 +232,14 @@ EXPORT_SYMBOL_GPL(copy_from_user_nofault);
 long copy_to_user_nofault(void __user *dst, const void *src, size_t size)
 {
 	long ret = -EFAULT;
-	mm_segment_t old_fs = get_fs();
+	mm_segment_t old_fs = force_uaccess_begin();
 
-	set_fs(USER_DS);
 	if (access_ok(dst, size)) {
 		pagefault_disable();
 		ret = __copy_to_user_inatomic(dst, src, size);
 		pagefault_enable();
 	}
-	set_fs(old_fs);
+	force_uaccess_end(old_fs);
 
 	if (ret)
 		return -EFAULT;
@@ -270,17 +268,17 @@ EXPORT_SYMBOL_GPL(copy_to_user_nofault);
 long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr,
 			      long count)
 {
-	mm_segment_t old_fs = get_fs();
+	mm_segment_t old_fs;
 	long ret;
 
 	if (unlikely(count <= 0))
 		return 0;
 
-	set_fs(USER_DS);
+	old_fs = force_uaccess_begin();
 	pagefault_disable();
 	ret = strncpy_from_user(dst, unsafe_addr, count);
 	pagefault_enable();
-	set_fs(old_fs);
+	force_uaccess_end(old_fs);
 
 	if (ret >= count) {
 		ret = count;
@@ -310,14 +308,14 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr,
  */
 long strnlen_user_nofault(const void __user *unsafe_addr, long count)
 {
-	mm_segment_t old_fs = get_fs();
+	mm_segment_t old_fs;
 	int ret;
 
-	set_fs(USER_DS);
+	old_fs = force_uaccess_begin();
 	pagefault_disable();
 	ret = strnlen_user(unsafe_addr, count);
 	pagefault_enable();
-	set_fs(old_fs);
+	force_uaccess_end(old_fs);
 
 	return ret;
 }

From fe81417596fa8b6577fedb7e206ff3e4c7015c13 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 11 Aug 2020 18:33:50 -0700
Subject: [PATCH 378/474] exec: use force_uaccess_begin during exec and exit

Both exec and exit want to ensure that the uaccess routines actually do
access user pointers.  Use the newly added force_uaccess_begin helper
instead of an open coded set_fs for that to prepare for kernel builds
where set_fs() does not exist.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Link: http://lkml.kernel.org/r/20200710135706.537715-7-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/exec.c     | 7 ++++++-
 kernel/exit.c | 2 +-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 3698252719a3..29ef78ae9f50 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1402,7 +1402,12 @@ int begin_new_exec(struct linux_binprm * bprm)
 	if (retval)
 		goto out_unlock;
 
-	set_fs(USER_DS);
+	/*
+	 * Ensure that the uaccess routines can actually operate on userspace
+	 * pointers:
+	 */
+	force_uaccess_begin();
+
 	me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD |
 					PF_NOFREEZE | PF_NO_SETAFFINITY);
 	flush_thread();
diff --git a/kernel/exit.c b/kernel/exit.c
index e731c414e024..c2d2961576f2 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -732,7 +732,7 @@ void __noreturn do_exit(long code)
 	 * mm_release()->clear_child_tid() from writing to a user-controlled
 	 * kernel address.
 	 */
-	set_fs(USER_DS);
+	force_uaccess_begin();
 
 	if (unlikely(in_atomic())) {
 		pr_info("note: %s[%d] exited with preempt_count %d\n",

From bd72866b8da499e60633ff28f8a4f6e09ca78efe Mon Sep 17 00:00:00 2001
From: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Date: Tue, 11 Aug 2020 18:33:54 -0700
Subject: [PATCH 379/474] alpha: fix annotation of io{read,write}{16,32}be()

These accessors must be used to read/write a big-endian bus.  The value
returned or written is native-endian.

However, these accessors are defined using be{16,32}_to_cpu() or
cpu_to_be{16,32}() to make the endian conversion but these expect a
__be{16,32} when none is present.  Keeping them would need a force cast
that would solve nothing at all.

So, do the conversion using swab{16,32}, like done in asm-generic for
similar situations.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Link: http://lkml.kernel.org/r/20200622114232.80039-1-luc.vanoostenryck@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/include/asm/io.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index a4d0c19f1e79..640e1a2f57b4 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -489,10 +489,10 @@ extern inline void writeq(u64 b, volatile void __iomem *addr)
 }
 #endif
 
-#define ioread16be(p) be16_to_cpu(ioread16(p))
-#define ioread32be(p) be32_to_cpu(ioread32(p))
-#define iowrite16be(v,p) iowrite16(cpu_to_be16(v), (p))
-#define iowrite32be(v,p) iowrite32(cpu_to_be32(v), (p))
+#define ioread16be(p) swab16(ioread16(p))
+#define ioread32be(p) swab32(ioread32(p))
+#define iowrite16be(v,p) iowrite16(swab16(v), (p))
+#define iowrite32be(v,p) iowrite32(swab32(v), (p))
 
 #define inb_p		inb
 #define inw_p		inw

From c5f748e2f2ad970078de11bd6b12bcd81147c636 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:33:57 -0700
Subject: [PATCH 380/474] include/linux/compiler-clang.h: drop duplicated word
 in a comment

Drop the doubled word "the" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Link: http://lkml.kernel.org/r/6a18c301-3505-742f-4dd7-0f38d0e537b9@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler-clang.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 8a072d00e688..cee0c728d39a 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -40,7 +40,7 @@
 #endif
 
 /*
- * Not all versions of clang implement the the type-generic versions
+ * Not all versions of clang implement the type-generic versions
  * of the builtin overflow checkers. Fortunately, clang implements
  * __has_builtin allowing us to avoid awkward version
  * checks. Unfortunately, we don't know which version of gcc clang

From cd1a406fa46f81b1a859ef874b8413a6fa6ac7e8 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:34:00 -0700
Subject: [PATCH 381/474] include/linux/exportfs.h: drop duplicated word in a
 comment

Drop the doubled word "a" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Link: http://lkml.kernel.org/r/c61b707a-8fd8-5b1b-aab0-679122881543@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/exportfs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index d896b8657085..3ceb72b67a7a 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -178,7 +178,7 @@ struct fid {
  * get_name:
  *    @get_name should find a name for the given @child in the given @parent
  *    directory.  The name should be stored in the @name (with the
- *    understanding that it is already pointing to a a %NAME_MAX+1 sized
+ *    understanding that it is already pointing to a %NAME_MAX+1 sized
  *    buffer.   get_name() should return %0 on success, a negative error code
  *    or error.  @get_name will be called without @parent->i_mutex held.
  *

From 121ae8da9cd49f7139bf80f26352337458e63fe1 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:34:04 -0700
Subject: [PATCH 382/474] include/linux/async_tx.h: drop duplicated word in a
 comment

Drop the doubled word "the" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Link: http://lkml.kernel.org/r/e85802f7-8f48-8b4c-29b3-ea237a2c7ae9@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/async_tx.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 75e582b8d2d9..4c328fef403c 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -36,7 +36,7 @@ struct dma_chan_ref {
 /**
  * async_tx_flags - modifiers for the async_* calls
  * @ASYNC_TX_XOR_ZERO_DST: this flag must be used for xor operations where the
- * the destination address is not a source.  The asynchronous case handles this
+ * destination address is not a source.  The asynchronous case handles this
  * implicitly, the synchronous case needs to zero the destination block.
  * @ASYNC_TX_XOR_DROP_DST: this flag must be used if the destination address is
  * also one of the source addresses.  In the synchronous case the destination

From f48ff83e9c1a8fc2e8bfedb4855933eb1ed159b2 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:34:07 -0700
Subject: [PATCH 383/474] include/linux/xz.h: drop duplicated word

Drop the doubled word "than" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Lasse Collin <lasse.collin@tukaani.org>
Link: http://lkml.kernel.org/r/05ebba7a-c1e4-01ae-fc7b-15c081b33f3e@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/xz.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/xz.h b/include/linux/xz.h
index 64cffa6ddfce..24ad7d875977 100644
--- a/include/linux/xz.h
+++ b/include/linux/xz.h
@@ -28,7 +28,7 @@
  * enum xz_mode - Operation mode
  *
  * @XZ_SINGLE:              Single-call mode. This uses less RAM than
- *                          than multi-call modes, because the LZMA2
+ *                          multi-call modes, because the LZMA2
  *                          dictionary doesn't need to be allocated as
  *                          part of the decoder state. All required data
  *                          structures are allocated at initialization,

From 8043fc147a97ec2eefc582487f344f2cbe86d12e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 11 Aug 2020 18:34:10 -0700
Subject: [PATCH 384/474] kernel: add a kernel_wait helper

Add a helper that waits for a pid and stores the status in the passed in
kernel pointer.  Use it to fix the usage of kernel_wait4 in
call_usermodehelper_exec_sync that only happens to work due to the
implicit set_fs(KERNEL_DS) for kernel threads.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Link: http://lkml.kernel.org/r/20200721130449.5008-1-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched/task.h |  1 +
 kernel/exit.c              | 16 ++++++++++++++++
 kernel/umh.c               | 29 ++++-------------------------
 3 files changed, 21 insertions(+), 25 deletions(-)

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index ae3060f0b0c9..a98965007eef 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -88,6 +88,7 @@ struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
+int kernel_wait(pid_t pid, int *stat);
 
 extern void free_task(struct task_struct *tsk);
 
diff --git a/kernel/exit.c b/kernel/exit.c
index c2d2961576f2..733e80f334e7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1626,6 +1626,22 @@ long kernel_wait4(pid_t upid, int __user *stat_addr, int options,
 	return ret;
 }
 
+int kernel_wait(pid_t pid, int *stat)
+{
+	struct wait_opts wo = {
+		.wo_type	= PIDTYPE_PID,
+		.wo_pid		= find_get_pid(pid),
+		.wo_flags	= WEXITED,
+	};
+	int ret;
+
+	ret = do_wait(&wo);
+	if (ret > 0 && wo.wo_stat)
+		*stat = wo.wo_stat;
+	put_pid(wo.wo_pid);
+	return ret;
+}
+
 SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
 		int, options, struct rusage __user *, ru)
 {
diff --git a/kernel/umh.c b/kernel/umh.c
index a25433f9cd9a..fcf3ee803630 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -119,37 +119,16 @@ static void call_usermodehelper_exec_sync(struct subprocess_info *sub_info)
 {
 	pid_t pid;
 
-	/* If SIGCLD is ignored kernel_wait4 won't populate the status. */
+	/* If SIGCLD is ignored do_wait won't populate the status. */
 	kernel_sigaction(SIGCHLD, SIG_DFL);
 	pid = kernel_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD);
-	if (pid < 0) {
+	if (pid < 0)
 		sub_info->retval = pid;
-	} else {
-		int ret = -ECHILD;
-		/*
-		 * Normally it is bogus to call wait4() from in-kernel because
-		 * wait4() wants to write the exit code to a userspace address.
-		 * But call_usermodehelper_exec_sync() always runs as kernel
-		 * thread (workqueue) and put_user() to a kernel address works
-		 * OK for kernel threads, due to their having an mm_segment_t
-		 * which spans the entire address space.
-		 *
-		 * Thus the __user pointer cast is valid here.
-		 */
-		kernel_wait4(pid, (int __user *)&ret, 0, NULL);
-
-		/*
-		 * If ret is 0, either call_usermodehelper_exec_async failed and
-		 * the real error code is already in sub_info->retval or
-		 * sub_info->retval is 0 anyway, so don't mess with it then.
-		 */
-		if (ret)
-			sub_info->retval = ret;
-	}
+	else
+		kernel_wait(pid, &sub_info->retval);
 
 	/* Restore default kernel sig handler */
 	kernel_sigaction(SIGCHLD, SIG_IGN);
-
 	umh_complete(sub_info);
 }
 

From 09c60546f04f732d194a171b3a4ccc9ae1e704ba Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Tue, 11 Aug 2020 18:34:13 -0700
Subject: [PATCH 385/474] ./Makefile: add debug option to enable function
 aligned on 32 bytes

Recently 0day reported many strange performance changes (regression or
improvement), in which there was no obvious relation between the culprit
commit and the benchmark at the first look, and it causes people to doubt
the test itself is wrong.

Upon further check, many of these cases are caused by the change to the
alignment of kernel text or data, as whole text/data of kernel are linked
together, change in one domain may affect alignments of other domains.

gcc has an option '-falign-functions=n' to force text aligned, and with
that option enabled, some of those performance changes will be gone, like
[1][2][3].

Add this option so that developers and 0day can easily find performance
bump caused by text alignment change, as tracking these strange bump is
quite time consuming.  Though it can't help in other cases like data
alignment changes like [4].

Following is some size data for v5.7 kernel built with a RHEL config used
in 0day:

    text      data      bss	 dec	   filename
  19738771  13292906  5554236  38585913	 vmlinux.noalign
  19758591  13297002  5529660  38585253	 vmlinux.align32

Raw vmlinux size in bytes:

	v5.7		v5.7+align32
	253950832	254018000	+0.02%

Some benchmark data, most of them have no big change:

  * hackbench:		[ -1.8%,  +0.5%]

  * fsmark:		[ -3.2%,  +3.4%]  # ext4/xfs/btrfs

  * kbuild:		[ -2.0%,  +0.9%]

  * will-it-scale:	[ -0.5%,  +1.8%]  # mmap1/pagefault3

  * netperf:
    - TCP_CRR		[+16.6%, +97.4%]
    - TCP_RR		[-18.5%,  -1.8%]
    - TCP_STREAM	[ -1.1%,  +1.9%]

[1] https://lore.kernel.org/lkml/20200114085637.GA29297@shao2-debian/
[2] https://lore.kernel.org/lkml/20200330011254.GA14393@feng-iot/
[3] https://lore.kernel.org/lkml/1d98d1f0-fe84-6df7-f5bd-f4cb2cdb7f45@intel.com/
[4] https://lore.kernel.org/lkml/20200205123216.GO12867@shao2-debian/

Signed-off-by: Feng Tang <feng.tang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Andi Kleen <andi.kleen@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Andy Shevchenko <andriy.shevchenko@intel.com>
Link: http://lkml.kernel.org/r/1595475001-90945-1-git-send-email-feng.tang@intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Makefile          |  4 ++++
 lib/Kconfig.debug | 11 +++++++++++
 2 files changed, 15 insertions(+)

diff --git a/Makefile b/Makefile
index 168dd19cad7c..254e80a96b23 100644
--- a/Makefile
+++ b/Makefile
@@ -893,6 +893,10 @@ KBUILD_CFLAGS	+= $(CC_FLAGS_SCS)
 export CC_FLAGS_SCS
 endif
 
+ifdef CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_32B
+KBUILD_CFLAGS += -falign-functions=32
+endif
+
 # arch Makefile may override CC so keep this after arch Makefile is included
 NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include)
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index a164785c3b48..ba12a58b2947 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -365,6 +365,17 @@ config SECTION_MISMATCH_WARN_ONLY
 
 	  If unsure, say Y.
 
+config DEBUG_FORCE_FUNCTION_ALIGN_32B
+	bool "Force all function address 32B aligned" if EXPERT
+	help
+	  There are cases that a commit from one domain changes the function
+	  address alignment of other domains, and cause magic performance
+	  bump (regression or improvement). Enable this option will help to
+	  verify if the bump is caused by function alignment changes, while
+	  it will slightly increase the kernel size and affect icache usage.
+
+	  It is mainly for debug and performance tuning use.
+
 #
 # Select this config option from the architecture Kconfig, if it
 # is preferred to always offer frame pointers as a config

From 376653435dacf84a8aca87e66aff94079a817cf2 Mon Sep 17 00:00:00 2001
From: Arvind Sankar <nivedita@alum.mit.edu>
Date: Tue, 11 Aug 2020 18:34:16 -0700
Subject: [PATCH 386/474] kernel.h: remove duplicate include of asm/div64.h

This seems to have been added inadvertently in commit
  72deb455b5ec ("block: remove CONFIG_LBDAF")

Fixes: 72deb455b5ec ("block: remove CONFIG_LBDAF")
Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/20200727034852.2813453-1-nivedita@alum.mit.edu
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 7339a00c895e..e19c13616666 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -17,7 +17,6 @@
 #include <asm/byteorder.h>
 #include <asm/div64.h>
 #include <uapi/linux/kernel.h>
-#include <asm/div64.h>
 
 #define STACK_MAGIC	0xdeadbeef
 

From 7f317d34906c1033f0752fc137dda04e43979bb8 Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Tue, 11 Aug 2020 18:34:19 -0700
Subject: [PATCH 387/474] include/: replace HTTP links with HTTPS ones

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/20200726110117.16346-1-grandmaster@al2klimov.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/clocksource/timer-ti-dm.h               | 2 +-
 include/linux/btree.h                           | 2 +-
 include/linux/delay.h                           | 2 +-
 include/linux/dma/k3-psil.h                     | 2 +-
 include/linux/dma/k3-udma-glue.h                | 2 +-
 include/linux/dma/ti-cppi5.h                    | 2 +-
 include/linux/irqchip/irq-omap-intc.h           | 2 +-
 include/linux/jhash.h                           | 2 +-
 include/linux/leds-ti-lmu-common.h              | 2 +-
 include/linux/platform_data/davinci-cpufreq.h   | 2 +-
 include/linux/platform_data/davinci_asp.h       | 2 +-
 include/linux/platform_data/elm.h               | 2 +-
 include/linux/platform_data/gpio-davinci.h      | 2 +-
 include/linux/platform_data/gpmc-omap.h         | 2 +-
 include/linux/platform_data/mtd-davinci-aemif.h | 2 +-
 include/linux/platform_data/omap-twl4030.h      | 2 +-
 include/linux/platform_data/uio_pruss.h         | 2 +-
 include/linux/platform_data/usb-omap.h          | 2 +-
 include/linux/soc/ti/k3-ringacc.h               | 2 +-
 include/linux/soc/ti/knav_qmss.h                | 2 +-
 include/linux/soc/ti/ti-msgmgr.h                | 2 +-
 include/linux/wkup_m3_ipc.h                     | 2 +-
 include/linux/xxhash.h                          | 2 +-
 include/linux/xz.h                              | 2 +-
 include/linux/zlib.h                            | 2 +-
 include/soc/arc/aux.h                           | 2 +-
 include/uapi/linux/elf.h                        | 2 +-
 include/uapi/linux/map_to_7segment.h            | 2 +-
 include/uapi/linux/types.h                      | 2 +-
 include/uapi/linux/usb/ch9.h                    | 2 +-
 30 files changed, 30 insertions(+), 30 deletions(-)

diff --git a/include/clocksource/timer-ti-dm.h b/include/clocksource/timer-ti-dm.h
index 531ca87fcd08..4c61dade8835 100644
--- a/include/clocksource/timer-ti-dm.h
+++ b/include/clocksource/timer-ti-dm.h
@@ -1,7 +1,7 @@
 /*
  * OMAP Dual-Mode Timers
  *
- * Copyright (C) 2010 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2010 Texas Instruments Incorporated - https://www.ti.com/
  * Tarun Kanti DebBarma <tarun.kanti@ti.com>
  * Thara Gopinath <thara@ti.com>
  *
diff --git a/include/linux/btree.h b/include/linux/btree.h
index 68f858c831b1..243ee544397a 100644
--- a/include/linux/btree.h
+++ b/include/linux/btree.h
@@ -10,7 +10,7 @@
  *
  * A B+Tree is a data structure for looking up arbitrary (currently allowing
  * unsigned long, u32, u64 and 2 * u64) keys into pointers. The data structure
- * is described at http://en.wikipedia.org/wiki/B-tree, we currently do not
+ * is described at https://en.wikipedia.org/wiki/B-tree, we currently do not
  * use binary search to find the key on lookups.
  *
  * Each B+Tree consists of a head, that contains bookkeeping information and
diff --git a/include/linux/delay.h b/include/linux/delay.h
index 5e016a4029d9..1d0e2ce6b6d9 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -16,7 +16,7 @@
  *  3. CPU clock rate changes.
  *
  * Please see this thread:
- *   http://lists.openwall.net/linux-kernel/2011/01/09/56
+ *   https://lists.openwall.net/linux-kernel/2011/01/09/56
  */
 
 #include <linux/kernel.h>
diff --git a/include/linux/dma/k3-psil.h b/include/linux/dma/k3-psil.h
index 61d5cc0ad601..1962f75fa2d3 100644
--- a/include/linux/dma/k3-psil.h
+++ b/include/linux/dma/k3-psil.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- *  Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ *  Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com
  */
 
 #ifndef K3_PSIL_H_
diff --git a/include/linux/dma/k3-udma-glue.h b/include/linux/dma/k3-udma-glue.h
index caadbab1632a..5eb34ad973a7 100644
--- a/include/linux/dma/k3-udma-glue.h
+++ b/include/linux/dma/k3-udma-glue.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- *  Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ *  Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com
  */
 
 #ifndef K3_UDMA_GLUE_H_
diff --git a/include/linux/dma/ti-cppi5.h b/include/linux/dma/ti-cppi5.h
index 579356ae447e..5896441ee604 100644
--- a/include/linux/dma/ti-cppi5.h
+++ b/include/linux/dma/ti-cppi5.h
@@ -2,7 +2,7 @@
 /*
  * CPPI5 descriptors interface
  *
- * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com
  */
 
 #ifndef __TI_CPPI5_H__
diff --git a/include/linux/irqchip/irq-omap-intc.h b/include/linux/irqchip/irq-omap-intc.h
index 216e5adf80ce..dca379c0d7eb 100644
--- a/include/linux/irqchip/irq-omap-intc.h
+++ b/include/linux/irqchip/irq-omap-intc.h
@@ -2,7 +2,7 @@
 /**
  * irq-omap-intc.h - INTC Idle Functions
  *
- * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com
  *
  * Author: Felipe Balbi <balbi@ti.com>
  */
diff --git a/include/linux/jhash.h b/include/linux/jhash.h
index ba2f6a9776b6..19ddd43aee68 100644
--- a/include/linux/jhash.h
+++ b/include/linux/jhash.h
@@ -5,7 +5,7 @@
  *
  * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net)
  *
- * http://burtleburtle.net/bob/hash/
+ * https://burtleburtle.net/bob/hash/
  *
  * These are the credits from Bob's sources:
  *
diff --git a/include/linux/leds-ti-lmu-common.h b/include/linux/leds-ti-lmu-common.h
index 5eb111f38803..420b61e5a213 100644
--- a/include/linux/leds-ti-lmu-common.h
+++ b/include/linux/leds-ti-lmu-common.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 // TI LMU Common Core
-// Copyright (C) 2018 Texas Instruments Incorporated - http://www.ti.com/
+// Copyright (C) 2018 Texas Instruments Incorporated - https://www.ti.com/
 
 #ifndef _TI_LMU_COMMON_H_
 #define _TI_LMU_COMMON_H_
diff --git a/include/linux/platform_data/davinci-cpufreq.h b/include/linux/platform_data/davinci-cpufreq.h
index 3fbf9f2793b5..bc208c64e3d7 100644
--- a/include/linux/platform_data/davinci-cpufreq.h
+++ b/include/linux/platform_data/davinci-cpufreq.h
@@ -2,7 +2,7 @@
 /*
  * TI DaVinci CPUFreq platform support.
  *
- * Copyright (C) 2009 Texas Instruments, Inc. http://www.ti.com/
+ * Copyright (C) 2009 Texas Instruments, Inc. https://www.ti.com/
  */
 
 #ifndef _MACH_DAVINCI_CPUFREQ_H
diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h
index 7fe80f1c7e08..5d1fb0d78a22 100644
--- a/include/linux/platform_data/davinci_asp.h
+++ b/include/linux/platform_data/davinci_asp.h
@@ -1,7 +1,7 @@
 /*
  * TI DaVinci Audio Serial Port support
  *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h
index 0f491d8abfdd..3cc78f0447b1 100644
--- a/include/linux/platform_data/elm.h
+++ b/include/linux/platform_data/elm.h
@@ -2,7 +2,7 @@
 /*
  * BCH Error Location Module
  *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #ifndef __ELM_H
diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h
index a93841bfb9f7..e182a46e609f 100644
--- a/include/linux/platform_data/gpio-davinci.h
+++ b/include/linux/platform_data/gpio-davinci.h
@@ -1,7 +1,7 @@
 /*
  * DaVinci GPIO Platform Related Defines
  *
- * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2013 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
diff --git a/include/linux/platform_data/gpmc-omap.h b/include/linux/platform_data/gpmc-omap.h
index ef663e570552..c9cc4e32435d 100644
--- a/include/linux/platform_data/gpmc-omap.h
+++ b/include/linux/platform_data/gpmc-omap.h
@@ -2,7 +2,7 @@
 /*
  * OMAP GPMC Platform data
  *
- * Copyright (C) 2014 Texas Instruments, Inc. - http://www.ti.com
+ * Copyright (C) 2014 Texas Instruments, Inc. - https://www.ti.com
  *	Roger Quadros <rogerq@ti.com>
  */
 
diff --git a/include/linux/platform_data/mtd-davinci-aemif.h b/include/linux/platform_data/mtd-davinci-aemif.h
index a403dd51dacc..a49826214a39 100644
--- a/include/linux/platform_data/mtd-davinci-aemif.h
+++ b/include/linux/platform_data/mtd-davinci-aemif.h
@@ -1,7 +1,7 @@
 /*
  * TI DaVinci AEMIF support
  *
- * Copyright 2010 (C) Texas Instruments, Inc. http://www.ti.com/
+ * Copyright 2010 (C) Texas Instruments, Inc. https://www.ti.com/
  *
  * This file is licensed under the terms of the GNU General Public License
  * version 2. This program is licensed "as is" without any warranty of any
diff --git a/include/linux/platform_data/omap-twl4030.h b/include/linux/platform_data/omap-twl4030.h
index 8419c8caf54e..0dd851ea1c72 100644
--- a/include/linux/platform_data/omap-twl4030.h
+++ b/include/linux/platform_data/omap-twl4030.h
@@ -3,7 +3,7 @@
  * omap-twl4030.h - ASoC machine driver for TI SoC based boards with twl4030
  *		    codec, header.
  *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com
  * All rights reserved.
  *
  * Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
diff --git a/include/linux/platform_data/uio_pruss.h b/include/linux/platform_data/uio_pruss.h
index 3d47d219827f..31f2e22661bc 100644
--- a/include/linux/platform_data/uio_pruss.h
+++ b/include/linux/platform_data/uio_pruss.h
@@ -3,7 +3,7 @@
  *
  * Platform data for uio_pruss driver
  *
- * Copyright (C) 2010-11 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2010-11 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
diff --git a/include/linux/platform_data/usb-omap.h b/include/linux/platform_data/usb-omap.h
index fa579b4c666b..5e70d667031c 100644
--- a/include/linux/platform_data/usb-omap.h
+++ b/include/linux/platform_data/usb-omap.h
@@ -1,7 +1,7 @@
 /*
  * usb-omap.h - Platform data for the various OMAP USB IPs
  *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com
  *
  * This software is distributed under the terms of the GNU General Public
  * License ("GPL") version 2, as published by the Free Software Foundation.
diff --git a/include/linux/soc/ti/k3-ringacc.h b/include/linux/soc/ti/k3-ringacc.h
index 7ac115432fa1..5a472eca5ee4 100644
--- a/include/linux/soc/ti/k3-ringacc.h
+++ b/include/linux/soc/ti/k3-ringacc.h
@@ -2,7 +2,7 @@
 /*
  * K3 Ring Accelerator (RA) subsystem interface
  *
- * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com
  */
 
 #ifndef __SOC_TI_K3_RINGACC_API_H_
diff --git a/include/linux/soc/ti/knav_qmss.h b/include/linux/soc/ti/knav_qmss.h
index 9745df6ed9d3..c75ef99c99ca 100644
--- a/include/linux/soc/ti/knav_qmss.h
+++ b/include/linux/soc/ti/knav_qmss.h
@@ -1,7 +1,7 @@
 /*
  * Keystone Navigator Queue Management Sub-System header
  *
- * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com
  * Author:	Sandeep Nair <sandeep_n@ti.com>
  *		Cyril Chemparathy <cyril@ti.com>
  *		Santosh Shilimkar <santosh.shilimkar@ti.com>
diff --git a/include/linux/soc/ti/ti-msgmgr.h b/include/linux/soc/ti/ti-msgmgr.h
index eac8e0c6fe11..1f6e76d423cf 100644
--- a/include/linux/soc/ti/ti-msgmgr.h
+++ b/include/linux/soc/ti/ti-msgmgr.h
@@ -1,7 +1,7 @@
 /*
  * Texas Instruments' Message Manager
  *
- * Copyright (C) 2015-2016 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015-2016 Texas Instruments Incorporated - https://www.ti.com/
  *	Nishanth Menon
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h
index e497e621dbb7..3f496967b538 100644
--- a/include/linux/wkup_m3_ipc.h
+++ b/include/linux/wkup_m3_ipc.h
@@ -1,7 +1,7 @@
 /*
  * TI Wakeup M3 for AMx3 SoCs Power Management Routines
  *
- * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/
  * Dave Gerlach <d-gerlach@ti.com>
  *
  * This program is free software; you can redistribute it and/or
diff --git a/include/linux/xxhash.h b/include/linux/xxhash.h
index 52b073fea17f..df42511438d0 100644
--- a/include/linux/xxhash.h
+++ b/include/linux/xxhash.h
@@ -34,7 +34,7 @@
  * ("BSD").
  *
  * You can contact the author at:
- * - xxHash homepage: http://cyan4973.github.io/xxHash/
+ * - xxHash homepage: https://cyan4973.github.io/xxHash/
  * - xxHash source repository: https://github.com/Cyan4973/xxHash
  */
 
diff --git a/include/linux/xz.h b/include/linux/xz.h
index 24ad7d875977..9884c8440188 100644
--- a/include/linux/xz.h
+++ b/include/linux/xz.h
@@ -2,7 +2,7 @@
  * XZ decompressor
  *
  * Authors: Lasse Collin <lasse.collin@tukaani.org>
- *          Igor Pavlov <http://7-zip.org/>
+ *          Igor Pavlov <https://7-zip.org/>
  *
  * This file has been put into the public domain.
  * You can do whatever you want with this file.
diff --git a/include/linux/zlib.h b/include/linux/zlib.h
index c757d848a758..78ede944c082 100644
--- a/include/linux/zlib.h
+++ b/include/linux/zlib.h
@@ -23,7 +23,7 @@
 
 
   The data format used by the zlib library is described by RFCs (Request for
-  Comments) 1950 to 1952 in the files http://www.ietf.org/rfc/rfc1950.txt
+  Comments) 1950 to 1952 in the files https://www.ietf.org/rfc/rfc1950.txt
   (zlib format), rfc1951.txt (deflate format) and rfc1952.txt (gzip format).
 */
 
diff --git a/include/soc/arc/aux.h b/include/soc/arc/aux.h
index e223c4ffa153..9c2eff6140b6 100644
--- a/include/soc/arc/aux.h
+++ b/include/soc/arc/aux.h
@@ -22,7 +22,7 @@ static inline int read_aux_reg(u32 r)
 
 /*
  * function helps elide unused variable warning
- * see: http://lists.infradead.org/pipermail/linux-snps-arc/2016-November/001748.html
+ * see: https://lists.infradead.org/pipermail/linux-snps-arc/2016-November/001748.html
  */
 static inline void write_aux_reg(u32 r, u32 v)
 {
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index c6dd0215482e..22220945a5fd 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -53,7 +53,7 @@ typedef __s64	Elf64_Sxword;
  *
  * - Oracle: Linker and Libraries.
  *   Part No: 817–1984–19, August 2011.
- *   http://docs.oracle.com/cd/E18752_01/pdf/817-1984.pdf
+ *   https://docs.oracle.com/cd/E18752_01/pdf/817-1984.pdf
  *
  * - System V ABI AMD64 Architecture Processor Supplement
  *   Draft Version 0.99.4,
diff --git a/include/uapi/linux/map_to_7segment.h b/include/uapi/linux/map_to_7segment.h
index f9ed18134b83..13a06e5e966e 100644
--- a/include/uapi/linux/map_to_7segment.h
+++ b/include/uapi/linux/map_to_7segment.h
@@ -24,7 +24,7 @@
  * of (ASCII) characters to a 7-segments notation.
  *
  * The 7 segment's wikipedia notation below is used as standard.
- * See: http://en.wikipedia.org/wiki/Seven_segment_display
+ * See: https://en.wikipedia.org/wiki/Seven_segment_display
  *
  * Notation:	+-a-+
  *		f   b
diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h
index 2fce8b6876e9..f6d2f83cbe29 100644
--- a/include/uapi/linux/types.h
+++ b/include/uapi/linux/types.h
@@ -7,7 +7,7 @@
 #ifndef __ASSEMBLY__
 #ifndef	__KERNEL__
 #ifndef __EXPORTED_HEADERS__
-#warning "Attempt to use kernel headers from user space, see http://kernelnewbies.org/KernelHeaders"
+#warning "Attempt to use kernel headers from user space, see https://kernelnewbies.org/KernelHeaders"
 #endif /* __EXPORTED_HEADERS__ */
 #endif
 
diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h
index 48766fdf6580..0f865ae4ba89 100644
--- a/include/uapi/linux/usb/ch9.h
+++ b/include/uapi/linux/usb/ch9.h
@@ -1229,7 +1229,7 @@ struct usb_set_sel_req {
  * As per USB compliance update, a device that is actively drawing
  * more than 100mA from USB must report itself as bus-powered in
  * the GetStatus(DEVICE) call.
- * http://compliance.usb.org/index.asp?UpdateFile=Electrical&Format=Standard#34
+ * https://compliance.usb.org/index.asp?UpdateFile=Electrical&Format=Standard#34
  */
 #define USB_SELF_POWER_VBUS_MAX_DRAW		100
 

From 9e58c5e2fcd8d8d8820ea277e0f577f563eed1f1 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 11 Aug 2020 18:34:23 -0700
Subject: [PATCH 388/474] include/linux/poison.h: remove obsolete comment

When the definition was changed, the comment became stale.  Just remove
it since there isn't anything useful to say here.

Fixes: b8a0255db958 ("include/linux/poison.h: use POISON_POINTER_DELTA for poison pointers")
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Vasily Kulikov <segoon@openwall.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20200730174108.GJ23808@casper.infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/poison.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/include/linux/poison.h b/include/linux/poison.h
index df34330b4e34..dc8ae5d8db03 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -24,10 +24,6 @@
 #define LIST_POISON2  ((void *) 0x122 + POISON_POINTER_DELTA)
 
 /********** include/linux/timer.h **********/
-/*
- * Magic number "tsta" to indicate a static timer initializer
- * for the object debugging code.
- */
 #define TIMER_ENTRY_STATIC	((void *) 0x300 + POISON_POINTER_DELTA)
 
 /********** mm/page_poison.c **********/

From 25fd529c34d063d1bef23742f2e8f8341c639dc3 Mon Sep 17 00:00:00 2001
From: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Date: Tue, 11 Aug 2020 18:34:26 -0700
Subject: [PATCH 389/474] sparse: group the defines by functionality

By popular demand, reorder the defines for sparse annotations and group
them by functionality.

Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Link: lore.kernel.org/r/CAMuHMdWQsirja-h3wBcZezk+H2Q_HShhAks8Hc8ps5fTAp=ObQ@mail.gmail.com
Link: http://lkml.kernel.org/r/20200621143652.53798-1-luc.vanoostenryck@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler_types.h | 44 +++++++++++++++++++---------------
 1 file changed, 25 insertions(+), 19 deletions(-)

diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 2e231ba8fe3f..4b33cb385f96 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -5,48 +5,54 @@
 #ifndef __ASSEMBLY__
 
 #ifdef __CHECKER__
+/* address spaces */
 # define __kernel	__attribute__((address_space(0)))
 # define __user		__attribute__((noderef, address_space(__user)))
-# define __safe		__attribute__((safe))
-# define __force	__attribute__((force))
-# define __nocast	__attribute__((nocast))
 # define __iomem	__attribute__((noderef, address_space(__iomem)))
+# define __percpu	__attribute__((noderef, address_space(__percpu)))
+# define __rcu		__attribute__((noderef, address_space(__rcu)))
+extern void __chk_user_ptr(const volatile void __user *);
+extern void __chk_io_ptr(const volatile void __iomem *);
+/* context/locking */
 # define __must_hold(x)	__attribute__((context(x,1,1)))
 # define __acquires(x)	__attribute__((context(x,0,1)))
 # define __releases(x)	__attribute__((context(x,1,0)))
 # define __acquire(x)	__context__(x,1)
 # define __release(x)	__context__(x,-1)
 # define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
-# define __percpu	__attribute__((noderef, address_space(__percpu)))
-# define __rcu		__attribute__((noderef, address_space(__rcu)))
+/* other */
+# define __force	__attribute__((force))
+# define __nocast	__attribute__((nocast))
+# define __safe		__attribute__((safe))
 # define __private	__attribute__((noderef))
-extern void __chk_user_ptr(const volatile void __user *);
-extern void __chk_io_ptr(const volatile void __iomem *);
 # define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member))
 #else /* __CHECKER__ */
+/* address spaces */
+# define __kernel
 # ifdef STRUCTLEAK_PLUGIN
-#  define __user __attribute__((user))
+#  define __user	__attribute__((user))
 # else
 #  define __user
 # endif
-# define __kernel
-# define __safe
-# define __force
-# define __nocast
 # define __iomem
-# define __chk_user_ptr(x) (void)0
-# define __chk_io_ptr(x) (void)0
-# define __builtin_warning(x, y...) (1)
+# define __percpu
+# define __rcu
+# define __chk_user_ptr(x)	(void)0
+# define __chk_io_ptr(x)	(void)0
+/* context/locking */
 # define __must_hold(x)
 # define __acquires(x)
 # define __releases(x)
-# define __acquire(x) (void)0
-# define __release(x) (void)0
+# define __acquire(x)	(void)0
+# define __release(x)	(void)0
 # define __cond_lock(x,c) (c)
-# define __percpu
-# define __rcu
+/* other */
+# define __force
+# define __nocast
+# define __safe
 # define __private
 # define ACCESS_PRIVATE(p, member) ((p)->member)
+# define __builtin_warning(x, y...) (1)
 #endif /* __CHECKER__ */
 
 /* Indirect macros required for expanded argument pasting, eg. __LINE__. */

From 5959f829a93c18ccf15715768317b58f5d9bf2d4 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Tue, 11 Aug 2020 18:34:29 -0700
Subject: [PATCH 390/474] lib/bitmap.c: fix bitmap_cut() for partial
 overlapping case

Patch series "lib: Fix bitmap_cut() for overlaps, add test"

This patch (of 2):

Yury Norov reports that bitmap_cut() will not produce the right outcome if
src and dst partially overlap, with src pointing at some location after
dst, because the memmove() affects src before we store the bits that we
need to keep, that is, the bits preceding the cut -- as long as we the
beginning of the cut is not aligned to a long.

Fix this by storing those bits before the memmove().

Note that this is just a theoretical concern so far, as the only user of
this function, pipapo_drop() from the nftables set back-end implemented in
net/netfilter/nft_set_pipapo.c, always supplies entirely overlapping src
and dst.

Fixes: 2092767168f0 ("bitmap: Introduce bitmap_cut(): cut bits and shift remaining")
Reported-by: Yury Norov <yury.norov@gmail.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Link: http://lkml.kernel.org/r/cover.1592155364.git.sbrivio@redhat.com
Link: http://lkml.kernel.org/r/003e38d4428cd6091ef00b5b03354f1bd7d9091e.1592155364.git.sbrivio@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/bitmap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/bitmap.c b/lib/bitmap.c
index 0364452b1617..c13d859bc7ab 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -212,13 +212,13 @@ void bitmap_cut(unsigned long *dst, const unsigned long *src,
 	unsigned long keep = 0, carry;
 	int i;
 
-	memmove(dst, src, len * sizeof(*dst));
-
 	if (first % BITS_PER_LONG) {
 		keep = src[first / BITS_PER_LONG] &
 		       (~0UL >> (BITS_PER_LONG - first % BITS_PER_LONG));
 	}
 
+	memmove(dst, src, len * sizeof(*dst));
+
 	while (cut--) {
 		for (i = first / BITS_PER_LONG; i < len; i++) {
 			if (i < len - 1)

From bcb32a1d82614ffb8a56f14c648c3970bcd2cf89 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Tue, 11 Aug 2020 18:34:32 -0700
Subject: [PATCH 391/474] lib/test_bitmap.c: add test for bitmap_cut()

Inspired by an original patch from Yury Norov: introduce a test for
bitmap_cut() that also makes sure functionality is as described for
partially overlapping src and dst.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Yury Norov <yury.norov@gmail.com>
Link: http://lkml.kernel.org/r/5fc45e6bbd4fa837cd9577f8a0c1d639df90a4ce.1592155364.git.sbrivio@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/test_bitmap.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)

diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index 6b13150667f5..df903c53952b 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -610,6 +610,63 @@ static void __init test_for_each_set_clump8(void)
 		expect_eq_clump8(start, CLUMP_EXP_NUMBITS, clump_exp, &clump);
 }
 
+struct test_bitmap_cut {
+	unsigned int first;
+	unsigned int cut;
+	unsigned int nbits;
+	unsigned long in[4];
+	unsigned long expected[4];
+};
+
+static struct test_bitmap_cut test_cut[] = {
+	{  0,  0,  8, { 0x0000000aUL, }, { 0x0000000aUL, }, },
+	{  0,  0, 32, { 0xdadadeadUL, }, { 0xdadadeadUL, }, },
+	{  0,  3,  8, { 0x000000aaUL, }, { 0x00000015UL, }, },
+	{  3,  3,  8, { 0x000000aaUL, }, { 0x00000012UL, }, },
+	{  0,  1, 32, { 0xa5a5a5a5UL, }, { 0x52d2d2d2UL, }, },
+	{  0,  8, 32, { 0xdeadc0deUL, }, { 0x00deadc0UL, }, },
+	{  1,  1, 32, { 0x5a5a5a5aUL, }, { 0x2d2d2d2cUL, }, },
+	{  0, 15, 32, { 0xa5a5a5a5UL, }, { 0x00014b4bUL, }, },
+	{  0, 16, 32, { 0xa5a5a5a5UL, }, { 0x0000a5a5UL, }, },
+	{ 15, 15, 32, { 0xa5a5a5a5UL, }, { 0x000125a5UL, }, },
+	{ 15, 16, 32, { 0xa5a5a5a5UL, }, { 0x0000a5a5UL, }, },
+	{ 16, 15, 32, { 0xa5a5a5a5UL, }, { 0x0001a5a5UL, }, },
+
+	{ BITS_PER_LONG, BITS_PER_LONG, BITS_PER_LONG,
+		{ 0xa5a5a5a5UL, 0xa5a5a5a5UL, },
+		{ 0xa5a5a5a5UL, 0xa5a5a5a5UL, },
+	},
+	{ 1, BITS_PER_LONG - 1, BITS_PER_LONG,
+		{ 0xa5a5a5a5UL, 0xa5a5a5a5UL, },
+		{ 0x00000001UL, 0x00000001UL, },
+	},
+
+	{ 0, BITS_PER_LONG * 2, BITS_PER_LONG * 2 + 1,
+		{ 0xa5a5a5a5UL, 0x00000001UL, 0x00000001UL, 0x00000001UL },
+		{ 0x00000001UL, },
+	},
+	{ 16, BITS_PER_LONG * 2 + 1, BITS_PER_LONG * 2 + 1 + 16,
+		{ 0x0000ffffUL, 0x5a5a5a5aUL, 0x5a5a5a5aUL, 0x5a5a5a5aUL },
+		{ 0x2d2dffffUL, },
+	},
+};
+
+static void __init test_bitmap_cut(void)
+{
+	unsigned long b[5], *in = &b[1], *out = &b[0];	/* Partial overlap */
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_cut); i++) {
+		struct test_bitmap_cut *t = &test_cut[i];
+
+		memcpy(in, t->in, sizeof(t->in));
+
+		bitmap_cut(out, in, t->first, t->cut, t->nbits);
+
+		expect_eq_bitmap(t->expected, out, t->nbits);
+	}
+}
+
 static void __init selftest(void)
 {
 	test_zero_clear();
@@ -623,6 +680,7 @@ static void __init selftest(void)
 	test_bitmap_parselist_user();
 	test_mem_optimisations();
 	test_for_each_set_clump8();
+	test_bitmap_cut();
 }
 
 KSTM_MODULE_LOADERS(test_bitmap);

From 0a650e472d2039a5f768acd82f2a7068bf338dfd Mon Sep 17 00:00:00 2001
From: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Date: Tue, 11 Aug 2020 18:34:35 -0700
Subject: [PATCH 392/474] lib/generic-radix-tree.c: remove unneeded __rcu

struct __genradix is defined as having its member 'root'
annotated as __rcu. But in the corresponding API RCU is not used.
Sparse reports this type mismatch as:
	lib/generic-radix-tree.c:56:35: warning: incorrect type in initializer (different address spaces)
	lib/generic-radix-tree.c:56:35:    expected struct genradix_root *r
	lib/generic-radix-tree.c:56:35:    got struct genradix_root [noderef] <asn:4> *__val
with 6 other ones.

So, correct root's type by removing this unneeded __rcu.

Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Link: http://lkml.kernel.org/r/20200621161745.55396-1-luc.vanoostenryck@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/generic-radix-tree.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h
index 02393c0c98f9..bfd00320c7f3 100644
--- a/include/linux/generic-radix-tree.h
+++ b/include/linux/generic-radix-tree.h
@@ -44,7 +44,7 @@
 struct genradix_root;
 
 struct __genradix {
-	struct genradix_root __rcu	*root;
+	struct genradix_root		*root;
 };
 
 /*

From 403f177304354990c36d5a7d125bce2b39bcbe2c Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 11 Aug 2020 18:34:38 -0700
Subject: [PATCH 393/474] lib/test_bitops: do the full test during module init

Currently, the bitops test consists of two parts: one part is executed
during module load, the second part during module unload.  This is
cumbersome for the user, as he has to perform two steps to execute all
tests, and is different from most (all?) other tests.

Merge the two parts, so both are executed during module load.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Link: http://lkml.kernel.org/r/20200706112900.7097-1-geert@linux-m68k.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/test_bitops.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/lib/test_bitops.c b/lib/test_bitops.c
index ced25e3a779b..471141ddd691 100644
--- a/lib/test_bitops.c
+++ b/lib/test_bitops.c
@@ -52,9 +52,9 @@ static unsigned long order_comb_long[][2] = {
 
 static int __init test_bitops_startup(void)
 {
-	int i;
+	int i, bit_set;
 
-	pr_warn("Loaded test module\n");
+	pr_info("Starting bitops test\n");
 	set_bit(BITOPS_4, g_bitmap);
 	set_bit(BITOPS_7, g_bitmap);
 	set_bit(BITOPS_11, g_bitmap);
@@ -81,12 +81,8 @@ static int __init test_bitops_startup(void)
 				       order_comb_long[i][0]);
 	}
 #endif
-	return 0;
-}
 
-static void __exit test_bitops_unstartup(void)
-{
-	int bit_set;
+	barrier();
 
 	clear_bit(BITOPS_4, g_bitmap);
 	clear_bit(BITOPS_7, g_bitmap);
@@ -98,7 +94,13 @@ static void __exit test_bitops_unstartup(void)
 	if (bit_set != BITOPS_LAST)
 		pr_err("ERROR: FOUND SET BIT %d\n", bit_set);
 
-	pr_warn("Unloaded test module\n");
+	pr_info("Completed bitops test\n");
+
+	return 0;
+}
+
+static void __exit test_bitops_unstartup(void)
+{
 }
 
 module_init(test_bitops_startup);

From f36331770406b8e693a3d8d71ab3ccbbeabc7142 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Tue, 11 Aug 2020 18:34:41 -0700
Subject: [PATCH 394/474] lib/test_lockup.c: make symbol 'test_works' static

Fix sparse build warning:

lib/test_lockup.c:403:1: warning:
 symbol '__pcpu_scope_test_works' was not declared. Should it be static?

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20200707112252.9047-1-weiyongjun1@huawei.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/test_lockup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/test_lockup.c b/lib/test_lockup.c
index ff26f36d729f..0f81252837b9 100644
--- a/lib/test_lockup.c
+++ b/lib/test_lockup.c
@@ -400,7 +400,7 @@ static void test_lockup(bool master)
 	test_unlock(master, true);
 }
 
-DEFINE_PER_CPU(struct work_struct, test_works);
+static DEFINE_PER_CPU(struct work_struct, test_works);
 
 static void test_work_fn(struct work_struct *work)
 {

From 63646bc9f95f7faf5345e54a59fd1ecdd4ba5316 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Tue, 11 Aug 2020 18:34:44 -0700
Subject: [PATCH 395/474] lib/Kconfig.debug: make TEST_LOCKUP depend on module

Since test_lockup is a test module to generate lockups, it is better to
limit TEST_LOCKUP to module (=m) or disabled (=n) because we can not use
the module parameters when CONFIG_TEST_LOCKUP=y.

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/1595555407-29875-1-git-send-email-yangtiezhu@loongson.cn
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/Kconfig.debug | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index ba12a58b2947..32300eb79d46 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1078,6 +1078,7 @@ config WQ_WATCHDOG
 
 config TEST_LOCKUP
 	tristate "Test module to generate lockups"
+	depends on m
 	help
 	  This builds the "test_lockup" module that helps to make sure
 	  that watchdogs and lockup detectors are working properly.

From 3adf3bae0d612357da516d39e1584f1547eb6e86 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Tue, 11 Aug 2020 18:34:47 -0700
Subject: [PATCH 396/474] lib/test_lockup.c: fix return value of
 test_lockup_init()

Since filp_open() returns an error pointer, we should use IS_ERR() to
check the return value and then return PTR_ERR() if failed to get the
actual return value instead of always -EINVAL.

E.g. without this patch:

[root@localhost loongson]# ls no_such_file
ls: cannot access no_such_file: No such file or directory
[root@localhost loongson]# modprobe test_lockup file_path=no_such_file lock_sb_umount time_secs=60 state=S
modprobe: ERROR: could not insert 'test_lockup': Invalid argument
[root@localhost loongson]# dmesg | tail -1
[  126.100596] test_lockup: cannot find file_path

With this patch:

[root@localhost loongson]# ls no_such_file
ls: cannot access no_such_file: No such file or directory
[root@localhost loongson]# modprobe test_lockup file_path=no_such_file lock_sb_umount time_secs=60 state=S
modprobe: ERROR: could not insert 'test_lockup': Unknown symbol in module, or unknown parameter (see dmesg)
[root@localhost loongson]# dmesg | tail -1
[   95.134362] test_lockup: failed to open no_such_file: -2

Fixes: aecd42df6d39 ("lib/test_lockup.c: add parameters for locking generic vfs locks")
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/1595555407-29875-2-git-send-email-yangtiezhu@loongson.cn
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/test_lockup.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/test_lockup.c b/lib/test_lockup.c
index 0f81252837b9..f1a020bcc763 100644
--- a/lib/test_lockup.c
+++ b/lib/test_lockup.c
@@ -512,8 +512,8 @@ static int __init test_lockup_init(void)
 	if (test_file_path[0]) {
 		test_file = filp_open(test_file_path, O_RDONLY, 0);
 		if (IS_ERR(test_file)) {
-			pr_err("cannot find file_path\n");
-			return -EINVAL;
+			pr_err("failed to open %s: %ld\n", test_file_path, PTR_ERR(test_file));
+			return PTR_ERR(test_file);
 		}
 		test_inode = file_inode(test_file);
 	} else if (test_lock_inode ||

From d89775fc929c5a1d91ed518a71b456da0865e5ff Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Tue, 11 Aug 2020 18:34:50 -0700
Subject: [PATCH 397/474] lib/: replace HTTP links with HTTPS ones

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Coly Li <colyli@suse.de>	[crc64.c]
Link: http://lkml.kernel.org/r/20200726112154.16510-1-grandmaster@al2klimov.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/Kconfig.debug        | 2 +-
 lib/crc64.c              | 2 +-
 lib/decompress_bunzip2.c | 2 +-
 lib/decompress_unlzma.c  | 6 +++---
 lib/math/rational.c      | 2 +-
 lib/rbtree.c             | 2 +-
 lib/ts_bm.c              | 2 +-
 lib/xxhash.c             | 2 +-
 lib/xz/xz_crc32.c        | 2 +-
 lib/xz/xz_dec_bcj.c      | 2 +-
 lib/xz/xz_dec_lzma2.c    | 2 +-
 lib/xz/xz_lzma2.h        | 2 +-
 lib/xz/xz_stream.h       | 2 +-
 13 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 32300eb79d46..5c5fbcb34af4 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2215,7 +2215,7 @@ config LIST_KUNIT_TEST
 	  and associated macros.
 
 	  KUnit tests run during boot and output the results to the debug log
-	  in TAP format (http://testanything.org/). Only useful for kernel devs
+	  in TAP format (https://testanything.org/). Only useful for kernel devs
 	  running the KUnit test harness, and not intended for inclusion into a
 	  production build.
 
diff --git a/lib/crc64.c b/lib/crc64.c
index f8928ce28280..47cfa054827f 100644
--- a/lib/crc64.c
+++ b/lib/crc64.c
@@ -4,7 +4,7 @@
  *
  * This is a basic crc64 implementation following ECMA-182 specification,
  * which can be found from,
- * http://www.ecma-international.org/publications/standards/Ecma-182.htm
+ * https://www.ecma-international.org/publications/standards/Ecma-182.htm
  *
  * Dr. Ross N. Williams has a great document to introduce the idea of CRC
  * algorithm, here the CRC64 code is also inspired by the table-driven
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 7c4932eed748..f9628f3924ce 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -34,7 +34,7 @@
 		Phone (337) 232-1234 or 1-800-738-2226
 		Fax   (337) 232-1297
 
-		http://www.hospiceacadiana.com/
+		https://www.hospiceacadiana.com/
 
 	Manuel
  */
diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c
index ed7a1fd819f2..1cf409ef8d04 100644
--- a/lib/decompress_unlzma.c
+++ b/lib/decompress_unlzma.c
@@ -8,7 +8,7 @@
  *implementation for lzma.
  *Copyright (C) 2006  Aurelien Jacobs < aurel@gnuage.org >
  *
- *Based on LzmaDecode.c from the LZMA SDK 4.22 (http://www.7-zip.org/)
+ *Based on LzmaDecode.c from the LZMA SDK 4.22 (https://www.7-zip.org/)
  *Copyright (C) 1999-2005  Igor Pavlov
  *
  *Copyrights of the parts, see headers below.
@@ -56,7 +56,7 @@ static long long INIT read_int(unsigned char *ptr, int size)
 /* Small range coder implementation for lzma.
  *Copyright (C) 2006  Aurelien Jacobs < aurel@gnuage.org >
  *
- *Based on LzmaDecode.c from the LZMA SDK 4.22 (http://www.7-zip.org/)
+ *Based on LzmaDecode.c from the LZMA SDK 4.22 (https://www.7-zip.org/)
  *Copyright (c) 1999-2005  Igor Pavlov
  */
 
@@ -213,7 +213,7 @@ rc_bit_tree_decode(struct rc *rc, uint16_t *p, int num_levels, int *symbol)
  * Small lzma deflate implementation.
  * Copyright (C) 2006  Aurelien Jacobs < aurel@gnuage.org >
  *
- * Based on LzmaDecode.c from the LZMA SDK 4.22 (http://www.7-zip.org/)
+ * Based on LzmaDecode.c from the LZMA SDK 4.22 (https://www.7-zip.org/)
  * Copyright (C) 1999-2005  Igor Pavlov
  */
 
diff --git a/lib/math/rational.c b/lib/math/rational.c
index 31fb27db2deb..df75c8809693 100644
--- a/lib/math/rational.c
+++ b/lib/math/rational.c
@@ -27,7 +27,7 @@
  * with the fractional part size described in given_denominator.
  *
  * for theoretical background, see:
- * http://en.wikipedia.org/wiki/Continued_fraction
+ * https://en.wikipedia.org/wiki/Continued_fraction
  */
 
 void rational_best_approximation(
diff --git a/lib/rbtree.c b/lib/rbtree.c
index 8545872e61db..c4ac5c2421f2 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -13,7 +13,7 @@
 #include <linux/export.h>
 
 /*
- * red-black trees properties:  http://en.wikipedia.org/wiki/Rbtree
+ * red-black trees properties:  https://en.wikipedia.org/wiki/Rbtree
  *
  *  1) A node is either red or black
  *  2) The root is black
diff --git a/lib/ts_bm.c b/lib/ts_bm.c
index 277cb4417ac2..4cf250031f0f 100644
--- a/lib/ts_bm.c
+++ b/lib/ts_bm.c
@@ -11,7 +11,7 @@
  *   [1] A Fast String Searching Algorithm, R.S. Boyer and Moore.
  *       Communications of the Association for Computing Machinery, 
  *       20(10), 1977, pp. 762-772.
- *       http://www.cs.utexas.edu/users/moore/publications/fstrpos.pdf
+ *       https://www.cs.utexas.edu/users/moore/publications/fstrpos.pdf
  *
  *   [2] Handbook of Exact String Matching Algorithms, Thierry Lecroq, 2004
  *       http://www-igm.univ-mlv.fr/~lecroq/string/string.pdf
diff --git a/lib/xxhash.c b/lib/xxhash.c
index aa61e2a3802f..d5bb9ff10607 100644
--- a/lib/xxhash.c
+++ b/lib/xxhash.c
@@ -34,7 +34,7 @@
  * ("BSD").
  *
  * You can contact the author at:
- * - xxHash homepage: http://cyan4973.github.io/xxHash/
+ * - xxHash homepage: https://cyan4973.github.io/xxHash/
  * - xxHash source repository: https://github.com/Cyan4973/xxHash
  */
 
diff --git a/lib/xz/xz_crc32.c b/lib/xz/xz_crc32.c
index 912aae5fa09e..88a2c35e1b59 100644
--- a/lib/xz/xz_crc32.c
+++ b/lib/xz/xz_crc32.c
@@ -2,7 +2,7 @@
  * CRC32 using the polynomial from IEEE-802.3
  *
  * Authors: Lasse Collin <lasse.collin@tukaani.org>
- *          Igor Pavlov <http://7-zip.org/>
+ *          Igor Pavlov <https://7-zip.org/>
  *
  * This file has been put into the public domain.
  * You can do whatever you want with this file.
diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c
index a768e6d28bbb..72ddac6ef2ec 100644
--- a/lib/xz/xz_dec_bcj.c
+++ b/lib/xz/xz_dec_bcj.c
@@ -2,7 +2,7 @@
  * Branch/Call/Jump (BCJ) filter decoders
  *
  * Authors: Lasse Collin <lasse.collin@tukaani.org>
- *          Igor Pavlov <http://7-zip.org/>
+ *          Igor Pavlov <https://7-zip.org/>
  *
  * This file has been put into the public domain.
  * You can do whatever you want with this file.
diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c
index 156f26fdc4c9..9f336bc07ed6 100644
--- a/lib/xz/xz_dec_lzma2.c
+++ b/lib/xz/xz_dec_lzma2.c
@@ -2,7 +2,7 @@
  * LZMA2 decoder
  *
  * Authors: Lasse Collin <lasse.collin@tukaani.org>
- *          Igor Pavlov <http://7-zip.org/>
+ *          Igor Pavlov <https://7-zip.org/>
  *
  * This file has been put into the public domain.
  * You can do whatever you want with this file.
diff --git a/lib/xz/xz_lzma2.h b/lib/xz/xz_lzma2.h
index 071d67bee9f5..92d852d4f87a 100644
--- a/lib/xz/xz_lzma2.h
+++ b/lib/xz/xz_lzma2.h
@@ -2,7 +2,7 @@
  * LZMA2 definitions
  *
  * Authors: Lasse Collin <lasse.collin@tukaani.org>
- *          Igor Pavlov <http://7-zip.org/>
+ *          Igor Pavlov <https://7-zip.org/>
  *
  * This file has been put into the public domain.
  * You can do whatever you want with this file.
diff --git a/lib/xz/xz_stream.h b/lib/xz/xz_stream.h
index 66cb5a7055ec..430bb3a0d195 100644
--- a/lib/xz/xz_stream.h
+++ b/lib/xz/xz_stream.h
@@ -19,7 +19,7 @@
 
 /*
  * See the .xz file format specification at
- * http://tukaani.org/xz/xz-file-format.txt
+ * https://tukaani.org/xz/xz-file-format.txt
  * to understand the container format.
  */
 

From b642e44e8ab335868b549fe5753b783ca47bf3a3 Mon Sep 17 00:00:00 2001
From: Kars Mulder <kerneldev@karsmulder.nl>
Date: Tue, 11 Aug 2020 18:34:53 -0700
Subject: [PATCH 398/474] kstrto*: correct documentation references to
 simple_strto*()

The documentation of the kstrto*() functions reference the simple_strtoull
function by "used as a replacement for [the obsolete] simple_strtoull".
All these functions describes themselves as replacements for the function
simple_strtoull, even though a function like kstrtol() would be more aptly
described as a replacement of simple_strtol().

Fix these references by making the documentation of kstrto*() reference
the closest simple_strto*() equivalent available.  The functions
kstrto[u]int() do not have direct simple_strto[u]int() equivalences, so
these are made to refer to simple_strto[u]l() instead.

Furthermore, add parentheses after function names, as is standard in
kernel documentation.

Fixes: 4c925d6031f71 ("kstrto*: add documentation")
Signed-off-by: Kars Mulder <kerneldev@karsmulder.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Eldad Zack <eldad@fogrefinery.com>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Mans Rullgard <mans@mansr.com>
Cc: Petr Mladek <pmladek@suse.com>
Link: http://lkml.kernel.org/r/1ee1-5f234c00-f3-165a6440@234394593
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 4 ++--
 lib/kstrtox.c          | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index e19c13616666..47b1dad63ffc 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -346,7 +346,7 @@ int __must_check kstrtoll(const char *s, unsigned int base, long long *res);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the simple_strtoull. Return code must be checked.
+ * Used as a replacement for the simple_strtoul(). Return code must be checked.
 */
 static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res)
 {
@@ -374,7 +374,7 @@ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsign
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the simple_strtoull. Return code must be checked.
+ * Used as a replacement for the simple_strtol(). Return code must be checked.
  */
 static inline int __must_check kstrtol(const char *s, unsigned int base, long *res)
 {
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index 1006bf70bf74..252ac414ba9a 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -115,7 +115,7 @@ static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * Used as a replacement for the obsolete simple_strtoull(). Return code must
  * be checked.
  */
 int kstrtoull(const char *s, unsigned int base, unsigned long long *res)
@@ -139,7 +139,7 @@ EXPORT_SYMBOL(kstrtoull);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * Used as a replacement for the obsolete simple_strtoll(). Return code must
  * be checked.
  */
 int kstrtoll(const char *s, unsigned int base, long long *res)
@@ -211,7 +211,7 @@ EXPORT_SYMBOL(_kstrtol);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * Used as a replacement for the obsolete simple_strtoul(). Return code must
  * be checked.
  */
 int kstrtouint(const char *s, unsigned int base, unsigned int *res)
@@ -242,7 +242,7 @@ EXPORT_SYMBOL(kstrtouint);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * Used as a replacement for the obsolete simple_strtol(). Return code must
  * be checked.
  */
 int kstrtoint(const char *s, unsigned int base, int *res)

From ef0f2685336bbc334e8b6997ce9b155e5f7edd31 Mon Sep 17 00:00:00 2001
From: Kars Mulder <kerneldev@karsmulder.nl>
Date: Tue, 11 Aug 2020 18:34:56 -0700
Subject: [PATCH 399/474] kstrto*: do not describe simple_strto*() as
 obsolete/replaced

The documentation of the kstrto*() functions describes kstrto*() as
"replacements" of the "obsolete" simple_strto*() functions.  Both of these
terms are inaccurate: they're not replacements because they have different
behaviour, and the simple_strto*() are not obsolete because there are
cases where they have benefits over kstrto*().

Remove usage of the terms "replacement" and "obsolete" in reference to
simple_strto*(), and instead use the term "preferred over".

Fixes: 4c925d6031f71 ("kstrto*: add documentation")
Fixes: 885e68e8b7b13 ("kernel.h: update comment about simple_strto<foo>() functions")
Signed-off-by: Kars Mulder <kerneldev@karsmulder.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Eldad Zack <eldad@fogrefinery.com>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Mans Rullgard <mans@mansr.com>
Cc: Petr Mladek <pmladek@suse.com>
Link: http://lkml.kernel.org/r/29b9-5f234c80-13-4e3aa200@244003027
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h |  4 ++--
 lib/kstrtox.c          | 12 ++++--------
 2 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 47b1dad63ffc..92517ae53e7c 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -346,7 +346,7 @@ int __must_check kstrtoll(const char *s, unsigned int base, long long *res);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the simple_strtoul(). Return code must be checked.
+ * Preferred over simple_strtoul(). Return code must be checked.
 */
 static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res)
 {
@@ -374,7 +374,7 @@ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsign
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the simple_strtol(). Return code must be checked.
+ * Preferred over simple_strtol(). Return code must be checked.
  */
 static inline int __must_check kstrtol(const char *s, unsigned int base, long *res)
 {
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index 252ac414ba9a..a14ccf905055 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -115,8 +115,7 @@ static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull(). Return code must
- * be checked.
+ * Preferred over simple_strtoull(). Return code must be checked.
  */
 int kstrtoull(const char *s, unsigned int base, unsigned long long *res)
 {
@@ -139,8 +138,7 @@ EXPORT_SYMBOL(kstrtoull);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoll(). Return code must
- * be checked.
+ * Preferred over simple_strtoll(). Return code must be checked.
  */
 int kstrtoll(const char *s, unsigned int base, long long *res)
 {
@@ -211,8 +209,7 @@ EXPORT_SYMBOL(_kstrtol);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoul(). Return code must
- * be checked.
+ * Preferred over simple_strtoul(). Return code must be checked.
  */
 int kstrtouint(const char *s, unsigned int base, unsigned int *res)
 {
@@ -242,8 +239,7 @@ EXPORT_SYMBOL(kstrtouint);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtol(). Return code must
- * be checked.
+ * Preferred over simple_strtol(). Return code must be checked.
  */
 int kstrtoint(const char *s, unsigned int base, int *res)
 {

From 6d511020e13d5d6f5f0af853e32ddef75c693ccc Mon Sep 17 00:00:00 2001
From: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Date: Tue, 11 Aug 2020 18:35:03 -0700
Subject: [PATCH 400/474] lib/test_bits.c: add tests of GENMASK

Add tests of GENMASK and GENMASK_ULL.

A few test cases that should fail compilation are provided under #ifdef
TEST_GENMASK_FAILURES

[rd.dunlap@gmail.com: add MODULE_LICENSE()]
  Link: http://lkml.kernel.org/r/dfc74524-0789-2827-4eff-476ddab65699@gmail.com
[weiyongjun1@huawei.com: make some functions static]
  Link: http://lkml.kernel.org/r/20200702150336.4756-1-weiyongjun1@huawei.com

Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Signed-off-by: Randy Dunlap <rd.dunlap@gmail.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Acked-by: William Breathitt Gray <vilhelm.gray@gmail.com>
Cc: Emil Velikov <emil.l.velikov@gmail.com>
Cc: Syed Nayyar Waris <syednwaris@gmail.com>
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Link: http://lkml.kernel.org/r/20200621054210.14804-2-rikard.falkeborn@gmail.com
Link: http://lkml.kernel.org/r/20200608221823.35799-2-rikard.falkeborn@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/Kconfig.debug | 11 +++++++
 lib/Makefile      |  1 +
 lib/test_bits.c   | 75 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 87 insertions(+)
 create mode 100644 lib/test_bits.c

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 5c5fbcb34af4..9ca1b11af1f6 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2236,6 +2236,17 @@ config LINEAR_RANGES_TEST
 
 	  If unsure, say N.
 
+config BITS_TEST
+	tristate "KUnit test for bits.h"
+	depends on KUNIT
+	help
+	  This builds the bits unit test.
+	  Tests the logic of macros defined in bits.h.
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
 config TEST_UDELAY
 	tristate "udelay test driver"
 	help
diff --git a/lib/Makefile b/lib/Makefile
index 9d1fd82ea145..e290fc5707ea 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -342,3 +342,4 @@ obj-$(CONFIG_PLDMFW) += pldmfw/
 # KUnit tests
 obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o
 obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o
+obj-$(CONFIG_BITS_TEST) += test_bits.o
diff --git a/lib/test_bits.c b/lib/test_bits.c
new file mode 100644
index 000000000000..c9368a2314e7
--- /dev/null
+++ b/lib/test_bits.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Test cases for functions and macros in bits.h
+ */
+
+#include <kunit/test.h>
+#include <linux/bits.h>
+
+
+static void genmask_test(struct kunit *test)
+{
+	KUNIT_EXPECT_EQ(test, 1ul, GENMASK(0, 0));
+	KUNIT_EXPECT_EQ(test, 3ul, GENMASK(1, 0));
+	KUNIT_EXPECT_EQ(test, 6ul, GENMASK(2, 1));
+	KUNIT_EXPECT_EQ(test, 0xFFFFFFFFul, GENMASK(31, 0));
+
+#ifdef TEST_GENMASK_FAILURES
+	/* these should fail compilation */
+	GENMASK(0, 1);
+	GENMASK(0, 10);
+	GENMASK(9, 10);
+#endif
+
+
+}
+
+static void genmask_ull_test(struct kunit *test)
+{
+	KUNIT_EXPECT_EQ(test, 1ull, GENMASK_ULL(0, 0));
+	KUNIT_EXPECT_EQ(test, 3ull, GENMASK_ULL(1, 0));
+	KUNIT_EXPECT_EQ(test, 0x000000ffffe00000ull, GENMASK_ULL(39, 21));
+	KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_ULL(63, 0));
+
+#ifdef TEST_GENMASK_FAILURES
+	/* these should fail compilation */
+	GENMASK_ULL(0, 1);
+	GENMASK_ULL(0, 10);
+	GENMASK_ULL(9, 10);
+#endif
+}
+
+static void genmask_input_check_test(struct kunit *test)
+{
+	unsigned int x, y;
+	int z, w;
+
+	/* Unknown input */
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(x, 0));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(0, x));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(x, y));
+
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(z, 0));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(0, z));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(z, w));
+
+	/* Valid input */
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(1, 1));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(39, 21));
+}
+
+
+static struct kunit_case bits_test_cases[] = {
+	KUNIT_CASE(genmask_test),
+	KUNIT_CASE(genmask_ull_test),
+	KUNIT_CASE(genmask_input_check_test),
+	{}
+};
+
+static struct kunit_suite bits_test_suite = {
+	.name = "bits-test",
+	.test_cases = bits_test_cases,
+};
+kunit_test_suite(bits_test_suite);
+
+MODULE_LICENSE("GPL");

From 50161266973bcc662e969e63d68fc7bff71de21b Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 11 Aug 2020 18:35:07 -0700
Subject: [PATCH 401/474] checkpatch: add test for possible misuse of
 IS_ENABLED() without CONFIG_

IS_ENABLED is almost always used with CONFIG_<FOO> defines.

Add a test to verify that the #define being tested starts with CONFIG_.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/e7fda760b91b769ba82844ba282d432c0d26d709.camel@perches.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 scripts/checkpatch.pl | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 599b8c4933a7..ba9ab2b42d73 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -6465,6 +6465,12 @@ sub process {
 			}
 		}
 
+# check for IS_ENABLED() without CONFIG_<FOO> ($rawline for comments too)
+		if ($rawline =~ /\bIS_ENABLED\s*\(\s*(\w+)\s*\)/ && $1 !~ /^CONFIG_/) {
+			WARN("IS_ENABLED_CONFIG",
+			     "IS_ENABLED($1) is normally used as IS_ENABLED(CONFIG_$1)\n" . $herecurr);
+		}
+
 # check for #if defined CONFIG_<FOO> || defined CONFIG_<FOO>_MODULE
 		if ($line =~ /^\+\s*#\s*if\s+defined(?:\s*\(?\s*|\s+)(CONFIG_[A-Z_]+)\s*\)?\s*\|\|\s*defined(?:\s*\(?\s*|\s+)\1_MODULE\s*\)?\s*$/) {
 			my $config = $1;

From 65b64b3bec3fa74937fdc18e5ccf10a48ee3a7d3 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 11 Aug 2020 18:35:10 -0700
Subject: [PATCH 402/474] checkpatch: add --fix option for ASSIGN_IN_IF

Add a --fix option for 2 types of single-line assignment in if statements

	if ((foo = bar(...)) < BAZ) {
expands to:
	foo = bar(..);
	if (foo < BAZ) {
and
	if ((foo = bar(...)) {
expands to:
	foo = bar(...);
	if (foo) {

if statements with assignments spanning multiple lines are
not converted with the --fix option.

if statements with additional logic are also not converted.

e.g.:	if ((foo = bar(...)) & BAZ == BAZ) {

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Julia Lawall <julia.lawall@lip6.fr>
Link: http://lkml.kernel.org/r/9bc7c782516f37948f202deba511bc95ed279bbd.camel@perches.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 scripts/checkpatch.pl | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index ba9ab2b42d73..5cb791eb4c6f 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -5020,8 +5020,30 @@ sub process {
 			my ($s, $c) = ($stat, $cond);
 
 			if ($c =~ /\bif\s*\(.*[^<>!=]=[^=].*/s) {
-				ERROR("ASSIGN_IN_IF",
-				      "do not use assignment in if condition\n" . $herecurr);
+				if (ERROR("ASSIGN_IN_IF",
+					  "do not use assignment in if condition\n" . $herecurr) &&
+				    $fix && $perl_version_ok) {
+					if ($rawline =~ /^\+(\s+)if\s*\(\s*(\!)?\s*\(\s*(($Lval)\s*=\s*$LvalOrFunc)\s*\)\s*(?:($Compare)\s*($FuncArg))?\s*\)\s*(\{)?\s*$/) {
+						my $space = $1;
+						my $not = $2;
+						my $statement = $3;
+						my $assigned = $4;
+						my $test = $8;
+						my $against = $9;
+						my $brace = $15;
+						fix_delete_line($fixlinenr, $rawline);
+						fix_insert_line($fixlinenr, "$space$statement;");
+						my $newline = "${space}if (";
+						$newline .= '!' if defined($not);
+						$newline .= '(' if (defined $not && defined($test) && defined($against));
+						$newline .= "$assigned";
+						$newline .= " $test $against" if (defined($test) && defined($against));
+						$newline .= ')' if (defined $not && defined($test) && defined($against));
+						$newline .= ')';
+						$newline .= " {" if (defined($brace));
+						fix_insert_line($fixlinenr + 1, $newline);
+					}
+				}
 			}
 
 			# Find out what is on the end of the line after the

From ced69da1db0b57bbb10054bd74201babc094f408 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Tue, 11 Aug 2020 18:35:13 -0700
Subject: [PATCH 403/474] checkpatch: fix CONST_STRUCT when
 const_structs.checkpatch is missing

Checkpatch reports warnings when some specific structs are not declared as
const in the code.  The list of structs to consider was initially defined
in the checkpatch.pl script itself, but it was later moved to an external
file (scripts/const_structs.checkpatch), in commit bf1fa1dae68e
("checkpatch: externalize the structs that should be const").  This
introduced two minor issues:

- When file scripts/const_structs.checkpatch is not present (for
  example, if checkpatch is run outside of the kernel directory with the
  "--no-tree" option), a warning is printed to stderr to tell the user
  that "No structs that should be const will be found". This is fair,
  but the warning is printed unconditionally, even if the option
  "--ignore CONST_STRUCT" is passed. In the latter case, we explicitly
  ask checkpatch to skip this check, so no warning should be printed.

- When scripts/const_structs.checkpatch is missing, or even when trying
  to silence the warning by adding an empty file, $const_structs is set
  to "", and the regex used for finding structs that should be const,
  "$line =~ /struct\s+($const_structs)(?!\s*\{)/)", matches all
  structs found in the code, thus reporting a number of false positives.

Let's fix the first item by skipping scripts/const_structs.checkpatch
processing if "CONST_STRUCT" checks are ignored, and the second one by
skipping the test if $const_structs is not defined. Since we modify the
read_words() function a little bit, update the checks for
$typedefsfile/$typeOtherTypedefs as well.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Joe Perches <joe@perches.com>
Link: http://lkml.kernel.org/r/20200623221822.3727-1-quentin@isovalent.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 scripts/checkpatch.pl | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 5cb791eb4c6f..1abddf8fe56e 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -59,7 +59,7 @@ my $spelling_file = "$D/spelling.txt";
 my $codespell = 0;
 my $codespellfile = "/usr/share/codespell/dictionary.txt";
 my $conststructsfile = "$D/const_structs.checkpatch";
-my $typedefsfile = "";
+my $typedefsfile;
 my $color = "auto";
 my $allow_c99_comments = 1; # Can be overridden by --ignore C99_COMMENT_TOLERANCE
 # git output parsing needs US English output, so first set backtick child process LANGUAGE
@@ -756,7 +756,7 @@ sub read_words {
 				next;
 			}
 
-			$$wordsRef .= '|' if ($$wordsRef ne "");
+			$$wordsRef .= '|' if (defined $$wordsRef);
 			$$wordsRef .= $line;
 		}
 		close($file);
@@ -766,16 +766,18 @@ sub read_words {
 	return 0;
 }
 
-my $const_structs = "";
-read_words(\$const_structs, $conststructsfile)
-    or warn "No structs that should be const will be found - file '$conststructsfile': $!\n";
+my $const_structs;
+if (show_type("CONST_STRUCT")) {
+	read_words(\$const_structs, $conststructsfile)
+	    or warn "No structs that should be const will be found - file '$conststructsfile': $!\n";
+}
 
-my $typeOtherTypedefs = "";
-if (length($typedefsfile)) {
+if (defined($typedefsfile)) {
+	my $typeOtherTypedefs;
 	read_words(\$typeOtherTypedefs, $typedefsfile)
 	    or warn "No additional types will be considered - file '$typedefsfile': $!\n";
+	$typeTypedefs .= '|' . $typeOtherTypedefs if (defined $typeOtherTypedefs);
 }
-$typeTypedefs .= '|' . $typeOtherTypedefs if ($typeOtherTypedefs ne "");
 
 sub build_types {
 	my $mods = "(?x:  \n" . join("|\n  ", (@modifierList, @modifierListFile)) . "\n)";
@@ -6643,7 +6645,8 @@ sub process {
 
 # check for various structs that are normally const (ops, kgdb, device_tree)
 # and avoid what seem like struct definitions 'struct foo {'
-		if ($line !~ /\bconst\b/ &&
+		if (defined($const_structs) &&
+		    $line !~ /\bconst\b/ &&
 		    $line =~ /\bstruct\s+($const_structs)\b(?!\s*\{)/) {
 			WARN("CONST_STRUCT",
 			     "struct $1 should normally be const\n" . $herecurr);

From 1a3dcf2e6b35faa1176b9cd8200094fbce16ba19 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 11 Aug 2020 18:35:16 -0700
Subject: [PATCH 404/474] checkpatch: add test for repeated words

Try to avoid adding repeated words either on the same line or consecutive
comment lines in a block

e.g.:

duplicated word in comment block

	/*
	 * this is a comment block where the last word of the previous
	 * previous line is also the first word of the next line
	 */

and simple duplication

	/* test this this again */

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/cda9b566ad67976e1acd62b053de50ee44a57250.camel@perches.com
Inspired-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 scripts/checkpatch.pl | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 1abddf8fe56e..114af54c3194 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -588,6 +588,8 @@ our @mode_permission_funcs = (
 	["__ATTR", 2],
 );
 
+my $word_pattern = '\b[A-Z]?[a-z]{2,}\b';
+
 #Create a search pattern for all these functions to speed up a loop below
 our $mode_perms_search = "";
 foreach my $entry (@mode_permission_funcs) {
@@ -3312,6 +3314,42 @@ sub process {
 			}
 		}
 
+# check for repeated words separated by a single space
+		if ($rawline =~ /^\+/) {
+			while ($rawline =~ /\b($word_pattern) (?=($word_pattern))/g) {
+
+				my $first = $1;
+				my $second = $2;
+
+				if ($first =~ /(?:struct|union|enum)/) {
+					pos($rawline) += length($first) + length($second) + 1;
+					next;
+				}
+
+				next if ($first ne $second);
+				next if ($first eq 'long');
+
+				if (WARN("REPEATED_WORD",
+					 "Possible repeated word: '$first'\n" . $herecurr) &&
+				    $fix) {
+					$fixed[$fixlinenr] =~ s/\b$first $second\b/$first/;
+				}
+			}
+
+			# if it's a repeated word on consecutive lines in a comment block
+			if ($prevline =~ /$;+\s*$/ &&
+			    $prevrawline =~ /($word_pattern)\s*$/) {
+				my $last_word = $1;
+				if ($rawline =~ /^\+\s*\*\s*$last_word /) {
+					if (WARN("REPEATED_WORD",
+						 "Possible repeated word: '$last_word'\n" . $hereprev) &&
+					    $fix) {
+						$fixed[$fixlinenr] =~ s/(\+\s*\*\s*)$last_word /$1/;
+					}
+				}
+			}
+		}
+
 # check for space before tabs.
 		if ($rawline =~ /^\+/ && $rawline =~ / \t/) {
 			my $herevet = "$here\n" . cat_vet($rawline) . "\n";

From ef3c005c0eb07a60949191bc6ee407d5f43cc502 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 11 Aug 2020 18:35:19 -0700
Subject: [PATCH 405/474] checkpatch: remove missing switch/case break test

This test doesn't work well and newer compilers are much better
at emitting this warning.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Cambda Zhu <cambda@linux.alibaba.com>
Link: http://lkml.kernel.org/r/7e25090c79f6a69d502ab8219863300790192fe2.camel@perches.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 scripts/checkpatch.pl | 25 -------------------------
 1 file changed, 25 deletions(-)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 114af54c3194..2cbeae6d9aee 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -6543,31 +6543,6 @@ sub process {
 			}
 		}
 
-# check for case / default statements not preceded by break/fallthrough/switch
-		if ($line =~ /^.\s*(?:case\s+(?:$Ident|$Constant)\s*|default):/) {
-			my $has_break = 0;
-			my $has_statement = 0;
-			my $count = 0;
-			my $prevline = $linenr;
-			while ($prevline > 1 && ($file || $count < 3) && !$has_break) {
-				$prevline--;
-				my $rline = $rawlines[$prevline - 1];
-				my $fline = $lines[$prevline - 1];
-				last if ($fline =~ /^\@\@/);
-				next if ($fline =~ /^\-/);
-				next if ($fline =~ /^.(?:\s*(?:case\s+(?:$Ident|$Constant)[\s$;]*|default):[\s$;]*)*$/);
-				$has_break = 1 if ($rline =~ /fall[\s_-]*(through|thru)/i);
-				next if ($fline =~ /^.[\s$;]*$/);
-				$has_statement = 1;
-				$count++;
-				$has_break = 1 if ($fline =~ /\bswitch\b|\b(?:break\s*;[\s$;]*$|exit\s*\(\b|return\b|goto\b|continue\b)/);
-			}
-			if (!$has_break && $has_statement) {
-				WARN("MISSING_BREAK",
-				     "Possible switch case/default not preceded by break or fallthrough comment\n" . $herecurr);
-			}
-		}
-
 # check for /* fallthrough */ like comment, prefer fallthrough;
 		my @fallthroughs = (
 			'fallthrough',

From 2fb3244f0a58ceb3d866ac63f644dfa31cae430f Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 11 Aug 2020 18:35:21 -0700
Subject: [PATCH 406/474] autofs: fix doubled word

Change doubled word "is" to "it is".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Ian Kent <raven@themaw.net>
Link: http://lkml.kernel.org/r/5a82befd-40f8-8dc0-3498-cbc0436cad9b@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/uapi/linux/auto_dev-ioctl.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/auto_dev-ioctl.h b/include/uapi/linux/auto_dev-ioctl.h
index 374742651c30..62e625356dc8 100644
--- a/include/uapi/linux/auto_dev-ioctl.h
+++ b/include/uapi/linux/auto_dev-ioctl.h
@@ -82,7 +82,7 @@ struct args_ismountpoint {
 /*
  * All the ioctls use this structure.
  * When sending a path size must account for the total length
- * of the chunk of memory otherwise is is the size of the
+ * of the chunk of memory otherwise it is the size of the
  * structure.
  */
 

From da27e0a0e5f655f0d58d4e153c3182bb2b290f64 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 11 Aug 2020 18:35:24 -0700
Subject: [PATCH 407/474] fs/minix: check return value of sb_getblk()

Patch series "fs/minix: fix syzbot bugs and set s_maxbytes".

This series fixes all syzbot bugs in the minix filesystem:

	KASAN: null-ptr-deref Write in get_block
	KASAN: use-after-free Write in get_block
	KASAN: use-after-free Read in get_block
	WARNING in inc_nlink
	KMSAN: uninit-value in get_block
	WARNING in drop_nlink

It also fixes the minix filesystem to set s_maxbytes correctly, so that
userspace sees the correct behavior when exceeding the max file size.

This patch (of 6):

sb_getblk() can fail, so check its return value.

This fixes a NULL pointer dereference.

Originally from Qiujun Huang.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+4a88b2b9dc280f47baf4@syzkaller.appspotmail.com
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Qiujun Huang <anenbupt@gmail.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200628060846.682158-1-ebiggers@kernel.org
Link: http://lkml.kernel.org/r/20200628060846.682158-2-ebiggers@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/minix/itree_common.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/minix/itree_common.c b/fs/minix/itree_common.c
index 043c3fdbc8e7..446148792f41 100644
--- a/fs/minix/itree_common.c
+++ b/fs/minix/itree_common.c
@@ -75,6 +75,7 @@ static int alloc_branch(struct inode *inode,
 	int n = 0;
 	int i;
 	int parent = minix_new_block(inode);
+	int err = -ENOSPC;
 
 	branch[0].key = cpu_to_block(parent);
 	if (parent) for (n = 1; n < num; n++) {
@@ -85,6 +86,11 @@ static int alloc_branch(struct inode *inode,
 			break;
 		branch[n].key = cpu_to_block(nr);
 		bh = sb_getblk(inode->i_sb, parent);
+		if (!bh) {
+			minix_free_block(inode, nr);
+			err = -ENOMEM;
+			break;
+		}
 		lock_buffer(bh);
 		memset(bh->b_data, 0, bh->b_size);
 		branch[n].bh = bh;
@@ -103,7 +109,7 @@ static int alloc_branch(struct inode *inode,
 		bforget(branch[i].bh);
 	for (i = 0; i < n; i++)
 		minix_free_block(inode, block_to_cpu(branch[i].key));
-	return -ENOSPC;
+	return err;
 }
 
 static inline int splice_branch(struct inode *inode,

From facb03dddec04e4aac1bb2139accdceb04deb1f3 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 11 Aug 2020 18:35:27 -0700
Subject: [PATCH 408/474] fs/minix: don't allow getting deleted inodes

If an inode has no links, we need to mark it bad rather than allowing it
to be accessed.  This avoids WARNINGs in inc_nlink() and drop_nlink() when
doing directory operations on a fuzzed filesystem.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+a9ac3de1b5de5fb10efc@syzkaller.appspotmail.com
Reported-by: syzbot+df958cf5688a96ad3287@syzkaller.appspotmail.com
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Qiujun Huang <anenbupt@gmail.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200628060846.682158-3-ebiggers@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/minix/inode.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 7cb5fd38eb14..2bca95abe8f4 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -468,6 +468,13 @@ static struct inode *V1_minix_iget(struct inode *inode)
 		iget_failed(inode);
 		return ERR_PTR(-EIO);
 	}
+	if (raw_inode->i_nlinks == 0) {
+		printk("MINIX-fs: deleted inode referenced: %lu\n",
+		       inode->i_ino);
+		brelse(bh);
+		iget_failed(inode);
+		return ERR_PTR(-ESTALE);
+	}
 	inode->i_mode = raw_inode->i_mode;
 	i_uid_write(inode, raw_inode->i_uid);
 	i_gid_write(inode, raw_inode->i_gid);
@@ -501,6 +508,13 @@ static struct inode *V2_minix_iget(struct inode *inode)
 		iget_failed(inode);
 		return ERR_PTR(-EIO);
 	}
+	if (raw_inode->i_nlinks == 0) {
+		printk("MINIX-fs: deleted inode referenced: %lu\n",
+		       inode->i_ino);
+		brelse(bh);
+		iget_failed(inode);
+		return ERR_PTR(-ESTALE);
+	}
 	inode->i_mode = raw_inode->i_mode;
 	i_uid_write(inode, raw_inode->i_uid);
 	i_gid_write(inode, raw_inode->i_gid);

From 270ef41094e9fa95273f288d7d785313ceab2ff3 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 11 Aug 2020 18:35:30 -0700
Subject: [PATCH 409/474] fs/minix: reject too-large maximum file size

If the minix filesystem tries to map a very large logical block number to
its on-disk location, block_to_path() can return offsets that are too
large, causing out-of-bounds memory accesses when accessing indirect index
blocks.  This should be prevented by the check against the maximum file
size, but this doesn't work because the maximum file size is read directly
from the on-disk superblock and isn't validated itself.

Fix this by validating the maximum file size at mount time.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+c7d9ec7a1a7272dd71b3@syzkaller.appspotmail.com
Reported-by: syzbot+3b7b03a0c28948054fb5@syzkaller.appspotmail.com
Reported-by: syzbot+6e056ee473568865f3e6@syzkaller.appspotmail.com
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Qiujun Huang <anenbupt@gmail.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200628060846.682158-4-ebiggers@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/minix/inode.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 2bca95abe8f4..0dd929346f3f 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -150,6 +150,23 @@ static int minix_remount (struct super_block * sb, int * flags, char * data)
 	return 0;
 }
 
+static bool minix_check_superblock(struct minix_sb_info *sbi)
+{
+	if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0)
+		return false;
+
+	/*
+	 * s_max_size must not exceed the block mapping limitation.  This check
+	 * is only needed for V1 filesystems, since V2/V3 support an extra level
+	 * of indirect blocks which places the limit well above U32_MAX.
+	 */
+	if (sbi->s_version == MINIX_V1 &&
+	    sbi->s_max_size > (7 + 512 + 512*512) * BLOCK_SIZE)
+		return false;
+
+	return true;
+}
+
 static int minix_fill_super(struct super_block *s, void *data, int silent)
 {
 	struct buffer_head *bh;
@@ -228,11 +245,12 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
 	} else
 		goto out_no_fs;
 
+	if (!minix_check_superblock(sbi))
+		goto out_illegal_sb;
+
 	/*
 	 * Allocate the buffer map to keep the superblock small.
 	 */
-	if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0)
-		goto out_illegal_sb;
 	i = (sbi->s_imap_blocks + sbi->s_zmap_blocks) * sizeof(bh);
 	map = kzalloc(i, GFP_KERNEL);
 	if (!map)

From 32ac86efff91a3e4ef8c3d1cadd4559e23c8e73a Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 11 Aug 2020 18:35:33 -0700
Subject: [PATCH 410/474] fs/minix: set s_maxbytes correctly

The minix filesystem leaves super_block::s_maxbytes at MAX_NON_LFS rather
than setting it to the actual filesystem-specific limit.  This is broken
because it means userspace doesn't see the standard behavior like getting
EFBIG and SIGXFSZ when exceeding the maximum file size.

Fix this by setting s_maxbytes correctly.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Qiujun Huang <anenbupt@gmail.com>
Link: http://lkml.kernel.org/r/20200628060846.682158-5-ebiggers@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/minix/inode.c    | 12 +++++++-----
 fs/minix/itree_v1.c |  2 +-
 fs/minix/itree_v2.c |  3 +--
 fs/minix/minix.h    |  1 -
 4 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 0dd929346f3f..7b09a9158e40 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -150,8 +150,10 @@ static int minix_remount (struct super_block * sb, int * flags, char * data)
 	return 0;
 }
 
-static bool minix_check_superblock(struct minix_sb_info *sbi)
+static bool minix_check_superblock(struct super_block *sb)
 {
+	struct minix_sb_info *sbi = minix_sb(sb);
+
 	if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0)
 		return false;
 
@@ -161,7 +163,7 @@ static bool minix_check_superblock(struct minix_sb_info *sbi)
 	 * of indirect blocks which places the limit well above U32_MAX.
 	 */
 	if (sbi->s_version == MINIX_V1 &&
-	    sbi->s_max_size > (7 + 512 + 512*512) * BLOCK_SIZE)
+	    sb->s_maxbytes > (7 + 512 + 512*512) * BLOCK_SIZE)
 		return false;
 
 	return true;
@@ -202,7 +204,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
 	sbi->s_zmap_blocks = ms->s_zmap_blocks;
 	sbi->s_firstdatazone = ms->s_firstdatazone;
 	sbi->s_log_zone_size = ms->s_log_zone_size;
-	sbi->s_max_size = ms->s_max_size;
+	s->s_maxbytes = ms->s_max_size;
 	s->s_magic = ms->s_magic;
 	if (s->s_magic == MINIX_SUPER_MAGIC) {
 		sbi->s_version = MINIX_V1;
@@ -233,7 +235,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
 		sbi->s_zmap_blocks = m3s->s_zmap_blocks;
 		sbi->s_firstdatazone = m3s->s_firstdatazone;
 		sbi->s_log_zone_size = m3s->s_log_zone_size;
-		sbi->s_max_size = m3s->s_max_size;
+		s->s_maxbytes = m3s->s_max_size;
 		sbi->s_ninodes = m3s->s_ninodes;
 		sbi->s_nzones = m3s->s_zones;
 		sbi->s_dirsize = 64;
@@ -245,7 +247,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
 	} else
 		goto out_no_fs;
 
-	if (!minix_check_superblock(sbi))
+	if (!minix_check_superblock(s))
 		goto out_illegal_sb;
 
 	/*
diff --git a/fs/minix/itree_v1.c b/fs/minix/itree_v1.c
index 046cc96ee7ad..c0d418209ead 100644
--- a/fs/minix/itree_v1.c
+++ b/fs/minix/itree_v1.c
@@ -29,7 +29,7 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
 	if (block < 0) {
 		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n",
 			block, inode->i_sb->s_bdev);
-	} else if (block >= (minix_sb(inode->i_sb)->s_max_size/BLOCK_SIZE)) {
+	} else if (block >= inode->i_sb->s_maxbytes/BLOCK_SIZE) {
 		if (printk_ratelimit())
 			printk("MINIX-fs: block_to_path: "
 			       "block %ld too big on dev %pg\n",
diff --git a/fs/minix/itree_v2.c b/fs/minix/itree_v2.c
index f7fc7ecccccc..ee8af2f9e282 100644
--- a/fs/minix/itree_v2.c
+++ b/fs/minix/itree_v2.c
@@ -32,8 +32,7 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
 	if (block < 0) {
 		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n",
 			block, sb->s_bdev);
-	} else if ((u64)block * (u64)sb->s_blocksize >=
-			minix_sb(sb)->s_max_size) {
+	} else if ((u64)block * (u64)sb->s_blocksize >= sb->s_maxbytes) {
 		if (printk_ratelimit())
 			printk("MINIX-fs: block_to_path: "
 			       "block %ld too big on dev %pg\n",
diff --git a/fs/minix/minix.h b/fs/minix/minix.h
index df081e8afcc3..168d45d3de73 100644
--- a/fs/minix/minix.h
+++ b/fs/minix/minix.h
@@ -32,7 +32,6 @@ struct minix_sb_info {
 	unsigned long s_zmap_blocks;
 	unsigned long s_firstdatazone;
 	unsigned long s_log_zone_size;
-	unsigned long s_max_size;
 	int s_dirsize;
 	int s_namelen;
 	struct buffer_head ** s_imap;

From 0a12c4a8069607247cb8edc3b035a664e636fd9a Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 11 Aug 2020 18:35:36 -0700
Subject: [PATCH 411/474] fs/minix: fix block limit check for V1 filesystems

The minix filesystem reads its maximum file size from its on-disk
superblock.  This value isn't necessarily a multiple of the block size.
When it's not, the V1 block mapping code doesn't allow mapping the last
possible block.  Commit 6ed6a722f9ab ("minixfs: fix block limit check")
fixed this in the V2 mapping code.  Fix it in the V1 mapping code too.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Qiujun Huang <anenbupt@gmail.com>
Link: http://lkml.kernel.org/r/20200628060846.682158-6-ebiggers@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/minix/itree_v1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/minix/itree_v1.c b/fs/minix/itree_v1.c
index c0d418209ead..405573a79aab 100644
--- a/fs/minix/itree_v1.c
+++ b/fs/minix/itree_v1.c
@@ -29,7 +29,7 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
 	if (block < 0) {
 		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n",
 			block, inode->i_sb->s_bdev);
-	} else if (block >= inode->i_sb->s_maxbytes/BLOCK_SIZE) {
+	} else if ((u64)block * BLOCK_SIZE >= inode->i_sb->s_maxbytes) {
 		if (printk_ratelimit())
 			printk("MINIX-fs: block_to_path: "
 			       "block %ld too big on dev %pg\n",

From f666f9fb9a36f1c833b9d18923572f0e4d304754 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 11 Aug 2020 18:35:39 -0700
Subject: [PATCH 412/474] fs/minix: remove expected error message in
 block_to_path()

When truncating a file to a size within the last allowed logical block,
block_to_path() is called with the *next* block.  This exceeds the limit,
causing the "block %ld too big" error message to be printed.

This case isn't actually an error; there are just no more blocks past that
point.  So, remove this error message.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Qiujun Huang <anenbupt@gmail.com>
Link: http://lkml.kernel.org/r/20200628060846.682158-7-ebiggers@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/minix/itree_v1.c | 12 ++++++------
 fs/minix/itree_v2.c | 12 ++++++------
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/fs/minix/itree_v1.c b/fs/minix/itree_v1.c
index 405573a79aab..1fed906042aa 100644
--- a/fs/minix/itree_v1.c
+++ b/fs/minix/itree_v1.c
@@ -29,12 +29,12 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
 	if (block < 0) {
 		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n",
 			block, inode->i_sb->s_bdev);
-	} else if ((u64)block * BLOCK_SIZE >= inode->i_sb->s_maxbytes) {
-		if (printk_ratelimit())
-			printk("MINIX-fs: block_to_path: "
-			       "block %ld too big on dev %pg\n",
-				block, inode->i_sb->s_bdev);
-	} else if (block < 7) {
+		return 0;
+	}
+	if ((u64)block * BLOCK_SIZE >= inode->i_sb->s_maxbytes)
+		return 0;
+
+	if (block < 7) {
 		offsets[n++] = block;
 	} else if ((block -= 7) < 512) {
 		offsets[n++] = 7;
diff --git a/fs/minix/itree_v2.c b/fs/minix/itree_v2.c
index ee8af2f9e282..9d00f31a2d9d 100644
--- a/fs/minix/itree_v2.c
+++ b/fs/minix/itree_v2.c
@@ -32,12 +32,12 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
 	if (block < 0) {
 		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n",
 			block, sb->s_bdev);
-	} else if ((u64)block * (u64)sb->s_blocksize >= sb->s_maxbytes) {
-		if (printk_ratelimit())
-			printk("MINIX-fs: block_to_path: "
-			       "block %ld too big on dev %pg\n",
-				block, sb->s_bdev);
-	} else if (block < DIRCOUNT) {
+		return 0;
+	}
+	if ((u64)block * (u64)sb->s_blocksize >= sb->s_maxbytes)
+		return 0;
+
+	if (block < DIRCOUNT) {
 		offsets[n++] = block;
 	} else if ((block -= DIRCOUNT) < INDIRCOUNT(sb)) {
 		offsets[n++] = DIRCOUNT;

From 1b0e31861d98920c3823c7519ae762499811df00 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 11 Aug 2020 18:35:43 -0700
Subject: [PATCH 413/474] nilfs2: only call unlock_new_inode() if I_NEW

Patch series "nilfs2 updates".

This patch (of 3):

unlock_new_inode() is only meant to be called after a new inode has
already been inserted into the hash table.  But nilfs_new_inode() can call
it even before it has inserted the inode, triggering the WARNING in
unlock_new_inode().  Fix this by only calling unlock_new_inode() if the
inode has the I_NEW flag set, indicating that it's in the table.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1595860111-3920-1-git-send-email-konishi.ryusuke@gmail.com
Link: http://lkml.kernel.org/r/1595860111-3920-2-git-send-email-konishi.ryusuke@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/nilfs2/inode.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 28009ec54420..3318dd1350b2 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -388,7 +388,8 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 
  failed_after_creation:
 	clear_nlink(inode);
-	unlock_new_inode(inode);
+	if (inode->i_state & I_NEW)
+		unlock_new_inode(inode);
 	iput(inode);  /*
 		       * raw_inode will be deleted through
 		       * nilfs_evict_inode().

From 2987a4cfc8332b4b516f3e03d29ec0316221e45f Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 11 Aug 2020 18:35:46 -0700
Subject: [PATCH 414/474] nilfs2: convert __nilfs_msg to integrate the level
 and format

Reduce object size a bit by removing the KERN_<LEVEL> as a separate
argument and adding it to the format string.

Reduce overall object size by about ~.5% (x86-64 defconfig w/ nilfs2)

old:
$ size -t fs/nilfs2/built-in.a | tail -1
 191738	   8676	     44	 200458	  30f0a	(TOTALS)

new:
$ size -t fs/nilfs2/built-in.a | tail -1
 190971	   8676	     44	 199691	  30c0b	(TOTALS)

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1595860111-3920-3-git-send-email-konishi.ryusuke@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/nilfs2/nilfs.h |  9 ++++-----
 fs/nilfs2/super.c | 16 +++++++++++-----
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 42395ba52da6..979a41016743 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -289,9 +289,8 @@ static inline int nilfs_mark_inode_dirty_sync(struct inode *inode)
 /* super.c */
 extern struct inode *nilfs_alloc_inode(struct super_block *);
 
-extern __printf(3, 4)
-void __nilfs_msg(struct super_block *sb, const char *level,
-		 const char *fmt, ...);
+__printf(2, 3)
+void __nilfs_msg(struct super_block *sb, const char *fmt, ...);
 extern __printf(3, 4)
 void __nilfs_error(struct super_block *sb, const char *function,
 		   const char *fmt, ...);
@@ -299,7 +298,7 @@ void __nilfs_error(struct super_block *sb, const char *function,
 #ifdef CONFIG_PRINTK
 
 #define nilfs_msg(sb, level, fmt, ...)					\
-	__nilfs_msg(sb, level, fmt, ##__VA_ARGS__)
+	__nilfs_msg(sb, level fmt, ##__VA_ARGS__)
 #define nilfs_error(sb, fmt, ...)					\
 	__nilfs_error(sb, __func__, fmt, ##__VA_ARGS__)
 
@@ -307,7 +306,7 @@ void __nilfs_error(struct super_block *sb, const char *function,
 
 #define nilfs_msg(sb, level, fmt, ...)					\
 	do {								\
-		no_printk(fmt, ##__VA_ARGS__);				\
+		no_printk(level fmt, ##__VA_ARGS__);			\
 		(void)(sb);						\
 	} while (0)
 #define nilfs_error(sb, fmt, ...)					\
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 5729ee86da9a..fef4821a1f0f 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -62,19 +62,25 @@ struct kmem_cache *nilfs_btree_path_cache;
 static int nilfs_setup_super(struct super_block *sb, int is_mount);
 static int nilfs_remount(struct super_block *sb, int *flags, char *data);
 
-void __nilfs_msg(struct super_block *sb, const char *level, const char *fmt,
-		 ...)
+void __nilfs_msg(struct super_block *sb, const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
+	int level;
 
 	va_start(args, fmt);
-	vaf.fmt = fmt;
+
+	level = printk_get_level(fmt);
+	vaf.fmt = printk_skip_level(fmt);
 	vaf.va = &args;
+
 	if (sb)
-		printk("%sNILFS (%s): %pV\n", level, sb->s_id, &vaf);
+		printk("%c%cNILFS (%s): %pV\n",
+		       KERN_SOH_ASCII, level, sb->s_id, &vaf);
 	else
-		printk("%sNILFS: %pV\n", level, &vaf);
+		printk("%c%cNILFS: %pV\n",
+		       KERN_SOH_ASCII, level, &vaf);
+
 	va_end(args);
 }
 

From a1d0747a393a079631130d61faa2a61027d1c789 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 11 Aug 2020 18:35:49 -0700
Subject: [PATCH 415/474] nilfs2: use a more common logging style

Add macros for nilfs_<level>(sb, fmt, ...) and convert the uses of
'nilfs_msg(sb, KERN_<LEVEL>, ...)' to 'nilfs_<level>(sb, ...)' so nilfs2
uses a logging style more like the typical kernel logging style.

Miscellanea:

o Realign arguments for these uses

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1595860111-3920-4-git-send-email-konishi.ryusuke@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/nilfs2/alloc.c     | 38 +++++++++----------
 fs/nilfs2/btree.c     | 42 ++++++++++-----------
 fs/nilfs2/cpfile.c    | 10 ++---
 fs/nilfs2/dat.c       | 14 +++----
 fs/nilfs2/direct.c    | 14 ++++---
 fs/nilfs2/gcinode.c   |  2 +-
 fs/nilfs2/ifile.c     |  4 +-
 fs/nilfs2/inode.c     | 29 +++++++--------
 fs/nilfs2/ioctl.c     | 37 +++++++++----------
 fs/nilfs2/mdt.c       |  2 +-
 fs/nilfs2/namei.c     |  6 +--
 fs/nilfs2/nilfs.h     |  9 +++++
 fs/nilfs2/page.c      | 11 +++---
 fs/nilfs2/recovery.c  | 32 +++++++---------
 fs/nilfs2/segbuf.c    |  2 +-
 fs/nilfs2/segment.c   | 38 +++++++++----------
 fs/nilfs2/sufile.c    | 29 +++++++--------
 fs/nilfs2/super.c     | 57 ++++++++++++++---------------
 fs/nilfs2/sysfs.c     | 29 +++++++--------
 fs/nilfs2/the_nilfs.c | 85 ++++++++++++++++++++-----------------------
 20 files changed, 239 insertions(+), 251 deletions(-)

diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 235b959fc2b3..adf3bb0a8048 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -613,10 +613,10 @@ void nilfs_palloc_commit_free_entry(struct inode *inode,
 	lock = nilfs_mdt_bgl_lock(inode, group);
 
 	if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap))
-		nilfs_msg(inode->i_sb, KERN_WARNING,
-			  "%s (ino=%lu): entry number %llu already freed",
-			  __func__, inode->i_ino,
-			  (unsigned long long)req->pr_entry_nr);
+		nilfs_warn(inode->i_sb,
+			   "%s (ino=%lu): entry number %llu already freed",
+			   __func__, inode->i_ino,
+			   (unsigned long long)req->pr_entry_nr);
 	else
 		nilfs_palloc_group_desc_add_entries(desc, lock, 1);
 
@@ -654,10 +654,10 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
 	lock = nilfs_mdt_bgl_lock(inode, group);
 
 	if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap))
-		nilfs_msg(inode->i_sb, KERN_WARNING,
-			  "%s (ino=%lu): entry number %llu already freed",
-			  __func__, inode->i_ino,
-			  (unsigned long long)req->pr_entry_nr);
+		nilfs_warn(inode->i_sb,
+			   "%s (ino=%lu): entry number %llu already freed",
+			   __func__, inode->i_ino,
+			   (unsigned long long)req->pr_entry_nr);
 	else
 		nilfs_palloc_group_desc_add_entries(desc, lock, 1);
 
@@ -763,10 +763,10 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 		do {
 			if (!nilfs_clear_bit_atomic(lock, group_offset,
 						    bitmap)) {
-				nilfs_msg(inode->i_sb, KERN_WARNING,
-					  "%s (ino=%lu): entry number %llu already freed",
-					  __func__, inode->i_ino,
-					  (unsigned long long)entry_nrs[j]);
+				nilfs_warn(inode->i_sb,
+					   "%s (ino=%lu): entry number %llu already freed",
+					   __func__, inode->i_ino,
+					   (unsigned long long)entry_nrs[j]);
 			} else {
 				n++;
 			}
@@ -808,10 +808,10 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 			ret = nilfs_palloc_delete_entry_block(inode,
 							      last_nrs[k]);
 			if (ret && ret != -ENOENT)
-				nilfs_msg(inode->i_sb, KERN_WARNING,
-					  "error %d deleting block that object (entry=%llu, ino=%lu) belongs to",
-					  ret, (unsigned long long)last_nrs[k],
-					  inode->i_ino);
+				nilfs_warn(inode->i_sb,
+					   "error %d deleting block that object (entry=%llu, ino=%lu) belongs to",
+					   ret, (unsigned long long)last_nrs[k],
+					   inode->i_ino);
 		}
 
 		desc_kaddr = kmap_atomic(desc_bh->b_page);
@@ -826,9 +826,9 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 		if (nfree == nilfs_palloc_entries_per_group(inode)) {
 			ret = nilfs_palloc_delete_bitmap_block(inode, group);
 			if (ret && ret != -ENOENT)
-				nilfs_msg(inode->i_sb, KERN_WARNING,
-					  "error %d deleting bitmap block of group=%lu, ino=%lu",
-					  ret, group, inode->i_ino);
+				nilfs_warn(inode->i_sb,
+					   "error %d deleting bitmap block of group=%lu, ino=%lu",
+					   ret, group, inode->i_ino);
 		}
 	}
 	return 0;
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 23e043eca237..f42ab57201e7 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -351,10 +351,10 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node,
 		     (flags & NILFS_BTREE_NODE_ROOT) ||
 		     nchildren < 0 ||
 		     nchildren > NILFS_BTREE_NODE_NCHILDREN_MAX(size))) {
-		nilfs_msg(inode->i_sb, KERN_CRIT,
-			  "bad btree node (ino=%lu, blocknr=%llu): level = %d, flags = 0x%x, nchildren = %d",
-			  inode->i_ino, (unsigned long long)blocknr, level,
-			  flags, nchildren);
+		nilfs_crit(inode->i_sb,
+			   "bad btree node (ino=%lu, blocknr=%llu): level = %d, flags = 0x%x, nchildren = %d",
+			   inode->i_ino, (unsigned long long)blocknr, level,
+			   flags, nchildren);
 		ret = 1;
 	}
 	return ret;
@@ -381,9 +381,9 @@ static int nilfs_btree_root_broken(const struct nilfs_btree_node *node,
 		     level >= NILFS_BTREE_LEVEL_MAX ||
 		     nchildren < 0 ||
 		     nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) {
-		nilfs_msg(inode->i_sb, KERN_CRIT,
-			  "bad btree root (ino=%lu): level = %d, flags = 0x%x, nchildren = %d",
-			  inode->i_ino, level, flags, nchildren);
+		nilfs_crit(inode->i_sb,
+			   "bad btree root (ino=%lu): level = %d, flags = 0x%x, nchildren = %d",
+			   inode->i_ino, level, flags, nchildren);
 		ret = 1;
 	}
 	return ret;
@@ -450,10 +450,10 @@ static int nilfs_btree_bad_node(const struct nilfs_bmap *btree,
 {
 	if (unlikely(nilfs_btree_node_get_level(node) != level)) {
 		dump_stack();
-		nilfs_msg(btree->b_inode->i_sb, KERN_CRIT,
-			  "btree level mismatch (ino=%lu): %d != %d",
-			  btree->b_inode->i_ino,
-			  nilfs_btree_node_get_level(node), level);
+		nilfs_crit(btree->b_inode->i_sb,
+			   "btree level mismatch (ino=%lu): %d != %d",
+			   btree->b_inode->i_ino,
+			   nilfs_btree_node_get_level(node), level);
 		return 1;
 	}
 	return 0;
@@ -508,7 +508,7 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr,
 
  out_no_wait:
 	if (!buffer_uptodate(bh)) {
-		nilfs_msg(btree->b_inode->i_sb, KERN_ERR,
+		nilfs_err(btree->b_inode->i_sb,
 			  "I/O error reading b-tree node block (ino=%lu, blocknr=%llu)",
 			  btree->b_inode->i_ino, (unsigned long long)ptr);
 		brelse(bh);
@@ -2074,10 +2074,10 @@ static int nilfs_btree_propagate(struct nilfs_bmap *btree,
 	ret = nilfs_btree_do_lookup(btree, path, key, NULL, level + 1, 0);
 	if (ret < 0) {
 		if (unlikely(ret == -ENOENT))
-			nilfs_msg(btree->b_inode->i_sb, KERN_CRIT,
-				  "writing node/leaf block does not appear in b-tree (ino=%lu) at key=%llu, level=%d",
-				  btree->b_inode->i_ino,
-				  (unsigned long long)key, level);
+			nilfs_crit(btree->b_inode->i_sb,
+				   "writing node/leaf block does not appear in b-tree (ino=%lu) at key=%llu, level=%d",
+				   btree->b_inode->i_ino,
+				   (unsigned long long)key, level);
 		goto out;
 	}
 
@@ -2114,11 +2114,11 @@ static void nilfs_btree_add_dirty_buffer(struct nilfs_bmap *btree,
 	if (level < NILFS_BTREE_LEVEL_NODE_MIN ||
 	    level >= NILFS_BTREE_LEVEL_MAX) {
 		dump_stack();
-		nilfs_msg(btree->b_inode->i_sb, KERN_WARNING,
-			  "invalid btree level: %d (key=%llu, ino=%lu, blocknr=%llu)",
-			  level, (unsigned long long)key,
-			  btree->b_inode->i_ino,
-			  (unsigned long long)bh->b_blocknr);
+		nilfs_warn(btree->b_inode->i_sb,
+			   "invalid btree level: %d (key=%llu, ino=%lu, blocknr=%llu)",
+			   level, (unsigned long long)key,
+			   btree->b_inode->i_ino,
+			   (unsigned long long)bh->b_blocknr);
 		return;
 	}
 
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index 8d41311b5db4..86d4d850d130 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -322,7 +322,7 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
 	int ret, ncps, nicps, nss, count, i;
 
 	if (unlikely(start == 0 || start > end)) {
-		nilfs_msg(cpfile->i_sb, KERN_ERR,
+		nilfs_err(cpfile->i_sb,
 			  "cannot delete checkpoints: invalid range [%llu, %llu)",
 			  (unsigned long long)start, (unsigned long long)end);
 		return -EINVAL;
@@ -376,7 +376,7 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
 								   cpfile, cno);
 					if (ret == 0)
 						continue;
-					nilfs_msg(cpfile->i_sb, KERN_ERR,
+					nilfs_err(cpfile->i_sb,
 						  "error %d deleting checkpoint block",
 						  ret);
 					break;
@@ -981,12 +981,10 @@ int nilfs_cpfile_read(struct super_block *sb, size_t cpsize,
 	int err;
 
 	if (cpsize > sb->s_blocksize) {
-		nilfs_msg(sb, KERN_ERR,
-			  "too large checkpoint size: %zu bytes", cpsize);
+		nilfs_err(sb, "too large checkpoint size: %zu bytes", cpsize);
 		return -EINVAL;
 	} else if (cpsize < NILFS_MIN_CHECKPOINT_SIZE) {
-		nilfs_msg(sb, KERN_ERR,
-			  "too small checkpoint size: %zu bytes", cpsize);
+		nilfs_err(sb, "too small checkpoint size: %zu bytes", cpsize);
 		return -EINVAL;
 	}
 
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 6f4066636be9..8bccdf1158fc 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -340,11 +340,11 @@ int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr)
 	kaddr = kmap_atomic(entry_bh->b_page);
 	entry = nilfs_palloc_block_get_entry(dat, vblocknr, entry_bh, kaddr);
 	if (unlikely(entry->de_blocknr == cpu_to_le64(0))) {
-		nilfs_msg(dat->i_sb, KERN_CRIT,
-			  "%s: invalid vblocknr = %llu, [%llu, %llu)",
-			  __func__, (unsigned long long)vblocknr,
-			  (unsigned long long)le64_to_cpu(entry->de_start),
-			  (unsigned long long)le64_to_cpu(entry->de_end));
+		nilfs_crit(dat->i_sb,
+			   "%s: invalid vblocknr = %llu, [%llu, %llu)",
+			   __func__, (unsigned long long)vblocknr,
+			   (unsigned long long)le64_to_cpu(entry->de_start),
+			   (unsigned long long)le64_to_cpu(entry->de_end));
 		kunmap_atomic(kaddr);
 		brelse(entry_bh);
 		return -EINVAL;
@@ -471,11 +471,11 @@ int nilfs_dat_read(struct super_block *sb, size_t entry_size,
 	int err;
 
 	if (entry_size > sb->s_blocksize) {
-		nilfs_msg(sb, KERN_ERR, "too large DAT entry size: %zu bytes",
+		nilfs_err(sb, "too large DAT entry size: %zu bytes",
 			  entry_size);
 		return -EINVAL;
 	} else if (entry_size < NILFS_MIN_DAT_ENTRY_SIZE) {
-		nilfs_msg(sb, KERN_ERR, "too small DAT entry size: %zu bytes",
+		nilfs_err(sb, "too small DAT entry size: %zu bytes",
 			  entry_size);
 		return -EINVAL;
 	}
diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c
index 533e24ea3a88..f353101955e3 100644
--- a/fs/nilfs2/direct.c
+++ b/fs/nilfs2/direct.c
@@ -328,16 +328,18 @@ static int nilfs_direct_assign(struct nilfs_bmap *bmap,
 
 	key = nilfs_bmap_data_get_key(bmap, *bh);
 	if (unlikely(key > NILFS_DIRECT_KEY_MAX)) {
-		nilfs_msg(bmap->b_inode->i_sb, KERN_CRIT,
-			  "%s (ino=%lu): invalid key: %llu", __func__,
-			  bmap->b_inode->i_ino, (unsigned long long)key);
+		nilfs_crit(bmap->b_inode->i_sb,
+			   "%s (ino=%lu): invalid key: %llu",
+			   __func__,
+			   bmap->b_inode->i_ino, (unsigned long long)key);
 		return -EINVAL;
 	}
 	ptr = nilfs_direct_get_ptr(bmap, key);
 	if (unlikely(ptr == NILFS_BMAP_INVALID_PTR)) {
-		nilfs_msg(bmap->b_inode->i_sb, KERN_CRIT,
-			  "%s (ino=%lu): invalid pointer: %llu", __func__,
-			  bmap->b_inode->i_ino, (unsigned long long)ptr);
+		nilfs_crit(bmap->b_inode->i_sb,
+			   "%s (ino=%lu): invalid pointer: %llu",
+			   __func__,
+			   bmap->b_inode->i_ino, (unsigned long long)ptr);
 		return -EINVAL;
 	}
 
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index aa3c328ee189..448320496856 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -142,7 +142,7 @@ int nilfs_gccache_wait_and_mark_dirty(struct buffer_head *bh)
 	if (!buffer_uptodate(bh)) {
 		struct inode *inode = bh->b_page->mapping->host;
 
-		nilfs_msg(inode->i_sb, KERN_ERR,
+		nilfs_err(inode->i_sb,
 			  "I/O error reading %s block for GC (ino=%lu, vblocknr=%llu)",
 			  buffer_nilfs_node(bh) ? "node" : "data",
 			  inode->i_ino, (unsigned long long)bh->b_blocknr);
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 4140d232cadc..02727ed3a7c6 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -142,8 +142,8 @@ int nilfs_ifile_get_inode_block(struct inode *ifile, ino_t ino,
 
 	err = nilfs_palloc_get_entry_block(ifile, ino, 0, out_bh);
 	if (unlikely(err))
-		nilfs_msg(sb, KERN_WARNING, "error %d reading inode: ino=%lu",
-			  err, (unsigned long)ino);
+		nilfs_warn(sb, "error %d reading inode: ino=%lu",
+			   err, (unsigned long)ino);
 	return err;
 }
 
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 3318dd1350b2..745d371d6fea 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -104,10 +104,10 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff,
 				 * However, the page having this block must
 				 * be locked in this case.
 				 */
-				nilfs_msg(inode->i_sb, KERN_WARNING,
-					  "%s (ino=%lu): a race condition while inserting a data block at offset=%llu",
-					  __func__, inode->i_ino,
-					  (unsigned long long)blkoff);
+				nilfs_warn(inode->i_sb,
+					   "%s (ino=%lu): a race condition while inserting a data block at offset=%llu",
+					   __func__, inode->i_ino,
+					   (unsigned long long)blkoff);
 				err = 0;
 			}
 			nilfs_transaction_abort(inode->i_sb);
@@ -707,9 +707,8 @@ static void nilfs_truncate_bmap(struct nilfs_inode_info *ii,
 		goto repeat;
 
 failed:
-	nilfs_msg(ii->vfs_inode.i_sb, KERN_WARNING,
-		  "error %d truncating bmap (ino=%lu)", ret,
-		  ii->vfs_inode.i_ino);
+	nilfs_warn(ii->vfs_inode.i_sb, "error %d truncating bmap (ino=%lu)",
+		   ret, ii->vfs_inode.i_ino);
 }
 
 void nilfs_truncate(struct inode *inode)
@@ -920,9 +919,9 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty)
 			 * This will happen when somebody is freeing
 			 * this inode.
 			 */
-			nilfs_msg(inode->i_sb, KERN_WARNING,
-				  "cannot set file dirty (ino=%lu): the file is being freed",
-				  inode->i_ino);
+			nilfs_warn(inode->i_sb,
+				   "cannot set file dirty (ino=%lu): the file is being freed",
+				   inode->i_ino);
 			spin_unlock(&nilfs->ns_inode_lock);
 			return -EINVAL; /*
 					 * NILFS_I_DIRTY may remain for
@@ -943,9 +942,9 @@ int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
 
 	err = nilfs_load_inode_block(inode, &ibh);
 	if (unlikely(err)) {
-		nilfs_msg(inode->i_sb, KERN_WARNING,
-			  "cannot mark inode dirty (ino=%lu): error %d loading inode block",
-			  inode->i_ino, err);
+		nilfs_warn(inode->i_sb,
+			   "cannot mark inode dirty (ino=%lu): error %d loading inode block",
+			   inode->i_ino, err);
 		return err;
 	}
 	nilfs_update_inode(inode, ibh, flags);
@@ -971,8 +970,8 @@ void nilfs_dirty_inode(struct inode *inode, int flags)
 	struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
 
 	if (is_bad_inode(inode)) {
-		nilfs_msg(inode->i_sb, KERN_WARNING,
-			  "tried to mark bad_inode dirty. ignored.");
+		nilfs_warn(inode->i_sb,
+			   "tried to mark bad_inode dirty. ignored.");
 		dump_stack();
 		return;
 	}
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 4ba73dbf3e8d..07d26f61f22a 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -569,25 +569,25 @@ static int nilfs_ioctl_move_inode_block(struct inode *inode,
 
 	if (unlikely(ret < 0)) {
 		if (ret == -ENOENT)
-			nilfs_msg(inode->i_sb, KERN_CRIT,
-				  "%s: invalid virtual block address (%s): ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu",
-				  __func__, vdesc->vd_flags ? "node" : "data",
-				  (unsigned long long)vdesc->vd_ino,
-				  (unsigned long long)vdesc->vd_cno,
-				  (unsigned long long)vdesc->vd_offset,
-				  (unsigned long long)vdesc->vd_blocknr,
-				  (unsigned long long)vdesc->vd_vblocknr);
+			nilfs_crit(inode->i_sb,
+				   "%s: invalid virtual block address (%s): ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu",
+				   __func__, vdesc->vd_flags ? "node" : "data",
+				   (unsigned long long)vdesc->vd_ino,
+				   (unsigned long long)vdesc->vd_cno,
+				   (unsigned long long)vdesc->vd_offset,
+				   (unsigned long long)vdesc->vd_blocknr,
+				   (unsigned long long)vdesc->vd_vblocknr);
 		return ret;
 	}
 	if (unlikely(!list_empty(&bh->b_assoc_buffers))) {
-		nilfs_msg(inode->i_sb, KERN_CRIT,
-			  "%s: conflicting %s buffer: ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu",
-			  __func__, vdesc->vd_flags ? "node" : "data",
-			  (unsigned long long)vdesc->vd_ino,
-			  (unsigned long long)vdesc->vd_cno,
-			  (unsigned long long)vdesc->vd_offset,
-			  (unsigned long long)vdesc->vd_blocknr,
-			  (unsigned long long)vdesc->vd_vblocknr);
+		nilfs_crit(inode->i_sb,
+			   "%s: conflicting %s buffer: ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu",
+			   __func__, vdesc->vd_flags ? "node" : "data",
+			   (unsigned long long)vdesc->vd_ino,
+			   (unsigned long long)vdesc->vd_cno,
+			   (unsigned long long)vdesc->vd_offset,
+			   (unsigned long long)vdesc->vd_blocknr,
+			   (unsigned long long)vdesc->vd_vblocknr);
 		brelse(bh);
 		return -EEXIST;
 	}
@@ -837,8 +837,7 @@ int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *nilfs,
 	return 0;
 
  failed:
-	nilfs_msg(nilfs->ns_sb, KERN_ERR, "error %d preparing GC: %s", ret,
-		  msg);
+	nilfs_err(nilfs->ns_sb, "error %d preparing GC: %s", ret, msg);
 	return ret;
 }
 
@@ -947,7 +946,7 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
 
 	ret = nilfs_ioctl_move_blocks(inode->i_sb, &argv[0], kbufs[0]);
 	if (ret < 0) {
-		nilfs_msg(inode->i_sb, KERN_ERR,
+		nilfs_err(inode->i_sb,
 			  "error %d preparing GC: cannot read source blocks",
 			  ret);
 	} else {
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 700870a92bc4..c0361ce45f62 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -199,7 +199,7 @@ static int nilfs_mdt_read_block(struct inode *inode, unsigned long block,
  out_no_wait:
 	err = -EIO;
 	if (!buffer_uptodate(first_bh)) {
-		nilfs_msg(inode->i_sb, KERN_ERR,
+		nilfs_err(inode->i_sb,
 			  "I/O error reading meta-data file (ino=%lu, block-offset=%lu)",
 			  inode->i_ino, block);
 		goto failed_bh;
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 9fe6d4ab74f0..a6ec7961d4f5 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -272,9 +272,9 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry)
 		goto out;
 
 	if (!inode->i_nlink) {
-		nilfs_msg(inode->i_sb, KERN_WARNING,
-			  "deleting nonexistent file (ino=%lu), %d",
-			  inode->i_ino, inode->i_nlink);
+		nilfs_warn(inode->i_sb,
+			   "deleting nonexistent file (ino=%lu), %d",
+			   inode->i_ino, inode->i_nlink);
 		set_nlink(inode, 1);
 	}
 	err = nilfs_delete_entry(de, page);
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 979a41016743..f8450ee3fd06 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -317,6 +317,15 @@ void __nilfs_error(struct super_block *sb, const char *function,
 
 #endif /* CONFIG_PRINTK */
 
+#define nilfs_crit(sb, fmt, ...)					\
+	nilfs_msg(sb, KERN_CRIT, fmt, ##__VA_ARGS__)
+#define nilfs_err(sb, fmt, ...)						\
+	nilfs_msg(sb, KERN_ERR, fmt, ##__VA_ARGS__)
+#define nilfs_warn(sb, fmt, ...)					\
+	nilfs_msg(sb, KERN_WARNING, fmt, ##__VA_ARGS__)
+#define nilfs_info(sb, fmt, ...)					\
+	nilfs_msg(sb, KERN_INFO, fmt, ##__VA_ARGS__)
+
 extern struct nilfs_super_block *
 nilfs_read_super_block(struct super_block *, u64, int, struct buffer_head **);
 extern int nilfs_store_magic_and_option(struct super_block *,
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index d7fc8d369d89..b175f1330408 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -391,9 +391,8 @@ void nilfs_clear_dirty_page(struct page *page, bool silent)
 	BUG_ON(!PageLocked(page));
 
 	if (!silent)
-		nilfs_msg(sb, KERN_WARNING,
-			  "discard dirty page: offset=%lld, ino=%lu",
-			  page_offset(page), inode->i_ino);
+		nilfs_warn(sb, "discard dirty page: offset=%lld, ino=%lu",
+			   page_offset(page), inode->i_ino);
 
 	ClearPageUptodate(page);
 	ClearPageMappedToDisk(page);
@@ -409,9 +408,9 @@ void nilfs_clear_dirty_page(struct page *page, bool silent)
 		do {
 			lock_buffer(bh);
 			if (!silent)
-				nilfs_msg(sb, KERN_WARNING,
-					  "discard dirty block: blocknr=%llu, size=%zu",
-					  (u64)bh->b_blocknr, bh->b_size);
+				nilfs_warn(sb,
+					   "discard dirty block: blocknr=%llu, size=%zu",
+					   (u64)bh->b_blocknr, bh->b_size);
 
 			set_mask_bits(&bh->b_state, clear_bits, 0);
 			unlock_buffer(bh);
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 140b663e91c7..0b453ef8fae5 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -51,7 +51,7 @@ static int nilfs_warn_segment_error(struct super_block *sb, int err)
 
 	switch (err) {
 	case NILFS_SEG_FAIL_IO:
-		nilfs_msg(sb, KERN_ERR, "I/O error reading segment");
+		nilfs_err(sb, "I/O error reading segment");
 		return -EIO;
 	case NILFS_SEG_FAIL_MAGIC:
 		msg = "Magic number mismatch";
@@ -72,10 +72,10 @@ static int nilfs_warn_segment_error(struct super_block *sb, int err)
 		msg = "No super root in the last segment";
 		break;
 	default:
-		nilfs_msg(sb, KERN_ERR, "unrecognized segment error %d", err);
+		nilfs_err(sb, "unrecognized segment error %d", err);
 		return -EINVAL;
 	}
-	nilfs_msg(sb, KERN_WARNING, "invalid segment: %s", msg);
+	nilfs_warn(sb, "invalid segment: %s", msg);
 	return -EINVAL;
 }
 
@@ -543,10 +543,10 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 		put_page(page);
 
  failed_inode:
-		nilfs_msg(sb, KERN_WARNING,
-			  "error %d recovering data block (ino=%lu, block-offset=%llu)",
-			  err, (unsigned long)rb->ino,
-			  (unsigned long long)rb->blkoff);
+		nilfs_warn(sb,
+			   "error %d recovering data block (ino=%lu, block-offset=%llu)",
+			   err, (unsigned long)rb->ino,
+			   (unsigned long long)rb->blkoff);
 		if (!err2)
 			err2 = err;
  next:
@@ -669,8 +669,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
 	}
 
 	if (nsalvaged_blocks) {
-		nilfs_msg(sb, KERN_INFO, "salvaged %lu blocks",
-			  nsalvaged_blocks);
+		nilfs_info(sb, "salvaged %lu blocks", nsalvaged_blocks);
 		ri->ri_need_recovery = NILFS_RECOVERY_ROLLFORWARD_DONE;
 	}
  out:
@@ -681,7 +680,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
  confused:
 	err = -EINVAL;
  failed:
-	nilfs_msg(sb, KERN_ERR,
+	nilfs_err(sb,
 		  "error %d roll-forwarding partial segment at blocknr = %llu",
 		  err, (unsigned long long)pseg_start);
 	goto out;
@@ -703,8 +702,8 @@ static void nilfs_finish_roll_forward(struct the_nilfs *nilfs,
 	set_buffer_dirty(bh);
 	err = sync_dirty_buffer(bh);
 	if (unlikely(err))
-		nilfs_msg(nilfs->ns_sb, KERN_WARNING,
-			  "buffer sync write failed during post-cleaning of recovery.");
+		nilfs_warn(nilfs->ns_sb,
+			   "buffer sync write failed during post-cleaning of recovery.");
 	brelse(bh);
 }
 
@@ -739,8 +738,7 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs,
 
 	err = nilfs_attach_checkpoint(sb, ri->ri_cno, true, &root);
 	if (unlikely(err)) {
-		nilfs_msg(sb, KERN_ERR,
-			  "error %d loading the latest checkpoint", err);
+		nilfs_err(sb, "error %d loading the latest checkpoint", err);
 		return err;
 	}
 
@@ -751,8 +749,7 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs,
 	if (ri->ri_need_recovery == NILFS_RECOVERY_ROLLFORWARD_DONE) {
 		err = nilfs_prepare_segment_for_recovery(nilfs, sb, ri);
 		if (unlikely(err)) {
-			nilfs_msg(sb, KERN_ERR,
-				  "error %d preparing segment for recovery",
+			nilfs_err(sb, "error %d preparing segment for recovery",
 				  err);
 			goto failed;
 		}
@@ -766,8 +763,7 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs,
 		nilfs_detach_log_writer(sb);
 
 		if (unlikely(err)) {
-			nilfs_msg(sb, KERN_ERR,
-				  "error %d writing segment for recovery",
+			nilfs_err(sb, "error %d writing segment for recovery",
 				  err);
 			goto failed;
 		}
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 20c479b5e41b..1a8729eded8b 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -505,7 +505,7 @@ static int nilfs_segbuf_wait(struct nilfs_segment_buffer *segbuf)
 	} while (--segbuf->sb_nbio > 0);
 
 	if (unlikely(atomic_read(&segbuf->sb_err) > 0)) {
-		nilfs_msg(segbuf->sb_super, KERN_ERR,
+		nilfs_err(segbuf->sb_super,
 			  "I/O error writing log (start-blocknr=%llu, block-count=%lu) in segment %llu",
 			  (unsigned long long)segbuf->sb_pseg_start,
 			  segbuf->sb_sum.nblocks,
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 91b58c897f92..a651e821c2de 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -158,7 +158,7 @@ static int nilfs_prepare_segment_lock(struct super_block *sb,
 		 * it is saved and will be restored on
 		 * nilfs_transaction_commit().
 		 */
-		nilfs_msg(sb, KERN_WARNING, "journal info from a different FS");
+		nilfs_warn(sb, "journal info from a different FS");
 		save = current->journal_info;
 	}
 	if (!ti) {
@@ -1940,9 +1940,9 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci,
 			err = nilfs_ifile_get_inode_block(
 				ifile, ii->vfs_inode.i_ino, &ibh);
 			if (unlikely(err)) {
-				nilfs_msg(sci->sc_super, KERN_WARNING,
-					  "log writer: error %d getting inode block (ino=%lu)",
-					  err, ii->vfs_inode.i_ino);
+				nilfs_warn(sci->sc_super,
+					   "log writer: error %d getting inode block (ino=%lu)",
+					   err, ii->vfs_inode.i_ino);
 				return err;
 			}
 			spin_lock(&nilfs->ns_inode_lock);
@@ -2449,7 +2449,7 @@ int nilfs_clean_segments(struct super_block *sb, struct nilfs_argv *argv,
 		if (likely(!err))
 			break;
 
-		nilfs_msg(sb, KERN_WARNING, "error %d cleaning segments", err);
+		nilfs_warn(sb, "error %d cleaning segments", err);
 		set_current_state(TASK_INTERRUPTIBLE);
 		schedule_timeout(sci->sc_interval);
 	}
@@ -2457,9 +2457,9 @@ int nilfs_clean_segments(struct super_block *sb, struct nilfs_argv *argv,
 		int ret = nilfs_discard_segments(nilfs, sci->sc_freesegs,
 						 sci->sc_nfreesegs);
 		if (ret) {
-			nilfs_msg(sb, KERN_WARNING,
-				  "error %d on discard request, turning discards off for the device",
-				  ret);
+			nilfs_warn(sb,
+				   "error %d on discard request, turning discards off for the device",
+				   ret);
 			nilfs_clear_opt(nilfs, DISCARD);
 		}
 	}
@@ -2540,9 +2540,9 @@ static int nilfs_segctor_thread(void *arg)
 	/* start sync. */
 	sci->sc_task = current;
 	wake_up(&sci->sc_wait_task); /* for nilfs_segctor_start_thread() */
-	nilfs_msg(sci->sc_super, KERN_INFO,
-		  "segctord starting. Construction interval = %lu seconds, CP frequency < %lu seconds",
-		  sci->sc_interval / HZ, sci->sc_mjcp_freq / HZ);
+	nilfs_info(sci->sc_super,
+		   "segctord starting. Construction interval = %lu seconds, CP frequency < %lu seconds",
+		   sci->sc_interval / HZ, sci->sc_mjcp_freq / HZ);
 
 	spin_lock(&sci->sc_state_lock);
  loop:
@@ -2616,8 +2616,8 @@ static int nilfs_segctor_start_thread(struct nilfs_sc_info *sci)
 	if (IS_ERR(t)) {
 		int err = PTR_ERR(t);
 
-		nilfs_msg(sci->sc_super, KERN_ERR,
-			  "error %d creating segctord thread", err);
+		nilfs_err(sci->sc_super, "error %d creating segctord thread",
+			  err);
 		return err;
 	}
 	wait_event(sci->sc_wait_task, sci->sc_task != NULL);
@@ -2727,14 +2727,14 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
 		nilfs_segctor_write_out(sci);
 
 	if (!list_empty(&sci->sc_dirty_files)) {
-		nilfs_msg(sci->sc_super, KERN_WARNING,
-			  "disposed unprocessed dirty file(s) when stopping log writer");
+		nilfs_warn(sci->sc_super,
+			   "disposed unprocessed dirty file(s) when stopping log writer");
 		nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1);
 	}
 
 	if (!list_empty(&sci->sc_iput_queue)) {
-		nilfs_msg(sci->sc_super, KERN_WARNING,
-			  "disposed unprocessed inode(s) in iput queue when stopping log writer");
+		nilfs_warn(sci->sc_super,
+			   "disposed unprocessed inode(s) in iput queue when stopping log writer");
 		nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1);
 	}
 
@@ -2812,8 +2812,8 @@ void nilfs_detach_log_writer(struct super_block *sb)
 	spin_lock(&nilfs->ns_inode_lock);
 	if (!list_empty(&nilfs->ns_dirty_files)) {
 		list_splice_init(&nilfs->ns_dirty_files, &garbage_list);
-		nilfs_msg(sb, KERN_WARNING,
-			  "disposed unprocessed dirty file(s) when detaching log writer");
+		nilfs_warn(sb,
+			   "disposed unprocessed dirty file(s) when detaching log writer");
 	}
 	spin_unlock(&nilfs->ns_inode_lock);
 	up_write(&nilfs->ns_segctor_sem);
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index bf3f8f05c89b..42ff67c0c14f 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -171,9 +171,9 @@ int nilfs_sufile_updatev(struct inode *sufile, __u64 *segnumv, size_t nsegs,
 	down_write(&NILFS_MDT(sufile)->mi_sem);
 	for (seg = segnumv; seg < segnumv + nsegs; seg++) {
 		if (unlikely(*seg >= nilfs_sufile_get_nsegments(sufile))) {
-			nilfs_msg(sufile->i_sb, KERN_WARNING,
-				  "%s: invalid segment number: %llu",
-				  __func__, (unsigned long long)*seg);
+			nilfs_warn(sufile->i_sb,
+				   "%s: invalid segment number: %llu",
+				   __func__, (unsigned long long)*seg);
 			nerr++;
 		}
 	}
@@ -230,9 +230,8 @@ int nilfs_sufile_update(struct inode *sufile, __u64 segnum, int create,
 	int ret;
 
 	if (unlikely(segnum >= nilfs_sufile_get_nsegments(sufile))) {
-		nilfs_msg(sufile->i_sb, KERN_WARNING,
-			  "%s: invalid segment number: %llu",
-			  __func__, (unsigned long long)segnum);
+		nilfs_warn(sufile->i_sb, "%s: invalid segment number: %llu",
+			   __func__, (unsigned long long)segnum);
 		return -EINVAL;
 	}
 	down_write(&NILFS_MDT(sufile)->mi_sem);
@@ -410,9 +409,8 @@ void nilfs_sufile_do_cancel_free(struct inode *sufile, __u64 segnum,
 	kaddr = kmap_atomic(su_bh->b_page);
 	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
 	if (unlikely(!nilfs_segment_usage_clean(su))) {
-		nilfs_msg(sufile->i_sb, KERN_WARNING,
-			  "%s: segment %llu must be clean", __func__,
-			  (unsigned long long)segnum);
+		nilfs_warn(sufile->i_sb, "%s: segment %llu must be clean",
+			   __func__, (unsigned long long)segnum);
 		kunmap_atomic(kaddr);
 		return;
 	}
@@ -468,9 +466,8 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
 	kaddr = kmap_atomic(su_bh->b_page);
 	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
 	if (nilfs_segment_usage_clean(su)) {
-		nilfs_msg(sufile->i_sb, KERN_WARNING,
-			  "%s: segment %llu is already clean",
-			  __func__, (unsigned long long)segnum);
+		nilfs_warn(sufile->i_sb, "%s: segment %llu is already clean",
+			   __func__, (unsigned long long)segnum);
 		kunmap_atomic(kaddr);
 		return;
 	}
@@ -1168,12 +1165,12 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize,
 	int err;
 
 	if (susize > sb->s_blocksize) {
-		nilfs_msg(sb, KERN_ERR,
-			  "too large segment usage size: %zu bytes", susize);
+		nilfs_err(sb, "too large segment usage size: %zu bytes",
+			  susize);
 		return -EINVAL;
 	} else if (susize < NILFS_MIN_SEGMENT_USAGE_SIZE) {
-		nilfs_msg(sb, KERN_ERR,
-			  "too small segment usage size: %zu bytes", susize);
+		nilfs_err(sb, "too small segment usage size: %zu bytes",
+			  susize);
 		return -EINVAL;
 	}
 
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index fef4821a1f0f..2eee5fb1a882 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -112,7 +112,7 @@ static void nilfs_set_error(struct super_block *sb)
  *
  * This implements the body of nilfs_error() macro.  Normally,
  * nilfs_error() should be used.  As for sustainable errors such as a
- * single-shot I/O error, nilfs_msg() should be used instead.
+ * single-shot I/O error, nilfs_err() should be used instead.
  *
  * Callers should not add a trailing newline since this will do it.
  */
@@ -184,8 +184,7 @@ static int nilfs_sync_super(struct super_block *sb, int flag)
 	}
 
 	if (unlikely(err)) {
-		nilfs_msg(sb, KERN_ERR, "unable to write superblock: err=%d",
-			  err);
+		nilfs_err(sb, "unable to write superblock: err=%d", err);
 		if (err == -EIO && nilfs->ns_sbh[1]) {
 			/*
 			 * sbp[0] points to newer log than sbp[1],
@@ -255,7 +254,7 @@ struct nilfs_super_block **nilfs_prepare_super(struct super_block *sb,
 		    sbp[1]->s_magic == cpu_to_le16(NILFS_SUPER_MAGIC)) {
 			memcpy(sbp[0], sbp[1], nilfs->ns_sbsize);
 		} else {
-			nilfs_msg(sb, KERN_CRIT, "superblock broke");
+			nilfs_crit(sb, "superblock broke");
 			return NULL;
 		}
 	} else if (sbp[1] &&
@@ -365,9 +364,9 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off)
 	offset = sb2off & (nilfs->ns_blocksize - 1);
 	nsbh = sb_getblk(sb, newblocknr);
 	if (!nsbh) {
-		nilfs_msg(sb, KERN_WARNING,
-			  "unable to move secondary superblock to block %llu",
-			  (unsigned long long)newblocknr);
+		nilfs_warn(sb,
+			   "unable to move secondary superblock to block %llu",
+			   (unsigned long long)newblocknr);
 		ret = -EIO;
 		goto out;
 	}
@@ -530,7 +529,7 @@ int nilfs_attach_checkpoint(struct super_block *sb, __u64 cno, int curr_mnt,
 	up_read(&nilfs->ns_segctor_sem);
 	if (unlikely(err)) {
 		if (err == -ENOENT || err == -EINVAL) {
-			nilfs_msg(sb, KERN_ERR,
+			nilfs_err(sb,
 				  "Invalid checkpoint (checkpoint number=%llu)",
 				  (unsigned long long)cno);
 			err = -EINVAL;
@@ -628,8 +627,7 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	err = nilfs_ifile_count_free_inodes(root->ifile,
 					    &nmaxinodes, &nfreeinodes);
 	if (unlikely(err)) {
-		nilfs_msg(sb, KERN_WARNING,
-			  "failed to count free inodes: err=%d", err);
+		nilfs_warn(sb, "failed to count free inodes: err=%d", err);
 		if (err == -ERANGE) {
 			/*
 			 * If nilfs_palloc_count_max_entries() returns
@@ -761,7 +759,7 @@ static int parse_options(char *options, struct super_block *sb, int is_remount)
 			break;
 		case Opt_snapshot:
 			if (is_remount) {
-				nilfs_msg(sb, KERN_ERR,
+				nilfs_err(sb,
 					  "\"%s\" option is invalid for remount",
 					  p);
 				return 0;
@@ -777,8 +775,7 @@ static int parse_options(char *options, struct super_block *sb, int is_remount)
 			nilfs_clear_opt(nilfs, DISCARD);
 			break;
 		default:
-			nilfs_msg(sb, KERN_ERR,
-				  "unrecognized mount option \"%s\"", p);
+			nilfs_err(sb, "unrecognized mount option \"%s\"", p);
 			return 0;
 		}
 	}
@@ -814,10 +811,10 @@ static int nilfs_setup_super(struct super_block *sb, int is_mount)
 	mnt_count = le16_to_cpu(sbp[0]->s_mnt_count);
 
 	if (nilfs->ns_mount_state & NILFS_ERROR_FS) {
-		nilfs_msg(sb, KERN_WARNING, "mounting fs with errors");
+		nilfs_warn(sb, "mounting fs with errors");
 #if 0
 	} else if (max_mnt_count >= 0 && mnt_count >= max_mnt_count) {
-		nilfs_msg(sb, KERN_WARNING, "maximal mount count reached");
+		nilfs_warn(sb, "maximal mount count reached");
 #endif
 	}
 	if (!max_mnt_count)
@@ -880,7 +877,7 @@ int nilfs_check_feature_compatibility(struct super_block *sb,
 	features = le64_to_cpu(sbp->s_feature_incompat) &
 		~NILFS_FEATURE_INCOMPAT_SUPP;
 	if (features) {
-		nilfs_msg(sb, KERN_ERR,
+		nilfs_err(sb,
 			  "couldn't mount because of unsupported optional features (%llx)",
 			  (unsigned long long)features);
 		return -EINVAL;
@@ -888,7 +885,7 @@ int nilfs_check_feature_compatibility(struct super_block *sb,
 	features = le64_to_cpu(sbp->s_feature_compat_ro) &
 		~NILFS_FEATURE_COMPAT_RO_SUPP;
 	if (!sb_rdonly(sb) && features) {
-		nilfs_msg(sb, KERN_ERR,
+		nilfs_err(sb,
 			  "couldn't mount RDWR because of unsupported optional features (%llx)",
 			  (unsigned long long)features);
 		return -EINVAL;
@@ -907,12 +904,12 @@ static int nilfs_get_root_dentry(struct super_block *sb,
 	inode = nilfs_iget(sb, root, NILFS_ROOT_INO);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
-		nilfs_msg(sb, KERN_ERR, "error %d getting root inode", ret);
+		nilfs_err(sb, "error %d getting root inode", ret);
 		goto out;
 	}
 	if (!S_ISDIR(inode->i_mode) || !inode->i_blocks || !inode->i_size) {
 		iput(inode);
-		nilfs_msg(sb, KERN_ERR, "corrupt root inode");
+		nilfs_err(sb, "corrupt root inode");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -940,7 +937,7 @@ static int nilfs_get_root_dentry(struct super_block *sb,
 	return ret;
 
  failed_dentry:
-	nilfs_msg(sb, KERN_ERR, "error %d getting root dentry", ret);
+	nilfs_err(sb, "error %d getting root dentry", ret);
 	goto out;
 }
 
@@ -960,7 +957,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
 		ret = (ret == -ENOENT) ? -EINVAL : ret;
 		goto out;
 	} else if (!ret) {
-		nilfs_msg(s, KERN_ERR,
+		nilfs_err(s,
 			  "The specified checkpoint is not a snapshot (checkpoint number=%llu)",
 			  (unsigned long long)cno);
 		ret = -EINVAL;
@@ -969,7 +966,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
 
 	ret = nilfs_attach_checkpoint(s, cno, false, &root);
 	if (ret) {
-		nilfs_msg(s, KERN_ERR,
+		nilfs_err(s,
 			  "error %d while loading snapshot (checkpoint number=%llu)",
 			  ret, (unsigned long long)cno);
 		goto out;
@@ -1066,7 +1063,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 	cno = nilfs_last_cno(nilfs);
 	err = nilfs_attach_checkpoint(sb, cno, true, &fsroot);
 	if (err) {
-		nilfs_msg(sb, KERN_ERR,
+		nilfs_err(sb,
 			  "error %d while loading last checkpoint (checkpoint number=%llu)",
 			  err, (unsigned long long)cno);
 		goto failed_unload;
@@ -1128,8 +1125,8 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 	err = -EINVAL;
 
 	if (!nilfs_valid_fs(nilfs)) {
-		nilfs_msg(sb, KERN_WARNING,
-			  "couldn't remount because the filesystem is in an incomplete recovery state");
+		nilfs_warn(sb,
+			   "couldn't remount because the filesystem is in an incomplete recovery state");
 		goto restore_opts;
 	}
 
@@ -1161,9 +1158,9 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 			~NILFS_FEATURE_COMPAT_RO_SUPP;
 		up_read(&nilfs->ns_sem);
 		if (features) {
-			nilfs_msg(sb, KERN_WARNING,
-				  "couldn't remount RDWR because of unsupported optional features (%llx)",
-				  (unsigned long long)features);
+			nilfs_warn(sb,
+				   "couldn't remount RDWR because of unsupported optional features (%llx)",
+				   (unsigned long long)features);
 			err = -EROFS;
 			goto restore_opts;
 		}
@@ -1222,7 +1219,7 @@ static int nilfs_parse_snapshot_option(const char *option,
 	return 0;
 
 parse_error:
-	nilfs_msg(NULL, KERN_ERR, "invalid option \"%s\": %s", option, msg);
+	nilfs_err(NULL, "invalid option \"%s\": %s", option, msg);
 	return 1;
 }
 
@@ -1325,7 +1322,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 	} else if (!sd.cno) {
 		if (nilfs_tree_is_busy(s->s_root)) {
 			if ((flags ^ s->s_flags) & SB_RDONLY) {
-				nilfs_msg(s, KERN_ERR,
+				nilfs_err(s,
 					  "the device already has a %s mount.",
 					  sb_rdonly(s) ? "read-only" : "read/write");
 				err = -EBUSY;
diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c
index e60be7bb55b0..303d71430bdd 100644
--- a/fs/nilfs2/sysfs.c
+++ b/fs/nilfs2/sysfs.c
@@ -263,8 +263,8 @@ nilfs_checkpoints_checkpoints_number_show(struct nilfs_checkpoints_attr *attr,
 	err = nilfs_cpfile_get_stat(nilfs->ns_cpfile, &cpstat);
 	up_read(&nilfs->ns_segctor_sem);
 	if (err < 0) {
-		nilfs_msg(nilfs->ns_sb, KERN_ERR,
-			  "unable to get checkpoint stat: err=%d", err);
+		nilfs_err(nilfs->ns_sb, "unable to get checkpoint stat: err=%d",
+			  err);
 		return err;
 	}
 
@@ -286,8 +286,8 @@ nilfs_checkpoints_snapshots_number_show(struct nilfs_checkpoints_attr *attr,
 	err = nilfs_cpfile_get_stat(nilfs->ns_cpfile, &cpstat);
 	up_read(&nilfs->ns_segctor_sem);
 	if (err < 0) {
-		nilfs_msg(nilfs->ns_sb, KERN_ERR,
-			  "unable to get checkpoint stat: err=%d", err);
+		nilfs_err(nilfs->ns_sb, "unable to get checkpoint stat: err=%d",
+			  err);
 		return err;
 	}
 
@@ -405,8 +405,8 @@ nilfs_segments_dirty_segments_show(struct nilfs_segments_attr *attr,
 	err = nilfs_sufile_get_stat(nilfs->ns_sufile, &sustat);
 	up_read(&nilfs->ns_segctor_sem);
 	if (err < 0) {
-		nilfs_msg(nilfs->ns_sb, KERN_ERR,
-			  "unable to get segment stat: err=%d", err);
+		nilfs_err(nilfs->ns_sb, "unable to get segment stat: err=%d",
+			  err);
 		return err;
 	}
 
@@ -779,15 +779,15 @@ nilfs_superblock_sb_update_frequency_store(struct nilfs_superblock_attr *attr,
 
 	err = kstrtouint(skip_spaces(buf), 0, &val);
 	if (err) {
-		nilfs_msg(nilfs->ns_sb, KERN_ERR,
-			  "unable to convert string: err=%d", err);
+		nilfs_err(nilfs->ns_sb, "unable to convert string: err=%d",
+			  err);
 		return err;
 	}
 
 	if (val < NILFS_SB_FREQ) {
 		val = NILFS_SB_FREQ;
-		nilfs_msg(nilfs->ns_sb, KERN_WARNING,
-			  "superblock update frequency cannot be lesser than 10 seconds");
+		nilfs_warn(nilfs->ns_sb,
+			   "superblock update frequency cannot be lesser than 10 seconds");
 	}
 
 	down_write(&nilfs->ns_sem);
@@ -990,8 +990,7 @@ int nilfs_sysfs_create_device_group(struct super_block *sb)
 	nilfs->ns_dev_subgroups = kzalloc(devgrp_size, GFP_KERNEL);
 	if (unlikely(!nilfs->ns_dev_subgroups)) {
 		err = -ENOMEM;
-		nilfs_msg(sb, KERN_ERR,
-			  "unable to allocate memory for device group");
+		nilfs_err(sb, "unable to allocate memory for device group");
 		goto failed_create_device_group;
 	}
 
@@ -1101,15 +1100,13 @@ int __init nilfs_sysfs_init(void)
 	nilfs_kset = kset_create_and_add(NILFS_ROOT_GROUP_NAME, NULL, fs_kobj);
 	if (!nilfs_kset) {
 		err = -ENOMEM;
-		nilfs_msg(NULL, KERN_ERR,
-			  "unable to create sysfs entry: err=%d", err);
+		nilfs_err(NULL, "unable to create sysfs entry: err=%d", err);
 		goto failed_sysfs_init;
 	}
 
 	err = sysfs_create_group(&nilfs_kset->kobj, &nilfs_feature_attr_group);
 	if (unlikely(err)) {
-		nilfs_msg(NULL, KERN_ERR,
-			  "unable to create feature group: err=%d", err);
+		nilfs_err(NULL, "unable to create feature group: err=%d", err);
 		goto cleanup_sysfs_init;
 	}
 
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 484785cdf96e..221a1cc597f0 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -183,7 +183,7 @@ static int nilfs_store_log_cursor(struct the_nilfs *nilfs,
 		nilfs_get_segnum_of_block(nilfs, nilfs->ns_last_pseg);
 	nilfs->ns_cno = nilfs->ns_last_cno + 1;
 	if (nilfs->ns_segnum >= nilfs->ns_nsegments) {
-		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+		nilfs_err(nilfs->ns_sb,
 			  "pointed segment number is out of range: segnum=%llu, nsegments=%lu",
 			  (unsigned long long)nilfs->ns_segnum,
 			  nilfs->ns_nsegments);
@@ -210,12 +210,12 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	int err;
 
 	if (!valid_fs) {
-		nilfs_msg(sb, KERN_WARNING, "mounting unchecked fs");
+		nilfs_warn(sb, "mounting unchecked fs");
 		if (s_flags & SB_RDONLY) {
-			nilfs_msg(sb, KERN_INFO,
-				  "recovery required for readonly filesystem");
-			nilfs_msg(sb, KERN_INFO,
-				  "write access will be enabled during recovery");
+			nilfs_info(sb,
+				   "recovery required for readonly filesystem");
+			nilfs_info(sb,
+				   "write access will be enabled during recovery");
 		}
 	}
 
@@ -230,12 +230,11 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 			goto scan_error;
 
 		if (!nilfs_valid_sb(sbp[1])) {
-			nilfs_msg(sb, KERN_WARNING,
-				  "unable to fall back to spare super block");
+			nilfs_warn(sb,
+				   "unable to fall back to spare super block");
 			goto scan_error;
 		}
-		nilfs_msg(sb, KERN_INFO,
-			  "trying rollback from an earlier position");
+		nilfs_info(sb, "trying rollback from an earlier position");
 
 		/*
 		 * restore super block with its spare and reconfigure
@@ -248,9 +247,9 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 		/* verify consistency between two super blocks */
 		blocksize = BLOCK_SIZE << le32_to_cpu(sbp[0]->s_log_block_size);
 		if (blocksize != nilfs->ns_blocksize) {
-			nilfs_msg(sb, KERN_WARNING,
-				  "blocksize differs between two super blocks (%d != %d)",
-				  blocksize, nilfs->ns_blocksize);
+			nilfs_warn(sb,
+				   "blocksize differs between two super blocks (%d != %d)",
+				   blocksize, nilfs->ns_blocksize);
 			goto scan_error;
 		}
 
@@ -269,8 +268,7 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 
 	err = nilfs_load_super_root(nilfs, sb, ri.ri_super_root);
 	if (unlikely(err)) {
-		nilfs_msg(sb, KERN_ERR, "error %d while loading super root",
-			  err);
+		nilfs_err(sb, "error %d while loading super root", err);
 		goto failed;
 	}
 
@@ -281,28 +279,28 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 		__u64 features;
 
 		if (nilfs_test_opt(nilfs, NORECOVERY)) {
-			nilfs_msg(sb, KERN_INFO,
-				  "norecovery option specified, skipping roll-forward recovery");
+			nilfs_info(sb,
+				   "norecovery option specified, skipping roll-forward recovery");
 			goto skip_recovery;
 		}
 		features = le64_to_cpu(nilfs->ns_sbp[0]->s_feature_compat_ro) &
 			~NILFS_FEATURE_COMPAT_RO_SUPP;
 		if (features) {
-			nilfs_msg(sb, KERN_ERR,
+			nilfs_err(sb,
 				  "couldn't proceed with recovery because of unsupported optional features (%llx)",
 				  (unsigned long long)features);
 			err = -EROFS;
 			goto failed_unload;
 		}
 		if (really_read_only) {
-			nilfs_msg(sb, KERN_ERR,
+			nilfs_err(sb,
 				  "write access unavailable, cannot proceed");
 			err = -EROFS;
 			goto failed_unload;
 		}
 		sb->s_flags &= ~SB_RDONLY;
 	} else if (nilfs_test_opt(nilfs, NORECOVERY)) {
-		nilfs_msg(sb, KERN_ERR,
+		nilfs_err(sb,
 			  "recovery cancelled because norecovery option was specified for a read/write mount");
 		err = -EINVAL;
 		goto failed_unload;
@@ -318,12 +316,12 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	up_write(&nilfs->ns_sem);
 
 	if (err) {
-		nilfs_msg(sb, KERN_ERR,
+		nilfs_err(sb,
 			  "error %d updating super block. recovery unfinished.",
 			  err);
 		goto failed_unload;
 	}
-	nilfs_msg(sb, KERN_INFO, "recovery complete");
+	nilfs_info(sb, "recovery complete");
 
  skip_recovery:
 	nilfs_clear_recovery_info(&ri);
@@ -331,7 +329,7 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	return 0;
 
  scan_error:
-	nilfs_msg(sb, KERN_ERR, "error %d while searching super root", err);
+	nilfs_err(sb, "error %d while searching super root", err);
 	goto failed;
 
  failed_unload:
@@ -378,7 +376,7 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 				   struct nilfs_super_block *sbp)
 {
 	if (le32_to_cpu(sbp->s_rev_level) < NILFS_MIN_SUPP_REV) {
-		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+		nilfs_err(nilfs->ns_sb,
 			  "unsupported revision (superblock rev.=%d.%d, current rev.=%d.%d). Please check the version of mkfs.nilfs(2).",
 			  le32_to_cpu(sbp->s_rev_level),
 			  le16_to_cpu(sbp->s_minor_rev_level),
@@ -391,13 +389,11 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 
 	nilfs->ns_inode_size = le16_to_cpu(sbp->s_inode_size);
 	if (nilfs->ns_inode_size > nilfs->ns_blocksize) {
-		nilfs_msg(nilfs->ns_sb, KERN_ERR,
-			  "too large inode size: %d bytes",
+		nilfs_err(nilfs->ns_sb, "too large inode size: %d bytes",
 			  nilfs->ns_inode_size);
 		return -EINVAL;
 	} else if (nilfs->ns_inode_size < NILFS_MIN_INODE_SIZE) {
-		nilfs_msg(nilfs->ns_sb, KERN_ERR,
-			  "too small inode size: %d bytes",
+		nilfs_err(nilfs->ns_sb, "too small inode size: %d bytes",
 			  nilfs->ns_inode_size);
 		return -EINVAL;
 	}
@@ -406,8 +402,7 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 
 	nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment);
 	if (nilfs->ns_blocks_per_segment < NILFS_SEG_MIN_BLOCKS) {
-		nilfs_msg(nilfs->ns_sb, KERN_ERR,
-			  "too short segment: %lu blocks",
+		nilfs_err(nilfs->ns_sb, "too short segment: %lu blocks",
 			  nilfs->ns_blocks_per_segment);
 		return -EINVAL;
 	}
@@ -417,7 +412,7 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 		le32_to_cpu(sbp->s_r_segments_percentage);
 	if (nilfs->ns_r_segments_percentage < 1 ||
 	    nilfs->ns_r_segments_percentage > 99) {
-		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+		nilfs_err(nilfs->ns_sb,
 			  "invalid reserved segments percentage: %lu",
 			  nilfs->ns_r_segments_percentage);
 		return -EINVAL;
@@ -503,16 +498,16 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
 
 	if (!sbp[0]) {
 		if (!sbp[1]) {
-			nilfs_msg(sb, KERN_ERR, "unable to read superblock");
+			nilfs_err(sb, "unable to read superblock");
 			return -EIO;
 		}
-		nilfs_msg(sb, KERN_WARNING,
-			  "unable to read primary superblock (blocksize = %d)",
-			  blocksize);
+		nilfs_warn(sb,
+			   "unable to read primary superblock (blocksize = %d)",
+			   blocksize);
 	} else if (!sbp[1]) {
-		nilfs_msg(sb, KERN_WARNING,
-			  "unable to read secondary superblock (blocksize = %d)",
-			  blocksize);
+		nilfs_warn(sb,
+			   "unable to read secondary superblock (blocksize = %d)",
+			   blocksize);
 	}
 
 	/*
@@ -534,14 +529,14 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
 	}
 	if (!valid[swp]) {
 		nilfs_release_super_block(nilfs);
-		nilfs_msg(sb, KERN_ERR, "couldn't find nilfs on the device");
+		nilfs_err(sb, "couldn't find nilfs on the device");
 		return -EINVAL;
 	}
 
 	if (!valid[!swp])
-		nilfs_msg(sb, KERN_WARNING,
-			  "broken superblock, retrying with spare superblock (blocksize = %d)",
-			  blocksize);
+		nilfs_warn(sb,
+			   "broken superblock, retrying with spare superblock (blocksize = %d)",
+			   blocksize);
 	if (swp)
 		nilfs_swap_super_block(nilfs);
 
@@ -575,7 +570,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
 
 	blocksize = sb_min_blocksize(sb, NILFS_MIN_BLOCK_SIZE);
 	if (!blocksize) {
-		nilfs_msg(sb, KERN_ERR, "unable to set blocksize");
+		nilfs_err(sb, "unable to set blocksize");
 		err = -EINVAL;
 		goto out;
 	}
@@ -594,7 +589,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbp->s_log_block_size);
 	if (blocksize < NILFS_MIN_BLOCK_SIZE ||
 	    blocksize > NILFS_MAX_BLOCK_SIZE) {
-		nilfs_msg(sb, KERN_ERR,
+		nilfs_err(sb,
 			  "couldn't mount because of unsupported filesystem blocksize %d",
 			  blocksize);
 		err = -EINVAL;
@@ -604,7 +599,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
 		int hw_blocksize = bdev_logical_block_size(sb->s_bdev);
 
 		if (blocksize < hw_blocksize) {
-			nilfs_msg(sb, KERN_ERR,
+			nilfs_err(sb,
 				  "blocksize %d too small for device (sector-size = %d)",
 				  blocksize, hw_blocksize);
 			err = -EINVAL;

From 88b2e9b06381551b707d980627ad0591191f7a2d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 11 Aug 2020 18:35:53 -0700
Subject: [PATCH 416/474] fs/ufs: avoid potential u32 multiplication overflow

The 64 bit ino is being compared to the product of two u32 values,
however, the multiplication is being performed using a 32 bit multiply so
there is a potential of an overflow.  To be fully safe, cast uspi->s_ncg
to a u64 to ensure a 64 bit multiplication occurs to avoid any chance of
overflow.

Fixes: f3e2a520f5fb ("ufs: NFS support")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Evgeniy Dushistov <dushistov@mail.ru>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Link: http://lkml.kernel.org/r/20200715170355.1081713-1-colin.king@canonical.com
Addresses-Coverity: ("Unintentional integer overflow")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ufs/super.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 1da0be667409..e3b69fb280e8 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -101,7 +101,7 @@ static struct inode *ufs_nfs_get_inode(struct super_block *sb, u64 ino, u32 gene
 	struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
 	struct inode *inode;
 
-	if (ino < UFS_ROOTINO || ino > uspi->s_ncg * uspi->s_ipg)
+	if (ino < UFS_ROOTINO || ino > (u64)uspi->s_ncg * uspi->s_ipg)
 		return ERR_PTR(-ESTALE);
 
 	inode = ufs_iget(sb, ino);

From e348e65a081d761caf72c2753c4e3d67bfb1ef80 Mon Sep 17 00:00:00 2001
From: Yubo Feng <fengyubo3@huawei.com>
Date: Tue, 11 Aug 2020 18:35:56 -0700
Subject: [PATCH 417/474] fatfs: switch write_lock to read_lock in
 fat_ioctl_get_attributes

There is no need to hold write_lock in fat_ioctl_get_attributes.
write_lock may make an impact on concurrency of fat_ioctl_get_attributes.

Signed-off-by: Yubo Feng <fengyubo3@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Link: http://lkml.kernel.org/r/1593308053-12702-1-git-send-email-fengyubo3@huawei.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fat/file.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/fat/file.c b/fs/fat/file.c
index 42134c58c87e..f9ee27cf4d7c 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -25,9 +25,9 @@ static int fat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr)
 {
 	u32 attr;
 
-	inode_lock(inode);
+	inode_lock_shared(inode);
 	attr = fat_make_attrs(inode);
-	inode_unlock(inode);
+	inode_unlock_shared(inode);
 
 	return put_user(attr, user_attr);
 }

From 4ecfed61de766f4655025a71d79c9a0f4793a3f4 Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Tue, 11 Aug 2020 18:35:59 -0700
Subject: [PATCH 418/474] VFAT/FAT/MSDOS FILESYSTEM: replace HTTP links with
 HTTPS ones

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `xmlns`:
        For each link, `http://[^# 	]*(?:\w|/)`:
	  If neither `gnu\.org/license`, nor `mozilla\.org/MPL`:
            If both the HTTP and HTTPS versions
            return 200 OK and serve the same content:
              Replace HTTP with HTTPS.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Link: http://lkml.kernel.org/r/20200708200409.22293-1-grandmaster@al2klimov.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fat/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig
index ca31993dcb47..66532a71e8fd 100644
--- a/fs/fat/Kconfig
+++ b/fs/fat/Kconfig
@@ -41,7 +41,7 @@ config MSDOS_FS
 	  they are compressed; to access compressed MSDOS partitions under
 	  Linux, you can either use the DOS emulator DOSEMU, described in the
 	  DOSEMU-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>, or try dmsdosfs in
+	  <https://www.tldp.org/docs.html#howto>, or try dmsdosfs in
 	  <ftp://ibiblio.org/pub/Linux/system/filesystems/dosfs/>. If you
 	  intend to use dosemu with a non-compressed MSDOS partition, say Y
 	  here) and MSDOS floppies. This means that file access becomes

From a090a5a7d73f79a9ae2dcc6e60d89bfc6864a65a Mon Sep 17 00:00:00 2001
From: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Date: Tue, 11 Aug 2020 18:36:01 -0700
Subject: [PATCH 419/474] fat: fix fat_ra_init() for data clusters == 0

If data clusters == 0, fat_ra_init() calls the ->ent_blocknr() for the
cluster beyond ->max_clusters.

This checks the limit before initialization to suppress the warning.

Reported-by: syzbot+756199124937b31a9b7e@syzkaller.appspotmail.com
Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/87mu462sv4.fsf@mail.parknet.co.jp
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fat/fatent.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c
index bbfe18c07417..f7e3304b7802 100644
--- a/fs/fat/fatent.c
+++ b/fs/fat/fatent.c
@@ -657,6 +657,9 @@ static void fat_ra_init(struct super_block *sb, struct fatent_ra *ra,
 	unsigned long ra_pages = sb->s_bdi->ra_pages;
 	unsigned int reada_blocks;
 
+	if (fatent->entry >= ent_limit)
+		return;
+
 	if (ra_pages > sb->s_bdi->io_pages)
 		ra_pages = rounddown(ra_pages, sb->s_bdi->io_pages);
 	reada_blocks = ra_pages << (PAGE_SHIFT - sb->s_blocksize_bits + 1);

From a089e3fd5a82aea20f3d9ec4caa5f4c65cc2cfcc Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Tue, 11 Aug 2020 18:36:04 -0700
Subject: [PATCH 420/474] fs/signalfd.c: fix inconsistent return codes for
 signalfd4

The kernel signalfd4() syscall returns different error codes when called
either in compat or native mode.  This behaviour makes correct emulation
in qemu and testing programs like LTP more complicated.

Fix the code to always return -in both modes- EFAULT for unaccessible user
memory, and EINVAL when called with an invalid signal mask.

Signed-off-by: Helge Deller <deller@gmx.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Laurent Vivier <laurent@vivier.eu>
Link: http://lkml.kernel.org/r/20200530100707.GA10159@ls3530.fritz.box
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/signalfd.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/signalfd.c b/fs/signalfd.c
index 44b6845b071c..5b78719be445 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -314,9 +314,10 @@ SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask,
 {
 	sigset_t mask;
 
-	if (sizemask != sizeof(sigset_t) ||
-	    copy_from_user(&mask, user_mask, sizeof(mask)))
+	if (sizemask != sizeof(sigset_t))
 		return -EINVAL;
+	if (copy_from_user(&mask, user_mask, sizeof(mask)))
+		return -EFAULT;
 	return do_signalfd4(ufd, &mask, flags);
 }
 
@@ -325,9 +326,10 @@ SYSCALL_DEFINE3(signalfd, int, ufd, sigset_t __user *, user_mask,
 {
 	sigset_t mask;
 
-	if (sizemask != sizeof(sigset_t) ||
-	    copy_from_user(&mask, user_mask, sizeof(mask)))
+	if (sizemask != sizeof(sigset_t))
 		return -EINVAL;
+	if (copy_from_user(&mask, user_mask, sizeof(mask)))
+		return -EFAULT;
 	return do_signalfd4(ufd, &mask, 0);
 }
 

From aaa3e7fb81d8a8598b993c8012f4b8aa18d92b20 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Tue, 11 Aug 2020 18:36:08 -0700
Subject: [PATCH 421/474] selftests: kmod: use variable NAME in
 kmod_test_0001()

Patch series "kmod/umh: a few fixes".

Tiezhu Yang had sent out a patch set with a slew of kmod selftest fixes,
and one patch which modified kmod to return 254 when a module was not
found.  This opened up pandora's box about why that was being used for and
low and behold its because when UMH_WAIT_PROC is used we call a
kernel_wait4() call but have never unwrapped the error code.  The commit
log for that fix details the rationale for the approach taken.  I'd
appreciate some review on that, in particular nfs folks as it seems a case
was never really hit before.

This patch (of 5):

Use the variable NAME instead of "\000" directly in kmod_test_0001().

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Lars Ellenberg <lars.ellenberg@linbit.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: J. Bruce Fields <bfields@fieldses.org>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Cc: James Morris <jmorris@namei.org>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Sergei Trofimovich <slyfox@gentoo.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Sergey Kvachonok <ravenexp@gmail.com>
Cc: Tony Vroon <chainsaw@gentoo.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Link: http://lkml.kernel.org/r/20200610154923.27510-1-mcgrof@kernel.org
Link: http://lkml.kernel.org/r/20200610154923.27510-2-mcgrof@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/kmod/kmod.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh
index ea2147248ebe..afd42387e8b2 100755
--- a/tools/testing/selftests/kmod/kmod.sh
+++ b/tools/testing/selftests/kmod/kmod.sh
@@ -343,7 +343,7 @@ kmod_test_0001_driver()
 
 	kmod_defaults_driver
 	config_num_threads 1
-	printf '\000' >"$DIR"/config_test_driver
+	printf $NAME >"$DIR"/config_test_driver
 	config_trigger ${FUNCNAME[0]}
 	config_expect_result ${FUNCNAME[0]} MODULE_NOT_FOUND
 }
@@ -354,7 +354,7 @@ kmod_test_0001_fs()
 
 	kmod_defaults_fs
 	config_num_threads 1
-	printf '\000' >"$DIR"/config_test_fs
+	printf $NAME >"$DIR"/config_test_fs
 	config_trigger ${FUNCNAME[0]}
 	config_expect_result ${FUNCNAME[0]} -EINVAL
 }

From 6f9e148c218641ad876845abdea4b0597468c55e Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Tue, 11 Aug 2020 18:36:12 -0700
Subject: [PATCH 422/474] kmod: remove redundant "be an" in the comment

There exists redundant "be an" in the comment, remove it.

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: David Howells <dhowells@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: James Morris <jmorris@namei.org>
Cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Cc: J. Bruce Fields <bfields@fieldses.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Lars Ellenberg <lars.ellenberg@linbit.com>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Sergei Trofimovich <slyfox@gentoo.org>
Cc: Sergey Kvachonok <ravenexp@gmail.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Tony Vroon <chainsaw@gentoo.org>
Cc: Christoph Hellwig <hch@infradead.org>
Link: http://lkml.kernel.org/r/20200610154923.27510-3-mcgrof@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/kmod.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/kernel/kmod.c b/kernel/kmod.c
index 37c3c4b97b8e..3cd075ce2a1e 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -36,9 +36,8 @@
  *
  * If you need less than 50 threads would mean we're dealing with systems
  * smaller than 3200 pages. This assumes you are capable of having ~13M memory,
- * and this would only be an be an upper limit, after which the OOM killer
- * would take effect. Systems like these are very unlikely if modules are
- * enabled.
+ * and this would only be an upper limit, after which the OOM killer would take
+ * effect. Systems like these are very unlikely if modules are enabled.
  */
 #define MAX_KMOD_CONCURRENT 50
 static atomic_t kmod_concurrent_max = ATOMIC_INIT(MAX_KMOD_CONCURRENT);

From 0776d1231bec0c7ab43baf440a3f5ef5f49dd795 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Tue, 11 Aug 2020 18:36:16 -0700
Subject: [PATCH 423/474] test_kmod: avoid potential double free in
 trigger_config_run_type()

Reset the member "test_fs" of the test configuration after a call of the
function "kfree_const" to a null pointer so that a double memory release
will not be performed.

Fixes: d9c6a72d6fa2 ("kmod: add test driver to stress test the module loader")
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: David Howells <dhowells@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: James Morris <jmorris@namei.org>
Cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Cc: J. Bruce Fields <bfields@fieldses.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Lars Ellenberg <lars.ellenberg@linbit.com>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Sergei Trofimovich <slyfox@gentoo.org>
Cc: Sergey Kvachonok <ravenexp@gmail.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Tony Vroon <chainsaw@gentoo.org>
Cc: Christoph Hellwig <hch@infradead.org>
Link: http://lkml.kernel.org/r/20200610154923.27510-4-mcgrof@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/test_kmod.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/test_kmod.c b/lib/test_kmod.c
index e651c37d56db..eab52770070d 100644
--- a/lib/test_kmod.c
+++ b/lib/test_kmod.c
@@ -745,7 +745,7 @@ static int trigger_config_run_type(struct kmod_test_device *test_dev,
 		break;
 	case TEST_KMOD_FS_TYPE:
 		kfree_const(config->test_fs);
-		config->test_driver = NULL;
+		config->test_fs = NULL;
 		copied = config_copy_test_fs(config, test_str,
 					     strlen(test_str));
 		break;

From f38c85f1ba6902e4e2e2bf1b84edf065a904cdeb Mon Sep 17 00:00:00 2001
From: Lepton Wu <ytht.net@gmail.com>
Date: Tue, 11 Aug 2020 18:36:20 -0700
Subject: [PATCH 424/474] coredump: add %f for executable filename

The document reads "%e" should be "executable filename" while actually it
could be changed by things like pr_ctl PR_SET_NAME.  People who uses "%e"
in core_pattern get surprised when they find out they get thread name
instead of executable filename.

This is either a bug of document or a bug of code.  Since the behavior of
"%e" is there for long time, it could bring another surprise for users if
we "fix" the code.

So we just "fix" the document.  And more, for users who really need the
"executable filename" in core_pattern, we introduce a new "%f" for the
real executable filename.  We already have "%E" for executable path in
kernel, so just reuse most of its code for the new added "%f" format.

Signed-off-by: Lepton Wu <ytht.net@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20200701031432.2978761-1-ytht.net@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/admin-guide/sysctl/kernel.rst |  3 ++-
 fs/coredump.c                               | 17 +++++++++++++----
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index 2ae9669eb22c..d4b32cc32bb7 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -164,7 +164,8 @@ core_pattern
 	%s		signal number
 	%t		UNIX time of dump
 	%h		hostname
-	%e		executable filename (may be shortened)
+	%e		executable filename (may be shortened, could be changed by prctl etc)
+	%f      	executable filename
 	%E		executable path
 	%c		maximum size of core file by resource limit RLIMIT_CORE
 	%<OTHER>	both are dropped
diff --git a/fs/coredump.c b/fs/coredump.c
index 7237f07ff6be..76e7c10edfc0 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -153,10 +153,10 @@ int cn_esc_printf(struct core_name *cn, const char *fmt, ...)
 	return ret;
 }
 
-static int cn_print_exe_file(struct core_name *cn)
+static int cn_print_exe_file(struct core_name *cn, bool name_only)
 {
 	struct file *exe_file;
-	char *pathbuf, *path;
+	char *pathbuf, *path, *ptr;
 	int ret;
 
 	exe_file = get_mm_exe_file(current->mm);
@@ -175,6 +175,11 @@ static int cn_print_exe_file(struct core_name *cn)
 		goto free_buf;
 	}
 
+	if (name_only) {
+		ptr = strrchr(path, '/');
+		if (ptr)
+			path = ptr + 1;
+	}
 	ret = cn_esc_printf(cn, "%s", path);
 
 free_buf:
@@ -301,12 +306,16 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm,
 					      utsname()->nodename);
 				up_read(&uts_sem);
 				break;
-			/* executable */
+			/* executable, could be changed by prctl PR_SET_NAME etc */
 			case 'e':
 				err = cn_esc_printf(cn, "%s", current->comm);
 				break;
+			/* file name of executable */
+			case 'f':
+				err = cn_print_exe_file(cn, true);
+				break;
 			case 'E':
-				err = cn_print_exe_file(cn);
+				err = cn_print_exe_file(cn, false);
 				break;
 			/* core limit size */
 			case 'c':

From db19c91c3b75cf8ece3ffd92a4e84a306a7547b0 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 11 Aug 2020 18:36:23 -0700
Subject: [PATCH 425/474] exec: change uselib(2) IS_SREG() failure to EACCES

Patch series "Relocate execve() sanity checks", v2.

While looking at the code paths for the proposed O_MAYEXEC flag, I saw
some things that looked like they should be fixed up.

  exec: Change uselib(2) IS_SREG() failure to EACCES
	This just regularizes the return code on uselib(2).

  exec: Move S_ISREG() check earlier
	This moves the S_ISREG() check even earlier than it was already.

  exec: Move path_noexec() check earlier
	This adds the path_noexec() check to the same place as the
	S_ISREG() check.

This patch (of 3):

Change uselib(2)' S_ISREG() error return to EACCES instead of EINVAL so
the behavior matches execve(2), and the seemingly documented value.  The
"not a regular file" failure mode of execve(2) is explicitly
documented[1], but it is not mentioned in uselib(2)[2] which does,
however, say that open(2) and mmap(2) errors may apply.  The documentation
for open(2) does not include a "not a regular file" error[3], but mmap(2)
does[4], and it is EACCES.

[1] http://man7.org/linux/man-pages/man2/execve.2.html#ERRORS
[2] http://man7.org/linux/man-pages/man2/uselib.2.html#ERRORS
[3] http://man7.org/linux/man-pages/man2/open.2.html#ERRORS
[4] http://man7.org/linux/man-pages/man2/mmap.2.html#ERRORS

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Eric Biggers <ebiggers3@gmail.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Link: http://lkml.kernel.org/r/20200605160013.3954297-1-keescook@chromium.org
Link: http://lkml.kernel.org/r/20200605160013.3954297-2-keescook@chromium.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/exec.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 29ef78ae9f50..c56aad307069 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -141,11 +141,10 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 	if (IS_ERR(file))
 		goto out;
 
-	error = -EINVAL;
+	error = -EACCES;
 	if (!S_ISREG(file_inode(file)->i_mode))
 		goto exit;
 
-	error = -EACCES;
 	if (path_noexec(&file->f_path))
 		goto exit;
 

From 633fb6ac39801514613fbe050db6abdc3fe744d5 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 11 Aug 2020 18:36:26 -0700
Subject: [PATCH 426/474] exec: move S_ISREG() check earlier

The execve(2)/uselib(2) syscalls have always rejected non-regular files.
Recently, it was noticed that a deadlock was introduced when trying to
execute pipes, as the S_ISREG() test was happening too late.  This was
fixed in commit 73601ea5b7b1 ("fs/open.c: allow opening only regular files
during execve()"), but it was added after inode_permission() had already
run, which meant LSMs could see bogus attempts to execute non-regular
files.

Move the test into the other inode type checks (which already look for
other pathological conditions[1]).  Since there is no need to use
FMODE_EXEC while we still have access to "acc_mode", also switch the test
to MAY_EXEC.

Also include a comment with the redundant S_ISREG() checks at the end of
execve(2)/uselib(2) to note that they are present to avoid any mistakes.

My notes on the call path, and related arguments, checks, etc:

do_open_execat()
    struct open_flags open_exec_flags = {
        .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
        .acc_mode = MAY_EXEC,
        ...
    do_filp_open(dfd, filename, open_flags)
        path_openat(nameidata, open_flags, flags)
            file = alloc_empty_file(open_flags, current_cred());
            do_open(nameidata, file, open_flags)
                may_open(path, acc_mode, open_flag)
		    /* new location of MAY_EXEC vs S_ISREG() test */
                    inode_permission(inode, MAY_OPEN | acc_mode)
                        security_inode_permission(inode, acc_mode)
                vfs_open(path, file)
                    do_dentry_open(file, path->dentry->d_inode, open)
                        /* old location of FMODE_EXEC vs S_ISREG() test */
                        security_file_open(f)
                        open()

[1] https://lore.kernel.org/lkml/202006041910.9EF0C602@keescook/

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Eric Biggers <ebiggers3@gmail.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Link: http://lkml.kernel.org/r/20200605160013.3954297-3-keescook@chromium.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/exec.c  | 14 ++++++++++++--
 fs/namei.c |  6 ++++--
 fs/open.c  |  6 ------
 3 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index c56aad307069..cc7ec7b9000b 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -141,8 +141,13 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 	if (IS_ERR(file))
 		goto out;
 
+	/*
+	 * may_open() has already checked for this, so it should be
+	 * impossible to trip now. But we need to be extra cautious
+	 * and check again at the very end too.
+	 */
 	error = -EACCES;
-	if (!S_ISREG(file_inode(file)->i_mode))
+	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)))
 		goto exit;
 
 	if (path_noexec(&file->f_path))
@@ -908,8 +913,13 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
 	if (IS_ERR(file))
 		goto out;
 
+	/*
+	 * may_open() has already checked for this, so it should be
+	 * impossible to trip now. But we need to be extra cautious
+	 * and check again at the very end too.
+	 */
 	err = -EACCES;
-	if (!S_ISREG(file_inode(file)->i_mode))
+	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)))
 		goto exit;
 
 	if (path_noexec(&file->f_path))
diff --git a/fs/namei.c b/fs/namei.c
index fde8fe086c09..9cc3b90abdff 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2849,16 +2849,18 @@ static int may_open(const struct path *path, int acc_mode, int flag)
 	case S_IFLNK:
 		return -ELOOP;
 	case S_IFDIR:
-		if (acc_mode & MAY_WRITE)
+		if (acc_mode & (MAY_WRITE | MAY_EXEC))
 			return -EISDIR;
 		break;
 	case S_IFBLK:
 	case S_IFCHR:
 		if (!may_open_dev(path))
 			return -EACCES;
-		/*FALLTHRU*/
+		fallthrough;
 	case S_IFIFO:
 	case S_IFSOCK:
+		if (acc_mode & MAY_EXEC)
+			return -EACCES;
 		flag &= ~O_TRUNC;
 		break;
 	}
diff --git a/fs/open.c b/fs/open.c
index c80e9f497e9b..9af548fb841b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -779,12 +779,6 @@ static int do_dentry_open(struct file *f,
 		return 0;
 	}
 
-	/* Any file opened for execve()/uselib() has to be a regular file. */
-	if (unlikely(f->f_flags & FMODE_EXEC && !S_ISREG(inode->i_mode))) {
-		error = -EACCES;
-		goto cleanup_file;
-	}
-
 	if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
 		error = get_write_access(inode);
 		if (unlikely(error))

From 0fd338b2d2cdf827091ae819ae90ad760b94ad0c Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 11 Aug 2020 18:36:30 -0700
Subject: [PATCH 427/474] exec: move path_noexec() check earlier

The path_noexec() check, like the regular file check, was happening too
late, letting LSMs see impossible execve()s.  Check it earlier as well in
may_open() and collect the redundant fs/exec.c path_noexec() test under
the same robustness comment as the S_ISREG() check.

My notes on the call path, and related arguments, checks, etc:

do_open_execat()
    struct open_flags open_exec_flags = {
        .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
        .acc_mode = MAY_EXEC,
        ...
    do_filp_open(dfd, filename, open_flags)
        path_openat(nameidata, open_flags, flags)
            file = alloc_empty_file(open_flags, current_cred());
            do_open(nameidata, file, open_flags)
                may_open(path, acc_mode, open_flag)
                    /* new location of MAY_EXEC vs path_noexec() test */
                    inode_permission(inode, MAY_OPEN | acc_mode)
                        security_inode_permission(inode, acc_mode)
                vfs_open(path, file)
                    do_dentry_open(file, path->dentry->d_inode, open)
                        security_file_open(f)
                        open()
    /* old location of path_noexec() test */

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Eric Biggers <ebiggers3@gmail.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Link: http://lkml.kernel.org/r/20200605160013.3954297-4-keescook@chromium.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/exec.c  | 12 ++++--------
 fs/namei.c |  4 ++++
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index cc7ec7b9000b..a57d9785832b 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -147,10 +147,8 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 	 * and check again at the very end too.
 	 */
 	error = -EACCES;
-	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)))
-		goto exit;
-
-	if (path_noexec(&file->f_path))
+	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) ||
+			 path_noexec(&file->f_path)))
 		goto exit;
 
 	fsnotify_open(file);
@@ -919,10 +917,8 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
 	 * and check again at the very end too.
 	 */
 	err = -EACCES;
-	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)))
-		goto exit;
-
-	if (path_noexec(&file->f_path))
+	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) ||
+			 path_noexec(&file->f_path)))
 		goto exit;
 
 	err = deny_write_access(file);
diff --git a/fs/namei.c b/fs/namei.c
index 9cc3b90abdff..fb318e06ba3c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2863,6 +2863,10 @@ static int may_open(const struct path *path, int acc_mode, int flag)
 			return -EACCES;
 		flag &= ~O_TRUNC;
 		break;
+	case S_IFREG:
+		if ((acc_mode & MAY_EXEC) && path_noexec(path))
+			return -EACCES;
+		break;
 	}
 
 	error = inode_permission(inode, MAY_OPEN | acc_mode);

From 0935288c6e008c0682ab6171fb5605dcc049e7bd Mon Sep 17 00:00:00 2001
From: Vijay Balakrishna <vijayb@linux.microsoft.com>
Date: Tue, 11 Aug 2020 18:36:33 -0700
Subject: [PATCH 428/474] kdump: append kernel build-id string to VMCOREINFO

Make kernel GNU build-id available in VMCOREINFO.  Having build-id in
VMCOREINFO facilitates presenting appropriate kernel namelist image with
debug information file to kernel crash dump analysis tools.  Currently
VMCOREINFO lacks uniquely identifiable key for crash analysis automation.

Regarding if this patch is necessary or matching of linux_banner and
OSRELEASE in VMCOREINFO employed by crash(8) meets the need -- IMO,
build-id approach more foolproof, in most instances it is a cryptographic
hash generated using internal code/ELF bits unlike kernel version string
upon which linux_banner is based that is external to the code.  I feel
each is intended for a different purpose.  Also OSRELEASE is not suitable
when two different kernel builds from same version with different features
enabled.

Currently for most linux (and non-linux) systems build-id can be extracted
using standard methods for file types such as user mode crash dumps,
shared libraries, loadable kernel modules etc., This is an exception for
linux kernel dump.  Having build-id in VMCOREINFO brings some uniformity
for automation tools.

Tyler said:

: I think this is a nice improvement over today's linux_banner approach for
: correlating vmlinux to a kernel dump.
:
: The elf notes parsing in this patch lines up with what is described in in
: the "Notes (Nhdr)" section of the elf(5) man page.
:
: BUILD_ID_MAX is sufficient to hold a sha1 build-id, which is the default
: build-id type today in GNU ld(2).  It is also sufficient to hold the
: "fast" build-id, which is the default build-id type today in LLVM lld(2).

Signed-off-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Tyler Hicks <tyhicks@linux.microsoft.com>
Acked-by: Baoquan He <bhe@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Link: http://lkml.kernel.org/r/1591849672-34104-1-git-send-email-vijayb@linux.microsoft.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/crash_core.h |  6 +++++
 kernel/crash_core.c        | 50 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 56 insertions(+)

diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index 525510a9f965..6594dbc34a37 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -38,6 +38,8 @@ phys_addr_t paddr_vmcoreinfo_note(void);
 
 #define VMCOREINFO_OSRELEASE(value) \
 	vmcoreinfo_append_str("OSRELEASE=%s\n", value)
+#define VMCOREINFO_BUILD_ID(value) \
+	vmcoreinfo_append_str("BUILD-ID=%s\n", value)
 #define VMCOREINFO_PAGESIZE(value) \
 	vmcoreinfo_append_str("PAGESIZE=%ld\n", value)
 #define VMCOREINFO_SYMBOL(name) \
@@ -64,6 +66,10 @@ extern unsigned char *vmcoreinfo_data;
 extern size_t vmcoreinfo_size;
 extern u32 *vmcoreinfo_note;
 
+/* raw contents of kernel .notes section */
+extern const void __start_notes __weak;
+extern const void __stop_notes __weak;
+
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
 void final_note(Elf_Word *buf);
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 18175687133a..106e4500fd53 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -11,6 +11,8 @@
 #include <asm/page.h>
 #include <asm/sections.h>
 
+#include <crypto/sha.h>
+
 /* vmcoreinfo stuff */
 unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
@@ -376,6 +378,53 @@ phys_addr_t __weak paddr_vmcoreinfo_note(void)
 }
 EXPORT_SYMBOL(paddr_vmcoreinfo_note);
 
+#define NOTES_SIZE (&__stop_notes - &__start_notes)
+#define BUILD_ID_MAX SHA1_DIGEST_SIZE
+#define NT_GNU_BUILD_ID 3
+
+struct elf_note_section {
+	struct elf_note	n_hdr;
+	u8 n_data[];
+};
+
+/*
+ * Add build ID from .notes section as generated by the GNU ld(1)
+ * or LLVM lld(1) --build-id option.
+ */
+static void add_build_id_vmcoreinfo(void)
+{
+	char build_id[BUILD_ID_MAX * 2 + 1];
+	int n_remain = NOTES_SIZE;
+
+	while (n_remain >= sizeof(struct elf_note)) {
+		const struct elf_note_section *note_sec =
+			&__start_notes + NOTES_SIZE - n_remain;
+		const u32 n_namesz = note_sec->n_hdr.n_namesz;
+
+		if (note_sec->n_hdr.n_type == NT_GNU_BUILD_ID &&
+		    n_namesz != 0 &&
+		    !strcmp((char *)&note_sec->n_data[0], "GNU")) {
+			if (note_sec->n_hdr.n_descsz <= BUILD_ID_MAX) {
+				const u32 n_descsz = note_sec->n_hdr.n_descsz;
+				const u8 *s = &note_sec->n_data[n_namesz];
+
+				s = PTR_ALIGN(s, 4);
+				bin2hex(build_id, s, n_descsz);
+				build_id[2 * n_descsz] = '\0';
+				VMCOREINFO_BUILD_ID(build_id);
+				return;
+			}
+			pr_warn("Build ID is too large to include in vmcoreinfo: %u > %u\n",
+				note_sec->n_hdr.n_descsz,
+				BUILD_ID_MAX);
+			return;
+		}
+		n_remain -= sizeof(struct elf_note) +
+			ALIGN(note_sec->n_hdr.n_namesz, 4) +
+			ALIGN(note_sec->n_hdr.n_descsz, 4);
+	}
+}
+
 static int __init crash_save_vmcoreinfo_init(void)
 {
 	vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
@@ -394,6 +443,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	}
 
 	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
+	add_build_id_vmcoreinfo();
 	VMCOREINFO_PAGESIZE(PAGE_SIZE);
 
 	VMCOREINFO_SYMBOL(init_uts_ns);

From 216ec27f3c5215d357f351fa103817c8b62ea804 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 11 Aug 2020 18:36:37 -0700
Subject: [PATCH 429/474] drivers/rapidio/devices/rio_mport_cdev.c: use
 struct_size() helper

Make use of the struct_size() helper instead of an open-coded version in
order to avoid any potential type mistakes.

This issue was found with the help of Coccinelle and, audited and fixed
manually.

Addresses KSPP ID: https://github.com/KSPP/linux/issues/83

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Alexandre Bounine <alex.bou9@gmail.com>
Link: http://lkml.kernel.org/r/20200619170843.GA24923@embeddedor
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/rapidio/devices/rio_mport_cdev.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 451608e960a1..3abbba8c2b5b 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -1710,8 +1710,7 @@ static int rio_mport_add_riodev(struct mport_cdev_priv *priv,
 	if (rval & RIO_PEF_SWITCH) {
 		rio_mport_read_config_32(mport, destid, hopcount,
 					 RIO_SWP_INFO_CAR, &swpinfo);
-		size += (RIO_GET_TOTAL_PORTS(swpinfo) *
-			 sizeof(rswitch->nextdev[0])) + sizeof(*rswitch);
+		size += struct_size(rswitch, nextdev, RIO_GET_TOTAL_PORTS(swpinfo));
 	}
 
 	rdev = kzalloc(size, GFP_KERNEL);

From 330d5589604d7c1d08caa097a97690d2e8c5bb3f Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 11 Aug 2020 18:36:40 -0700
Subject: [PATCH 430/474] drivers/rapidio/rio-scan.c: use struct_size() helper

Make use of the struct_size() helper instead of an open-coded version in
order to avoid any potential type mistakes.

Also, while there, use the preferred form for passing a size of a struct.
The alternative form where struct name is spelled out hurts readability
and introduces an opportunity for a bug when the pointer variable type is
changed but the corresponding sizeof that is passed as argument is not.

This issue was found with the help of Coccinelle and, audited and fixed
manually.

Addresses KSPP ID: https://github.com/KSPP/linux/issues/83

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Alexandre Bounine <alex.bou9@gmail.com>
Link: http://lkml.kernel.org/r/20200619170445.GA22641@embeddedor
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/rapidio/rio-scan.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c
index eb8ed28533f8..19b0c33f4a62 100644
--- a/drivers/rapidio/rio-scan.c
+++ b/drivers/rapidio/rio-scan.c
@@ -330,7 +330,7 @@ static struct rio_dev *rio_setup_device(struct rio_net *net,
 	size_t size;
 	u32 swpinfo = 0;
 
-	size = sizeof(struct rio_dev);
+	size = sizeof(*rdev);
 	if (rio_mport_read_config_32(port, destid, hopcount,
 				     RIO_PEF_CAR, &result))
 		return NULL;
@@ -338,10 +338,8 @@ static struct rio_dev *rio_setup_device(struct rio_net *net,
 	if (result & (RIO_PEF_SWITCH | RIO_PEF_MULTIPORT)) {
 		rio_mport_read_config_32(port, destid, hopcount,
 					 RIO_SWP_INFO_CAR, &swpinfo);
-		if (result & RIO_PEF_SWITCH) {
-			size += (RIO_GET_TOTAL_PORTS(swpinfo) *
-				sizeof(rswitch->nextdev[0])) + sizeof(*rswitch);
-		}
+		if (result & RIO_PEF_SWITCH)
+			size += struct_size(rswitch, nextdev, RIO_GET_TOTAL_PORTS(swpinfo));
 	}
 
 	rdev = kzalloc(size, GFP_KERNEL);

From d71375499d7b0a954e3012d4e16ccad3f28e3d1c Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 11 Aug 2020 18:36:43 -0700
Subject: [PATCH 431/474] rapidio/rio_mport_cdev: use array_size() helper in
 copy_{from,to}_user()

Use array_size() helper instead of the open-coded version in
copy_{from,to}_user().  These sorts of multiplication factors need to be
wrapped in array_size().

This issue was found with the help of Coccinelle and, audited and fixed
manually.

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Alexandre Bounine <alex.bou9@gmail.com>
Link: http://lkml.kernel.org/r/20200616183050.GA31840@embeddedor
Addresses-KSPP-ID: https://github.com/KSPP/linux/issues/83
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/rapidio/devices/rio_mport_cdev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 3abbba8c2b5b..c07ceec3c6d4 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -981,7 +981,7 @@ static int rio_mport_transfer_ioctl(struct file *filp, void __user *arg)
 
 	if (unlikely(copy_from_user(transfer,
 				    (void __user *)(uintptr_t)transaction.block,
-				    transaction.count * sizeof(*transfer)))) {
+				    array_size(sizeof(*transfer), transaction.count)))) {
 		ret = -EFAULT;
 		goto out_free;
 	}
@@ -994,7 +994,7 @@ static int rio_mport_transfer_ioctl(struct file *filp, void __user *arg)
 
 	if (unlikely(copy_to_user((void __user *)(uintptr_t)transaction.block,
 				  transfer,
-				  transaction.count * sizeof(*transfer))))
+				  array_size(sizeof(*transfer), transaction.count))))
 		ret = -EFAULT;
 
 out_free:

From 79076e1241bb3bf02d0aac7d39120d8161fe07b1 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Tue, 11 Aug 2020 18:36:46 -0700
Subject: [PATCH 432/474] kernel/panic.c: make oops_may_print() return bool

The return value of oops_may_print() is true or false, so change its type
to reflect that.

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Xuefeng Li <lixuefeng@loongson.cn>
Link: http://lkml.kernel.org/r/1591103358-32087-1-git-send-email-yangtiezhu@loongson.cn
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 2 +-
 kernel/panic.c         | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 92517ae53e7c..211005163682 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -322,7 +322,7 @@ void nmi_panic(struct pt_regs *regs, const char *msg);
 extern void oops_enter(void);
 extern void oops_exit(void);
 void print_oops_end_marker(void);
-extern int oops_may_print(void);
+extern bool oops_may_print(void);
 void do_exit(long error_code) __noreturn;
 void complete_and_exit(struct completion *, long) __noreturn;
 
diff --git a/kernel/panic.c b/kernel/panic.c
index e2157ca387c8..93ba061d1c79 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -505,7 +505,7 @@ static void do_oops_enter_exit(void)
  * Return true if the calling CPU is allowed to print oops-related info.
  * This is a bit racy..
  */
-int oops_may_print(void)
+bool oops_may_print(void)
 {
 	return pause_on_oops_flag == 0;
 }

From 9d5b134f9f51dd5a67adf8fdc4f59af97e540ceb Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Tue, 11 Aug 2020 18:36:49 -0700
Subject: [PATCH 433/474] lib/Kconfig.debug: fix typo in the help text of
 CONFIG_PANIC_TIMEOUT

There exists duplicated "the" in the help text of CONFIG_PANIC_TIMEOUT,
Remove it.

Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Xuefeng Li <lixuefeng@loongson.cn>
Link: http://lkml.kernel.org/r/1591103358-32087-2-git-send-email-yangtiezhu@loongson.cn
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/Kconfig.debug | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 9ca1b11af1f6..e068c3c7189a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -917,7 +917,7 @@ config PANIC_TIMEOUT
 	int "panic timeout"
 	default 0
 	help
-	  Set the timeout value (in seconds) until a reboot occurs when the
+	  Set the timeout value (in seconds) until a reboot occurs when
 	  the kernel panics. If n = 0, then we wait forever. A timeout
 	  value n > 0 will wait n seconds before rebooting, while a timeout
 	  value n < 0 will reboot immediately.

From 63037f74725ddd8a767ed2ad0369e60a3bf1f2ce Mon Sep 17 00:00:00 2001
From: Yue Hu <huyue2@yulong.com>
Date: Tue, 11 Aug 2020 18:36:53 -0700
Subject: [PATCH 434/474] panic: make print_oops_end_marker() static

Since print_oops_end_marker() is not used externally, also remove it in
kernel.h at the same time.

Signed-off-by: Yue Hu <huyue2@yulong.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/20200724011516.12756-1-zbestahu@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 1 -
 kernel/panic.c         | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 211005163682..500def620d8f 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -321,7 +321,6 @@ void panic(const char *fmt, ...) __noreturn __cold;
 void nmi_panic(struct pt_regs *regs, const char *msg);
 extern void oops_enter(void);
 extern void oops_exit(void);
-void print_oops_end_marker(void);
 extern bool oops_may_print(void);
 void do_exit(long error_code) __noreturn;
 void complete_and_exit(struct completion *, long) __noreturn;
diff --git a/kernel/panic.c b/kernel/panic.c
index 93ba061d1c79..aef8872ba843 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -551,7 +551,7 @@ static int init_oops_id(void)
 }
 late_initcall(init_oops_id);
 
-void print_oops_end_marker(void)
+static void print_oops_end_marker(void)
 {
 	init_oops_id();
 	pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id);

From 31a1b9878c0667945b078c92bce907552f57f2b6 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Tue, 11 Aug 2020 18:36:56 -0700
Subject: [PATCH 435/474] kcov: unconditionally add -fno-stack-protector to
 compiler options

Unconditionally add -fno-stack-protector to KCOV's compiler options, as
all supported compilers support the option.  This saves a compiler
invocation to determine if the option is supported.

Because Clang does not support -fno-conserve-stack, and
-fno-stack-protector was wrapped in the same cc-option, we were missing
-fno-stack-protector with Clang. Unconditionally adding this option
fixes this for Clang.

Suggested-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Alexander Potapenko <glider@google.com>
Link: http://lkml.kernel.org/r/20200615184302.7591-1-elver@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/Makefile b/kernel/Makefile
index 5350fd292910..b3da548691c9 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -36,7 +36,7 @@ KCOV_INSTRUMENT_stacktrace.o := n
 KCOV_INSTRUMENT_kcov.o := n
 KASAN_SANITIZE_kcov.o := n
 KCSAN_SANITIZE_kcov.o := n
-CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
+CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack) -fno-stack-protector
 
 # cond_syscall is currently not LTO compatible
 CFLAGS_sys_ni.o = $(DISABLE_LTO)

From fed79d057d0842d2e381632b783af30745dd7938 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Tue, 11 Aug 2020 18:36:59 -0700
Subject: [PATCH 436/474] kcov: make some symbols static

Fix sparse build warnings:

kernel/kcov.c:99:1: warning:
 symbol '__pcpu_scope_kcov_percpu_data' was not declared. Should it be static?
kernel/kcov.c:778:6: warning:
 symbol 'kcov_remote_softirq_start' was not declared. Should it be static?
kernel/kcov.c:795:6: warning:
 symbol 'kcov_remote_softirq_stop' was not declared. Should it be static?

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrey Konovalov <andreyknvl@google.com>
Link: http://lkml.kernel.org/r/20200702115501.73077-1-weiyongjun1@huawei.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/kcov.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/kcov.c b/kernel/kcov.c
index 6afae0bcbac4..6b8368be89c8 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -96,7 +96,7 @@ struct kcov_percpu_data {
 	int			saved_sequence;
 };
 
-DEFINE_PER_CPU(struct kcov_percpu_data, kcov_percpu_data);
+static DEFINE_PER_CPU(struct kcov_percpu_data, kcov_percpu_data);
 
 /* Must be called with kcov_remote_lock locked. */
 static struct kcov_remote *kcov_remote_find(u64 handle)
@@ -775,7 +775,7 @@ static inline bool kcov_mode_enabled(unsigned int mode)
 	return (mode & ~KCOV_IN_CTXSW) != KCOV_MODE_DISABLED;
 }
 
-void kcov_remote_softirq_start(struct task_struct *t)
+static void kcov_remote_softirq_start(struct task_struct *t)
 {
 	struct kcov_percpu_data *data = this_cpu_ptr(&kcov_percpu_data);
 	unsigned int mode;
@@ -792,7 +792,7 @@ void kcov_remote_softirq_start(struct task_struct *t)
 	}
 }
 
-void kcov_remote_softirq_stop(struct task_struct *t)
+static void kcov_remote_softirq_stop(struct task_struct *t)
 {
 	struct kcov_percpu_data *data = this_cpu_ptr(&kcov_percpu_data);
 

From a3ec9f38a97545b5923a90a1052cbdb3683b9631 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Tue, 11 Aug 2020 18:37:02 -0700
Subject: [PATCH 437/474] scripts/gdb: fix python 3.8 SyntaxWarning

Fixes the observed warnings:
scripts/gdb/linux/rbtree.py:20: SyntaxWarning: "is" with a literal. Did
you mean "=="?
  if node is 0:
scripts/gdb/linux/rbtree.py:36: SyntaxWarning: "is" with a literal. Did
you mean "=="?
  if node is 0:

It looks like this is a new warning added in Python 3.8. I've only seen
this once after adding the add-auto-load-safe-path rule to my ~/.gdbinit
for a new tree.

Fixes: commit 449ca0c95ea2 ("scripts/gdb: add rb tree iterating utilities")
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Cc: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Kieran Bingham <kbingham@kernel.org>
Cc: Aymeric Agon-Rambosson <aymeric.agon@yandex.com>
Link: http://lkml.kernel.org/r/20200805225015.2847624-1-ndesaulniers@google.com
Link: https://adamj.eu/tech/2020/01/21/why-does-python-3-8-syntaxwarning-for-is-literal/
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 scripts/gdb/linux/rbtree.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scripts/gdb/linux/rbtree.py b/scripts/gdb/linux/rbtree.py
index c4b991607917..fe462855eefd 100644
--- a/scripts/gdb/linux/rbtree.py
+++ b/scripts/gdb/linux/rbtree.py
@@ -17,7 +17,7 @@ def rb_first(root):
         raise gdb.GdbError("Must be struct rb_root not {}".format(root.type))
 
     node = root['rb_node']
-    if node is 0:
+    if node == 0:
         return None
 
     while node['rb_left']:
@@ -33,7 +33,7 @@ def rb_last(root):
         raise gdb.GdbError("Must be struct rb_root not {}".format(root.type))
 
     node = root['rb_node']
-    if node is 0:
+    if node == 0:
         return None
 
     while node['rb_right']:

From 00898e8599a184ae05e2c00903e85dc80d82a43d Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Tue, 11 Aug 2020 18:37:05 -0700
Subject: [PATCH 438/474] ipc: uninline functions

Two functions are only called via function pointers, don't bother
inlining them.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Link: http://lkml.kernel.org/r/20200710200312.GA960353@localhost.localdomain
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 ipc/sem.c | 3 +--
 ipc/shm.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/ipc/sem.c b/ipc/sem.c
index 3687b71151b3..8c0244e0365e 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -585,8 +585,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 /*
  * Called with sem_ids.rwsem and ipcp locked.
  */
-static inline int sem_more_checks(struct kern_ipc_perm *ipcp,
-				struct ipc_params *params)
+static int sem_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params)
 {
 	struct sem_array *sma;
 
diff --git a/ipc/shm.c b/ipc/shm.c
index bf38d7e2fbe9..fd296135a5e6 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -711,8 +711,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 /*
  * Called with shm_ids.rwsem and ipcp locked.
  */
-static inline int shm_more_checks(struct kern_ipc_perm *ipcp,
-				struct ipc_params *params)
+static int shm_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params)
 {
 	struct shmid_kernel *shp;
 

From ce14489c8e2d327b56ff3253a3642a6d79b9bca2 Mon Sep 17 00:00:00 2001
From: Liao Pingfang <liao.pingfang@zte.com.cn>
Date: Tue, 11 Aug 2020 18:37:08 -0700
Subject: [PATCH 439/474] ipc/shm.c: remove the superfluous break

Remove the superfuous break, as there is a 'return' before it.

Signed-off-by: Liao Pingfang <liao.pingfang@zte.com.cn>
Signed-off-by: Yi Wang <wang.yi59@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1594724361-11525-1-git-send-email-wang.yi59@zte.com.cn
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 ipc/shm.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/ipc/shm.c b/ipc/shm.c
index fd296135a5e6..f1ed36e3ac9f 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1380,7 +1380,6 @@ static long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr, int versio
 	case SHM_LOCK:
 	case SHM_UNLOCK:
 		return shmctl_do_lock(ns, shmid, cmd);
-		break;
 	default:
 		return -EINVAL;
 	}

From c7073bab5772e0e2ab2c766a05f68174974b1ab5 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:11 -0700
Subject: [PATCH 440/474] mm/page_isolation: prefer the node of the source page

Patch series "clean-up the migration target allocation functions", v5.

This patch (of 9):

For locality, it's better to migrate the page to the same node rather than
the node of the current caller's cpu.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Link: http://lkml.kernel.org/r/1594622517-20681-1-git-send-email-iamjoonsoo.kim@lge.com
Link: http://lkml.kernel.org/r/1594622517-20681-2-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_isolation.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index f6d07c5f0d34..aec26d972b9f 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -309,5 +309,7 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 
 struct page *alloc_migrate_target(struct page *page, unsigned long private)
 {
-	return new_page_nodemask(page, numa_node_id(), &node_states[N_MEMORY]);
+	int nid = page_to_nid(page);
+
+	return new_page_nodemask(page, nid, &node_states[N_MEMORY]);
 }

From b4b382238ed2f94f0d3860f9120b66404fa99463 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:14 -0700
Subject: [PATCH 441/474] mm/migrate: move migration helper from .h to .c

It's not performance sensitive function.  Move it to .c.  This is a
preparation step for future change.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1594622517-20681-3-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/migrate.h | 33 +++++----------------------------
 mm/migrate.c            | 29 +++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 28 deletions(-)

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 540998d9810b..abeb4b15b297 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -31,34 +31,6 @@ enum migrate_reason {
 /* In mm/debug.c; also keep sync with include/trace/events/migrate.h */
 extern const char *migrate_reason_names[MR_TYPES];
 
-static inline struct page *new_page_nodemask(struct page *page,
-				int preferred_nid, nodemask_t *nodemask)
-{
-	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL;
-	unsigned int order = 0;
-	struct page *new_page = NULL;
-
-	if (PageHuge(page))
-		return alloc_huge_page_nodemask(page_hstate(compound_head(page)),
-				preferred_nid, nodemask);
-
-	if (PageTransHuge(page)) {
-		gfp_mask |= GFP_TRANSHUGE;
-		order = HPAGE_PMD_ORDER;
-	}
-
-	if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
-		gfp_mask |= __GFP_HIGHMEM;
-
-	new_page = __alloc_pages_nodemask(gfp_mask, order,
-				preferred_nid, nodemask);
-
-	if (new_page && PageTransHuge(new_page))
-		prep_transhuge_page(new_page);
-
-	return new_page;
-}
-
 #ifdef CONFIG_MIGRATION
 
 extern void putback_movable_pages(struct list_head *l);
@@ -67,6 +39,8 @@ extern int migrate_page(struct address_space *mapping,
 			enum migrate_mode mode);
 extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
 		unsigned long private, enum migrate_mode mode, int reason);
+extern struct page *new_page_nodemask(struct page *page,
+		int preferred_nid, nodemask_t *nodemask);
 extern int isolate_movable_page(struct page *page, isolate_mode_t mode);
 extern void putback_movable_page(struct page *page);
 
@@ -85,6 +59,9 @@ static inline int migrate_pages(struct list_head *l, new_page_t new,
 		free_page_t free, unsigned long private, enum migrate_mode mode,
 		int reason)
 	{ return -ENOSYS; }
+static inline struct page *new_page_nodemask(struct page *page,
+		int preferred_nid, nodemask_t *nodemask)
+	{ return NULL; }
 static inline int isolate_movable_page(struct page *page, isolate_mode_t mode)
 	{ return -EBUSY; }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 52896b4921a7..5269bc520aee 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1538,6 +1538,35 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 	return rc;
 }
 
+struct page *new_page_nodemask(struct page *page,
+				int preferred_nid, nodemask_t *nodemask)
+{
+	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL;
+	unsigned int order = 0;
+	struct page *new_page = NULL;
+
+	if (PageHuge(page))
+		return alloc_huge_page_nodemask(
+				page_hstate(compound_head(page)),
+				preferred_nid, nodemask);
+
+	if (PageTransHuge(page)) {
+		gfp_mask |= GFP_TRANSHUGE;
+		order = HPAGE_PMD_ORDER;
+	}
+
+	if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
+		gfp_mask |= __GFP_HIGHMEM;
+
+	new_page = __alloc_pages_nodemask(gfp_mask, order,
+				preferred_nid, nodemask);
+
+	if (new_page && PageTransHuge(new_page))
+		prep_transhuge_page(new_page);
+
+	return new_page;
+}
+
 #ifdef CONFIG_NUMA
 
 static int store_status(int __user *status, int start, int value, int nr)

From d92bbc2719bd2be237ee336113b63492a6baca3b Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:17 -0700
Subject: [PATCH 442/474] mm/hugetlb: unify migration callbacks

There is no difference between two migration callback functions,
alloc_huge_page_node() and alloc_huge_page_nodemask(), except
__GFP_THISNODE handling.  It's redundant to have two almost similar
functions in order to handle this flag.  So, this patch tries to remove
one by introducing a new argument, gfp_mask, to
alloc_huge_page_nodemask().

After introducing gfp_mask argument, it's caller's job to provide correct
gfp_mask.  So, every callsites for alloc_huge_page_nodemask() are changed
to provide gfp_mask.

Note that it's safe to remove a node id check in alloc_huge_page_node()
since there is no caller passing NUMA_NO_NODE as a node id.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1594622517-20681-4-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h | 26 ++++++++++++++++++--------
 mm/hugetlb.c            | 35 ++---------------------------------
 mm/mempolicy.c          | 10 ++++++----
 mm/migrate.c            | 11 +++++++----
 4 files changed, 33 insertions(+), 49 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index a520bf26e5d8..3517edde681e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -10,6 +10,7 @@
 #include <linux/list.h>
 #include <linux/kref.h>
 #include <linux/pgtable.h>
+#include <linux/gfp.h>
 
 struct ctl_table;
 struct user_struct;
@@ -506,9 +507,8 @@ struct huge_bootmem_page {
 
 struct page *alloc_huge_page(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
-struct page *alloc_huge_page_node(struct hstate *h, int nid);
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-				nodemask_t *nmask);
+				nodemask_t *nmask, gfp_t gfp_mask);
 struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 				unsigned long address);
 struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
@@ -694,6 +694,15 @@ static inline bool hugepage_movable_supported(struct hstate *h)
 	return true;
 }
 
+/* Movability of hugepages depends on migration support. */
+static inline gfp_t htlb_alloc_mask(struct hstate *h)
+{
+	if (hugepage_movable_supported(h))
+		return GFP_HIGHUSER_MOVABLE;
+	else
+		return GFP_HIGHUSER;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
@@ -761,13 +770,9 @@ static inline struct page *alloc_huge_page(struct vm_area_struct *vma,
 	return NULL;
 }
 
-static inline struct page *alloc_huge_page_node(struct hstate *h, int nid)
-{
-	return NULL;
-}
-
 static inline struct page *
-alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask)
+alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
+			nodemask_t *nmask, gfp_t gfp_mask)
 {
 	return NULL;
 }
@@ -880,6 +885,11 @@ static inline bool hugepage_movable_supported(struct hstate *h)
 	return false;
 }
 
+static inline gfp_t htlb_alloc_mask(struct hstate *h)
+{
+	return 0;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b66bf74e999e..eaab9ef88e9d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1093,15 +1093,6 @@ static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask,
 	return NULL;
 }
 
-/* Movability of hugepages depends on migration support. */
-static inline gfp_t htlb_alloc_mask(struct hstate *h)
-{
-	if (hugepage_movable_supported(h))
-		return GFP_HIGHUSER_MOVABLE;
-	else
-		return GFP_HIGHUSER;
-}
-
 static struct page *dequeue_huge_page_vma(struct hstate *h,
 				struct vm_area_struct *vma,
 				unsigned long address, int avoid_reserve,
@@ -1985,32 +1976,10 @@ struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h,
 	return page;
 }
 
-/* page migration callback function */
-struct page *alloc_huge_page_node(struct hstate *h, int nid)
-{
-	gfp_t gfp_mask = htlb_alloc_mask(h);
-	struct page *page = NULL;
-
-	if (nid != NUMA_NO_NODE)
-		gfp_mask |= __GFP_THISNODE;
-
-	spin_lock(&hugetlb_lock);
-	if (h->free_huge_pages - h->resv_huge_pages > 0)
-		page = dequeue_huge_page_nodemask(h, gfp_mask, nid, NULL);
-	spin_unlock(&hugetlb_lock);
-
-	if (!page)
-		page = alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
-
-	return page;
-}
-
 /* page migration callback function */
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-		nodemask_t *nmask)
+		nodemask_t *nmask, gfp_t gfp_mask)
 {
-	gfp_t gfp_mask = htlb_alloc_mask(h);
-
 	spin_lock(&hugetlb_lock);
 	if (h->free_huge_pages - h->resv_huge_pages > 0) {
 		struct page *page;
@@ -2038,7 +2007,7 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 
 	gfp_mask = htlb_alloc_mask(h);
 	node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	page = alloc_huge_page_nodemask(h, node, nodemask);
+	page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask);
 	mpol_cond_put(mpol);
 
 	return page;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 25b7e412c20b..9ae2b704bdf6 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1068,10 +1068,12 @@ static int migrate_page_add(struct page *page, struct list_head *pagelist,
 /* page allocation callback for NUMA node migration */
 struct page *alloc_new_node_page(struct page *page, unsigned long node)
 {
-	if (PageHuge(page))
-		return alloc_huge_page_node(page_hstate(compound_head(page)),
-					node);
-	else if (PageTransHuge(page)) {
+	if (PageHuge(page)) {
+		struct hstate *h = page_hstate(compound_head(page));
+		gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
+
+		return alloc_huge_page_nodemask(h, node, NULL, gfp_mask);
+	} else if (PageTransHuge(page)) {
 		struct page *thp;
 
 		thp = alloc_pages_node(node,
diff --git a/mm/migrate.c b/mm/migrate.c
index 5269bc520aee..8d084e9bc13b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1545,10 +1545,13 @@ struct page *new_page_nodemask(struct page *page,
 	unsigned int order = 0;
 	struct page *new_page = NULL;
 
-	if (PageHuge(page))
-		return alloc_huge_page_nodemask(
-				page_hstate(compound_head(page)),
-				preferred_nid, nodemask);
+	if (PageHuge(page)) {
+		struct hstate *h = page_hstate(compound_head(page));
+
+		gfp_mask = htlb_alloc_mask(h);
+		return alloc_huge_page_nodemask(h, preferred_nid,
+						nodemask, gfp_mask);
+	}
 
 	if (PageTransHuge(page)) {
 		gfp_mask |= GFP_TRANSHUGE;

From 9933a0c8a5396df6dbaef809a9ee4ad64ebc3abe Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:20 -0700
Subject: [PATCH 443/474] mm/migrate: clear __GFP_RECLAIM to make the migration
 callback consistent with regular THP allocations

new_page_nodemask is a migration callback and it tries to use a common gfp
flags for the target page allocation whether it is a base page or a THP.
The later only adds GFP_TRANSHUGE to the given mask.  This results in the
allocation being slightly more aggressive than necessary because the
resulting gfp mask will contain also __GFP_RECLAIM_KSWAPD.  THP
allocations usually exclude this flag to reduce over eager background
reclaim during a high THP allocation load which has been seen during large
mmaps initialization.  There is no indication that this is a problem for
migration as well but theoretically the same might happen when migrating
large mappings to a different node.  Make the migration callback
consistent with regular THP allocations.

[akpm@linux-foundation.org: fix comment typo, per Vlastimil]

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1594622517-20681-5-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/migrate.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/mm/migrate.c b/mm/migrate.c
index 8d084e9bc13b..46cca5c2ebff 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1554,6 +1554,11 @@ struct page *new_page_nodemask(struct page *page,
 	}
 
 	if (PageTransHuge(page)) {
+		/*
+		 * clear __GFP_RECLAIM to make the migration callback
+		 * consistent with regular THP allocations.
+		 */
+		gfp_mask &= ~__GFP_RECLAIM;
 		gfp_mask |= GFP_TRANSHUGE;
 		order = HPAGE_PMD_ORDER;
 	}

From 19fc7bed252c16ace29491e4cfa2bafb264eb505 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:25 -0700
Subject: [PATCH 444/474] mm/migrate: introduce a standard migration target
 allocation function

There are some similar functions for migration target allocation.  Since
there is no fundamental difference, it's better to keep just one rather
than keeping all variants.  This patch implements base migration target
allocation function.  In the following patches, variants will be converted
to use this function.

Changes should be mechanical, but, unfortunately, there are some
differences.  First, some callers' nodemask is assgined to NULL since NULL
nodemask will be considered as all available nodes, that is,
&node_states[N_MEMORY].  Second, for hugetlb page allocation, gfp_mask is
redefined as regular hugetlb allocation gfp_mask plus __GFP_THISNODE if
user provided gfp_mask has it.  This is because future caller of this
function requires to set this node constaint.  Lastly, if provided nodeid
is NUMA_NO_NODE, nodeid is set up to the node where migration source
lives.  It helps to remove simple wrappers for setting up the nodeid.

Note that PageHighmem() call in previous function is changed to open-code
"is_highmem_idx()" since it provides more readability.

[akpm@linux-foundation.org: tweak patch title, per Vlastimil]
[akpm@linux-foundation.org: fix typo in comment]

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1594622517-20681-6-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h | 15 +++++++++++++++
 include/linux/migrate.h |  9 +++++----
 mm/internal.h           |  7 +++++++
 mm/memory-failure.c     |  7 +++++--
 mm/memory_hotplug.c     | 12 ++++++++----
 mm/migrate.c            | 26 ++++++++++++++++----------
 mm/page_isolation.c     |  7 +++++--
 7 files changed, 61 insertions(+), 22 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 3517edde681e..30e1f14119c8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -703,6 +703,16 @@ static inline gfp_t htlb_alloc_mask(struct hstate *h)
 		return GFP_HIGHUSER;
 }
 
+static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
+{
+	gfp_t modified_mask = htlb_alloc_mask(h);
+
+	/* Some callers might want to enforce node */
+	modified_mask |= (gfp_mask & __GFP_THISNODE);
+
+	return modified_mask;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
@@ -890,6 +900,11 @@ static inline gfp_t htlb_alloc_mask(struct hstate *h)
 	return 0;
 }
 
+static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
+{
+	return 0;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index abeb4b15b297..0f8d1583fa8e 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -10,6 +10,8 @@
 typedef struct page *new_page_t(struct page *page, unsigned long private);
 typedef void free_page_t(struct page *page, unsigned long private);
 
+struct migration_target_control;
+
 /*
  * Return values from addresss_space_operations.migratepage():
  * - negative errno on page migration failure;
@@ -39,8 +41,7 @@ extern int migrate_page(struct address_space *mapping,
 			enum migrate_mode mode);
 extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
 		unsigned long private, enum migrate_mode mode, int reason);
-extern struct page *new_page_nodemask(struct page *page,
-		int preferred_nid, nodemask_t *nodemask);
+extern struct page *alloc_migration_target(struct page *page, unsigned long private);
 extern int isolate_movable_page(struct page *page, isolate_mode_t mode);
 extern void putback_movable_page(struct page *page);
 
@@ -59,8 +60,8 @@ static inline int migrate_pages(struct list_head *l, new_page_t new,
 		free_page_t free, unsigned long private, enum migrate_mode mode,
 		int reason)
 	{ return -ENOSYS; }
-static inline struct page *new_page_nodemask(struct page *page,
-		int preferred_nid, nodemask_t *nodemask)
+static inline struct page *alloc_migration_target(struct page *page,
+		unsigned long private)
 	{ return NULL; }
 static inline int isolate_movable_page(struct page *page, isolate_mode_t mode)
 	{ return -EBUSY; }
diff --git a/mm/internal.h b/mm/internal.h
index 42cf0b610847..f725aa8a9698 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -614,4 +614,11 @@ static inline bool is_migrate_highatomic_page(struct page *page)
 
 void setup_zone_pageset(struct zone *zone);
 extern struct page *alloc_new_node_page(struct page *page, unsigned long node);
+
+struct migration_target_control {
+	int nid;		/* preferred node id */
+	nodemask_t *nmask;
+	gfp_t gfp_mask;
+};
+
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 47b8ccb1fb9b..f1aa6433f404 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1648,9 +1648,12 @@ EXPORT_SYMBOL(unpoison_memory);
 
 static struct page *new_page(struct page *p, unsigned long private)
 {
-	int nid = page_to_nid(p);
+	struct migration_target_control mtc = {
+		.nid = page_to_nid(p),
+		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+	};
 
-	return new_page_nodemask(p, nid, &node_states[N_MEMORY]);
+	return alloc_migration_target(p, (unsigned long)&mtc);
 }
 
 /*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0a9e1972fbe7..c32ead89c911 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1276,19 +1276,23 @@ static int scan_movable_pages(unsigned long start, unsigned long end,
 
 static struct page *new_node_page(struct page *page, unsigned long private)
 {
-	int nid = page_to_nid(page);
 	nodemask_t nmask = node_states[N_MEMORY];
+	struct migration_target_control mtc = {
+		.nid = page_to_nid(page),
+		.nmask = &nmask,
+		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+	};
 
 	/*
 	 * try to allocate from a different node but reuse this node if there
 	 * are no other online nodes to be used (e.g. we are offlining a part
 	 * of the only existing node)
 	 */
-	node_clear(nid, nmask);
+	node_clear(mtc.nid, nmask);
 	if (nodes_empty(nmask))
-		node_set(nid, nmask);
+		node_set(mtc.nid, nmask);
 
-	return new_page_nodemask(page, nid, &nmask);
+	return alloc_migration_target(page, (unsigned long)&mtc);
 }
 
 static int
diff --git a/mm/migrate.c b/mm/migrate.c
index 46cca5c2ebff..48b1f149494b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1538,19 +1538,26 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 	return rc;
 }
 
-struct page *new_page_nodemask(struct page *page,
-				int preferred_nid, nodemask_t *nodemask)
+struct page *alloc_migration_target(struct page *page, unsigned long private)
 {
-	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL;
+	struct migration_target_control *mtc;
+	gfp_t gfp_mask;
 	unsigned int order = 0;
 	struct page *new_page = NULL;
+	int nid;
+	int zidx;
+
+	mtc = (struct migration_target_control *)private;
+	gfp_mask = mtc->gfp_mask;
+	nid = mtc->nid;
+	if (nid == NUMA_NO_NODE)
+		nid = page_to_nid(page);
 
 	if (PageHuge(page)) {
 		struct hstate *h = page_hstate(compound_head(page));
 
-		gfp_mask = htlb_alloc_mask(h);
-		return alloc_huge_page_nodemask(h, preferred_nid,
-						nodemask, gfp_mask);
+		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
+		return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask);
 	}
 
 	if (PageTransHuge(page)) {
@@ -1562,12 +1569,11 @@ struct page *new_page_nodemask(struct page *page,
 		gfp_mask |= GFP_TRANSHUGE;
 		order = HPAGE_PMD_ORDER;
 	}
-
-	if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
+	zidx = zone_idx(page_zone(page));
+	if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE)
 		gfp_mask |= __GFP_HIGHMEM;
 
-	new_page = __alloc_pages_nodemask(gfp_mask, order,
-				preferred_nid, nodemask);
+	new_page = __alloc_pages_nodemask(gfp_mask, order, nid, mtc->nmask);
 
 	if (new_page && PageTransHuge(new_page))
 		prep_transhuge_page(new_page);
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index aec26d972b9f..f25c66ea37ac 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -309,7 +309,10 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 
 struct page *alloc_migrate_target(struct page *page, unsigned long private)
 {
-	int nid = page_to_nid(page);
+	struct migration_target_control mtc = {
+		.nid = page_to_nid(page),
+		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+	};
 
-	return new_page_nodemask(page, nid, &node_states[N_MEMORY]);
+	return alloc_migration_target(page, (unsigned long)&mtc);
 }

From a097631160c3b71a12db224ece7d72208c9b6846 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:28 -0700
Subject: [PATCH 445/474] mm/mempolicy: use a standard migration target
 allocation callback

There is a well-defined migration target allocation callback.  Use it.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1594622517-20681-7-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/internal.h  |  1 -
 mm/mempolicy.c | 31 ++++++-------------------------
 mm/migrate.c   |  8 ++++++--
 3 files changed, 12 insertions(+), 28 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index f725aa8a9698..d11a9a8d2135 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -613,7 +613,6 @@ static inline bool is_migrate_highatomic_page(struct page *page)
 }
 
 void setup_zone_pageset(struct zone *zone);
-extern struct page *alloc_new_node_page(struct page *page, unsigned long node);
 
 struct migration_target_control {
 	int nid;		/* preferred node id */
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 9ae2b704bdf6..afaa09ff9f6c 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1065,29 +1065,6 @@ static int migrate_page_add(struct page *page, struct list_head *pagelist,
 	return 0;
 }
 
-/* page allocation callback for NUMA node migration */
-struct page *alloc_new_node_page(struct page *page, unsigned long node)
-{
-	if (PageHuge(page)) {
-		struct hstate *h = page_hstate(compound_head(page));
-		gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
-
-		return alloc_huge_page_nodemask(h, node, NULL, gfp_mask);
-	} else if (PageTransHuge(page)) {
-		struct page *thp;
-
-		thp = alloc_pages_node(node,
-			(GFP_TRANSHUGE | __GFP_THISNODE),
-			HPAGE_PMD_ORDER);
-		if (!thp)
-			return NULL;
-		prep_transhuge_page(thp);
-		return thp;
-	} else
-		return __alloc_pages_node(node, GFP_HIGHUSER_MOVABLE |
-						    __GFP_THISNODE, 0);
-}
-
 /*
  * Migrate pages from one node to a target node.
  * Returns error or the number of pages not migrated.
@@ -1098,6 +1075,10 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 	nodemask_t nmask;
 	LIST_HEAD(pagelist);
 	int err = 0;
+	struct migration_target_control mtc = {
+		.nid = dest,
+		.gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE,
+	};
 
 	nodes_clear(nmask);
 	node_set(source, nmask);
@@ -1112,8 +1093,8 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 			flags | MPOL_MF_DISCONTIG_OK, &pagelist);
 
 	if (!list_empty(&pagelist)) {
-		err = migrate_pages(&pagelist, alloc_new_node_page, NULL, dest,
-					MIGRATE_SYNC, MR_SYSCALL);
+		err = migrate_pages(&pagelist, alloc_migration_target, NULL,
+				(unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL);
 		if (err)
 			putback_movable_pages(&pagelist);
 	}
diff --git a/mm/migrate.c b/mm/migrate.c
index 48b1f149494b..5053439be6ab 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1598,9 +1598,13 @@ static int do_move_pages_to_node(struct mm_struct *mm,
 		struct list_head *pagelist, int node)
 {
 	int err;
+	struct migration_target_control mtc = {
+		.nid = node,
+		.gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE,
+	};
 
-	err = migrate_pages(pagelist, alloc_new_node_page, NULL, node,
-			MIGRATE_SYNC, MR_SYSCALL);
+	err = migrate_pages(pagelist, alloc_migration_target, NULL,
+			(unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL);
 	if (err)
 		putback_movable_pages(pagelist);
 	return err;

From 8b94e0b8be360cf5460331e56a2678ba265f0694 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:31 -0700
Subject: [PATCH 446/474] mm/page_alloc: remove a wrapper for
 alloc_migration_target()

There is a well-defined standard migration target callback.  Use it
directly.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1594622517-20681-8-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c     |  8 ++++++--
 mm/page_isolation.c | 10 ----------
 2 files changed, 6 insertions(+), 12 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d80c9bac489c..8b7d0ecf30b1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8347,6 +8347,10 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 	unsigned long pfn = start;
 	unsigned int tries = 0;
 	int ret = 0;
+	struct migration_target_control mtc = {
+		.nid = zone_to_nid(cc->zone),
+		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+	};
 
 	migrate_prep();
 
@@ -8373,8 +8377,8 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 							&cc->migratepages);
 		cc->nr_migratepages -= nr_reclaimed;
 
-		ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
-				    NULL, 0, cc->mode, MR_CONTIG_RANGE);
+		ret = migrate_pages(&cc->migratepages, alloc_migration_target,
+				NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE);
 	}
 	if (ret < 0) {
 		putback_movable_pages(&cc->migratepages);
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index f25c66ea37ac..242c03121d73 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -306,13 +306,3 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 
 	return pfn < end_pfn ? -EBUSY : 0;
 }
-
-struct page *alloc_migrate_target(struct page *page, unsigned long private)
-{
-	struct migration_target_control mtc = {
-		.nid = page_to_nid(page),
-		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
-	};
-
-	return alloc_migration_target(page, (unsigned long)&mtc);
-}

From 41b4dc14ee807cb1bd15e67cad287534046f92dc Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:34 -0700
Subject: [PATCH 447/474] mm/gup: restrict CMA region by using allocation scope
 API

We have well defined scope API to exclude CMA region.  Use it rather than
manipulating gfp_mask manually.  With this change, we can now restore
__GFP_MOVABLE for gfp_mask like as usual migration target allocation.  It
would result in that the ZONE_MOVABLE is also searched by page allocator.
For hugetlb, gfp_mask is redefined since it has a regular allocation mask
filter for migration target.  __GPF_NOWARN is added to hugetlb gfp_mask
filter since a new user for gfp_mask filter, gup, want to be silent when
allocation fails.

Note that this can be considered as a fix for the commit 9a4e9f3b2d73
("mm: update get_user_pages_longterm to migrate pages allocated from CMA
region").  However, "Fixes" tag isn't added here since it is just
suboptimal but it doesn't cause any problem.

Suggested-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Link: http://lkml.kernel.org/r/1596180906-8442-1-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |  2 ++
 mm/gup.c                | 17 ++++++++---------
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 30e1f14119c8..d86c82749836 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -710,6 +710,8 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
 	/* Some callers might want to enforce node */
 	modified_mask |= (gfp_mask & __GFP_THISNODE);
 
+	modified_mask |= (gfp_mask & __GFP_NOWARN);
+
 	return modified_mask;
 }
 
diff --git a/mm/gup.c b/mm/gup.c
index d8a33dd1430d..6c20c6e37635 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1620,10 +1620,12 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
 	 * Trying to allocate a page for migration. Ignore allocation
 	 * failure warnings. We don't force __GFP_THISNODE here because
 	 * this node here is the node where we have CMA reservation and
-	 * in some case these nodes will have really less non movable
+	 * in some case these nodes will have really less non CMA
 	 * allocation memory.
+	 *
+	 * Note that CMA region is prohibited by allocation scope.
 	 */
-	gfp_t gfp_mask = GFP_USER | __GFP_NOWARN;
+	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_NOWARN;
 
 	if (PageHighMem(page))
 		gfp_mask |= __GFP_HIGHMEM;
@@ -1631,6 +1633,8 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
 #ifdef CONFIG_HUGETLB_PAGE
 	if (PageHuge(page)) {
 		struct hstate *h = page_hstate(page);
+
+		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
 		/*
 		 * We don't want to dequeue from the pool because pool pages will
 		 * mostly be from the CMA region.
@@ -1645,11 +1649,6 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
 		 */
 		gfp_t thp_gfpmask = GFP_TRANSHUGE | __GFP_NOWARN;
 
-		/*
-		 * Remove the movable mask so that we don't allocate from
-		 * CMA area again.
-		 */
-		thp_gfpmask &= ~__GFP_MOVABLE;
 		thp = __alloc_pages_node(nid, thp_gfpmask, HPAGE_PMD_ORDER);
 		if (!thp)
 			return NULL;
@@ -1795,7 +1794,6 @@ static long __gup_longterm_locked(struct task_struct *tsk,
 				     vmas_tmp, NULL, gup_flags);
 
 	if (gup_flags & FOLL_LONGTERM) {
-		memalloc_nocma_restore(flags);
 		if (rc < 0)
 			goto out;
 
@@ -1808,9 +1806,10 @@ static long __gup_longterm_locked(struct task_struct *tsk,
 
 		rc = check_and_migrate_cma_pages(tsk, mm, start, rc, pages,
 						 vmas_tmp, gup_flags);
+out:
+		memalloc_nocma_restore(flags);
 	}
 
-out:
 	if (vmas_tmp != vmas)
 		kfree(vmas_tmp);
 	return rc;

From bbe88753bd42b1faf1458dde8f58ff1239990436 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:38 -0700
Subject: [PATCH 448/474] mm/hugetlb: make hugetlb migration callback CMA aware

new_non_cma_page() in gup.c requires to allocate the new page that is not
on the CMA area.  new_non_cma_page() implements it by using allocation
scope APIs.

However, there is a work-around for hugetlb.  Normal hugetlb page
allocation API for migration is alloc_huge_page_nodemask().  It consists
of two steps.  First is dequeing from the pool.  Second is, if there is no
available page on the queue, allocating by using the page allocator.

new_non_cma_page() can't use this API since first step (deque) isn't aware
of scope API to exclude CMA area.  So, new_non_cma_page() exports hugetlb
internal function for the second step, alloc_migrate_huge_page(), to
global scope and uses it directly.  This is suboptimal since hugetlb pages
on the queue cannot be utilized.

This patch tries to fix this situation by making the deque function on
hugetlb CMA aware.  In the deque function, CMA memory is skipped if
PF_MEMALLOC_NOCMA flag is found.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1596180906-8442-2-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |  2 --
 mm/gup.c                |  6 +-----
 mm/hugetlb.c            | 11 +++++++++--
 3 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d86c82749836..d5cc5f802dd4 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -511,8 +511,6 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
 				nodemask_t *nmask, gfp_t gfp_mask);
 struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 				unsigned long address);
-struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
-				     int nid, nodemask_t *nmask);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
 
diff --git a/mm/gup.c b/mm/gup.c
index 6c20c6e37635..c55427beeb26 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1635,11 +1635,7 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
 		struct hstate *h = page_hstate(page);
 
 		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
-		/*
-		 * We don't want to dequeue from the pool because pool pages will
-		 * mostly be from the CMA region.
-		 */
-		return alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
+		return alloc_huge_page_nodemask(h, nid, NULL, gfp_mask);
 	}
 #endif
 	if (PageTransHuge(page)) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index eaab9ef88e9d..a301c2d672bf 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -19,6 +19,7 @@
 #include <linux/memblock.h>
 #include <linux/sysfs.h>
 #include <linux/slab.h>
+#include <linux/sched/mm.h>
 #include <linux/mmdebug.h>
 #include <linux/sched/signal.h>
 #include <linux/rmap.h>
@@ -1040,10 +1041,16 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 {
 	struct page *page;
+	bool nocma = !!(current->flags & PF_MEMALLOC_NOCMA);
+
+	list_for_each_entry(page, &h->hugepage_freelists[nid], lru) {
+		if (nocma && is_migrate_cma_page(page))
+			continue;
 
-	list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
 		if (!PageHWPoison(page))
 			break;
+	}
+
 	/*
 	 * if 'non-isolated free hugepage' not found on the list,
 	 * the allocation fails.
@@ -1935,7 +1942,7 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
 	return page;
 }
 
-struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
+static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
 				     int nid, nodemask_t *nmask)
 {
 	struct page *page;

From ed03d924587e7dfc54f1ace81e5f5a497a7d9666 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 11 Aug 2020 18:37:41 -0700
Subject: [PATCH 449/474] mm/gup: use a standard migration target allocation
 callback

There is a well-defined migration target allocation callback. Use it.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1596180906-8442-3-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/gup.c | 54 ++++++------------------------------------------------
 1 file changed, 6 insertions(+), 48 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index c55427beeb26..e9d1d0cc18f0 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1609,52 +1609,6 @@ static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
 }
 
 #ifdef CONFIG_CMA
-static struct page *new_non_cma_page(struct page *page, unsigned long private)
-{
-	/*
-	 * We want to make sure we allocate the new page from the same node
-	 * as the source page.
-	 */
-	int nid = page_to_nid(page);
-	/*
-	 * Trying to allocate a page for migration. Ignore allocation
-	 * failure warnings. We don't force __GFP_THISNODE here because
-	 * this node here is the node where we have CMA reservation and
-	 * in some case these nodes will have really less non CMA
-	 * allocation memory.
-	 *
-	 * Note that CMA region is prohibited by allocation scope.
-	 */
-	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_NOWARN;
-
-	if (PageHighMem(page))
-		gfp_mask |= __GFP_HIGHMEM;
-
-#ifdef CONFIG_HUGETLB_PAGE
-	if (PageHuge(page)) {
-		struct hstate *h = page_hstate(page);
-
-		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
-		return alloc_huge_page_nodemask(h, nid, NULL, gfp_mask);
-	}
-#endif
-	if (PageTransHuge(page)) {
-		struct page *thp;
-		/*
-		 * ignore allocation failure warnings
-		 */
-		gfp_t thp_gfpmask = GFP_TRANSHUGE | __GFP_NOWARN;
-
-		thp = __alloc_pages_node(nid, thp_gfpmask, HPAGE_PMD_ORDER);
-		if (!thp)
-			return NULL;
-		prep_transhuge_page(thp);
-		return thp;
-	}
-
-	return __alloc_pages_node(nid, gfp_mask, 0);
-}
-
 static long check_and_migrate_cma_pages(struct task_struct *tsk,
 					struct mm_struct *mm,
 					unsigned long start,
@@ -1669,6 +1623,10 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk,
 	bool migrate_allow = true;
 	LIST_HEAD(cma_page_list);
 	long ret = nr_pages;
+	struct migration_target_control mtc = {
+		.nid = NUMA_NO_NODE,
+		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_NOWARN,
+	};
 
 check_again:
 	for (i = 0; i < nr_pages;) {
@@ -1714,8 +1672,8 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk,
 		for (i = 0; i < nr_pages; i++)
 			put_page(pages[i]);
 
-		if (migrate_pages(&cma_page_list, new_non_cma_page,
-				  NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
+		if (migrate_pages(&cma_page_list, alloc_migration_target, NULL,
+			(unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
 			/*
 			 * some of the pages failed migration. Do get_user_pages
 			 * without migration.

From bce617edecada007aee8610fbe2c14d10b8de2f6 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:37:44 -0700
Subject: [PATCH 450/474] mm: do page fault accounting in handle_mm_fault

Patch series "mm: Page fault accounting cleanups", v5.

This is v5 of the pf accounting cleanup series.  It originates from Gerald
Schaefer's report on an issue a week ago regarding to incorrect page fault
accountings for retried page fault after commit 4064b9827063 ("mm: allow
VM_FAULT_RETRY for multiple times"):

  https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/

What this series did:

  - Correct page fault accounting: we do accounting for a page fault
    (no matter whether it's from #PF handling, or gup, or anything else)
    only with the one that completed the fault.  For example, page fault
    retries should not be counted in page fault counters.  Same to the
    perf events.

  - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf
    event is used in an adhoc way across different archs.

    Case (1): for many archs it's done at the entry of a page fault
    handler, so that it will also cover e.g.  errornous faults.

    Case (2): for some other archs, it is only accounted when the page
    fault is resolved successfully.

    Case (3): there're still quite some archs that have not enabled
    this perf event.

    Since this series will touch merely all the archs, we unify this
    perf event to always follow case (1), which is the one that makes most
    sense.  And since we moved the accounting into handle_mm_fault, the
    other two MAJ/MIN perf events are well taken care of naturally.

  - Unify definition of "major faults": the definition of "major
    fault" is slightly changed when used in accounting (not
    VM_FAULT_MAJOR).  More information in patch 1.

  - Always account the page fault onto the one that triggered the page
    fault.  This does not matter much for #PF handlings, but mostly for
    gup.  More information on this in patch 25.

Patchset layout:

Patch 1:     Introduced the accounting in handle_mm_fault(), not enabled.
Patch 2-23:  Enable the new accounting for arch #PF handlers one by one.
Patch 24:    Enable the new accounting for the rest outliers (gup, iommu, etc.)
Patch 25:    Cleanup GUP task_struct pointer since it's not needed any more

This patch (of 25):

This is a preparation patch to move page fault accountings into the
general code in handle_mm_fault().  This includes both the per task
flt_maj/flt_min counters, and the major/minor page fault perf events.  To
do this, the pt_regs pointer is passed into handle_mm_fault().

PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault
handlers.

So far, all the pt_regs pointer that passed into handle_mm_fault() is
NULL, which means this patch should have no intented functional change.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Cain <bcain@codeaurora.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Ley Foon Tan <ley.foon.tan@intel.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Rich Felker <dalias@libc.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com
Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/mm/fault.c         |  2 +-
 arch/arc/mm/fault.c           |  2 +-
 arch/arm/mm/fault.c           |  2 +-
 arch/arm64/mm/fault.c         |  2 +-
 arch/csky/mm/fault.c          |  3 +-
 arch/hexagon/mm/vm_fault.c    |  2 +-
 arch/ia64/mm/fault.c          |  2 +-
 arch/m68k/mm/fault.c          |  2 +-
 arch/microblaze/mm/fault.c    |  2 +-
 arch/mips/mm/fault.c          |  2 +-
 arch/nds32/mm/fault.c         |  2 +-
 arch/nios2/mm/fault.c         |  2 +-
 arch/openrisc/mm/fault.c      |  2 +-
 arch/parisc/mm/fault.c        |  2 +-
 arch/powerpc/mm/copro_fault.c |  2 +-
 arch/powerpc/mm/fault.c       |  2 +-
 arch/riscv/mm/fault.c         |  2 +-
 arch/s390/mm/fault.c          |  2 +-
 arch/sh/mm/fault.c            |  2 +-
 arch/sparc/mm/fault_32.c      |  4 +--
 arch/sparc/mm/fault_64.c      |  2 +-
 arch/um/kernel/trap.c         |  2 +-
 arch/x86/mm/fault.c           |  2 +-
 arch/xtensa/mm/fault.c        |  2 +-
 drivers/iommu/amd/iommu_v2.c  |  2 +-
 drivers/iommu/intel/svm.c     |  3 +-
 include/linux/mm.h            |  7 ++--
 mm/gup.c                      |  4 +--
 mm/hmm.c                      |  3 +-
 mm/ksm.c                      |  3 +-
 mm/memory.c                   | 64 ++++++++++++++++++++++++++++++++++-
 31 files changed, 103 insertions(+), 34 deletions(-)

diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index c2303a8c2b9f..1983e43a5e2f 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -148,7 +148,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	/* If for any reason at all we couldn't handle the fault,
 	   make sure we exit gracefully rather than endlessly redo
 	   the fault.  */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 7287c793d1c9..587dea524e6b 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -130,7 +130,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 		goto bad_area;
 	}
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index c6550eddfce1..01a8e0f8fef7 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -224,7 +224,7 @@ __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
 		goto out;
 	}
 
-	return handle_mm_fault(vma, addr & PAGE_MASK, flags);
+	return handle_mm_fault(vma, addr & PAGE_MASK, flags, NULL);
 
 check_stack:
 	/* Don't allow expansion below FIRST_USER_ADDRESS */
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 8afb238ff335..be29f4076fe3 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -428,7 +428,7 @@ static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
 	 */
 	if (!(vma->vm_flags & vm_flags))
 		return VM_FAULT_BADACCESS;
-	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags);
+	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags, NULL);
 }
 
 static bool is_el0_instruction_abort(unsigned int esr)
diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c
index b1dce9f2f04d..b252e6e4d32f 100644
--- a/arch/csky/mm/fault.c
+++ b/arch/csky/mm/fault.c
@@ -150,7 +150,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0,
+				NULL);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index cd3808f96b93..f12f330e7946 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -88,7 +88,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 		break;
 	}
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 3a4dec334cc5..abf2808f9b4b 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -143,7 +143,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	 * sure we exit gracefully rather than endlessly redo the
 	 * fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 508abb63da67..08b35a318ebe 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -134,7 +134,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 	pr_debug("handle_mm_fault returns %x\n", fault);
 
 	if (fault_signal_pending(fault, regs))
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index a2bfe587b491..1a3d4c4ca28b 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -214,7 +214,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 01b168a90434..b1db39784db9 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -152,7 +152,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c
index 8fb73f6401a0..d0ecc8fb5b23 100644
--- a/arch/nds32/mm/fault.c
+++ b/arch/nds32/mm/fault.c
@@ -206,7 +206,7 @@ void do_page_fault(unsigned long entry, unsigned long addr,
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, addr, flags);
+	fault = handle_mm_fault(vma, addr, flags, NULL);
 
 	/*
 	 * If we need to retry but a fatal signal is pending, handle the
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 4112ef0e247e..86beb9a2698e 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -131,7 +131,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index d2224ccca294..3daa491d1edb 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -159,7 +159,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 66ac0719bd49..e32d06928c24 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -302,7 +302,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 	 * fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index b83abbead4a2..2d0276abe0a6 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -64,7 +64,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 	}
 
 	ret = 0;
-	*flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0);
+	*flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL);
 	if (unlikely(*flt & VM_FAULT_ERROR)) {
 		if (*flt & VM_FAULT_OOM) {
 			ret = -ENOMEM;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 925a7231abb3..c6a5225a3521 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -511,7 +511,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	major |= fault & VM_FAULT_MAJOR;
 
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 5873835a3e6b..30c1124d0fb6 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -109,7 +109,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, addr, flags);
+	fault = handle_mm_fault(vma, addr, flags, NULL);
 
 	/*
 	 * If we need to retry but a fatal signal is pending, handle the
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index aebf9183bedd..ad783aaaf649 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -476,7 +476,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 	if (fault_signal_pending(fault, regs)) {
 		fault = VM_FAULT_SIGNAL;
 		if (flags & FAULT_FLAG_RETRY_NOWAIT)
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index fbe1f2fe9a8c..3c0a11827f7e 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -482,7 +482,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR)))
 		if (mm_fault_error(regs, error_code, address, fault))
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index cfef656eda0f..06af03db4417 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -234,7 +234,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -410,7 +410,7 @@ static void force_user_fault(unsigned long address, int write)
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
 	}
-	switch (handle_mm_fault(vma, address, flags)) {
+	switch (handle_mm_fault(vma, address, flags, NULL)) {
 	case VM_FAULT_SIGBUS:
 	case VM_FAULT_OOM:
 		goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index a3806614e4dc..9ebee14ee893 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -422,7 +422,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 			goto bad_area;
 	}
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		goto exit_exception;
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 2b3afa354a90..8d9870d76da1 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -71,7 +71,7 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	do {
 		vm_fault_t fault;
 
-		fault = handle_mm_fault(vma, address, flags);
+		fault = handle_mm_fault(vma, address, flags, NULL);
 
 		if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 			goto out_nosemaphore;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 0c7643d9f7cb..e1bf5555d80a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1291,7 +1291,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 	 * userland). The return to userland is identified whenever
 	 * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 	major |= fault & VM_FAULT_MAJOR;
 
 	/* Quick path to respond to signals */
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index c128dcc7c85b..e72c8c1359a6 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -107,7 +107,7 @@ void do_page_fault(struct pt_regs *regs)
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, NULL);
 
 	if (fault_signal_pending(fault, regs))
 		return;
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index e4b025c5637c..c259108ab6dd 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -495,7 +495,7 @@ static void do_fault(struct work_struct *work)
 	if (access_error(vma, fault))
 		goto out;
 
-	ret = handle_mm_fault(vma, address, flags);
+	ret = handle_mm_fault(vma, address, flags, NULL);
 out:
 	mmap_read_unlock(mm);
 
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 6c87c807a0ab..5ae59a6ad681 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -872,7 +872,8 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 			goto invalid;
 
 		ret = handle_mm_fault(vma, address,
-				      req->wr_req ? FAULT_FLAG_WRITE : 0);
+				      req->wr_req ? FAULT_FLAG_WRITE : 0,
+				      NULL);
 		if (ret & VM_FAULT_ERROR)
 			goto invalid;
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f97b10117d44..ec0ffb423769 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -38,6 +38,7 @@ struct file_ra_state;
 struct user_struct;
 struct writeback_control;
 struct bdi_writeback;
+struct pt_regs;
 
 void init_mm_internals(void);
 
@@ -1658,7 +1659,8 @@ int invalidate_inode_page(struct page *page);
 
 #ifdef CONFIG_MMU
 extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
-			unsigned long address, unsigned int flags);
+				  unsigned long address, unsigned int flags,
+				  struct pt_regs *regs);
 extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 			    unsigned long address, unsigned int fault_flags,
 			    bool *unlocked);
@@ -1668,7 +1670,8 @@ void unmap_mapping_range(struct address_space *mapping,
 		loff_t const holebegin, loff_t const holelen, int even_cows);
 #else
 static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
-		unsigned long address, unsigned int flags)
+					 unsigned long address, unsigned int flags,
+					 struct pt_regs *regs)
 {
 	/* should never happen if there's no MMU */
 	BUG();
diff --git a/mm/gup.c b/mm/gup.c
index e9d1d0cc18f0..ae7121d729fa 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -884,7 +884,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 		fault_flags |= FAULT_FLAG_TRIED;
 	}
 
-	ret = handle_mm_fault(vma, address, fault_flags);
+	ret = handle_mm_fault(vma, address, fault_flags, NULL);
 	if (ret & VM_FAULT_ERROR) {
 		int err = vm_fault_to_errno(ret, *flags);
 
@@ -1238,7 +1238,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 	    fatal_signal_pending(current))
 		return -EINTR;
 
-	ret = handle_mm_fault(vma, address, fault_flags);
+	ret = handle_mm_fault(vma, address, fault_flags, NULL);
 	major |= ret & VM_FAULT_MAJOR;
 	if (ret & VM_FAULT_ERROR) {
 		int err = vm_fault_to_errno(ret, 0);
diff --git a/mm/hmm.c b/mm/hmm.c
index bb279319bf40..943cb2ba4442 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -75,7 +75,8 @@ static int hmm_vma_fault(unsigned long addr, unsigned long end,
 	}
 
 	for (; addr < end; addr += PAGE_SIZE)
-		if (handle_mm_fault(vma, addr, fault_flags) & VM_FAULT_ERROR)
+		if (handle_mm_fault(vma, addr, fault_flags, NULL) &
+		    VM_FAULT_ERROR)
 			return -EFAULT;
 	return -EBUSY;
 }
diff --git a/mm/ksm.c b/mm/ksm.c
index 217842a66912..0aa2247bddd7 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -480,7 +480,8 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 			break;
 		if (PageKsm(page))
 			ret = handle_mm_fault(vma, addr,
-					FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE);
+					      FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE,
+					      NULL);
 		else
 			ret = VM_FAULT_WRITE;
 		put_page(page);
diff --git a/mm/memory.c b/mm/memory.c
index 325bb575e7ec..9b7d35734caa 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -71,6 +71,8 @@
 #include <linux/dax.h>
 #include <linux/oom.h>
 #include <linux/numa.h>
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
 
 #include <trace/events/kmem.h>
 
@@ -4356,6 +4358,64 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 	return handle_pte_fault(&vmf);
 }
 
+/**
+ * mm_account_fault - Do page fault accountings
+ *
+ * @regs: the pt_regs struct pointer.  When set to NULL, will skip accounting
+ *        of perf event counters, but we'll still do the per-task accounting to
+ *        the task who triggered this page fault.
+ * @address: the faulted address.
+ * @flags: the fault flags.
+ * @ret: the fault retcode.
+ *
+ * This will take care of most of the page fault accountings.  Meanwhile, it
+ * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter
+ * updates.  However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should
+ * still be in per-arch page fault handlers at the entry of page fault.
+ */
+static inline void mm_account_fault(struct pt_regs *regs,
+				    unsigned long address, unsigned int flags,
+				    vm_fault_t ret)
+{
+	bool major;
+
+	/*
+	 * We don't do accounting for some specific faults:
+	 *
+	 * - Unsuccessful faults (e.g. when the address wasn't valid).  That
+	 *   includes arch_vma_access_permitted() failing before reaching here.
+	 *   So this is not a "this many hardware page faults" counter.  We
+	 *   should use the hw profiling for that.
+	 *
+	 * - Incomplete faults (VM_FAULT_RETRY).  They will only be counted
+	 *   once they're completed.
+	 */
+	if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY))
+		return;
+
+	/*
+	 * We define the fault as a major fault when the final successful fault
+	 * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't
+	 * handle it immediately previously).
+	 */
+	major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED);
+
+	/*
+	 * If the fault is done for GUP, regs will be NULL, and we will skip
+	 * the fault accounting.
+	 */
+	if (!regs)
+		return;
+
+	if (major) {
+		current->maj_flt++;
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
+	} else {
+		current->min_flt++;
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
+	}
+}
+
 /*
  * By the time we get here, we already hold the mm semaphore
  *
@@ -4363,7 +4423,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
  * return value.  See filemap_fault() and __lock_page_or_retry().
  */
 vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
-		unsigned int flags)
+			   unsigned int flags, struct pt_regs *regs)
 {
 	vm_fault_t ret;
 
@@ -4404,6 +4464,8 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 			mem_cgroup_oom_synchronize(false);
 	}
 
+	mm_account_fault(regs, address, flags, ret);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(handle_mm_fault);

From c0f6eda41f97dbe4e4feda914c18d019b9b9fccd Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:37:49 -0700
Subject: [PATCH 451/474] mm/alpha: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().

Add the missing PERF_COUNT_SW_PAGE_FAULTS perf events too.  Note, the
other two perf events (PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN]) were done in
handle_mm_fault().

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Link: http://lkml.kernel.org/r/20200707225021.200906-3-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/mm/fault.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 1983e43a5e2f..09172f017efc 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -25,6 +25,7 @@
 #include <linux/interrupt.h>
 #include <linux/extable.h>
 #include <linux/uaccess.h>
+#include <linux/perf_event.h>
 
 extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
 
@@ -116,6 +117,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 #endif
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
@@ -148,7 +150,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	/* If for any reason at all we couldn't handle the fault,
 	   make sure we exit gracefully rather than endlessly redo
 	   the fault.  */
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -164,10 +166,6 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	}
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 

From 52e3f8d03052036ce97296915a3746421a1da1d0 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:37:52 -0700
Subject: [PATCH 452/474] mm/arc: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Fix PERF_COUNT_SW_PAGE_FAULTS perf event manually for page fault retries,
by moving it before taking mmap_sem.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Vineet Gupta <vgupta@synopsys.com>
Link: http://lkml.kernel.org/r/20200707225021.200906-4-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arc/mm/fault.c | 18 +++---------------
 1 file changed, 3 insertions(+), 15 deletions(-)

diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 587dea524e6b..f5657cb68e4f 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -105,6 +105,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 	if (write)
 		flags |= FAULT_FLAG_WRITE;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 
@@ -130,7 +131,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 		goto bad_area;
 	}
 
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
@@ -155,22 +156,9 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 	 * Major/minor page fault accounting
 	 * (in case of retry we only land here once)
 	 */
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
-
-	if (likely(!(fault & VM_FAULT_ERROR))) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-				      regs, address);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-				      regs, address);
-		}
-
+	if (likely(!(fault & VM_FAULT_ERROR)))
 		/* Normal return path: fault Handled Gracefully */
 		return;
-	}
 
 	if (!user_mode(regs))
 		goto no_context;

From 79fea6c6548e28400d7870c61477d35aecb7baf8 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:37:54 -0700
Subject: [PATCH 453/474] mm/arm: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.  To do this, we need to pass
the pt_regs pointer into __do_page_fault().

Fix PERF_COUNT_SW_PAGE_FAULTS perf event manually for page fault retries,
by moving it before taking mmap_sem.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Will Deacon <will@kernel.org>
Link: http://lkml.kernel.org/r/20200707225021.200906-5-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/mm/fault.c | 25 ++++++-------------------
 1 file changed, 6 insertions(+), 19 deletions(-)

diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 01a8e0f8fef7..efa402025031 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -202,7 +202,8 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
 
 static vm_fault_t __kprobes
 __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
-		unsigned int flags, struct task_struct *tsk)
+		unsigned int flags, struct task_struct *tsk,
+		struct pt_regs *regs)
 {
 	struct vm_area_struct *vma;
 	vm_fault_t fault;
@@ -224,7 +225,7 @@ __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
 		goto out;
 	}
 
-	return handle_mm_fault(vma, addr & PAGE_MASK, flags, NULL);
+	return handle_mm_fault(vma, addr & PAGE_MASK, flags, regs);
 
 check_stack:
 	/* Don't allow expansion below FIRST_USER_ADDRESS */
@@ -266,6 +267,8 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
 		flags |= FAULT_FLAG_WRITE;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
 	/*
 	 * As per x86, we may deadlock here.  However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -290,7 +293,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 #endif
 	}
 
-	fault = __do_page_fault(mm, addr, fsr, flags, tsk);
+	fault = __do_page_fault(mm, addr, fsr, flags, tsk, regs);
 
 	/* If we need to retry but a fatal signal is pending, handle the
 	 * signal first. We do not need to release the mmap_lock because
@@ -302,23 +305,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		return 0;
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
-
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 	if (!(fault & VM_FAULT_ERROR) && flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-					regs, addr);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-					regs, addr);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 			goto retry;

From 6a1bb025d28e1026fead73b7b33e2dfccba3f4d2 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:37:57 -0700
Subject: [PATCH 454/474] mm/arm64: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.  To do this, we pass pt_regs
pointer into __do_page_fault().

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Link: http://lkml.kernel.org/r/20200707225021.200906-6-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/mm/fault.c | 29 ++++++-----------------------
 1 file changed, 6 insertions(+), 23 deletions(-)

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index be29f4076fe3..f07333e86c2f 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -404,7 +404,8 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
 #define VM_FAULT_BADACCESS	0x020000
 
 static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
-			   unsigned int mm_flags, unsigned long vm_flags)
+				  unsigned int mm_flags, unsigned long vm_flags,
+				  struct pt_regs *regs)
 {
 	struct vm_area_struct *vma = find_vma(mm, addr);
 
@@ -428,7 +429,7 @@ static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
 	 */
 	if (!(vma->vm_flags & vm_flags))
 		return VM_FAULT_BADACCESS;
-	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags, NULL);
+	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags, regs);
 }
 
 static bool is_el0_instruction_abort(unsigned int esr)
@@ -450,7 +451,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 {
 	const struct fault_info *inf;
 	struct mm_struct *mm = current->mm;
-	vm_fault_t fault, major = 0;
+	vm_fault_t fault;
 	unsigned long vm_flags = VM_ACCESS_FLAGS;
 	unsigned int mm_flags = FAULT_FLAG_DEFAULT;
 
@@ -516,8 +517,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 #endif
 	}
 
-	fault = __do_page_fault(mm, addr, mm_flags, vm_flags);
-	major |= fault & VM_FAULT_MAJOR;
+	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, regs);
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
@@ -538,25 +538,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	 * Handle the "normal" (no error) case first.
 	 */
 	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
-			      VM_FAULT_BADACCESS)))) {
-		/*
-		 * Major/minor page fault accounting is only done
-		 * once. If we go through a retry, it is extremely
-		 * likely that the page will be found in page cache at
-		 * that point.
-		 */
-		if (major) {
-			current->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
-				      addr);
-		} else {
-			current->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
-				      addr);
-		}
-
+			      VM_FAULT_BADACCESS))))
 		return 0;
-	}
 
 	/*
 	 * If we are in kernel mode at this point, we have no context to

From a2a9e439baf8aca2af1e614fab7956c09091a6d1 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:00 -0700
Subject: [PATCH 455/474] mm/csky: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Guo Ren <guoren@kernel.org>
Link: http://lkml.kernel.org/r/20200707225021.200906-7-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/csky/mm/fault.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c
index b252e6e4d32f..081b178b41b1 100644
--- a/arch/csky/mm/fault.c
+++ b/arch/csky/mm/fault.c
@@ -151,7 +151,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
 	 * the fault.
 	 */
 	fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0,
-				NULL);
+				regs);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -161,16 +161,6 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
 			goto bad_area;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR) {
-		tsk->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
-			      address);
-	} else {
-		tsk->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
-			      address);
-	}
-
 	mmap_read_unlock(mm);
 	return;
 

From e08157c3c4239fac29879143019c96498ba9c2bc Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:03 -0700
Subject: [PATCH 456/474] mm/hexagon: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Add the missing PERF_COUNT_SW_PAGE_FAULTS perf events too.  Note, the
other two perf events (PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN]) were done in
handle_mm_fault().

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Brian Cain <bcain@codeaurora.org>
Link: http://lkml.kernel.org/r/20200707225021.200906-8-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/hexagon/mm/vm_fault.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index f12f330e7946..ef32c5a84ff3 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -18,6 +18,7 @@
 #include <linux/signal.h>
 #include <linux/extable.h>
 #include <linux/hardirq.h>
+#include <linux/perf_event.h>
 
 /*
  * Decode of hardware exception sends us to one of several
@@ -53,6 +54,8 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
@@ -88,7 +91,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 		break;
 	}
 
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -96,10 +99,6 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 	/* The most common case -- we are done. */
 	if (likely(!(fault & VM_FAULT_ERROR))) {
 		if (flags & FAULT_FLAG_ALLOW_RETRY) {
-			if (fault & VM_FAULT_MAJOR)
-				current->maj_flt++;
-			else
-				current->min_flt++;
 			if (fault & VM_FAULT_RETRY) {
 				flags |= FAULT_FLAG_TRIED;
 				goto retry;

From b444eed891cf8656af1f59d239f77c5338481774 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:06 -0700
Subject: [PATCH 457/474] mm/ia64: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Add the missing PERF_COUNT_SW_PAGE_FAULTS perf events too.  Note, the
other two perf events (PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN]) were done in
handle_mm_fault().

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: "Luck, Tony" <tony.luck@intel.com>
Link: http://lkml.kernel.org/r/20200707225021.200906-9-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/mm/fault.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index abf2808f9b4b..cd9766d2b6e0 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -14,6 +14,7 @@
 #include <linux/kdebug.h>
 #include <linux/prefetch.h>
 #include <linux/uaccess.h>
+#include <linux/perf_event.h>
 
 #include <asm/processor.h>
 #include <asm/exception.h>
@@ -105,6 +106,8 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 		flags |= FAULT_FLAG_USER;
 	if (mask & VM_WRITE)
 		flags |= FAULT_FLAG_WRITE;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 
@@ -143,7 +146,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	 * sure we exit gracefully rather than endlessly redo the
 	 * fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -166,10 +169,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	}
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 

From e1c17f627b4232e2c7e9edb7151fa60a746150ee Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:09 -0700
Subject: [PATCH 458/474] mm/m68k: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Add the missing PERF_COUNT_SW_PAGE_FAULTS perf events too.  Note, the
other two perf events (PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN]) were done in
handle_mm_fault().

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Link: http://lkml.kernel.org/r/20200707225021.200906-10-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/m68k/mm/fault.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 08b35a318ebe..795f483b1050 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -12,6 +12,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
+#include <linux/perf_event.h>
 
 #include <asm/setup.h>
 #include <asm/traps.h>
@@ -84,6 +85,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 
@@ -134,7 +137,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 	pr_debug("handle_mm_fault returns %x\n", fault);
 
 	if (fault_signal_pending(fault, regs))
@@ -150,16 +153,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 		BUG();
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 

From aeb6aefc3129307858e4d5a4b73ae28f1871ae05 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:12 -0700
Subject: [PATCH 459/474] mm/microblaze: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Add the missing PERF_COUNT_SW_PAGE_FAULTS perf events too.  Note, the
other two perf events (PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN]) were done in
handle_mm_fault().

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Simek <monstr@monstr.eu>
Link: http://lkml.kernel.org/r/20200707225021.200906-11-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/microblaze/mm/fault.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 1a3d4c4ca28b..b3fed2cecf84 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -28,6 +28,7 @@
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
+#include <linux/perf_event.h>
 
 #include <asm/page.h>
 #include <asm/mmu.h>
@@ -121,6 +122,8 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -214,7 +217,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -230,10 +233,6 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	}
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (unlikely(fault & VM_FAULT_MAJOR))
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 

From 2558fd7f5c3eda31d4474c7cdc8dc4b3bb6526f5 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:15 -0700
Subject: [PATCH 460/474] mm/mips: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Fix PERF_COUNT_SW_PAGE_FAULTS perf event manually for page fault retries,
by moving it before taking mmap_sem.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Link: http://lkml.kernel.org/r/20200707225021.200906-12-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/mips/mm/fault.c | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index b1db39784db9..7c871b14e74a 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -96,6 +96,8 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
@@ -152,12 +154,11 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -168,15 +169,6 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 		BUG();
 	}
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-						  regs, address);
-			tsk->maj_flt++;
-		} else {
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-						  regs, address);
-			tsk->min_flt++;
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 

From daf7bf5d90397bc0f3d7b45030461f55eb9c74fa Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:19 -0700
Subject: [PATCH 461/474] mm/nds32: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Fix PERF_COUNT_SW_PAGE_FAULTS perf event manually for page fault retries,
by moving it before taking mmap_sem.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Greentime Hu <green.hu@gmail.com>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Link: http://lkml.kernel.org/r/20200707225021.200906-13-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/nds32/mm/fault.c | 19 +++----------------
 1 file changed, 3 insertions(+), 16 deletions(-)

diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c
index d0ecc8fb5b23..f02524eb6d56 100644
--- a/arch/nds32/mm/fault.c
+++ b/arch/nds32/mm/fault.c
@@ -121,6 +121,8 @@ void do_page_fault(unsigned long entry, unsigned long addr,
 	if (unlikely(faulthandler_disabled() || !mm))
 		goto no_context;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
 	/*
 	 * As per x86, we may deadlock here. However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -206,7 +208,7 @@ void do_page_fault(unsigned long entry, unsigned long addr,
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, addr, flags, NULL);
+	fault = handle_mm_fault(vma, addr, flags, regs);
 
 	/*
 	 * If we need to retry but a fatal signal is pending, handle the
@@ -228,22 +230,7 @@ void do_page_fault(unsigned long entry, unsigned long addr,
 			goto bad_area;
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the initial
-	 * attempt. If we go through a retry, it is extremely likely that the
-	 * page will be found in page cache at that point.
-	 */
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
-				      1, regs, addr);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
-				      1, regs, addr);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 

From 4487dcf9b75180eb5115c196ca9bd6ebefade5b3 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:22 -0700
Subject: [PATCH 462/474] mm/nios2: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Add the missing PERF_COUNT_SW_PAGE_FAULTS perf events too.  Note, the
other two perf events (PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN]) were done in
handle_mm_fault().

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Ley Foon Tan <ley.foon.tan@intel.com>
Link: http://lkml.kernel.org/r/20200707225021.200906-14-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/nios2/mm/fault.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 86beb9a2698e..9476feecf512 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -24,6 +24,7 @@
 #include <linux/mm.h>
 #include <linux/extable.h>
 #include <linux/uaccess.h>
+#include <linux/perf_event.h>
 
 #include <asm/mmu_context.h>
 #include <asm/traps.h>
@@ -83,6 +84,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
 	if (!mmap_read_trylock(mm)) {
 		if (!user_mode(regs) && !search_exception_tables(regs->ea))
 			goto bad_area_nosemaphore;
@@ -131,7 +134,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -146,16 +149,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
 		BUG();
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 

From 38caa902dccad61e02273c18a633fc5be91aeca5 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:25 -0700
Subject: [PATCH 463/474] mm/openrisc: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Add the missing PERF_COUNT_SW_PAGE_FAULTS perf events too.  Note, the
other two perf events (PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN]) were done in
handle_mm_fault().

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Stafford Horne <shorne@gmail.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Link: http://lkml.kernel.org/r/20200707225021.200906-15-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/openrisc/mm/fault.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index 3daa491d1edb..ca97d9baab51 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -15,6 +15,7 @@
 #include <linux/interrupt.h>
 #include <linux/extable.h>
 #include <linux/sched/signal.h>
+#include <linux/perf_event.h>
 
 #include <linux/uaccess.h>
 #include <asm/siginfo.h>
@@ -103,6 +104,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (in_interrupt() || !mm)
 		goto no_context;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
@@ -159,7 +162,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -176,10 +179,6 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
 		/*RGD modeled on Cris */
-		if (fault & VM_FAULT_MAJOR)
-			tsk->maj_flt++;
-		else
-			tsk->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 

From af8a7926273645dc81f9e7f5c3e18136abebf05b Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:28 -0700
Subject: [PATCH 464/474] mm/parisc: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Add the missing PERF_COUNT_SW_PAGE_FAULTS perf events too.  Note, the
other two perf events (PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN]) were done in
handle_mm_fault().

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Helge Deller <deller@gmx.de>
Link: http://lkml.kernel.org/r/20200707225021.200906-16-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/parisc/mm/fault.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index e32d06928c24..4bfe2da9fbe3 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -18,6 +18,7 @@
 #include <linux/extable.h>
 #include <linux/uaccess.h>
 #include <linux/hugetlb.h>
+#include <linux/perf_event.h>
 
 #include <asm/traps.h>
 
@@ -281,6 +282,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 	acc_type = parisc_acctyp(code, regs->iir);
 	if (acc_type & VM_WRITE)
 		flags |= FAULT_FLAG_WRITE;
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma_prev(mm, address, &prev_vma);
@@ -302,7 +304,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 	 * fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -323,10 +325,6 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 		BUG();
 	}
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			/*
 			 * No need to mmap_read_unlock(mm) as we would

From 428fdc094492e720c342f1c934e7972cbc328d13 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:31 -0700
Subject: [PATCH 465/474] mm/powerpc: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Link: http://lkml.kernel.org/r/20200707225021.200906-17-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/mm/fault.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index c6a5225a3521..0add963a849b 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -511,7 +511,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	major |= fault & VM_FAULT_MAJOR;
 
@@ -537,14 +537,9 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 	/*
 	 * Major/minor page fault accounting.
 	 */
-	if (major) {
-		current->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
+	if (major)
 		cmo_account_page_fault();
-	} else {
-		current->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
-	}
+
 	return 0;
 }
 NOKPROBE_SYMBOL(__do_page_fault);

From 5ac365a458902214adfbe3567c94e114cc91cde6 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:34 -0700
Subject: [PATCH 466/474] mm/riscv: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Pekka Enberg <penberg@kernel.org>
Acked-by: Palmer Dabbelt <palmerdabbelt@google.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Link: http://lkml.kernel.org/r/20200707225021.200906-18-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/riscv/mm/fault.c | 16 +---------------
 1 file changed, 1 insertion(+), 15 deletions(-)

diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 30c1124d0fb6..716d64e36f83 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -109,7 +109,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, addr, flags, NULL);
+	fault = handle_mm_fault(vma, addr, flags, regs);
 
 	/*
 	 * If we need to retry but a fatal signal is pending, handle the
@@ -127,21 +127,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 		BUG();
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
-				      1, regs, addr);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
-				      1, regs, addr);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 

From 35e45f3e5a1fe652df2153f2b1c7dd234d448356 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:37 -0700
Subject: [PATCH 467/474] mm/s390: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Acked-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Link: http://lkml.kernel.org/r/20200707225021.200906-19-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/mm/fault.c | 16 +---------------
 1 file changed, 1 insertion(+), 15 deletions(-)

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index ad783aaaf649..4c8c063bce5b 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -476,7 +476,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 	if (fault_signal_pending(fault, regs)) {
 		fault = VM_FAULT_SIGNAL;
 		if (flags & FAULT_FLAG_RETRY_NOWAIT)
@@ -486,21 +486,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
 	if (unlikely(fault & VM_FAULT_ERROR))
 		goto out_up;
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-				      regs, address);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-				      regs, address);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			if (IS_ENABLED(CONFIG_PGSTE) && gmap &&
 			    (flags & FAULT_FLAG_RETRY_NOWAIT)) {

From 105f886220e944b6aa01accfad59af49341703c4 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:40 -0700
Subject: [PATCH 468/474] mm/sh: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Link: http://lkml.kernel.org/r/20200707225021.200906-20-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/sh/mm/fault.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 3c0a11827f7e..482668a2f6d3 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -482,22 +482,13 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR)))
 		if (mm_fault_error(regs, error_code, address, fault))
 			return;
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-				      regs, address);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-				      regs, address);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 

From 56e10e6ab11924b19b7c9583750fdd4e440e25c8 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:43 -0700
Subject: [PATCH 469/474] mm/sparc32: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: David S. Miller <davem@davemloft.net>
Link: http://lkml.kernel.org/r/20200707225021.200906-21-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/sparc/mm/fault_32.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 06af03db4417..8071bfd72349 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -234,7 +234,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -250,15 +250,6 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	}
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			current->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
-				      1, regs, address);
-		} else {
-			current->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
-				      1, regs, address);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 

From f08147df4092dd5093b85dbccbd34a7843fb60bf Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:46 -0700
Subject: [PATCH 470/474] mm/sparc64: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: David S. Miller <davem@davemloft.net>
Link: http://lkml.kernel.org/r/20200707225021.200906-22-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/sparc/mm/fault_64.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 9ebee14ee893..0a6bcc85fba7 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -422,7 +422,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 			goto bad_area;
 	}
 
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		goto exit_exception;
@@ -438,15 +438,6 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 	}
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			current->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
-				      1, regs, address);
-		} else {
-			current->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
-				      1, regs, address);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 

From 968614fc7b8410e1ee99d0111015a1bf3e955f64 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:49 -0700
Subject: [PATCH 471/474] mm/x86: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/20200707225021.200906-23-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/mm/fault.c | 17 ++---------------
 1 file changed, 2 insertions(+), 15 deletions(-)

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index e1bf5555d80a..35f1498e9832 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1139,7 +1139,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
 	struct mm_struct *mm;
-	vm_fault_t fault, major = 0;
+	vm_fault_t fault;
 	unsigned int flags = FAULT_FLAG_DEFAULT;
 
 	tsk = current;
@@ -1291,8 +1291,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 	 * userland). The return to userland is identified whenever
 	 * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags.
 	 */
-	fault = handle_mm_fault(vma, address, flags, NULL);
-	major |= fault & VM_FAULT_MAJOR;
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
@@ -1319,18 +1318,6 @@ void do_user_addr_fault(struct pt_regs *regs,
 		return;
 	}
 
-	/*
-	 * Major/minor page fault accounting. If any of the events
-	 * returned VM_FAULT_MAJOR, we account it as a major fault.
-	 */
-	if (major) {
-		tsk->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
-	} else {
-		tsk->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
-	}
-
 	check_v8086_mode(regs, address, tsk);
 }
 NOKPROBE_SYMBOL(do_user_addr_fault);

From 484e51e4af528a408b8e0f2db4865625169279cf Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:53 -0700
Subject: [PATCH 472/474] mm/xtensa: use general page fault accounting

Use the general page fault accounting by passing regs into
handle_mm_fault().  It naturally solve the issue of multiple page fault
accounting when page fault retry happened.

Remove the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf events because it's
now also done in handle_mm_fault().

Move the PERF_COUNT_SW_PAGE_FAULTS event higher before taking mmap_sem for
the fault, then it'll match with the rest of the archs.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Max Filippov <jcmvbkbc@gmail.com>
Cc: Chris Zankel <chris@zankel.net>
Link: http://lkml.kernel.org/r/20200707225021.200906-24-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/xtensa/mm/fault.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index e72c8c1359a6..7666408ce12a 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -72,6 +72,9 @@ void do_page_fault(struct pt_regs *regs)
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
@@ -107,7 +110,7 @@ void do_page_fault(struct pt_regs *regs)
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags, NULL);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -122,10 +125,6 @@ void do_page_fault(struct pt_regs *regs)
 		BUG();
 	}
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
@@ -139,12 +138,6 @@ void do_page_fault(struct pt_regs *regs)
 	}
 
 	mmap_read_unlock(mm);
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
-	if (flags & VM_FAULT_MAJOR)
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
-	else
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
-
 	return;
 
 	/* Something tried to access memory that isn't in our memory map..

From a2beb5f1efede6924a4258462a5660572e6ca864 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:38:57 -0700
Subject: [PATCH 473/474] mm: clean up the last pieces of page fault
 accountings

Here're the last pieces of page fault accounting that were still done
outside handle_mm_fault() where we still have regs==NULL when calling
handle_mm_fault():

arch/powerpc/mm/copro_fault.c:   copro_handle_mm_fault
arch/sparc/mm/fault_32.c:        force_user_fault
arch/um/kernel/trap.c:           handle_page_fault
mm/gup.c:                        faultin_page
                                 fixup_user_fault
mm/hmm.c:                        hmm_vma_fault
mm/ksm.c:                        break_ksm

Some of them has the issue of duplicated accounting for page fault
retries.  Some of them didn't do the accounting at all.

This patch cleans all these up by letting handle_mm_fault() to do per-task
page fault accounting even if regs==NULL (though we'll still skip the perf
event accountings).  With that, we can safely remove all the outliers now.

There's another functional change in that now we account the page faults
to the caller of gup, rather than the task_struct that passed into the gup
code.  More information of this can be found at [1].

After this patch, below things should never be touched again outside
handle_mm_fault():

  - task_struct.[maj|min]_flt
  - PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN]

[1] https://lore.kernel.org/lkml/CAHk-=wj_V2Tps2QrMn20_W0OJF9xqNh52XSGA42s-ZJ8Y+GyKw@mail.gmail.com/

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Cain <bcain@codeaurora.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Ley Foon Tan <ley.foon.tan@intel.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Rich Felker <dalias@libc.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/20200707225021.200906-25-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/mm/copro_fault.c |  5 -----
 arch/um/kernel/trap.c         |  4 ----
 mm/gup.c                      | 13 -------------
 mm/memory.c                   | 17 ++++++++++-------
 4 files changed, 10 insertions(+), 29 deletions(-)

diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 2d0276abe0a6..8acd00178956 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -76,11 +76,6 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 		BUG();
 	}
 
-	if (*flt & VM_FAULT_MAJOR)
-		current->maj_flt++;
-	else
-		current->min_flt++;
-
 out_unlock:
 	mmap_read_unlock(mm);
 	return ret;
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 8d9870d76da1..ad12f78bda7e 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -88,10 +88,6 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 			BUG();
 		}
 		if (flags & FAULT_FLAG_ALLOW_RETRY) {
-			if (fault & VM_FAULT_MAJOR)
-				current->maj_flt++;
-			else
-				current->min_flt++;
 			if (fault & VM_FAULT_RETRY) {
 				flags |= FAULT_FLAG_TRIED;
 
diff --git a/mm/gup.c b/mm/gup.c
index ae7121d729fa..d5d44c68fa19 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -893,13 +893,6 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 		BUG();
 	}
 
-	if (tsk) {
-		if (ret & VM_FAULT_MAJOR)
-			tsk->maj_flt++;
-		else
-			tsk->min_flt++;
-	}
-
 	if (ret & VM_FAULT_RETRY) {
 		if (locked && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
 			*locked = 0;
@@ -1255,12 +1248,6 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 		goto retry;
 	}
 
-	if (tsk) {
-		if (major)
-			tsk->maj_flt++;
-		else
-			tsk->min_flt++;
-	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(fixup_user_fault);
diff --git a/mm/memory.c b/mm/memory.c
index 9b7d35734caa..2b7f0e00f312 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4400,20 +4400,23 @@ static inline void mm_account_fault(struct pt_regs *regs,
 	 */
 	major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED);
 
+	if (major)
+		current->maj_flt++;
+	else
+		current->min_flt++;
+
 	/*
-	 * If the fault is done for GUP, regs will be NULL, and we will skip
-	 * the fault accounting.
+	 * If the fault is done for GUP, regs will be NULL.  We only do the
+	 * accounting for the per thread fault counters who triggered the
+	 * fault, and we skip the perf event updates.
 	 */
 	if (!regs)
 		return;
 
-	if (major) {
-		current->maj_flt++;
+	if (major)
 		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
-	} else {
-		current->min_flt++;
+	else
 		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
-	}
 }
 
 /*

From 64019a2e467a288a16b65ab55ddcbf58c1b00187 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 11 Aug 2020 18:39:01 -0700
Subject: [PATCH 474/474] mm/gup: remove task_struct pointer for all gup code

After the cleanup of page fault accounting, gup does not need to pass
task_struct around any more.  Remove that parameter in the whole gup
stack.

Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Link: http://lkml.kernel.org/r/20200707225021.200906-26-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arc/kernel/process.c                   |   2 +-
 arch/s390/kvm/interrupt.c                   |   2 +-
 arch/s390/kvm/kvm-s390.c                    |   2 +-
 arch/s390/kvm/priv.c                        |   8 +-
 arch/s390/mm/gmap.c                         |   4 +-
 drivers/gpu/drm/i915/gem/i915_gem_userptr.c |   2 +-
 drivers/infiniband/core/umem_odp.c          |   2 +-
 drivers/vfio/vfio_iommu_type1.c             |   4 +-
 fs/exec.c                                   |   2 +-
 include/linux/mm.h                          |   9 +-
 kernel/events/uprobes.c                     |   6 +-
 kernel/futex.c                              |   2 +-
 mm/gup.c                                    | 101 ++++++++------------
 mm/memory.c                                 |   2 +-
 mm/process_vm_access.c                      |   2 +-
 security/tomoyo/domain.c                    |   2 +-
 virt/kvm/async_pf.c                         |   2 +-
 virt/kvm/kvm_main.c                         |   2 +-
 18 files changed, 69 insertions(+), 87 deletions(-)

diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index e12c80d71b78..efeba1fe7252 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -91,7 +91,7 @@ SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
 		 goto fail;
 
 	mmap_read_lock(current->mm);
-	ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr,
+	ret = fixup_user_fault(current->mm, (unsigned long) uaddr,
 			       FAULT_FLAG_WRITE, NULL);
 	mmap_read_unlock(current->mm);
 
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 1608fd99bbee..2f177298c663 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2768,7 +2768,7 @@ static struct page *get_map_page(struct kvm *kvm, u64 uaddr)
 	struct page *page = NULL;
 
 	mmap_read_lock(kvm->mm);
-	get_user_pages_remote(NULL, kvm->mm, uaddr, 1, FOLL_WRITE,
+	get_user_pages_remote(kvm->mm, uaddr, 1, FOLL_WRITE,
 			      &page, NULL, NULL);
 	mmap_read_unlock(kvm->mm);
 	return page;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 66da278a67fb..6b74b92c1a58 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1892,7 +1892,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 
 		r = set_guest_storage_key(current->mm, hva, keys[i], 0);
 		if (r) {
-			r = fixup_user_fault(current, current->mm, hva,
+			r = fixup_user_fault(current->mm, hva,
 					     FAULT_FLAG_WRITE, &unlocked);
 			if (r)
 				break;
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 2f721a923b54..cd74989ce0b0 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -273,7 +273,7 @@ static int handle_iske(struct kvm_vcpu *vcpu)
 	rc = get_guest_storage_key(current->mm, vmaddr, &key);
 
 	if (rc) {
-		rc = fixup_user_fault(current, current->mm, vmaddr,
+		rc = fixup_user_fault(current->mm, vmaddr,
 				      FAULT_FLAG_WRITE, &unlocked);
 		if (!rc) {
 			mmap_read_unlock(current->mm);
@@ -319,7 +319,7 @@ static int handle_rrbe(struct kvm_vcpu *vcpu)
 	mmap_read_lock(current->mm);
 	rc = reset_guest_reference_bit(current->mm, vmaddr);
 	if (rc < 0) {
-		rc = fixup_user_fault(current, current->mm, vmaddr,
+		rc = fixup_user_fault(current->mm, vmaddr,
 				      FAULT_FLAG_WRITE, &unlocked);
 		if (!rc) {
 			mmap_read_unlock(current->mm);
@@ -390,7 +390,7 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 						m3 & SSKE_MC);
 
 		if (rc < 0) {
-			rc = fixup_user_fault(current, current->mm, vmaddr,
+			rc = fixup_user_fault(current->mm, vmaddr,
 					      FAULT_FLAG_WRITE, &unlocked);
 			rc = !rc ? -EAGAIN : rc;
 		}
@@ -1094,7 +1094,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 			rc = cond_set_guest_storage_key(current->mm, vmaddr,
 							key, NULL, nq, mr, mc);
 			if (rc < 0) {
-				rc = fixup_user_fault(current, current->mm, vmaddr,
+				rc = fixup_user_fault(current->mm, vmaddr,
 						      FAULT_FLAG_WRITE, &unlocked);
 				rc = !rc ? -EAGAIN : rc;
 			}
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 190357ff86b3..8747487c50a8 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -649,7 +649,7 @@ int gmap_fault(struct gmap *gmap, unsigned long gaddr,
 		rc = vmaddr;
 		goto out_up;
 	}
-	if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags,
+	if (fixup_user_fault(gmap->mm, vmaddr, fault_flags,
 			     &unlocked)) {
 		rc = -EFAULT;
 		goto out_up;
@@ -879,7 +879,7 @@ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr,
 
 	BUG_ON(gmap_is_shadow(gmap));
 	fault_flags = (prot == PROT_WRITE) ? FAULT_FLAG_WRITE : 0;
-	if (fixup_user_fault(current, mm, vmaddr, fault_flags, &unlocked))
+	if (fixup_user_fault(mm, vmaddr, fault_flags, &unlocked))
 		return -EFAULT;
 	if (unlocked)
 		/* lost mmap_lock, caller has to retry __gmap_translate */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index e946032b13e4..2c2bf24140c9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -469,7 +469,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 					locked = 1;
 				}
 				ret = pin_user_pages_remote
-					(work->task, mm,
+					(mm,
 					 obj->userptr.ptr + pinned * PAGE_SIZE,
 					 npages - pinned,
 					 flags,
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 5e32f61a2fe4..cc6b4befde7c 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -439,7 +439,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 		 * complex (and doesn't gain us much performance in most use
 		 * cases).
 		 */
-		npages = get_user_pages_remote(owning_process, owning_mm,
+		npages = get_user_pages_remote(owning_mm,
 				user_virt, gup_num_pages,
 				flags, local_page_list, NULL, NULL);
 		mmap_read_unlock(owning_mm);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 5e556ac9102a..9d41105bfd01 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -425,7 +425,7 @@ static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm,
 	if (ret) {
 		bool unlocked = false;
 
-		ret = fixup_user_fault(NULL, mm, vaddr,
+		ret = fixup_user_fault(mm, vaddr,
 				       FAULT_FLAG_REMOTE |
 				       (write_fault ?  FAULT_FLAG_WRITE : 0),
 				       &unlocked);
@@ -453,7 +453,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 		flags |= FOLL_WRITE;
 
 	mmap_read_lock(mm);
-	ret = pin_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM,
+	ret = pin_user_pages_remote(mm, vaddr, 1, flags | FOLL_LONGTERM,
 				    page, NULL, NULL);
 	if (ret == 1) {
 		*pfn = page_to_pfn(page[0]);
diff --git a/fs/exec.c b/fs/exec.c
index a57d9785832b..a91003e28eaa 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -217,7 +217,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 	 * We are doing an exec().  'current' is the process
 	 * doing the exec and bprm->mm is the new process's mm.
 	 */
-	ret = get_user_pages_remote(current, bprm->mm, pos, 1, gup_flags,
+	ret = get_user_pages_remote(bprm->mm, pos, 1, gup_flags,
 			&page, NULL, NULL);
 	if (ret <= 0)
 		return NULL;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ec0ffb423769..e7602a3bcef1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1661,7 +1661,7 @@ int invalidate_inode_page(struct page *page);
 extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
 				  unsigned long address, unsigned int flags,
 				  struct pt_regs *regs);
-extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+extern int fixup_user_fault(struct mm_struct *mm,
 			    unsigned long address, unsigned int fault_flags,
 			    bool *unlocked);
 void unmap_mapping_pages(struct address_space *mapping,
@@ -1677,8 +1677,7 @@ static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
 	BUG();
 	return VM_FAULT_SIGBUS;
 }
-static inline int fixup_user_fault(struct task_struct *tsk,
-		struct mm_struct *mm, unsigned long address,
+static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address,
 		unsigned int fault_flags, bool *unlocked)
 {
 	/* should never happen if there's no MMU */
@@ -1704,11 +1703,11 @@ extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
 extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long addr, void *buf, int len, unsigned int gup_flags);
 
-long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+long get_user_pages_remote(struct mm_struct *mm,
 			    unsigned long start, unsigned long nr_pages,
 			    unsigned int gup_flags, struct page **pages,
 			    struct vm_area_struct **vmas, int *locked);
-long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+long pin_user_pages_remote(struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
 			   unsigned int gup_flags, struct page **pages,
 			   struct vm_area_struct **vmas, int *locked);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 49047d479c57..649fd53dc9ad 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -376,7 +376,7 @@ __update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d)
 	if (!vaddr || !d)
 		return -EINVAL;
 
-	ret = get_user_pages_remote(NULL, mm, vaddr, 1,
+	ret = get_user_pages_remote(mm, vaddr, 1,
 			FOLL_WRITE, &page, &vma, NULL);
 	if (unlikely(ret <= 0)) {
 		/*
@@ -477,7 +477,7 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	if (is_register)
 		gup_flags |= FOLL_SPLIT_PMD;
 	/* Read the page with vaddr into memory */
-	ret = get_user_pages_remote(NULL, mm, vaddr, 1, gup_flags,
+	ret = get_user_pages_remote(mm, vaddr, 1, gup_flags,
 				    &old_page, &vma, NULL);
 	if (ret <= 0)
 		return ret;
@@ -2029,7 +2029,7 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	 * but we treat this as a 'remote' access since it is
 	 * essentially a kernel access to the memory.
 	 */
-	result = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &page,
+	result = get_user_pages_remote(mm, vaddr, 1, FOLL_FORCE, &page,
 			NULL, NULL);
 	if (result < 0)
 		return result;
diff --git a/kernel/futex.c b/kernel/futex.c
index 83404124b77b..61e8153e6c76 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -678,7 +678,7 @@ static int fault_in_user_writeable(u32 __user *uaddr)
 	int ret;
 
 	mmap_read_lock(mm);
-	ret = fixup_user_fault(current, mm, (unsigned long)uaddr,
+	ret = fixup_user_fault(mm, (unsigned long)uaddr,
 			       FAULT_FLAG_WRITE, NULL);
 	mmap_read_unlock(mm);
 
diff --git a/mm/gup.c b/mm/gup.c
index d5d44c68fa19..39e58df6925d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -859,7 +859,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
  * does not include FOLL_NOWAIT, the mmap_lock may be released.  If it
  * is, *@locked will be set to 0 and -EBUSY returned.
  */
-static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
+static int faultin_page(struct vm_area_struct *vma,
 		unsigned long address, unsigned int *flags, int *locked)
 {
 	unsigned int fault_flags = 0;
@@ -962,7 +962,6 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 
 /**
  * __get_user_pages() - pin user pages in memory
- * @tsk:	task_struct of target task
  * @mm:		mm_struct of target mm
  * @start:	starting user address
  * @nr_pages:	number of pages from start to pin
@@ -1021,7 +1020,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
  * instead of __get_user_pages. __get_user_pages should be used only if
  * you need some special @gup_flags.
  */
-static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+static long __get_user_pages(struct mm_struct *mm,
 		unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
 		struct vm_area_struct **vmas, int *locked)
@@ -1103,8 +1102,7 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
 		page = follow_page_mask(vma, start, foll_flags, &ctx);
 		if (!page) {
-			ret = faultin_page(tsk, vma, start, &foll_flags,
-					   locked);
+			ret = faultin_page(vma, start, &foll_flags, locked);
 			switch (ret) {
 			case 0:
 				goto retry;
@@ -1178,8 +1176,6 @@ static bool vma_permits_fault(struct vm_area_struct *vma,
 
 /**
  * fixup_user_fault() - manually resolve a user page fault
- * @tsk:	the task_struct to use for page fault accounting, or
- *		NULL if faults are not to be recorded.
  * @mm:		mm_struct of target mm
  * @address:	user address
  * @fault_flags:flags to pass down to handle_mm_fault()
@@ -1207,7 +1203,7 @@ static bool vma_permits_fault(struct vm_area_struct *vma,
  * This function will not return with an unlocked mmap_lock. So it has not the
  * same semantics wrt the @mm->mmap_lock as does filemap_fault().
  */
-int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+int fixup_user_fault(struct mm_struct *mm,
 		     unsigned long address, unsigned int fault_flags,
 		     bool *unlocked)
 {
@@ -1256,8 +1252,7 @@ EXPORT_SYMBOL_GPL(fixup_user_fault);
  * Please note that this function, unlike __get_user_pages will not
  * return 0 for nr_pages > 0 without FOLL_NOWAIT
  */
-static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
-						struct mm_struct *mm,
+static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
 						unsigned long start,
 						unsigned long nr_pages,
 						struct page **pages,
@@ -1290,7 +1285,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 	pages_done = 0;
 	lock_dropped = false;
 	for (;;) {
-		ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages,
+		ret = __get_user_pages(mm, start, nr_pages, flags, pages,
 				       vmas, locked);
 		if (!locked)
 			/* VM_FAULT_RETRY couldn't trigger, bypass */
@@ -1350,7 +1345,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 		}
 
 		*locked = 1;
-		ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED,
+		ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED,
 				       pages, NULL, locked);
 		if (!*locked) {
 			/* Continue to retry until we succeeded */
@@ -1437,7 +1432,7 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 	 * We made sure addr is within a VMA, so the following will
 	 * not result in a stack expansion that recurses back here.
 	 */
-	return __get_user_pages(current, mm, start, nr_pages, gup_flags,
+	return __get_user_pages(mm, start, nr_pages, gup_flags,
 				NULL, NULL, locked);
 }
 
@@ -1521,7 +1516,7 @@ struct page *get_dump_page(unsigned long addr)
 	struct vm_area_struct *vma;
 	struct page *page;
 
-	if (__get_user_pages(current, current->mm, addr, 1,
+	if (__get_user_pages(current->mm, addr, 1,
 			     FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
 			     NULL) < 1)
 		return NULL;
@@ -1530,8 +1525,7 @@ struct page *get_dump_page(unsigned long addr)
 }
 #endif /* CONFIG_ELF_CORE */
 #else /* CONFIG_MMU */
-static long __get_user_pages_locked(struct task_struct *tsk,
-		struct mm_struct *mm, unsigned long start,
+static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
 		unsigned long nr_pages, struct page **pages,
 		struct vm_area_struct **vmas, int *locked,
 		unsigned int foll_flags)
@@ -1596,8 +1590,7 @@ static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
 }
 
 #ifdef CONFIG_CMA
-static long check_and_migrate_cma_pages(struct task_struct *tsk,
-					struct mm_struct *mm,
+static long check_and_migrate_cma_pages(struct mm_struct *mm,
 					unsigned long start,
 					unsigned long nr_pages,
 					struct page **pages,
@@ -1675,7 +1668,7 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk,
 		 * again migrating any new CMA pages which we failed to isolate
 		 * earlier.
 		 */
-		ret = __get_user_pages_locked(tsk, mm, start, nr_pages,
+		ret = __get_user_pages_locked(mm, start, nr_pages,
 						   pages, vmas, NULL,
 						   gup_flags);
 
@@ -1689,8 +1682,7 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk,
 	return ret;
 }
 #else
-static long check_and_migrate_cma_pages(struct task_struct *tsk,
-					struct mm_struct *mm,
+static long check_and_migrate_cma_pages(struct mm_struct *mm,
 					unsigned long start,
 					unsigned long nr_pages,
 					struct page **pages,
@@ -1705,8 +1697,7 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk,
  * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
  * allows us to process the FOLL_LONGTERM flag.
  */
-static long __gup_longterm_locked(struct task_struct *tsk,
-				  struct mm_struct *mm,
+static long __gup_longterm_locked(struct mm_struct *mm,
 				  unsigned long start,
 				  unsigned long nr_pages,
 				  struct page **pages,
@@ -1731,7 +1722,7 @@ static long __gup_longterm_locked(struct task_struct *tsk,
 		flags = memalloc_nocma_save();
 	}
 
-	rc = __get_user_pages_locked(tsk, mm, start, nr_pages, pages,
+	rc = __get_user_pages_locked(mm, start, nr_pages, pages,
 				     vmas_tmp, NULL, gup_flags);
 
 	if (gup_flags & FOLL_LONGTERM) {
@@ -1745,7 +1736,7 @@ static long __gup_longterm_locked(struct task_struct *tsk,
 			goto out;
 		}
 
-		rc = check_and_migrate_cma_pages(tsk, mm, start, rc, pages,
+		rc = check_and_migrate_cma_pages(mm, start, rc, pages,
 						 vmas_tmp, gup_flags);
 out:
 		memalloc_nocma_restore(flags);
@@ -1756,22 +1747,20 @@ static long __gup_longterm_locked(struct task_struct *tsk,
 	return rc;
 }
 #else /* !CONFIG_FS_DAX && !CONFIG_CMA */
-static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
-						  struct mm_struct *mm,
+static __always_inline long __gup_longterm_locked(struct mm_struct *mm,
 						  unsigned long start,
 						  unsigned long nr_pages,
 						  struct page **pages,
 						  struct vm_area_struct **vmas,
 						  unsigned int flags)
 {
-	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+	return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
 				       NULL, flags);
 }
 #endif /* CONFIG_FS_DAX || CONFIG_CMA */
 
 #ifdef CONFIG_MMU
-static long __get_user_pages_remote(struct task_struct *tsk,
-				    struct mm_struct *mm,
+static long __get_user_pages_remote(struct mm_struct *mm,
 				    unsigned long start, unsigned long nr_pages,
 				    unsigned int gup_flags, struct page **pages,
 				    struct vm_area_struct **vmas, int *locked)
@@ -1790,20 +1779,18 @@ static long __get_user_pages_remote(struct task_struct *tsk,
 		 * This will check the vmas (even if our vmas arg is NULL)
 		 * and return -ENOTSUPP if DAX isn't allowed in this case:
 		 */
-		return __gup_longterm_locked(tsk, mm, start, nr_pages, pages,
+		return __gup_longterm_locked(mm, start, nr_pages, pages,
 					     vmas, gup_flags | FOLL_TOUCH |
 					     FOLL_REMOTE);
 	}
 
-	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+	return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
 				       locked,
 				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
 }
 
 /**
  * get_user_pages_remote() - pin user pages in memory
- * @tsk:	the task_struct to use for page fault accounting, or
- *		NULL if faults are not to be recorded.
  * @mm:		mm_struct of target mm
  * @start:	starting user address
  * @nr_pages:	number of pages from start to pin
@@ -1862,7 +1849,7 @@ static long __get_user_pages_remote(struct task_struct *tsk,
  * should use get_user_pages_remote because it cannot pass
  * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
  */
-long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+long get_user_pages_remote(struct mm_struct *mm,
 		unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
 		struct vm_area_struct **vmas, int *locked)
@@ -1874,13 +1861,13 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
 		return -EINVAL;
 
-	return __get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags,
+	return __get_user_pages_remote(mm, start, nr_pages, gup_flags,
 				       pages, vmas, locked);
 }
 EXPORT_SYMBOL(get_user_pages_remote);
 
 #else /* CONFIG_MMU */
-long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+long get_user_pages_remote(struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
 			   unsigned int gup_flags, struct page **pages,
 			   struct vm_area_struct **vmas, int *locked)
@@ -1888,8 +1875,7 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 	return 0;
 }
 
-static long __get_user_pages_remote(struct task_struct *tsk,
-				    struct mm_struct *mm,
+static long __get_user_pages_remote(struct mm_struct *mm,
 				    unsigned long start, unsigned long nr_pages,
 				    unsigned int gup_flags, struct page **pages,
 				    struct vm_area_struct **vmas, int *locked)
@@ -1909,11 +1895,10 @@ static long __get_user_pages_remote(struct task_struct *tsk,
  * @vmas:       array of pointers to vmas corresponding to each page.
  *              Or NULL if the caller does not require them.
  *
- * This is the same as get_user_pages_remote(), just with a
- * less-flexible calling convention where we assume that the task
- * and mm being operated on are the current task's and don't allow
- * passing of a locked parameter.  We also obviously don't pass
- * FOLL_REMOTE in here.
+ * This is the same as get_user_pages_remote(), just with a less-flexible
+ * calling convention where we assume that the mm being operated on belongs to
+ * the current task, and doesn't allow passing of a locked parameter.  We also
+ * obviously don't pass FOLL_REMOTE in here.
  */
 long get_user_pages(unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
@@ -1926,7 +1911,7 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
 	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
 		return -EINVAL;
 
-	return __gup_longterm_locked(current, current->mm, start, nr_pages,
+	return __gup_longterm_locked(current->mm, start, nr_pages,
 				     pages, vmas, gup_flags | FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages);
@@ -1936,7 +1921,7 @@ EXPORT_SYMBOL(get_user_pages);
  *
  *      mmap_read_lock(mm);
  *      do_something()
- *      get_user_pages(tsk, mm, ..., pages, NULL);
+ *      get_user_pages(mm, ..., pages, NULL);
  *      mmap_read_unlock(mm);
  *
  *  to:
@@ -1944,7 +1929,7 @@ EXPORT_SYMBOL(get_user_pages);
  *      int locked = 1;
  *      mmap_read_lock(mm);
  *      do_something()
- *      get_user_pages_locked(tsk, mm, ..., pages, &locked);
+ *      get_user_pages_locked(mm, ..., pages, &locked);
  *      if (locked)
  *          mmap_read_unlock(mm);
  *
@@ -1982,7 +1967,7 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
 	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
 		return -EINVAL;
 
-	return __get_user_pages_locked(current, current->mm, start, nr_pages,
+	return __get_user_pages_locked(current->mm, start, nr_pages,
 				       pages, NULL, locked,
 				       gup_flags | FOLL_TOUCH);
 }
@@ -1992,12 +1977,12 @@ EXPORT_SYMBOL(get_user_pages_locked);
  * get_user_pages_unlocked() is suitable to replace the form:
  *
  *      mmap_read_lock(mm);
- *      get_user_pages(tsk, mm, ..., pages, NULL);
+ *      get_user_pages(mm, ..., pages, NULL);
  *      mmap_read_unlock(mm);
  *
  *  with:
  *
- *      get_user_pages_unlocked(tsk, mm, ..., pages);
+ *      get_user_pages_unlocked(mm, ..., pages);
  *
  * It is functionally equivalent to get_user_pages_fast so
  * get_user_pages_fast should be used instead if specific gup_flags
@@ -2020,7 +2005,7 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		return -EINVAL;
 
 	mmap_read_lock(mm);
-	ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL,
+	ret = __get_user_pages_locked(mm, start, nr_pages, pages, NULL,
 				      &locked, gup_flags | FOLL_TOUCH);
 	if (locked)
 		mmap_read_unlock(mm);
@@ -2665,7 +2650,7 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
 	 */
 	if (gup_flags & FOLL_LONGTERM) {
 		mmap_read_lock(current->mm);
-		ret = __gup_longterm_locked(current, current->mm,
+		ret = __gup_longterm_locked(current->mm,
 					    start, nr_pages,
 					    pages, NULL, gup_flags);
 		mmap_read_unlock(current->mm);
@@ -2908,10 +2893,8 @@ int pin_user_pages_fast_only(unsigned long start, int nr_pages,
 EXPORT_SYMBOL_GPL(pin_user_pages_fast_only);
 
 /**
- * pin_user_pages_remote() - pin pages of a remote process (task != current)
+ * pin_user_pages_remote() - pin pages of a remote process
  *
- * @tsk:	the task_struct to use for page fault accounting, or
- *		NULL if faults are not to be recorded.
  * @mm:		mm_struct of target mm
  * @start:	starting user address
  * @nr_pages:	number of pages from start to pin
@@ -2932,7 +2915,7 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast_only);
  * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
  * see Documentation/core-api/pin_user_pages.rst for details.
  */
-long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+long pin_user_pages_remote(struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
 			   unsigned int gup_flags, struct page **pages,
 			   struct vm_area_struct **vmas, int *locked)
@@ -2942,7 +2925,7 @@ long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 		return -EINVAL;
 
 	gup_flags |= FOLL_PIN;
-	return __get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags,
+	return __get_user_pages_remote(mm, start, nr_pages, gup_flags,
 				       pages, vmas, locked);
 }
 EXPORT_SYMBOL(pin_user_pages_remote);
@@ -2974,7 +2957,7 @@ long pin_user_pages(unsigned long start, unsigned long nr_pages,
 		return -EINVAL;
 
 	gup_flags |= FOLL_PIN;
-	return __gup_longterm_locked(current, current->mm, start, nr_pages,
+	return __gup_longterm_locked(current->mm, start, nr_pages,
 				     pages, vmas, gup_flags);
 }
 EXPORT_SYMBOL(pin_user_pages);
@@ -3019,7 +3002,7 @@ long pin_user_pages_locked(unsigned long start, unsigned long nr_pages,
 		return -EINVAL;
 
 	gup_flags |= FOLL_PIN;
-	return __get_user_pages_locked(current, current->mm, start, nr_pages,
+	return __get_user_pages_locked(current->mm, start, nr_pages,
 				       pages, NULL, locked,
 				       gup_flags | FOLL_TOUCH);
 }
diff --git a/mm/memory.c b/mm/memory.c
index 2b7f0e00f312..228efaca75d3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4742,7 +4742,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		void *maddr;
 		struct page *page = NULL;
 
-		ret = get_user_pages_remote(tsk, mm, addr, 1,
+		ret = get_user_pages_remote(mm, addr, 1,
 				gup_flags, &page, &vma, NULL);
 		if (ret <= 0) {
 #ifndef CONFIG_HAVE_IOREMAP_PROT
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index cc85ce81914a..29c052099aff 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -105,7 +105,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
 		 * current/current->mm
 		 */
 		mmap_read_lock(mm);
-		pinned_pages = pin_user_pages_remote(task, mm, pa, pinned_pages,
+		pinned_pages = pin_user_pages_remote(mm, pa, pinned_pages,
 						     flags, process_pages,
 						     NULL, &locked);
 		if (locked)
diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c
index 53b3e1f5f227..dc4ecc0b2038 100644
--- a/security/tomoyo/domain.c
+++ b/security/tomoyo/domain.c
@@ -914,7 +914,7 @@ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos,
 	 * (represented by bprm).  'current' is the process doing
 	 * the execve().
 	 */
-	if (get_user_pages_remote(current, bprm->mm, pos, 1,
+	if (get_user_pages_remote(bprm->mm, pos, 1,
 				FOLL_FORCE, &page, NULL, NULL) <= 0)
 		return false;
 #else
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 390f758d5a27..dd777688d14a 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -61,7 +61,7 @@ static void async_pf_execute(struct work_struct *work)
 	 * access remotely.
 	 */
 	mmap_read_lock(mm);
-	get_user_pages_remote(NULL, mm, addr, 1, FOLL_WRITE, NULL, NULL,
+	get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, NULL,
 			&locked);
 	if (locked)
 		mmap_read_unlock(mm);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2c2c0254c2d8..737666db02de 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1893,7 +1893,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
 		 * not call the fault handler, so do it here.
 		 */
 		bool unlocked = false;
-		r = fixup_user_fault(current, current->mm, addr,
+		r = fixup_user_fault(current->mm, addr,
 				     (write_fault ? FAULT_FLAG_WRITE : 0),
 				     &unlocked);
 		if (unlocked)