From 5bc1cf1466f635682c3e26eb4179541feeefb1be Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Mon, 18 May 2020 22:16:56 +0800 Subject: [PATCH 001/291] iommu/qcom: add optional 'tbu' clock for TLB invalidate On some SoCs like MSM8939 with A405 adreno, there is a gfx_tbu clock needs to be on while doing TLB invalidate. Otherwise, TLBSYNC status will not be correctly reflected, causing the system to go into a bad state. Add it as an optional clock, so that platforms that have this clock can pass it over DT. While adding the third clock, let's switch to bulk clk API to simplify the enable/disable calls. clk_bulk_get() cannot used because the existing two clocks are required while the new one is optional. Signed-off-by: Shawn Guo Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200518141656.26284-1-shawn.guo@linaro.org Signed-off-by: Joerg Roedel --- drivers/iommu/qcom_iommu.c | 62 ++++++++++++++++---------------------- 1 file changed, 26 insertions(+), 36 deletions(-) diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index 0e2a96467767..116d8188f87f 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -37,14 +37,20 @@ #define SMMU_INTR_SEL_NS 0x2000 +enum qcom_iommu_clk { + CLK_IFACE, + CLK_BUS, + CLK_TBU, + CLK_NUM, +}; + struct qcom_iommu_ctx; struct qcom_iommu_dev { /* IOMMU core code handle */ struct iommu_device iommu; struct device *dev; - struct clk *iface_clk; - struct clk *bus_clk; + struct clk_bulk_data clks[CLK_NUM]; void __iomem *local_base; u32 sec_id; u8 num_ctxs; @@ -626,32 +632,6 @@ static const struct iommu_ops qcom_iommu_ops = { .pgsize_bitmap = SZ_4K | SZ_64K | SZ_1M | SZ_16M, }; -static int qcom_iommu_enable_clocks(struct qcom_iommu_dev *qcom_iommu) -{ - int ret; - - ret = clk_prepare_enable(qcom_iommu->iface_clk); - if (ret) { - dev_err(qcom_iommu->dev, "Couldn't enable iface_clk\n"); - return ret; - } - - ret = clk_prepare_enable(qcom_iommu->bus_clk); - if (ret) { - dev_err(qcom_iommu->dev, "Couldn't enable bus_clk\n"); - clk_disable_unprepare(qcom_iommu->iface_clk); - return ret; - } - - return 0; -} - -static void qcom_iommu_disable_clocks(struct qcom_iommu_dev *qcom_iommu) -{ - clk_disable_unprepare(qcom_iommu->bus_clk); - clk_disable_unprepare(qcom_iommu->iface_clk); -} - static int qcom_iommu_sec_ptbl_init(struct device *dev) { size_t psize = 0; @@ -808,6 +788,7 @@ static int qcom_iommu_device_probe(struct platform_device *pdev) struct qcom_iommu_dev *qcom_iommu; struct device *dev = &pdev->dev; struct resource *res; + struct clk *clk; int ret, max_asid = 0; /* find the max asid (which is 1:1 to ctx bank idx), so we know how @@ -827,17 +808,26 @@ static int qcom_iommu_device_probe(struct platform_device *pdev) if (res) qcom_iommu->local_base = devm_ioremap_resource(dev, res); - qcom_iommu->iface_clk = devm_clk_get(dev, "iface"); - if (IS_ERR(qcom_iommu->iface_clk)) { + clk = devm_clk_get(dev, "iface"); + if (IS_ERR(clk)) { dev_err(dev, "failed to get iface clock\n"); - return PTR_ERR(qcom_iommu->iface_clk); + return PTR_ERR(clk); } + qcom_iommu->clks[CLK_IFACE].clk = clk; - qcom_iommu->bus_clk = devm_clk_get(dev, "bus"); - if (IS_ERR(qcom_iommu->bus_clk)) { + clk = devm_clk_get(dev, "bus"); + if (IS_ERR(clk)) { dev_err(dev, "failed to get bus clock\n"); - return PTR_ERR(qcom_iommu->bus_clk); + return PTR_ERR(clk); } + qcom_iommu->clks[CLK_BUS].clk = clk; + + clk = devm_clk_get_optional(dev, "tbu"); + if (IS_ERR(clk)) { + dev_err(dev, "failed to get tbu clock\n"); + return PTR_ERR(clk); + } + qcom_iommu->clks[CLK_TBU].clk = clk; if (of_property_read_u32(dev->of_node, "qcom,iommu-secure-id", &qcom_iommu->sec_id)) { @@ -909,14 +899,14 @@ static int __maybe_unused qcom_iommu_resume(struct device *dev) { struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev); - return qcom_iommu_enable_clocks(qcom_iommu); + return clk_bulk_prepare_enable(CLK_NUM, qcom_iommu->clks); } static int __maybe_unused qcom_iommu_suspend(struct device *dev) { struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev); - qcom_iommu_disable_clocks(qcom_iommu); + clk_bulk_disable_unprepare(CLK_NUM, qcom_iommu->clks); return 0; } From a9b9b2af40c717adbc4981acd29c53b92be3a99a Mon Sep 17 00:00:00 2001 From: Wang Qing Date: Mon, 15 Jun 2020 16:54:02 +0800 Subject: [PATCH 002/291] backlight: lm3533_bl: Use kobj_to_dev() instead Use kobj_to_dev() instead of container_of() Signed-off-by: Wang Qing Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/lm3533_bl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/backlight/lm3533_bl.c b/drivers/video/backlight/lm3533_bl.c index ee09d1bd02b9..0c7830f793de 100644 --- a/drivers/video/backlight/lm3533_bl.c +++ b/drivers/video/backlight/lm3533_bl.c @@ -235,7 +235,7 @@ static struct attribute *lm3533_bl_attributes[] = { static umode_t lm3533_bl_attr_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 lm3533_bl *bl = dev_get_drvdata(dev); umode_t mode = attr->mode; From d378cdd0113878e3860f954d16dd3e91defb1492 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 26 May 2020 11:53:28 -0700 Subject: [PATCH 003/291] platform/chrome: cros_ec_debugfs: Control uptime information request When EC does not support uptime command (EC_CMD_GET_UPTIME_INFO), do not create the uptime sysfs entry point. User space application will not probe the file needlessly. The EC console log will not contain EC_CMD_GET_UPTIME_INFO anymore. Signed-off-by: Gwendal Grignou Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_debugfs.c | 24 +++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/drivers/platform/chrome/cros_ec_debugfs.c b/drivers/platform/chrome/cros_ec_debugfs.c index ecfada00e6c5..272c89837d74 100644 --- a/drivers/platform/chrome/cros_ec_debugfs.c +++ b/drivers/platform/chrome/cros_ec_debugfs.c @@ -242,6 +242,25 @@ static ssize_t cros_ec_pdinfo_read(struct file *file, read_buf, p - read_buf); } +static bool cros_ec_uptime_is_supported(struct cros_ec_device *ec_dev) +{ + struct { + struct cros_ec_command cmd; + struct ec_response_uptime_info resp; + } __packed msg = {}; + int ret; + + msg.cmd.command = EC_CMD_GET_UPTIME_INFO; + msg.cmd.insize = sizeof(msg.resp); + + ret = cros_ec_cmd_xfer_status(ec_dev, &msg.cmd); + if (ret == -EPROTO && msg.cmd.result == EC_RES_INVALID_COMMAND) + return false; + + /* Other errors maybe a transient error, do not rule about support. */ + return true; +} + static ssize_t cros_ec_uptime_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -444,8 +463,9 @@ static int cros_ec_debugfs_probe(struct platform_device *pd) debugfs_create_file("pdinfo", 0444, debug_info->dir, debug_info, &cros_ec_pdinfo_fops); - debugfs_create_file("uptime", 0444, debug_info->dir, debug_info, - &cros_ec_uptime_fops); + if (cros_ec_uptime_is_supported(ec->ec_dev)) + debugfs_create_file("uptime", 0444, debug_info->dir, debug_info, + &cros_ec_uptime_fops); debugfs_create_x32("last_resume_result", 0444, debug_info->dir, &ec->ec_dev->last_resume_result); From f28adb41dab4a2795fd959750df57adffd2bb0be Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Tue, 19 May 2020 14:46:04 -0700 Subject: [PATCH 004/291] platform/chrome: cros_ec_typec: Register Type C switches Register Type C mux and switch handles, when provided via firmware bindings. These will allow the cros-ec-typec driver, and also alternate mode drivers to configure connected Muxes correctly, according to PD information retrieved from the Chrome OS EC. Signed-off-by: Prashant Malani Reviewed-by: Heikki Krogerus Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_typec.c | 47 +++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index 66b8d21092af..6e79f917314b 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -14,6 +14,8 @@ #include #include #include +#include +#include #define DRV_NAME "cros-ec-typec" @@ -25,6 +27,9 @@ struct cros_typec_port { struct typec_partner *partner; /* Port partner PD identity info. */ struct usb_pd_identity p_identity; + struct typec_switch *ori_sw; + struct typec_mux *mux; + struct usb_role_switch *role_sw; }; /* Platform-specific data for the Chrome OS EC Type C controller. */ @@ -84,6 +89,40 @@ static int cros_typec_parse_port_props(struct typec_capability *cap, return 0; } +static int cros_typec_get_switch_handles(struct cros_typec_port *port, + struct fwnode_handle *fwnode, + struct device *dev) +{ + port->mux = fwnode_typec_mux_get(fwnode, NULL); + if (IS_ERR(port->mux)) { + dev_dbg(dev, "Mux handle not found.\n"); + goto mux_err; + } + + port->ori_sw = fwnode_typec_switch_get(fwnode); + if (IS_ERR(port->ori_sw)) { + dev_dbg(dev, "Orientation switch handle not found.\n"); + goto ori_sw_err; + } + + port->role_sw = fwnode_usb_role_switch_get(fwnode); + if (IS_ERR(port->role_sw)) { + dev_dbg(dev, "USB role switch handle not found.\n"); + goto role_sw_err; + } + + return 0; + +role_sw_err: + usb_role_switch_put(port->role_sw); +ori_sw_err: + typec_switch_put(port->ori_sw); +mux_err: + typec_mux_put(port->mux); + + return -ENODEV; +} + static void cros_unregister_ports(struct cros_typec_data *typec) { int i; @@ -91,6 +130,9 @@ static void cros_unregister_ports(struct cros_typec_data *typec) for (i = 0; i < typec->num_ports; i++) { if (!typec->ports[i]) continue; + usb_role_switch_put(typec->ports[i]->role_sw); + typec_switch_put(typec->ports[i]->ori_sw); + typec_mux_put(typec->ports[i]->mux); typec_unregister_port(typec->ports[i]->port); } } @@ -153,6 +195,11 @@ static int cros_typec_init_ports(struct cros_typec_data *typec) ret = PTR_ERR(cros_port->port); goto unregister_ports; } + + ret = cros_typec_get_switch_handles(cros_port, fwnode, dev); + if (ret) + dev_dbg(dev, "No switch control for port %d\n", + port_num); } return 0; From e32b16c31339e37d3cdc814f2773b74c1dbf660c Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Thu, 28 May 2020 04:36:03 -0700 Subject: [PATCH 005/291] platform/chrome: cros_ec: Update mux state bits Sync the EC_CMD_USB_PD_MUX_INFO mux state bit fields with the Chrome EC code base. The newly added bit fields will be used for cros-ec-typec mux control. Signed-off-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra --- include/linux/platform_data/cros_ec_commands.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 69210881ebac..a7b0fc440c35 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -5207,11 +5207,15 @@ struct ec_params_usb_pd_mux_info { } __ec_align1; /* Flags representing mux state */ -#define USB_PD_MUX_USB_ENABLED BIT(0) /* USB connected */ -#define USB_PD_MUX_DP_ENABLED BIT(1) /* DP connected */ -#define USB_PD_MUX_POLARITY_INVERTED BIT(2) /* CC line Polarity inverted */ -#define USB_PD_MUX_HPD_IRQ BIT(3) /* HPD IRQ is asserted */ -#define USB_PD_MUX_HPD_LVL BIT(4) /* HPD level is asserted */ +#define USB_PD_MUX_NONE 0 /* Open switch */ +#define USB_PD_MUX_USB_ENABLED BIT(0) /* USB connected */ +#define USB_PD_MUX_DP_ENABLED BIT(1) /* DP connected */ +#define USB_PD_MUX_POLARITY_INVERTED BIT(2) /* CC line Polarity inverted */ +#define USB_PD_MUX_HPD_IRQ BIT(3) /* HPD IRQ is asserted */ +#define USB_PD_MUX_HPD_LVL BIT(4) /* HPD level is asserted */ +#define USB_PD_MUX_SAFE_MODE BIT(5) /* DP is in safe mode */ +#define USB_PD_MUX_TBT_COMPAT_ENABLED BIT(6) /* TBT compat enabled */ +#define USB_PD_MUX_USB4_ENABLED BIT(7) /* USB4 enabled */ struct ec_response_usb_pd_mux_info { uint8_t flags; /* USB_PD_MUX_*-encoded USB mux state */ From 2ee97377a0d459fb3c484e49fb471ac6add06441 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Thu, 28 May 2020 04:36:05 -0700 Subject: [PATCH 006/291] platform/chrome: cros_ec_typec: Register PD CTRL cmd v2 Recognize EC_CMD_USB_PD_CONTROL command version 2. This is necessary in order to process Type C mux information (like DP alt mode pin configuration), which is needed by the Type C Connector class API to configure the Type C muxes correctly While we are here, rename the struct member storing this version number from cmd_ver to pd_ctrl_ver, which more accurately reflects what is being stored. Also, slightly change the logic for calling cros_typec_set_port_params_*(). Now, v0 is called when pd_ctrl_ver is 0, and v1 is called otherwise. Signed-off-by: Prashant Malani Reviewed-by: Heikki Krogerus Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_typec.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index 6e79f917314b..d69a88464cef 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -37,7 +37,7 @@ struct cros_typec_data { struct device *dev; struct cros_ec_device *ec; int num_ports; - unsigned int cmd_ver; + unsigned int pd_ctrl_ver; /* Array of ports, indexed by port number. */ struct cros_typec_port *ports[EC_USB_PD_MAX_PORTS]; struct notifier_block nb; @@ -340,7 +340,7 @@ static int cros_typec_port_update(struct cros_typec_data *typec, int port_num) req.mux = USB_PD_CTRL_MUX_NO_CHANGE; req.swap = USB_PD_CTRL_SWAP_NONE; - ret = cros_typec_ec_command(typec, typec->cmd_ver, + ret = cros_typec_ec_command(typec, typec->pd_ctrl_ver, EC_CMD_USB_PD_CONTROL, &req, sizeof(req), &resp, sizeof(resp)); if (ret < 0) @@ -351,7 +351,7 @@ static int cros_typec_port_update(struct cros_typec_data *typec, int port_num) dev_dbg(typec->dev, "Polarity %d: 0x%hhx\n", port_num, resp.polarity); dev_dbg(typec->dev, "State %d: %s\n", port_num, resp.state); - if (typec->cmd_ver == 1) + if (typec->pd_ctrl_ver != 0) cros_typec_set_port_params_v1(typec, port_num, &resp); else cros_typec_set_port_params_v0(typec, port_num, @@ -374,13 +374,15 @@ static int cros_typec_get_cmd_version(struct cros_typec_data *typec) if (ret < 0) return ret; - if (resp.version_mask & EC_VER_MASK(1)) - typec->cmd_ver = 1; + if (resp.version_mask & EC_VER_MASK(2)) + typec->pd_ctrl_ver = 2; + else if (resp.version_mask & EC_VER_MASK(1)) + typec->pd_ctrl_ver = 1; else - typec->cmd_ver = 0; + typec->pd_ctrl_ver = 0; dev_dbg(typec->dev, "PD Control has version mask 0x%hhx\n", - typec->cmd_ver); + typec->pd_ctrl_ver); return 0; } From 7e7def15fa4bc9d6a2fa3d1d379286591c249381 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Thu, 28 May 2020 04:36:07 -0700 Subject: [PATCH 007/291] platform/chrome: cros_ec_typec: Add USB mux control Add support to configure various Type C switches appropriately using the Type C connector class API, when the Chrome OS EC informs the AP that the USB operating mode has been entered. Signed-off-by: Prashant Malani Reviewed-by: Heikki Krogerus Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_typec.c | 102 +++++++++++++++++++++++- 1 file changed, 98 insertions(+), 4 deletions(-) diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index d69a88464cef..9ebf9abed16f 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -30,6 +31,10 @@ struct cros_typec_port { struct typec_switch *ori_sw; struct typec_mux *mux; struct usb_role_switch *role_sw; + + /* Variables keeping track of switch state. */ + struct typec_mux_state state; + uint8_t mux_flags; }; /* Platform-specific data for the Chrome OS EC Type C controller. */ @@ -264,6 +269,23 @@ static int cros_typec_add_partner(struct cros_typec_data *typec, int port_num, return ret; } +static void cros_typec_remove_partner(struct cros_typec_data *typec, + int port_num) +{ + struct cros_typec_port *port = typec->ports[port_num]; + + port->state.alt = NULL; + port->state.mode = TYPEC_STATE_USB; + port->state.data = NULL; + + usb_role_switch_set_role(port->role_sw, USB_ROLE_NONE); + typec_switch_set(port->ori_sw, TYPEC_ORIENTATION_NONE); + typec_mux_set(port->mux, &port->state); + + typec_unregister_partner(port->partner); + port->partner = NULL; +} + static void cros_typec_set_port_params_v0(struct cros_typec_data *typec, int port_num, struct ec_response_usb_pd_control *resp) { @@ -317,16 +339,69 @@ static void cros_typec_set_port_params_v1(struct cros_typec_data *typec, } else { if (!typec->ports[port_num]->partner) return; - - typec_unregister_partner(typec->ports[port_num]->partner); - typec->ports[port_num]->partner = NULL; + cros_typec_remove_partner(typec, port_num); } } +static int cros_typec_get_mux_info(struct cros_typec_data *typec, int port_num, + struct ec_response_usb_pd_mux_info *resp) +{ + struct ec_params_usb_pd_mux_info req = { + .port = port_num, + }; + + return cros_typec_ec_command(typec, 0, EC_CMD_USB_PD_MUX_INFO, &req, + sizeof(req), resp, sizeof(*resp)); +} + +static int cros_typec_usb_safe_state(struct cros_typec_port *port) +{ + port->state.mode = TYPEC_STATE_SAFE; + + return typec_mux_set(port->mux, &port->state); +} + +int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num, + uint8_t mux_flags) +{ + struct cros_typec_port *port = typec->ports[port_num]; + enum typec_orientation orientation; + int ret; + + if (!port->partner) + return 0; + + if (mux_flags & USB_PD_MUX_POLARITY_INVERTED) + orientation = TYPEC_ORIENTATION_REVERSE; + else + orientation = TYPEC_ORIENTATION_NORMAL; + + ret = typec_switch_set(port->ori_sw, orientation); + if (ret) + return ret; + + port->state.alt = NULL; + port->state.mode = TYPEC_STATE_USB; + + if (mux_flags & USB_PD_MUX_SAFE_MODE) + ret = cros_typec_usb_safe_state(port); + else if (mux_flags & USB_PD_MUX_USB_ENABLED) + ret = typec_mux_set(port->mux, &port->state); + else { + dev_info(typec->dev, + "Unsupported mode requested, mux flags: %x\n", + mux_flags); + ret = -ENOTSUPP; + } + + return ret; +} + static int cros_typec_port_update(struct cros_typec_data *typec, int port_num) { struct ec_params_usb_pd_control req; struct ec_response_usb_pd_control_v1 resp; + struct ec_response_usb_pd_mux_info mux_resp; int ret; if (port_num < 0 || port_num >= typec->num_ports) { @@ -357,7 +432,26 @@ static int cros_typec_port_update(struct cros_typec_data *typec, int port_num) cros_typec_set_port_params_v0(typec, port_num, (struct ec_response_usb_pd_control *) &resp); - return 0; + /* Update the switches if they exist, according to requested state */ + ret = cros_typec_get_mux_info(typec, port_num, &mux_resp); + if (ret < 0) { + dev_warn(typec->dev, + "Failed to get mux info for port: %d, err = %d\n", + port_num, ret); + return 0; + } + + /* No change needs to be made, let's exit early. */ + if (typec->ports[port_num]->mux_flags == mux_resp.flags) + return 0; + + typec->ports[port_num]->mux_flags = mux_resp.flags; + ret = cros_typec_configure_mux(typec, port_num, mux_resp.flags); + if (ret) + dev_warn(typec->dev, "Configure muxes failed, err = %d\n", ret); + + return usb_role_switch_set_role(typec->ports[port_num]->role_sw, + !!(resp.role & PD_CTRL_RESP_ROLE_DATA)); } static int cros_typec_get_cmd_version(struct cros_typec_data *typec) From 410457b99c7ea3e0cf8de1054e175ba3c2213d33 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Thu, 28 May 2020 04:36:10 -0700 Subject: [PATCH 008/291] platform/chrome: cros_ec_typec: Support DP alt mode Handle Chrome EC mux events to configure on-board muxes correctly while entering DP alternate mode. Since we don't surface SVID and VDO information regarding the DP alternate mode, configure the Type C muxes directly from the port driver. Later, when mode discovery information is correctly surfaced to the driver, we can register the DP alternate mode driver and let it handle the mux configuration. Also, modify the struct_typec_state state management to account for the addition of DP alternate mode. Signed-off-by: Prashant Malani Reviewed-by: Heikki Krogerus Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_typec.c | 90 ++++++++++++++++++++++--- 1 file changed, 80 insertions(+), 10 deletions(-) diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index 9ebf9abed16f..509fc761906b 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -15,11 +15,18 @@ #include #include #include +#include #include #include #define DRV_NAME "cros-ec-typec" +/* Supported alt modes. */ +enum { + CROS_EC_ALTMODE_DP = 0, + CROS_EC_ALTMODE_MAX, +}; + /* Per port data. */ struct cros_typec_port { struct typec_port *port; @@ -35,6 +42,9 @@ struct cros_typec_port { /* Variables keeping track of switch state. */ struct typec_mux_state state; uint8_t mux_flags; + + /* Port alt modes. */ + struct typec_altmode p_altmode[CROS_EC_ALTMODE_MAX]; }; /* Platform-specific data for the Chrome OS EC Type C controller. */ @@ -142,6 +152,24 @@ static void cros_unregister_ports(struct cros_typec_data *typec) } } +/* + * Fake the alt mode structs until we actually start registering Type C port + * and partner alt modes. + */ +static void cros_typec_register_port_altmodes(struct cros_typec_data *typec, + int port_num) +{ + struct cros_typec_port *port = typec->ports[port_num]; + + /* All PD capable CrOS devices are assumed to support DP altmode. */ + port->p_altmode[CROS_EC_ALTMODE_DP].svid = USB_TYPEC_DP_SID; + port->p_altmode[CROS_EC_ALTMODE_DP].mode = USB_TYPEC_DP_MODE; + + port->state.alt = NULL; + port->state.mode = TYPEC_STATE_USB; + port->state.data = NULL; +} + static int cros_typec_init_ports(struct cros_typec_data *typec) { struct device *dev = typec->dev; @@ -205,6 +233,8 @@ static int cros_typec_init_ports(struct cros_typec_data *typec) if (ret) dev_dbg(dev, "No switch control for port %d\n", port_num); + + cros_typec_register_port_altmodes(typec, port_num); } return 0; @@ -361,8 +391,46 @@ static int cros_typec_usb_safe_state(struct cros_typec_port *port) return typec_mux_set(port->mux, &port->state); } +/* Spoof the VDOs that were likely communicated by the partner. */ +static int cros_typec_enable_dp(struct cros_typec_data *typec, + int port_num, + struct ec_response_usb_pd_control_v2 *pd_ctrl) +{ + struct cros_typec_port *port = typec->ports[port_num]; + struct typec_displayport_data dp_data; + int ret; + + if (typec->pd_ctrl_ver < 2) { + dev_err(typec->dev, + "PD_CTRL version too old: %d\n", typec->pd_ctrl_ver); + return -ENOTSUPP; + } + + /* Status VDO. */ + dp_data.status = DP_STATUS_ENABLED; + if (port->mux_flags & USB_PD_MUX_HPD_IRQ) + dp_data.status |= DP_STATUS_IRQ_HPD; + if (port->mux_flags & USB_PD_MUX_HPD_LVL) + dp_data.status |= DP_STATUS_HPD_STATE; + + /* Configuration VDO. */ + dp_data.conf = DP_CONF_SET_PIN_ASSIGN(pd_ctrl->dp_mode); + if (!port->state.alt) { + port->state.alt = &port->p_altmode[CROS_EC_ALTMODE_DP]; + ret = cros_typec_usb_safe_state(port); + if (ret) + return ret; + } + + port->state.data = &dp_data; + port->state.mode = TYPEC_MODAL_STATE(ffs(pd_ctrl->dp_mode)); + + return typec_mux_set(port->mux, &port->state); +} + int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num, - uint8_t mux_flags) + uint8_t mux_flags, + struct ec_response_usb_pd_control_v2 *pd_ctrl) { struct cros_typec_port *port = typec->ports[port_num]; enum typec_orientation orientation; @@ -380,14 +448,15 @@ int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num, if (ret) return ret; - port->state.alt = NULL; - port->state.mode = TYPEC_STATE_USB; - - if (mux_flags & USB_PD_MUX_SAFE_MODE) + if (mux_flags & USB_PD_MUX_DP_ENABLED) { + ret = cros_typec_enable_dp(typec, port_num, pd_ctrl); + } else if (mux_flags & USB_PD_MUX_SAFE_MODE) { ret = cros_typec_usb_safe_state(port); - else if (mux_flags & USB_PD_MUX_USB_ENABLED) + } else if (mux_flags & USB_PD_MUX_USB_ENABLED) { + port->state.alt = NULL; + port->state.mode = TYPEC_STATE_USB; ret = typec_mux_set(port->mux, &port->state); - else { + } else { dev_info(typec->dev, "Unsupported mode requested, mux flags: %x\n", mux_flags); @@ -400,7 +469,7 @@ int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num, static int cros_typec_port_update(struct cros_typec_data *typec, int port_num) { struct ec_params_usb_pd_control req; - struct ec_response_usb_pd_control_v1 resp; + struct ec_response_usb_pd_control_v2 resp; struct ec_response_usb_pd_mux_info mux_resp; int ret; @@ -427,7 +496,8 @@ static int cros_typec_port_update(struct cros_typec_data *typec, int port_num) dev_dbg(typec->dev, "State %d: %s\n", port_num, resp.state); if (typec->pd_ctrl_ver != 0) - cros_typec_set_port_params_v1(typec, port_num, &resp); + cros_typec_set_port_params_v1(typec, port_num, + (struct ec_response_usb_pd_control_v1 *)&resp); else cros_typec_set_port_params_v0(typec, port_num, (struct ec_response_usb_pd_control *) &resp); @@ -446,7 +516,7 @@ static int cros_typec_port_update(struct cros_typec_data *typec, int port_num) return 0; typec->ports[port_num]->mux_flags = mux_resp.flags; - ret = cros_typec_configure_mux(typec, port_num, mux_resp.flags); + ret = cros_typec_configure_mux(typec, port_num, mux_resp.flags, &resp); if (ret) dev_warn(typec->dev, "Configure muxes failed, err = %d\n", ret); From 285e74ab4f94d921a56fcf66320b3cd65e35b6bc Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Tue, 14 Apr 2020 19:09:43 -0300 Subject: [PATCH 009/291] hwspinlock: Simplify Kconfig Every hwspinlock driver is expected to depend on the hwspinlock core, so it's possible to simplify the Kconfig, factoring out the HWSPINLOCK dependency. Reviewed-by: Baolin Wang Signed-off-by: Ezequiel Garcia Link: https://lore.kernel.org/r/20200414220943.6203-1-ezequiel@collabora.com Signed-off-by: Bjorn Andersson --- drivers/hwspinlock/Kconfig | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/hwspinlock/Kconfig b/drivers/hwspinlock/Kconfig index 826a1054100d..32cd26352f38 100644 --- a/drivers/hwspinlock/Kconfig +++ b/drivers/hwspinlock/Kconfig @@ -6,9 +6,10 @@ menuconfig HWSPINLOCK bool "Hardware Spinlock drivers" +if HWSPINLOCK + config HWSPINLOCK_OMAP tristate "OMAP Hardware Spinlock device" - depends on HWSPINLOCK depends on ARCH_OMAP4 || SOC_OMAP5 || SOC_DRA7XX || SOC_AM33XX || SOC_AM43XX || ARCH_K3 || COMPILE_TEST help Say y here to support the OMAP Hardware Spinlock device (firstly @@ -18,7 +19,6 @@ config HWSPINLOCK_OMAP config HWSPINLOCK_QCOM tristate "Qualcomm Hardware Spinlock device" - depends on HWSPINLOCK depends on ARCH_QCOM || COMPILE_TEST select MFD_SYSCON help @@ -30,7 +30,6 @@ config HWSPINLOCK_QCOM config HWSPINLOCK_SIRF tristate "SIRF Hardware Spinlock device" - depends on HWSPINLOCK depends on ARCH_SIRF || COMPILE_TEST help Say y here to support the SIRF Hardware Spinlock device, which @@ -43,7 +42,6 @@ config HWSPINLOCK_SIRF config HWSPINLOCK_SPRD tristate "SPRD Hardware Spinlock device" depends on ARCH_SPRD || COMPILE_TEST - depends on HWSPINLOCK help Say y here to support the SPRD Hardware Spinlock device. @@ -52,7 +50,6 @@ config HWSPINLOCK_SPRD config HWSPINLOCK_STM32 tristate "STM32 Hardware Spinlock device" depends on MACH_STM32MP157 || COMPILE_TEST - depends on HWSPINLOCK help Say y here to support the STM32 Hardware Spinlock device. @@ -60,7 +57,6 @@ config HWSPINLOCK_STM32 config HSEM_U8500 tristate "STE Hardware Semaphore functionality" - depends on HWSPINLOCK depends on ARCH_U8500 || COMPILE_TEST help Say y here to support the STE Hardware Semaphore functionality, which @@ -68,3 +64,5 @@ config HSEM_U8500 SoC. If unsure, say N. + +endif # HWSPINLOCK From 447b4eb6ceeb2d0d83d7f5aa248f2798f167cfda Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Fri, 19 Jun 2020 19:00:37 -0700 Subject: [PATCH 010/291] platform/chrome: cros_ec_typec: Make configure_mux static Since cros_typec_configure_mux() is only used in cros-ec-typec, it should be marked static. Fixes: 7e7def15fa4b ("platform/chrome: cros_ec_typec: Add USB mux control") Reported-by: kernel test robot Signed-off-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_typec.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index 509fc761906b..1df1386f32e4 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -428,9 +428,9 @@ static int cros_typec_enable_dp(struct cros_typec_data *typec, return typec_mux_set(port->mux, &port->state); } -int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num, - uint8_t mux_flags, - struct ec_response_usb_pd_control_v2 *pd_ctrl) +static int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num, + uint8_t mux_flags, + struct ec_response_usb_pd_control_v2 *pd_ctrl) { struct cros_typec_port *port = typec->ports[port_num]; enum typec_orientation orientation; From 5e48a03bb9bff1728164040d71aa03cdb3cdfca2 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 24 Jun 2020 01:09:23 -0700 Subject: [PATCH 011/291] platform/chrome: cros_ec: Add TBT pd_ctrl fields To support Thunderbolt compatibility mode, synchronize ec_response_usb_pd_control_v2 with the Chrome EC version, so that we get the Thunderbolt related control fields and macros. Signed-off-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra --- .../linux/platform_data/cros_ec_commands.h | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index a7b0fc440c35..b808570bdd04 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -4917,15 +4917,26 @@ struct ec_response_usb_pd_control_v1 { #define USBC_PD_CC_UFP_ATTACHED 4 /* UFP attached to usbc */ #define USBC_PD_CC_DFP_ATTACHED 5 /* DPF attached to usbc */ +/* Active/Passive Cable */ +#define USB_PD_CTRL_ACTIVE_CABLE BIT(0) +/* Optical/Non-optical cable */ +#define USB_PD_CTRL_OPTICAL_CABLE BIT(1) +/* 3rd Gen TBT device (or AMA)/2nd gen tbt Adapter */ +#define USB_PD_CTRL_TBT_LEGACY_ADAPTER BIT(2) +/* Active Link Uni-Direction */ +#define USB_PD_CTRL_ACTIVE_LINK_UNIDIR BIT(3) + struct ec_response_usb_pd_control_v2 { uint8_t enabled; uint8_t role; uint8_t polarity; char state[32]; - uint8_t cc_state; /* USBC_PD_CC_*Encoded cc state */ - uint8_t dp_mode; /* Current DP pin mode (MODE_DP_PIN_[A-E]) */ - /* CL:1500994 Current cable type */ - uint8_t reserved_cable_type; + uint8_t cc_state; /* enum pd_cc_states representing cc state */ + uint8_t dp_mode; /* Current DP pin mode (MODE_DP_PIN_[A-E]) */ + uint8_t reserved; /* Reserved for future use */ + uint8_t control_flags; /* USB_PD_CTRL_*flags */ + uint8_t cable_speed; /* TBT_SS_* cable speed */ + uint8_t cable_gen; /* TBT_GEN3_* cable rounded support */ } __ec_align1; #define EC_CMD_USB_PD_PORTS 0x0102 From 5b30bd35aab4bcea6a06627a1e943659d82a71cb Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 24 Jun 2020 01:09:24 -0700 Subject: [PATCH 012/291] platform/chrome: cros_ec_typec: Add TBT compat support Add mux control support for Thunderbolt compatibility mode. Suggested-by: Heikki Krogerus Co-developed-by: Azhar Shaikh Co-developed-by: Casey Bowman Signed-off-by: Prashant Malani Reviewed-by: Heikki Krogerus Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_typec.c | 70 ++++++++++++++++++++++++- 1 file changed, 69 insertions(+), 1 deletion(-) diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index 1df1386f32e4..0c041b79cbba 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #define DRV_NAME "cros-ec-typec" @@ -24,6 +25,7 @@ /* Supported alt modes. */ enum { CROS_EC_ALTMODE_DP = 0, + CROS_EC_ALTMODE_TBT, CROS_EC_ALTMODE_MAX, }; @@ -165,6 +167,14 @@ static void cros_typec_register_port_altmodes(struct cros_typec_data *typec, port->p_altmode[CROS_EC_ALTMODE_DP].svid = USB_TYPEC_DP_SID; port->p_altmode[CROS_EC_ALTMODE_DP].mode = USB_TYPEC_DP_MODE; + /* + * Register TBT compatibility alt mode. The EC will not enter the mode + * if it doesn't support it, so it's safe to register it unconditionally + * here for now. + */ + port->p_altmode[CROS_EC_ALTMODE_TBT].svid = USB_TYPEC_TBT_SID; + port->p_altmode[CROS_EC_ALTMODE_TBT].mode = TYPEC_ANY_MODE; + port->state.alt = NULL; port->state.mode = TYPEC_STATE_USB; port->state.data = NULL; @@ -391,6 +401,62 @@ static int cros_typec_usb_safe_state(struct cros_typec_port *port) return typec_mux_set(port->mux, &port->state); } +/* + * Spoof the VDOs that were likely communicated by the partner for TBT alt + * mode. + */ +static int cros_typec_enable_tbt(struct cros_typec_data *typec, + int port_num, + struct ec_response_usb_pd_control_v2 *pd_ctrl) +{ + struct cros_typec_port *port = typec->ports[port_num]; + struct typec_thunderbolt_data data; + int ret; + + if (typec->pd_ctrl_ver < 2) { + dev_err(typec->dev, + "PD_CTRL version too old: %d\n", typec->pd_ctrl_ver); + return -ENOTSUPP; + } + + /* Device Discover Mode VDO */ + data.device_mode = TBT_MODE; + + if (pd_ctrl->control_flags & USB_PD_CTRL_TBT_LEGACY_ADAPTER) + data.device_mode = TBT_SET_ADAPTER(TBT_ADAPTER_TBT3); + + /* Cable Discover Mode VDO */ + data.cable_mode = TBT_MODE; + data.cable_mode |= TBT_SET_CABLE_SPEED(pd_ctrl->cable_speed); + + if (pd_ctrl->control_flags & USB_PD_CTRL_OPTICAL_CABLE) + data.cable_mode |= TBT_CABLE_OPTICAL; + + if (pd_ctrl->control_flags & USB_PD_CTRL_ACTIVE_LINK_UNIDIR) + data.cable_mode |= TBT_CABLE_LINK_TRAINING; + + if (pd_ctrl->cable_gen) + data.cable_mode |= TBT_CABLE_ROUNDED; + + /* Enter Mode VDO */ + data.enter_vdo = TBT_SET_CABLE_SPEED(pd_ctrl->cable_speed); + + if (pd_ctrl->control_flags & USB_PD_CTRL_ACTIVE_CABLE) + data.enter_vdo |= TBT_ENTER_MODE_ACTIVE_CABLE; + + if (!port->state.alt) { + port->state.alt = &port->p_altmode[CROS_EC_ALTMODE_TBT]; + ret = cros_typec_usb_safe_state(port); + if (ret) + return ret; + } + + port->state.data = &data; + port->state.mode = TYPEC_TBT_MODE; + + return typec_mux_set(port->mux, &port->state); +} + /* Spoof the VDOs that were likely communicated by the partner. */ static int cros_typec_enable_dp(struct cros_typec_data *typec, int port_num, @@ -448,7 +514,9 @@ static int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num, if (ret) return ret; - if (mux_flags & USB_PD_MUX_DP_ENABLED) { + if (mux_flags & USB_PD_MUX_TBT_COMPAT_ENABLED) { + ret = cros_typec_enable_tbt(typec, port_num, pd_ctrl); + } else if (mux_flags & USB_PD_MUX_DP_ENABLED) { ret = cros_typec_enable_dp(typec, port_num, pd_ctrl); } else if (mux_flags & USB_PD_MUX_SAFE_MODE) { ret = cros_typec_usb_safe_state(port); From d3e3d2be688b4b5864538de61e750721a311e4fc Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Tue, 2 Jun 2020 14:08:18 +0100 Subject: [PATCH 013/291] iommu/iova: Don't BUG on invalid PFNs Unlike the other instances which represent a complete loss of consistency within the rcache mechanism itself, or a fundamental and obvious misconfiguration by an IOMMU driver, the BUG_ON() in iova_magazine_free_pfns() can be provoked at more or less any time in a "spooky action-at-a-distance" manner by any old device driver passing nonsense to dma_unmap_*() which then propagates through to queue_iova(). Not only is this well outside the IOVA layer's control, it's also nowhere near fatal enough to justify panicking anyway - all that really achieves is to make debugging the offending driver more difficult. Let's simply WARN and otherwise ignore bogus PFNs. Reported-by: Prakash Gupta Signed-off-by: Robin Murphy Reviewed-by: Prakash Gupta Link: https://lore.kernel.org/r/acbd2d092b42738a03a21b417ce64e27f8c91c86.1591103298.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/iova.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 49fc01f2a28d..45a251da5453 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -811,7 +811,9 @@ iova_magazine_free_pfns(struct iova_magazine *mag, struct iova_domain *iovad) for (i = 0 ; i < mag->size; ++i) { struct iova *iova = private_find_iova(iovad, mag->pfns[i]); - BUG_ON(!iova); + if (WARN_ON(!iova)) + continue; + private_free_iova(iovad, iova); } From f5e383ac8b58f421ac0a005f6df4f2e9eefeb93f Mon Sep 17 00:00:00 2001 From: Denis Efremov Date: Thu, 4 Jun 2020 15:37:09 +0300 Subject: [PATCH 014/291] iommu/pamu: Use kzfree() in fsl_pamu_probe() Use kzfree() instead of opencoded memset with 0 followed by kfree(). Null check is not required since kzfree() checks for NULL internally. Signed-off-by: Denis Efremov Link: https://lore.kernel.org/r/20200604123709.96561-1-efremov@linux.com Signed-off-by: Joerg Roedel --- drivers/iommu/fsl_pamu.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c index cde281b97afa..099a11a35fb9 100644 --- a/drivers/iommu/fsl_pamu.c +++ b/drivers/iommu/fsl_pamu.c @@ -1174,10 +1174,7 @@ static int fsl_pamu_probe(struct platform_device *pdev) if (irq != NO_IRQ) free_irq(irq, data); - if (data) { - memset(data, 0, sizeof(struct pamu_isr_data)); - kfree(data); - } + kzfree(data); if (pamu_regs) iounmap(pamu_regs); From e725a00a8f2e1ae866c29f956d637a889f561882 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sat, 6 Jun 2020 12:16:17 -0700 Subject: [PATCH 015/291] iommu/qcom: Change CONFIG_BIG_ENDIAN to CONFIG_CPU_BIG_ENDIAN CONFIG_BIG_ENDIAN does not exist as a Kconfig symbol. Signed-off-by: Joe Perches Reviewed-by: Rob Clark Link: https://lore.kernel.org/r/5a663096b489b86472fe3bfbd5138c411d669bad.camel@perches.com Signed-off-by: Joerg Roedel --- drivers/iommu/qcom_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index 801768cf86c6..cca39b209158 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -310,7 +310,7 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain, ARM_SMMU_SCTLR_M | ARM_SMMU_SCTLR_S1_ASIDPNE | ARM_SMMU_SCTLR_CFCFG; - if (IS_ENABLED(CONFIG_BIG_ENDIAN)) + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) reg |= ARM_SMMU_SCTLR_E; iommu_writel(ctx, ARM_SMMU_CB_SCTLR, reg); From 215c224f4dfa89f1d97500f419092c0110da3c2e Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Thu, 11 Jun 2020 20:10:29 +0900 Subject: [PATCH 016/291] dt-bindings: iommu: renesas,ipmmu-vmsa: add r8a77961 support Add support for r8a77961 (R-Car M3-W+). Signed-off-by: Yoshihiro Shimoda Reviewed-by: Geert Uytterhoeven Acked-by: Rob Herring Link: https://lore.kernel.org/r/1591873830-10128-2-git-send-email-yoshihiro.shimoda.uh@renesas.com Signed-off-by: Joerg Roedel --- Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml index 39675cf4ed71..e9d28a4060fa 100644 --- a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml +++ b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml @@ -35,6 +35,7 @@ properties: - renesas,ipmmu-r8a774c0 # RZ/G2E - renesas,ipmmu-r8a7795 # R-Car H3 - renesas,ipmmu-r8a7796 # R-Car M3-W + - renesas,ipmmu-r8a77961 # R-Car M3-W+ - renesas,ipmmu-r8a77965 # R-Car M3-N - renesas,ipmmu-r8a77970 # R-Car V3M - renesas,ipmmu-r8a77980 # R-Car V3H From 17fe16181639801bfeba647a1e452a75efe651b4 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Thu, 11 Jun 2020 20:10:30 +0900 Subject: [PATCH 017/291] iommu/renesas: Add support for r8a77961 Add support for r8a77961 (R-Car M3-W+). Signed-off-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/1591873830-10128-3-git-send-email-yoshihiro.shimoda.uh@renesas.com Signed-off-by: Joerg Roedel --- drivers/iommu/ipmmu-vmsa.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 4c2972f3153b..b57b1f213a48 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -3,7 +3,7 @@ * IOMMU API for Renesas VMSA-compatible IPMMU * Author: Laurent Pinchart * - * Copyright (C) 2014 Renesas Electronics Corporation + * Copyright (C) 2014-2020 Renesas Electronics Corporation */ #include @@ -753,6 +753,7 @@ static const struct soc_device_attribute soc_rcar_gen3_whitelist[] = { { .soc_id = "r8a774b1", }, { .soc_id = "r8a774c0", }, { .soc_id = "r8a7795", .revision = "ES3.*" }, + { .soc_id = "r8a77961", }, { .soc_id = "r8a77965", }, { .soc_id = "r8a77990", }, { .soc_id = "r8a77995", }, @@ -969,6 +970,9 @@ static const struct of_device_id ipmmu_of_ids[] = { }, { .compatible = "renesas,ipmmu-r8a7796", .data = &ipmmu_features_rcar_gen3, + }, { + .compatible = "renesas,ipmmu-r8a77961", + .data = &ipmmu_features_rcar_gen3, }, { .compatible = "renesas,ipmmu-r8a77965", .data = &ipmmu_features_rcar_gen3, From 3c5ca501b46b91e68b935b4bd752a0aba5232208 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Thu, 25 Jun 2020 19:02:41 +0200 Subject: [PATCH 018/291] platform/chrome: cros_ec_spi: Document missing function parameters Kerneldoc expects all kernel function members to be documented. Fixes the following W=1 level warnings: cros_ec_spi.c:153: warning: Function parameter or member 'ec_dev' not described in 'receive_n_bytes' cros_ec_spi.c:153: warning: Function parameter or member 'buf' not described in 'receive_n_bytes' cros_ec_spi.c:153: warning: Function parameter or member 'n' not described in 'receive_n_bytes' Signed-off-by: Enric Balletbo i Serra Reviewed-by: Gwendal Grignou --- drivers/platform/chrome/cros_ec_spi.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/platform/chrome/cros_ec_spi.c b/drivers/platform/chrome/cros_ec_spi.c index debea5c4c829..a74e91df264b 100644 --- a/drivers/platform/chrome/cros_ec_spi.c +++ b/drivers/platform/chrome/cros_ec_spi.c @@ -148,6 +148,10 @@ static int terminate_request(struct cros_ec_device *ec_dev) * receive_n_bytes - receive n bytes from the EC. * * Assumes buf is a pointer into the ec_dev->din buffer + * + * @ec_dev: ChromeOS EC device. + * @buf: Pointer to the buffer receiving the data. + * @n: Number of bytes received. */ static int receive_n_bytes(struct cros_ec_device *ec_dev, u8 *buf, int n) { From 9a876ba58d1e660e7957dd7afd1129b615eb1e04 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Thu, 25 Jun 2020 19:03:00 +0200 Subject: [PATCH 019/291] platform/chrome: cros_ec_rpmsg: Document missing struct parameters Kerneldoc expects all kernel structure member to be documented. Fixes the following W=1 level warnings: cros_ec_rpmsg.c:49: warning: Function parameter or member 'ept' not described in 'cros_ec_rpmsg' cros_ec_rpmsg.c:49: warning: Function parameter or member 'has_pending_host_event' not described in 'cros_ec_rpmsg' cros_ec_rpmsg.c:49: warning: Function parameter or member 'probe_done' not described in 'cros_ec_rpmsg' Signed-off-by: Enric Balletbo i Serra Reviewed-by: Gwendal Grignou --- drivers/platform/chrome/cros_ec_rpmsg.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/platform/chrome/cros_ec_rpmsg.c b/drivers/platform/chrome/cros_ec_rpmsg.c index 7e8629e3db74..30d0ba3b8889 100644 --- a/drivers/platform/chrome/cros_ec_rpmsg.c +++ b/drivers/platform/chrome/cros_ec_rpmsg.c @@ -38,6 +38,9 @@ struct cros_ec_rpmsg_response { * @rpdev: rpmsg device we are connected to * @xfer_ack: completion for host command transfer. * @host_event_work: Work struct for pending host event. + * @ept: The rpmsg endpoint of this channel. + * @has_pending_host_event: Boolean used to check if there is a pending event. + * @probe_done: Flag to indicate that probe is done. */ struct cros_ec_rpmsg { struct rpmsg_device *rpdev; From aaa3cbbac326c95308e315f1ab964a3369c4d07d Mon Sep 17 00:00:00 2001 From: Qiushi Wu Date: Fri, 22 May 2020 22:16:08 -0500 Subject: [PATCH 020/291] platform/chrome: cros_ec_ishtp: Fix a double-unlock issue MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In function cros_ec_ishtp_probe(), "up_write" is already called before function "cros_ec_dev_init". But "up_write" will be called again after the calling of the function "cros_ec_dev_init" failed. Thus add a call of the function “down_write” in this if branch for the completion of the exception handling. Fixes: 26a14267aff2 ("platform/chrome: Add ChromeOS EC ISHTP driver") Signed-off-by: Qiushi Wu Tested-by: Mathew King Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_ishtp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c index ed794a7ddba9..81364029af36 100644 --- a/drivers/platform/chrome/cros_ec_ishtp.c +++ b/drivers/platform/chrome/cros_ec_ishtp.c @@ -681,8 +681,10 @@ static int cros_ec_ishtp_probe(struct ishtp_cl_device *cl_device) /* Register croc_ec_dev mfd */ rv = cros_ec_dev_init(client_data); - if (rv) + if (rv) { + down_write(&init_lock); goto end_cros_ec_dev_init_error; + } return 0; From 970471914c67b70df24def6b2a30cc42acbebded Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 16 Jun 2020 16:47:14 +0200 Subject: [PATCH 021/291] iommu: Allow page responses without PASID Some PCIe devices do not expect a PASID value in PRI Page Responses. If the "PRG Response PASID Required" bit in the PRI capability is zero, then the OS should not set the PASID field. Similarly on Arm SMMU, responses to stall events do not have a PASID. Currently iommu_page_response() systematically checks that the PASID in the page response corresponds to the one in the page request. This can't work with virtualization because a page response coming from a guest OS won't have a PASID if the passed-through device does not require one. Add a flag to page requests that declares whether the corresponding response needs to have a PASID. When this flag isn't set, allow page responses without PASID. Reported-by: Shameerali Kolothum Thodi Signed-off-by: Jean-Philippe Brucker Link: https://lore.kernel.org/r/20200616144712.748818-1-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 25 ++++++++++++++++++------- include/uapi/linux/iommu.h | 6 +++++- 2 files changed, 23 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index d43120eb1dc5..1ed1e14a1f0c 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1185,11 +1185,12 @@ EXPORT_SYMBOL_GPL(iommu_report_device_fault); int iommu_page_response(struct device *dev, struct iommu_page_response *msg) { - bool pasid_valid; + bool needs_pasid; int ret = -EINVAL; struct iommu_fault_event *evt; struct iommu_fault_page_request *prm; struct dev_iommu *param = dev->iommu; + bool has_pasid = msg->flags & IOMMU_PAGE_RESP_PASID_VALID; struct iommu_domain *domain = iommu_get_domain_for_dev(dev); if (!domain || !domain->ops->page_response) @@ -1214,14 +1215,24 @@ int iommu_page_response(struct device *dev, */ list_for_each_entry(evt, ¶m->fault_param->faults, list) { prm = &evt->fault.prm; - pasid_valid = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID; - - if ((pasid_valid && prm->pasid != msg->pasid) || - prm->grpid != msg->grpid) + if (prm->grpid != msg->grpid) continue; - /* Sanitize the reply */ - msg->flags = pasid_valid ? IOMMU_PAGE_RESP_PASID_VALID : 0; + /* + * If the PASID is required, the corresponding request is + * matched using the group ID, the PASID valid bit and the PASID + * value. Otherwise only the group ID matches request and + * response. + */ + needs_pasid = prm->flags & IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID; + if (needs_pasid && (!has_pasid || msg->pasid != prm->pasid)) + continue; + + if (!needs_pasid && has_pasid) { + /* No big deal, just clear it. */ + msg->flags &= ~IOMMU_PAGE_RESP_PASID_VALID; + msg->pasid = 0; + } ret = domain->ops->page_response(dev, evt, msg); list_del(&evt->list); diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index e907b7091a46..c2b2caf9ed41 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -81,7 +81,10 @@ struct iommu_fault_unrecoverable { /** * struct iommu_fault_page_request - Page Request data * @flags: encodes whether the corresponding fields are valid and whether this - * is the last page in group (IOMMU_FAULT_PAGE_REQUEST_* values) + * is the last page in group (IOMMU_FAULT_PAGE_REQUEST_* values). + * When IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID is set, the page response + * must have the same PASID value as the page request. When it is clear, + * the page response should not have a PASID. * @pasid: Process Address Space ID * @grpid: Page Request Group Index * @perm: requested page permissions (IOMMU_FAULT_PERM_* values) @@ -92,6 +95,7 @@ struct iommu_fault_page_request { #define IOMMU_FAULT_PAGE_REQUEST_PASID_VALID (1 << 0) #define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE (1 << 1) #define IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA (1 << 2) +#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID (1 << 3) __u32 flags; __u32 pasid; __u32 grpid; From 9a295ff0ffc94e1be60d604fee0cce4fbb3b8964 Mon Sep 17 00:00:00 2001 From: Paul Menzel Date: Wed, 17 Jun 2020 00:04:20 +0200 Subject: [PATCH 022/291] iommu/amd: Print extended features in one line to fix divergent log levels Currently, Linux logs the two messages below. [ 0.979142] pci 0000:00:00.2: AMD-Vi: Extended features (0xf77ef22294ada): [ 0.979546] PPR NX GT IA GA PC GA_vAPIC The log level of these lines differs though. The first one has level *info*, while the second has level *warn*, which is confusing. $ dmesg -T --level=info | grep "Extended features" [Tue Jun 16 21:46:58 2020] pci 0000:00:00.2: AMD-Vi: Extended features (0xf77ef22294ada): $ dmesg -T --level=warn | grep "PPR" [Tue Jun 16 21:46:58 2020] PPR NX GT IA GA PC GA_vAPIC The problem is, that commit 3928aa3f57 ("iommu/amd: Detect and enable guest vAPIC support") introduced a newline, causing `pr_cont()`, used to print the features, to default back to the default log level. /** * pr_cont - Continues a previous log message in the same line. * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_CONT loglevel. It should only be * used when continuing a log message with no newline ('\n') enclosed. Otherwise * it defaults back to KERN_DEFAULT loglevel. */ #define pr_cont(fmt, ...) \ printk(KERN_CONT fmt, ##__VA_ARGS__) So, remove the line break, so only one line is logged. Fixes: 3928aa3f57 ("iommu/amd: Detect and enable guest vAPIC support") Signed-off-by: Paul Menzel Reviewed-by: Suravee Suthikulpanit Cc: Suravee Suthikulpanit Cc: iommu@lists.linux-foundation.org Link: https://lore.kernel.org/r/20200616220420.19466-1-pmenzel@molgen.mpg.de Signed-off-by: Joerg Roedel --- drivers/iommu/amd/init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 6ebd4825e320..232683ea10e0 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1842,7 +1842,7 @@ static void print_iommu_info(void) pci_info(pdev, "Found IOMMU cap 0x%hx\n", iommu->cap_ptr); if (iommu->cap & (1 << IOMMU_CAP_EFR)) { - pci_info(pdev, "Extended features (%#llx):\n", + pci_info(pdev, "Extended features (%#llx):", iommu->features); for (i = 0; i < ARRAY_SIZE(feat_str); ++i) { if (iommu_feature(iommu, (1ULL << i))) From 70fcd3592b05fde4d95938cd5a20e996b4ef4e15 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 26 Jun 2020 10:05:46 +0200 Subject: [PATCH 023/291] iommu/amd: Add helper functions to update domain->pt_root Do not call atomic64_set() directly to update the domain page-table root and use two new helper functions. This makes it easier to implement additional work necessary when the page-table is updated. Signed-off-by: Joerg Roedel Link: https://lore.kernel.org/r/20200626080547.24865-2-joro@8bytes.org --- drivers/iommu/amd/iommu.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-) diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 74cca1757172..5286ddcfc2f9 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -162,7 +162,18 @@ static void amd_iommu_domain_get_pgtable(struct protection_domain *domain, pgtable->mode = pt_root & 7; /* lowest 3 bits encode pgtable mode */ } -static u64 amd_iommu_domain_encode_pgtable(u64 *root, int mode) +static void amd_iommu_domain_set_pt_root(struct protection_domain *domain, u64 root) +{ + atomic64_set(&domain->pt_root, root); +} + +static void amd_iommu_domain_clr_pt_root(struct protection_domain *domain) +{ + amd_iommu_domain_set_pt_root(domain, 0); +} + +static void amd_iommu_domain_set_pgtable(struct protection_domain *domain, + u64 *root, int mode) { u64 pt_root; @@ -170,7 +181,7 @@ static u64 amd_iommu_domain_encode_pgtable(u64 *root, int mode) pt_root = mode & 7; pt_root |= (u64)root; - return pt_root; + amd_iommu_domain_set_pt_root(domain, pt_root); } static struct iommu_dev_data *alloc_dev_data(u16 devid) @@ -1410,7 +1421,7 @@ static bool increase_address_space(struct protection_domain *domain, struct domain_pgtable pgtable; unsigned long flags; bool ret = true; - u64 *pte, root; + u64 *pte; spin_lock_irqsave(&domain->lock, flags); @@ -1438,8 +1449,7 @@ static bool increase_address_space(struct protection_domain *domain, * Device Table needs to be updated and flushed before the new root can * be published. */ - root = amd_iommu_domain_encode_pgtable(pte, pgtable.mode); - atomic64_set(&domain->pt_root, root); + amd_iommu_domain_set_pgtable(domain, pte, pgtable.mode); ret = true; @@ -2319,7 +2329,7 @@ static void protection_domain_free(struct protection_domain *domain) domain_id_free(domain->id); amd_iommu_domain_get_pgtable(domain, &pgtable); - atomic64_set(&domain->pt_root, 0); + amd_iommu_domain_clr_pt_root(domain); free_pagetable(&pgtable); kfree(domain); @@ -2327,7 +2337,7 @@ static void protection_domain_free(struct protection_domain *domain) static int protection_domain_init(struct protection_domain *domain, int mode) { - u64 *pt_root = NULL, root; + u64 *pt_root = NULL; BUG_ON(mode < PAGE_MODE_NONE || mode > PAGE_MODE_6_LEVEL); @@ -2343,8 +2353,7 @@ static int protection_domain_init(struct protection_domain *domain, int mode) return -ENOMEM; } - root = amd_iommu_domain_encode_pgtable(pt_root, mode); - atomic64_set(&domain->pt_root, root); + amd_iommu_domain_set_pgtable(domain, pt_root, mode); return 0; } @@ -2713,8 +2722,8 @@ void amd_iommu_domain_direct_map(struct iommu_domain *dom) /* First save pgtable configuration*/ amd_iommu_domain_get_pgtable(domain, &pgtable); - /* Update data structure */ - atomic64_set(&domain->pt_root, 0); + /* Remove page-table from domain */ + amd_iommu_domain_clr_pt_root(domain); /* Make changes visible to IOMMUs */ update_domain(domain); From 0f45b04da18305726c18d4b6169c4083f301d91c Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:24 +0200 Subject: [PATCH 024/291] iommu/exynos: Use dev_iommu_priv_get/set() Remove the use of dev->archdata.iommu and use the private per-device pointer provided by IOMMU core code instead. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Acked-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200625130836.1916-2-joro@8bytes.org --- drivers/iommu/exynos-iommu.c | 20 +++++++++---------- .../media/platform/s5p-mfc/s5p_mfc_iommu.h | 4 +++- 2 files changed, 13 insertions(+), 11 deletions(-) diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 60c8a56e4a3f..6a9b67302369 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -173,7 +173,7 @@ static u32 lv2ent_offset(sysmmu_iova_t iova) #define REG_V5_FAULT_AR_VA 0x070 #define REG_V5_FAULT_AW_VA 0x080 -#define has_sysmmu(dev) (dev->archdata.iommu != NULL) +#define has_sysmmu(dev) (dev_iommu_priv_get(dev) != NULL) static struct device *dma_dev; static struct kmem_cache *lv2table_kmem_cache; @@ -226,7 +226,7 @@ static const struct sysmmu_fault_info sysmmu_v5_faults[] = { }; /* - * This structure is attached to dev.archdata.iommu of the master device + * This structure is attached to dev->iommu->priv of the master device * on device add, contains a list of SYSMMU controllers defined by device tree, * which are bound to given master device. It is usually referenced by 'owner' * pointer. @@ -670,7 +670,7 @@ static int __maybe_unused exynos_sysmmu_suspend(struct device *dev) struct device *master = data->master; if (master) { - struct exynos_iommu_owner *owner = master->archdata.iommu; + struct exynos_iommu_owner *owner = dev_iommu_priv_get(master); mutex_lock(&owner->rpm_lock); if (data->domain) { @@ -688,7 +688,7 @@ static int __maybe_unused exynos_sysmmu_resume(struct device *dev) struct device *master = data->master; if (master) { - struct exynos_iommu_owner *owner = master->archdata.iommu; + struct exynos_iommu_owner *owner = dev_iommu_priv_get(master); mutex_lock(&owner->rpm_lock); if (data->domain) { @@ -837,8 +837,8 @@ static void exynos_iommu_domain_free(struct iommu_domain *iommu_domain) static void exynos_iommu_detach_device(struct iommu_domain *iommu_domain, struct device *dev) { - struct exynos_iommu_owner *owner = dev->archdata.iommu; struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain); + struct exynos_iommu_owner *owner = dev_iommu_priv_get(dev); phys_addr_t pagetable = virt_to_phys(domain->pgtable); struct sysmmu_drvdata *data, *next; unsigned long flags; @@ -875,8 +875,8 @@ static void exynos_iommu_detach_device(struct iommu_domain *iommu_domain, static int exynos_iommu_attach_device(struct iommu_domain *iommu_domain, struct device *dev) { - struct exynos_iommu_owner *owner = dev->archdata.iommu; struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain); + struct exynos_iommu_owner *owner = dev_iommu_priv_get(dev); struct sysmmu_drvdata *data; phys_addr_t pagetable = virt_to_phys(domain->pgtable); unsigned long flags; @@ -1237,7 +1237,7 @@ static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *iommu_domain, static struct iommu_device *exynos_iommu_probe_device(struct device *dev) { - struct exynos_iommu_owner *owner = dev->archdata.iommu; + struct exynos_iommu_owner *owner = dev_iommu_priv_get(dev); struct sysmmu_drvdata *data; if (!has_sysmmu(dev)) @@ -1263,7 +1263,7 @@ static struct iommu_device *exynos_iommu_probe_device(struct device *dev) static void exynos_iommu_release_device(struct device *dev) { - struct exynos_iommu_owner *owner = dev->archdata.iommu; + struct exynos_iommu_owner *owner = dev_iommu_priv_get(dev); struct sysmmu_drvdata *data; if (!has_sysmmu(dev)) @@ -1287,8 +1287,8 @@ static void exynos_iommu_release_device(struct device *dev) static int exynos_iommu_of_xlate(struct device *dev, struct of_phandle_args *spec) { - struct exynos_iommu_owner *owner = dev->archdata.iommu; struct platform_device *sysmmu = of_find_device_by_node(spec->np); + struct exynos_iommu_owner *owner = dev_iommu_priv_get(dev); struct sysmmu_drvdata *data, *entry; if (!sysmmu) @@ -1305,7 +1305,7 @@ static int exynos_iommu_of_xlate(struct device *dev, INIT_LIST_HEAD(&owner->controllers); mutex_init(&owner->rpm_lock); - dev->archdata.iommu = owner; + dev_iommu_priv_set(dev, owner); } list_for_each_entry(entry, &owner->controllers, owner_node) diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_iommu.h b/drivers/media/platform/s5p-mfc/s5p_mfc_iommu.h index 152a713fff78..1a32266b7ddc 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc_iommu.h +++ b/drivers/media/platform/s5p-mfc/s5p_mfc_iommu.h @@ -9,9 +9,11 @@ #if defined(CONFIG_EXYNOS_IOMMU) +#include + static inline bool exynos_is_iommu_available(struct device *dev) { - return dev->archdata.iommu != NULL; + return dev_iommu_priv_get(dev) != NULL; } #else From 01b9d4e21148c89fdbab3d6b3705f9791314b631 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:25 +0200 Subject: [PATCH 025/291] iommu/vt-d: Use dev_iommu_priv_get/set() Remove the use of dev->archdata.iommu and use the private per-device pointer provided by IOMMU core code instead. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/20200625130836.1916-3-joro@8bytes.org --- .../gpu/drm/i915/selftests/mock_gem_device.c | 10 ++++++++-- drivers/iommu/intel/iommu.c | 18 +++++++++--------- 2 files changed, 17 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index 9b105b811f1f..e08601905a64 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -24,6 +24,7 @@ #include #include +#include #include @@ -118,6 +119,9 @@ struct drm_i915_private *mock_gem_device(void) { struct drm_i915_private *i915; struct pci_dev *pdev; +#if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) + struct dev_iommu iommu; +#endif int err; pdev = kzalloc(sizeof(*pdev), GFP_KERNEL); @@ -136,8 +140,10 @@ struct drm_i915_private *mock_gem_device(void) dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) - /* hack to disable iommu for the fake device; force identity mapping */ - pdev->dev.archdata.iommu = (void *)-1; + /* HACK HACK HACK to disable iommu for the fake device; force identity mapping */ + memset(&iommu, 0, sizeof(iommu)); + iommu.priv = (void *)-1; + pdev->dev.iommu = &iommu; #endif pci_set_drvdata(pdev, i915); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index d759e7234e98..2ce490c2eab8 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -372,7 +372,7 @@ struct device_domain_info *get_domain_info(struct device *dev) if (!dev) return NULL; - info = dev->archdata.iommu; + info = dev_iommu_priv_get(dev); if (unlikely(info == DUMMY_DEVICE_DOMAIN_INFO || info == DEFER_DEVICE_DOMAIN_INFO)) return NULL; @@ -743,12 +743,12 @@ struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, static int iommu_dummy(struct device *dev) { - return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO; + return dev_iommu_priv_get(dev) == DUMMY_DEVICE_DOMAIN_INFO; } static bool attach_deferred(struct device *dev) { - return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO; + return dev_iommu_priv_get(dev) == DEFER_DEVICE_DOMAIN_INFO; } /** @@ -2420,7 +2420,7 @@ static inline void unlink_domain_info(struct device_domain_info *info) list_del(&info->link); list_del(&info->global); if (info->dev) - info->dev->archdata.iommu = NULL; + dev_iommu_priv_set(info->dev, NULL); } static void domain_remove_dev_info(struct dmar_domain *domain) @@ -2453,7 +2453,7 @@ static void do_deferred_attach(struct device *dev) { struct iommu_domain *domain; - dev->archdata.iommu = NULL; + dev_iommu_priv_set(dev, NULL); domain = iommu_get_domain_for_dev(dev); if (domain) intel_iommu_attach_device(domain, dev); @@ -2599,7 +2599,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, list_add(&info->link, &domain->devices); list_add(&info->global, &device_domain_list); if (dev) - dev->archdata.iommu = info; + dev_iommu_priv_set(dev, info); spin_unlock_irqrestore(&device_domain_lock, flags); /* PASID table is mandatory for a PCI device in scalable mode. */ @@ -4004,7 +4004,7 @@ static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev) if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) { pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n"); add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); - pdev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO; + dev_iommu_priv_set(&pdev->dev, DUMMY_DEVICE_DOMAIN_INFO); } } DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu); @@ -4043,7 +4043,7 @@ static void __init init_no_remapping_devices(void) drhd->ignored = 1; for_each_active_dev_scope(drhd->devices, drhd->devices_cnt, i, dev) - dev->archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO; + dev_iommu_priv_set(dev, DUMMY_DEVICE_DOMAIN_INFO); } } } @@ -5665,7 +5665,7 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) return ERR_PTR(-ENODEV); if (translation_pre_enabled(iommu)) - dev->archdata.iommu = DEFER_DEVICE_DOMAIN_INFO; + dev_iommu_priv_set(dev, DEFER_DEVICE_DOMAIN_INFO); return &iommu->iommu; } From 4bbe0c7ccc431dcf06242860a7900f92800724c0 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:26 +0200 Subject: [PATCH 026/291] iommu/msm: Use dev_iommu_priv_get/set() Remove the use of dev->archdata.iommu and use the private per-device pointer provided by IOMMU core code instead. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20200625130836.1916-4-joro@8bytes.org --- drivers/iommu/msm_iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 3d8a63555c25..f773cc85f311 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -593,14 +593,14 @@ static void insert_iommu_master(struct device *dev, struct msm_iommu_dev **iommu, struct of_phandle_args *spec) { - struct msm_iommu_ctx_dev *master = dev->archdata.iommu; + struct msm_iommu_ctx_dev *master = dev_iommu_priv_get(dev); int sid; if (list_empty(&(*iommu)->ctx_list)) { master = kzalloc(sizeof(*master), GFP_ATOMIC); master->of_node = dev->of_node; list_add(&master->list, &(*iommu)->ctx_list); - dev->archdata.iommu = master; + dev_iommu_priv_set(dev, master); } for (sid = 0; sid < master->num_mids; sid++) From 97ea1202601a7f936c9c9a86f900ec001cb589d3 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:27 +0200 Subject: [PATCH 027/291] iommu/omap: Use dev_iommu_priv_get/set() Remove the use of dev->archdata.iommu and use the private per-device pointer provided by IOMMU core code instead. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20200625130836.1916-5-joro@8bytes.org --- drivers/iommu/omap-iommu.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index c8282cc212cb..e84ead6fb234 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -71,7 +71,7 @@ static struct omap_iommu_domain *to_omap_domain(struct iommu_domain *dom) **/ void omap_iommu_save_ctx(struct device *dev) { - struct omap_iommu_arch_data *arch_data = dev->archdata.iommu; + struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev); struct omap_iommu *obj; u32 *p; int i; @@ -101,7 +101,7 @@ EXPORT_SYMBOL_GPL(omap_iommu_save_ctx); **/ void omap_iommu_restore_ctx(struct device *dev) { - struct omap_iommu_arch_data *arch_data = dev->archdata.iommu; + struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev); struct omap_iommu *obj; u32 *p; int i; @@ -1398,7 +1398,7 @@ static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da, static int omap_iommu_count(struct device *dev) { - struct omap_iommu_arch_data *arch_data = dev->archdata.iommu; + struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev); int count = 0; while (arch_data->iommu_dev) { @@ -1459,8 +1459,8 @@ static void omap_iommu_detach_fini(struct omap_iommu_domain *odomain) static int omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev) { + struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev); struct omap_iommu_domain *omap_domain = to_omap_domain(domain); - struct omap_iommu_arch_data *arch_data = dev->archdata.iommu; struct omap_iommu_device *iommu; struct omap_iommu *oiommu; int ret = 0; @@ -1524,7 +1524,7 @@ omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev) static void _omap_iommu_detach_dev(struct omap_iommu_domain *omap_domain, struct device *dev) { - struct omap_iommu_arch_data *arch_data = dev->archdata.iommu; + struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev); struct omap_iommu_device *iommu = omap_domain->iommus; struct omap_iommu *oiommu; int i; @@ -1650,7 +1650,7 @@ static struct iommu_device *omap_iommu_probe_device(struct device *dev) int num_iommus, i; /* - * Allocate the archdata iommu structure for DT-based devices. + * Allocate the per-device iommu structure for DT-based devices. * * TODO: Simplify this when removing non-DT support completely from the * IOMMU users. @@ -1698,7 +1698,7 @@ static struct iommu_device *omap_iommu_probe_device(struct device *dev) of_node_put(np); } - dev->archdata.iommu = arch_data; + dev_iommu_priv_set(dev, arch_data); /* * use the first IOMMU alone for the sysfs device linking. @@ -1712,19 +1712,19 @@ static struct iommu_device *omap_iommu_probe_device(struct device *dev) static void omap_iommu_release_device(struct device *dev) { - struct omap_iommu_arch_data *arch_data = dev->archdata.iommu; + struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev); if (!dev->of_node || !arch_data) return; - dev->archdata.iommu = NULL; + dev_iommu_priv_set(dev, NULL); kfree(arch_data); } static struct iommu_group *omap_iommu_device_group(struct device *dev) { - struct omap_iommu_arch_data *arch_data = dev->archdata.iommu; + struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev); struct iommu_group *group = ERR_PTR(-EINVAL); if (!arch_data) From 8b9cc3b71bfda8e7c273b8f0fd80a8860ed077ad Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:28 +0200 Subject: [PATCH 028/291] iommu/rockchip: Use dev_iommu_priv_get/set() Remove the use of dev->archdata.iommu and use the private per-device pointer provided by IOMMU core code instead. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20200625130836.1916-6-joro@8bytes.org --- drivers/iommu/rockchip-iommu.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index d25c2486ca07..e5d86b7177de 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -836,7 +836,7 @@ static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova, static struct rk_iommu *rk_iommu_from_dev(struct device *dev) { - struct rk_iommudata *data = dev->archdata.iommu; + struct rk_iommudata *data = dev_iommu_priv_get(dev); return data ? data->iommu : NULL; } @@ -1059,7 +1059,7 @@ static struct iommu_device *rk_iommu_probe_device(struct device *dev) struct rk_iommudata *data; struct rk_iommu *iommu; - data = dev->archdata.iommu; + data = dev_iommu_priv_get(dev); if (!data) return ERR_PTR(-ENODEV); @@ -1073,7 +1073,7 @@ static struct iommu_device *rk_iommu_probe_device(struct device *dev) static void rk_iommu_release_device(struct device *dev) { - struct rk_iommudata *data = dev->archdata.iommu; + struct rk_iommudata *data = dev_iommu_priv_get(dev); device_link_del(data->link); } @@ -1100,7 +1100,7 @@ static int rk_iommu_of_xlate(struct device *dev, iommu_dev = of_find_device_by_node(args->np); data->iommu = platform_get_drvdata(iommu_dev); - dev->archdata.iommu = data; + dev_iommu_priv_set(dev, data); platform_device_put(iommu_dev); From a5616e24609a2bb3dc6ea1ab360207fa1198c976 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:29 +0200 Subject: [PATCH 029/291] iommu/tegra: Use dev_iommu_priv_get/set() Remove the use of dev->archdata.iommu and use the private per-device pointer provided by IOMMU core code instead. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20200625130836.1916-7-joro@8bytes.org --- drivers/iommu/tegra-gart.c | 8 ++++---- drivers/iommu/tegra-smmu.c | 8 ++++---- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index 5fbdff6ff41a..fac720273889 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -113,8 +113,8 @@ static int gart_iommu_attach_dev(struct iommu_domain *domain, if (gart->active_domain && gart->active_domain != domain) { ret = -EBUSY; - } else if (dev->archdata.iommu != domain) { - dev->archdata.iommu = domain; + } else if (dev_iommu_priv_get(dev) != domain) { + dev_iommu_priv_set(dev, domain); gart->active_domain = domain; gart->active_devices++; } @@ -131,8 +131,8 @@ static void gart_iommu_detach_dev(struct iommu_domain *domain, spin_lock(&gart->dom_lock); - if (dev->archdata.iommu == domain) { - dev->archdata.iommu = NULL; + if (dev_iommu_priv_get(dev) == domain) { + dev_iommu_priv_set(dev, NULL); if (--gart->active_devices == 0) gart->active_domain = NULL; diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 7426b7666e2b..124c8848ab7e 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -465,7 +465,7 @@ static void tegra_smmu_as_unprepare(struct tegra_smmu *smmu, static int tegra_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) { - struct tegra_smmu *smmu = dev->archdata.iommu; + struct tegra_smmu *smmu = dev_iommu_priv_get(dev); struct tegra_smmu_as *as = to_smmu_as(domain); struct device_node *np = dev->of_node; struct of_phandle_args args; @@ -780,7 +780,7 @@ static struct iommu_device *tegra_smmu_probe_device(struct device *dev) * supported by the Linux kernel, so abort after the * first match. */ - dev->archdata.iommu = smmu; + dev_iommu_priv_set(dev, smmu); break; } @@ -797,7 +797,7 @@ static struct iommu_device *tegra_smmu_probe_device(struct device *dev) static void tegra_smmu_release_device(struct device *dev) { - dev->archdata.iommu = NULL; + dev_iommu_priv_set(dev, NULL); } static const struct tegra_smmu_group_soc * @@ -856,7 +856,7 @@ static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu, static struct iommu_group *tegra_smmu_device_group(struct device *dev) { struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct tegra_smmu *smmu = dev->archdata.iommu; + struct tegra_smmu *smmu = dev_iommu_priv_get(dev); struct iommu_group *group; group = tegra_smmu_group_get(smmu, fwspec->ids[0]); From 2263d818bceff516254bfce4091632530720505a Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:30 +0200 Subject: [PATCH 030/291] iommu/pamu: Use dev_iommu_priv_get/set() Remove the use of dev->archdata.iommu_domain and use the private per-device pointer provided by IOMMU core code instead. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20200625130836.1916-8-joro@8bytes.org --- drivers/iommu/fsl_pamu_domain.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c index 928d37771ece..b2110767caf4 100644 --- a/drivers/iommu/fsl_pamu_domain.c +++ b/drivers/iommu/fsl_pamu_domain.c @@ -323,7 +323,7 @@ static void remove_device_ref(struct device_domain_info *info, u32 win_cnt) pamu_disable_liodn(info->liodn); spin_unlock_irqrestore(&iommu_lock, flags); spin_lock_irqsave(&device_domain_lock, flags); - info->dev->archdata.iommu_domain = NULL; + dev_iommu_priv_set(info->dev, NULL); kmem_cache_free(iommu_devinfo_cache, info); spin_unlock_irqrestore(&device_domain_lock, flags); } @@ -352,7 +352,7 @@ static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct d * Check here if the device is already attached to domain or not. * If the device is already attached to a domain detach it. */ - old_domain_info = dev->archdata.iommu_domain; + old_domain_info = dev_iommu_priv_get(dev); if (old_domain_info && old_domain_info->domain != dma_domain) { spin_unlock_irqrestore(&device_domain_lock, flags); detach_device(dev, old_domain_info->domain); @@ -371,8 +371,8 @@ static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct d * the info for the first LIODN as all * LIODNs share the same domain */ - if (!dev->archdata.iommu_domain) - dev->archdata.iommu_domain = info; + if (!dev_iommu_priv_get(dev)) + dev_iommu_priv_set(dev, info); spin_unlock_irqrestore(&device_domain_lock, flags); } From 589601720d9d0366670eb415a4a62692d7af3713 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:31 +0200 Subject: [PATCH 031/291] iommu/mediatek: Do no use dev->archdata.iommu The iommu private pointer is already used in the Mediatek IOMMU v1 driver, so move the dma_iommu_mapping pointer into 'struct mtk_iommu_data' and do not use dev->archdata.iommu anymore. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20200625130836.1916-9-joro@8bytes.org --- drivers/iommu/mtk_iommu.h | 2 ++ drivers/iommu/mtk_iommu_v1.c | 10 ++++------ 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index ea949a324e33..1682406e98dc 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -62,6 +62,8 @@ struct mtk_iommu_data { struct iommu_device iommu; const struct mtk_iommu_plat_data *plat_data; + struct dma_iommu_mapping *mapping; /* For mtk_iommu_v1.c */ + struct list_head list; struct mtk_smi_larb_iommu larb_imu[MTK_LARB_NR_MAX]; }; diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index c9d79cff4d17..82ddfe9170d4 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -269,7 +269,7 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain, int ret; /* Only allow the domain created internally. */ - mtk_mapping = data->dev->archdata.iommu; + mtk_mapping = data->mapping; if (mtk_mapping->domain != domain) return 0; @@ -369,7 +369,6 @@ static int mtk_iommu_create_mapping(struct device *dev, struct mtk_iommu_data *data; struct platform_device *m4updev; struct dma_iommu_mapping *mtk_mapping; - struct device *m4udev; int ret; if (args->args_count != 1) { @@ -401,8 +400,7 @@ static int mtk_iommu_create_mapping(struct device *dev, return ret; data = dev_iommu_priv_get(dev); - m4udev = data->dev; - mtk_mapping = m4udev->archdata.iommu; + mtk_mapping = data->mapping; if (!mtk_mapping) { /* MTK iommu support 4GB iova address space. */ mtk_mapping = arm_iommu_create_mapping(&platform_bus_type, @@ -410,7 +408,7 @@ static int mtk_iommu_create_mapping(struct device *dev, if (IS_ERR(mtk_mapping)) return PTR_ERR(mtk_mapping); - m4udev->archdata.iommu = mtk_mapping; + data->mapping = mtk_mapping; } return 0; @@ -459,7 +457,7 @@ static void mtk_iommu_probe_finalize(struct device *dev) int err; data = dev_iommu_priv_get(dev); - mtk_mapping = data->dev->archdata.iommu; + mtk_mapping = data->mapping; err = arm_iommu_attach_device(dev, mtk_mapping); if (err) From ad962d864c61a73757085847027a532cbe2c1353 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:32 +0200 Subject: [PATCH 032/291] x86: Remove dev->archdata.iommu pointer There are no users left, all drivers have been converted to use the per-device private pointer offered by IOMMU core. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Acked-by: Borislav Petkov Link: https://lore.kernel.org/r/20200625130836.1916-10-joro@8bytes.org --- arch/x86/include/asm/device.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index 49bd6cf3eec9..7c0a52ca2f4d 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -3,9 +3,6 @@ #define _ASM_X86_DEVICE_H struct dev_archdata { -#ifdef CONFIG_IOMMU_API - void *iommu; /* hook for IOMMU specific extension */ -#endif }; struct pdev_archdata { From 0b660afe310855c6eef35f8082594f32e3b05511 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:33 +0200 Subject: [PATCH 033/291] ia64: Remove dev->archdata.iommu pointer There are no users left, all drivers have been converted to use the per-device private pointer offered by IOMMU core. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20200625130836.1916-11-joro@8bytes.org --- arch/ia64/include/asm/device.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/ia64/include/asm/device.h b/arch/ia64/include/asm/device.h index 3eb397415381..918b198cd5bb 100644 --- a/arch/ia64/include/asm/device.h +++ b/arch/ia64/include/asm/device.h @@ -6,9 +6,6 @@ #define _ASM_IA64_DEVICE_H struct dev_archdata { -#ifdef CONFIG_IOMMU_API - void *iommu; /* hook for IOMMU specific extension */ -#endif }; struct pdev_archdata { From fb0fd5f70c1bfc9cdf5406e82d5de0ecdbe1e80c Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:34 +0200 Subject: [PATCH 034/291] arm: Remove dev->archdata.iommu pointer There are no users left, all drivers have been converted to use the per-device private pointer offered by IOMMU core. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20200625130836.1916-12-joro@8bytes.org --- arch/arm/include/asm/device.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h index c675bc0d5aa8..be666f58bf7a 100644 --- a/arch/arm/include/asm/device.h +++ b/arch/arm/include/asm/device.h @@ -9,9 +9,6 @@ struct dev_archdata { #ifdef CONFIG_DMABOUNCE struct dmabounce_device_info *dmabounce; #endif -#ifdef CONFIG_IOMMU_API - void *iommu; /* private IOMMU data */ -#endif #ifdef CONFIG_ARM_DMA_USE_IOMMU struct dma_iommu_mapping *mapping; #endif From 5866a75b50b381fa05028e7ff3f2272ed006e321 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:35 +0200 Subject: [PATCH 035/291] arm64: Remove dev->archdata.iommu pointer There are no users left, all drivers have been converted to use the per-device private pointer offered by IOMMU core. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Acked-by: Will Deacon Link: https://lore.kernel.org/r/20200625130836.1916-13-joro@8bytes.org --- arch/arm64/include/asm/device.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm64/include/asm/device.h b/arch/arm64/include/asm/device.h index 12b778d55342..996498751318 100644 --- a/arch/arm64/include/asm/device.h +++ b/arch/arm64/include/asm/device.h @@ -6,9 +6,6 @@ #define __ASM_DEVICE_H struct dev_archdata { -#ifdef CONFIG_IOMMU_API - void *iommu; /* private IOMMU data */ -#endif }; struct pdev_archdata { From 6255c8c8d256b38b550b35c6362750f64ce46b8d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 25 Jun 2020 15:08:36 +0200 Subject: [PATCH 036/291] powerpc/dma: Remove dev->archdata.iommu_domain There are no users left, so remove the pointer and save some memory. Signed-off-by: Joerg Roedel Reviewed-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20200625130836.1916-14-joro@8bytes.org --- arch/powerpc/include/asm/device.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index 266542769e4b..1bc595213338 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -34,9 +34,6 @@ struct dev_archdata { struct iommu_table *iommu_table_base; #endif -#ifdef CONFIG_IOMMU_API - void *iommu_domain; -#endif #ifdef CONFIG_PPC64 struct pci_dn *pci_data; #endif From ca37faf3d7005b5588f045edfac1d82799c408a7 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Tue, 30 Jun 2020 10:17:56 +0200 Subject: [PATCH 037/291] iommu: Move sg_table wrapper out of CONFIG_IOMMU_SUPPORT Move the recently added sg_table wrapper out of CONFIG_IOMMU_SUPPORT to let the client code copile also when IOMMU support is disabled. Fixes: 48530d9fab0d ("iommu: add generic helper for mapping sgtable objects") Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200630081756.18526-1-m.szyprowski@samsung.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 5f0b7859d2eb..5657d4fef9f2 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -457,22 +457,6 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t io extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); -/** - * iommu_map_sgtable - Map the given buffer to the IOMMU domain - * @domain: The IOMMU domain to perform the mapping - * @iova: The start address to map the buffer - * @sgt: The sg_table object describing the buffer - * @prot: IOMMU protection bits - * - * Creates a mapping at @iova for the buffer described by a scatterlist - * stored in the given sg_table object in the provided IOMMU domain. - */ -static inline size_t iommu_map_sgtable(struct iommu_domain *domain, - unsigned long iova, struct sg_table *sgt, int prot) -{ - return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot); -} - extern void iommu_get_resv_regions(struct device *dev, struct list_head *list); extern void iommu_put_resv_regions(struct device *dev, struct list_head *list); extern void generic_iommu_put_resv_regions(struct device *dev, @@ -1079,6 +1063,22 @@ static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) } #endif /* CONFIG_IOMMU_API */ +/** + * iommu_map_sgtable - Map the given buffer to the IOMMU domain + * @domain: The IOMMU domain to perform the mapping + * @iova: The start address to map the buffer + * @sgt: The sg_table object describing the buffer + * @prot: IOMMU protection bits + * + * Creates a mapping at @iova for the buffer described by a scatterlist + * stored in the given sg_table object in the provided IOMMU domain. + */ +static inline size_t iommu_map_sgtable(struct iommu_domain *domain, + unsigned long iova, struct sg_table *sgt, int prot) +{ + return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot); +} + #ifdef CONFIG_IOMMU_DEBUGFS extern struct dentry *iommu_debugfs_dir; void iommu_debugfs_setup(void); From 557d4bec009330567ce99692918abbe9c77528e0 Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Fri, 5 Jun 2020 00:00:25 -0700 Subject: [PATCH 038/291] iommu: Add include/uapi/linux/iommu.h to MAINTAINERS file When include/uapi/linux/iommu.h was created it was never added to the file list in MAINTAINERS. Signed-off-by: Jerry Snitselaar Cc: Joerg Roedel Link: https://lore.kernel.org/r/20200605070025.216124-1-jsnitsel@redhat.com Signed-off-by: Joerg Roedel --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 496fd4eafb68..c23352059a6b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9014,6 +9014,7 @@ F: drivers/iommu/ F: include/linux/iommu.h F: include/linux/iova.h F: include/linux/of_iommu.h +F: include/uapi/linux/iommu.h IO_URING M: Jens Axboe From bdc4094591c3809e53eb7792344248bb447768c3 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Mon, 29 Jun 2020 12:32:23 +0200 Subject: [PATCH 039/291] platform/chrome: cros_ec_typec: Add a dependency on USB_ROLE_SWITCH As reported by the kernel test robot the cros_ec_typec driver fails to build if the USB_ROLE_SWITCH is not selected, to fix that, add a dependency on that symbol. This fixes the following build error: drivers/platform/chrome/cros_ec_typec.c:133: undefined reference to `usb_role_switch_put' ld: drivers/platform/chrome/cros_ec_typec.o: in function `cros_typec_get_switch_handles': drivers/platform/chrome/cros_ec_typec.c:108: undefined reference to `fwnode_usb_role_switch_get' ld: drivers/platform/chrome/cros_ec_typec.c:117: undefined reference to `usb_role_switch_put' Fixes: 7e7def15fa4b ("platform/chrome: cros_ec_typec: Add USB mux control") Reported-by: kernel test robot Acked-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig index cf072153bdc5..a056031dee81 100644 --- a/drivers/platform/chrome/Kconfig +++ b/drivers/platform/chrome/Kconfig @@ -218,6 +218,7 @@ config CROS_EC_TYPEC tristate "ChromeOS EC Type-C Connector Control" depends on MFD_CROS_EC_DEV && TYPEC depends on CROS_USBPD_NOTIFY + depends on USB_ROLE_SWITCH default MFD_CROS_EC_DEV help If you say Y here, you get support for accessing Type C connector From 83cbc69df8b8ec598ff8ca7629be34a50274e5b5 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Mon, 29 Jun 2020 14:13:27 -0700 Subject: [PATCH 040/291] platform/chrome: cros_ec_typec: Use workqueue for port update Use a work queue to call the port update routines, instead of doing it directly in the PD notifier callback. This will prevent other drivers with PD notifier callbacks from being blocked on the port update routine completing. Signed-off-by: Prashant Malani Reviewed-by: Guenter Roeck Reviewed-by: Heikki Krogerus Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_typec.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index 0c041b79cbba..9901bf2a96c2 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -58,6 +58,7 @@ struct cros_typec_data { /* Array of ports, indexed by port number. */ struct cros_typec_port *ports[EC_USB_PD_MAX_PORTS]; struct notifier_block nb; + struct work_struct port_work; }; static int cros_typec_parse_port_props(struct typec_capability *cap, @@ -619,11 +620,9 @@ static int cros_typec_get_cmd_version(struct cros_typec_data *typec) return 0; } -static int cros_ec_typec_event(struct notifier_block *nb, - unsigned long host_event, void *_notify) +static void cros_typec_port_work(struct work_struct *work) { - struct cros_typec_data *typec = container_of(nb, struct cros_typec_data, - nb); + struct cros_typec_data *typec = container_of(work, struct cros_typec_data, port_work); int ret, i; for (i = 0; i < typec->num_ports; i++) { @@ -631,6 +630,14 @@ static int cros_ec_typec_event(struct notifier_block *nb, if (ret < 0) dev_warn(typec->dev, "Update failed for port: %d\n", i); } +} + +static int cros_ec_typec_event(struct notifier_block *nb, + unsigned long host_event, void *_notify) +{ + struct cros_typec_data *typec = container_of(nb, struct cros_typec_data, nb); + + schedule_work(&typec->port_work); return NOTIFY_OK; } @@ -689,6 +696,12 @@ static int cros_typec_probe(struct platform_device *pdev) if (ret < 0) return ret; + INIT_WORK(&typec->port_work, cros_typec_port_work); + + /* + * Safe to call port update here, since we haven't registered the + * PD notifier yet. + */ for (i = 0; i < typec->num_ports; i++) { ret = cros_typec_port_update(typec, i); if (ret < 0) From 20b736872f7f324438649a277ec711a646ce8e8d Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Mon, 29 Jun 2020 14:13:29 -0700 Subject: [PATCH 041/291] platform/chrome: cros_ec_typec: Add PM support Define basic suspend resume functions for cros-ec-typec. On suspend, we simply ensure that any pending port update work is completed, and on resume, we re-poll the port state to account for any changes/disconnections that might have occurred during suspend. Signed-off-by: Prashant Malani Reviewed-by: Guenter Roeck Reviewed-by: Heikki Krogerus Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_typec.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index 9901bf2a96c2..3eae01f4c9f7 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -720,11 +720,35 @@ static int cros_typec_probe(struct platform_device *pdev) return ret; } +static int __maybe_unused cros_typec_suspend(struct device *dev) +{ + struct cros_typec_data *typec = dev_get_drvdata(dev); + + cancel_work_sync(&typec->port_work); + + return 0; +} + +static int __maybe_unused cros_typec_resume(struct device *dev) +{ + struct cros_typec_data *typec = dev_get_drvdata(dev); + + /* Refresh port state. */ + schedule_work(&typec->port_work); + + return 0; +} + +static const struct dev_pm_ops cros_typec_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(cros_typec_suspend, cros_typec_resume) +}; + static struct platform_driver cros_typec_driver = { .driver = { .name = DRV_NAME, .acpi_match_table = ACPI_PTR(cros_typec_acpi_id), .of_match_table = of_match_ptr(cros_typec_of_match), + .pm = &cros_typec_pm_ops, }, .probe = cros_typec_probe, }; From e48bc01ed5adec203676c735365373b31c3c7600 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 30 Jun 2020 00:52:03 -0700 Subject: [PATCH 042/291] platform/chrome: cros_ec_sensorhub: Fix EC timestamp overflow EC is using 32 bit timestamps (us), and before converting it to 64bit they were not casted, so it would overflow every 4s. Regular overflow every ~70 minutes was not taken into account either. Signed-off-by: Gwendal Grignou Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_sensorhub_ring.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/platform/chrome/cros_ec_sensorhub_ring.c b/drivers/platform/chrome/cros_ec_sensorhub_ring.c index 24e48d96ed76..b1c641c72f51 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub_ring.c +++ b/drivers/platform/chrome/cros_ec_sensorhub_ring.c @@ -419,9 +419,7 @@ cros_ec_sensor_ring_process_event(struct cros_ec_sensorhub *sensorhub, * Disable filtering since we might add more jitter * if b is in a random point in time. */ - new_timestamp = fifo_timestamp - - fifo_info->timestamp * 1000 + - in->timestamp * 1000; + new_timestamp = c - b * 1000 + a * 1000; /* * The timestamp can be stale if we had to use the fifo * info timestamp. From e1915eec54a6b4902664eaf6fb7a20de5624c4dd Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 26 Jun 2020 22:37:41 +0200 Subject: [PATCH 043/291] backlight: sky81452: Convert to GPIO descriptors The SKY81452 backlight driver just obtains a GPIO (named "gpios" in the device tree) drives it high and leaves it high until the driver is removed. Switch to use GPIO descriptors for this, simple and straight-forward. Cc: Gyungoh Yoo Signed-off-by: Linus Walleij Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/sky81452-backlight.c | 18 ++++-------------- .../linux/platform_data/sky81452-backlight.h | 6 ++++-- 2 files changed, 8 insertions(+), 16 deletions(-) diff --git a/drivers/video/backlight/sky81452-backlight.c b/drivers/video/backlight/sky81452-backlight.c index 2355f00f5773..81d2c8f3ca50 100644 --- a/drivers/video/backlight/sky81452-backlight.c +++ b/drivers/video/backlight/sky81452-backlight.c @@ -8,12 +8,11 @@ #include #include -#include +#include #include #include #include #include -#include #include #include #include @@ -182,7 +181,7 @@ static struct sky81452_bl_platform_data *sky81452_bl_parse_dt( pdata->ignore_pwm = of_property_read_bool(np, "skyworks,ignore-pwm"); pdata->dpwm_mode = of_property_read_bool(np, "skyworks,dpwm-mode"); pdata->phase_shift = of_property_read_bool(np, "skyworks,phase-shift"); - pdata->gpio_enable = of_get_gpio(np, 0); + pdata->gpiod_enable = devm_gpiod_get_optional(dev, NULL, GPIOD_OUT_HIGH); ret = of_property_count_u32_elems(np, "led-sources"); if (ret < 0) { @@ -264,15 +263,6 @@ static int sky81452_bl_probe(struct platform_device *pdev) return PTR_ERR(pdata); } - if (gpio_is_valid(pdata->gpio_enable)) { - ret = devm_gpio_request_one(dev, pdata->gpio_enable, - GPIOF_OUT_INIT_HIGH, "sky81452-en"); - if (ret < 0) { - dev_err(dev, "failed to request GPIO. err=%d\n", ret); - return ret; - } - } - ret = sky81452_bl_init_device(regmap, pdata); if (ret < 0) { dev_err(dev, "failed to initialize. err=%d\n", ret); @@ -312,8 +302,8 @@ static int sky81452_bl_remove(struct platform_device *pdev) bd->props.brightness = 0; backlight_update_status(bd); - if (gpio_is_valid(pdata->gpio_enable)) - gpio_set_value_cansleep(pdata->gpio_enable, 0); + if (pdata->gpiod_enable) + gpiod_set_value_cansleep(pdata->gpiod_enable, 0); return 0; } diff --git a/include/linux/platform_data/sky81452-backlight.h b/include/linux/platform_data/sky81452-backlight.h index 02653d92d84f..d6f46670d923 100644 --- a/include/linux/platform_data/sky81452-backlight.h +++ b/include/linux/platform_data/sky81452-backlight.h @@ -9,11 +9,13 @@ #ifndef _SKY81452_BACKLIGHT_H #define _SKY81452_BACKLIGHT_H +#include + /** * struct sky81452_platform_data * @name: backlight driver name. If it is not defined, default name is lcd-backlight. - * @gpio_enable:GPIO number which control EN pin + * @gpios_enable:GPIO descriptor which control EN pin * @enable: Enable mask for current sink channel 1, 2, 3, 4, 5 and 6. * @ignore_pwm: true if DPWMI should be ignored. * @dpwm_mode: true is DPWM dimming mode, otherwise Analog dimming mode. @@ -23,7 +25,7 @@ */ struct sky81452_bl_platform_data { const char *name; - int gpio_enable; + struct gpio_desc *gpiod_enable; unsigned int enable; bool ignore_pwm; bool dpwm_mode; From 08bf73a6f056d84fd52a58c5d165523dd84be535 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 26 Jun 2020 22:37:42 +0200 Subject: [PATCH 044/291] backlight: sky81452: Privatize platform data The only way the platform data for the SKY81452 ever gets populated is through the device tree. The MFD device is bothered with this for no reason at all. Just allocate the platform data in the driver and be happy. Cc: Gyungoh Yoo Signed-off-by: Linus Walleij Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/mfd/sky81452.c | 2 - drivers/video/backlight/sky81452-backlight.c | 34 +++++++++++++---- include/linux/mfd/sky81452.h | 2 - .../linux/platform_data/sky81452-backlight.h | 37 ------------------- 4 files changed, 27 insertions(+), 48 deletions(-) delete mode 100644 include/linux/platform_data/sky81452-backlight.h diff --git a/drivers/mfd/sky81452.c b/drivers/mfd/sky81452.c index 76eedfae8553..3ad35bf0c015 100644 --- a/drivers/mfd/sky81452.c +++ b/drivers/mfd/sky81452.c @@ -47,8 +47,6 @@ static int sky81452_probe(struct i2c_client *client, memset(cells, 0, sizeof(cells)); cells[0].name = "sky81452-backlight"; cells[0].of_compatible = "skyworks,sky81452-backlight"; - cells[0].platform_data = pdata->bl_pdata; - cells[0].pdata_size = sizeof(*pdata->bl_pdata); cells[1].name = "sky81452-regulator"; cells[1].platform_data = pdata->regulator_init_data; cells[1].pdata_size = sizeof(*pdata->regulator_init_data); diff --git a/drivers/video/backlight/sky81452-backlight.c b/drivers/video/backlight/sky81452-backlight.c index 81d2c8f3ca50..83ccb3d940fa 100644 --- a/drivers/video/backlight/sky81452-backlight.c +++ b/drivers/video/backlight/sky81452-backlight.c @@ -15,7 +15,6 @@ #include #include #include -#include #include /* registers */ @@ -41,6 +40,29 @@ #define SKY81452_DEFAULT_NAME "lcd-backlight" #define SKY81452_MAX_BRIGHTNESS (SKY81452_CS + 1) +/** + * struct sky81452_platform_data + * @name: backlight driver name. + If it is not defined, default name is lcd-backlight. + * @gpios_enable:GPIO descriptor which control EN pin + * @enable: Enable mask for current sink channel 1, 2, 3, 4, 5 and 6. + * @ignore_pwm: true if DPWMI should be ignored. + * @dpwm_mode: true is DPWM dimming mode, otherwise Analog dimming mode. + * @phase_shift:true is phase shift mode. + * @short_detecion_threshold: It should be one of 4, 5, 6 and 7V. + * @boost_current_limit: It should be one of 2300, 2750mA. + */ +struct sky81452_bl_platform_data { + const char *name; + struct gpio_desc *gpiod_enable; + unsigned int enable; + bool ignore_pwm; + bool dpwm_mode; + bool phase_shift; + unsigned int short_detection_threshold; + unsigned int boost_current_limit; +}; + #define CTZ(b) __builtin_ctz(b) static int sky81452_bl_update_status(struct backlight_device *bd) @@ -251,17 +273,15 @@ static int sky81452_bl_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct regmap *regmap = dev_get_drvdata(dev->parent); - struct sky81452_bl_platform_data *pdata = dev_get_platdata(dev); + struct sky81452_bl_platform_data *pdata; struct backlight_device *bd; struct backlight_properties props; const char *name; int ret; - if (!pdata) { - pdata = sky81452_bl_parse_dt(dev); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); - } + pdata = sky81452_bl_parse_dt(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); ret = sky81452_bl_init_device(regmap, pdata); if (ret < 0) { diff --git a/include/linux/mfd/sky81452.h b/include/linux/mfd/sky81452.h index d469aa481243..b08570ff34df 100644 --- a/include/linux/mfd/sky81452.h +++ b/include/linux/mfd/sky81452.h @@ -9,11 +9,9 @@ #ifndef _SKY81452_H #define _SKY81452_H -#include #include struct sky81452_platform_data { - struct sky81452_bl_platform_data *bl_pdata; struct regulator_init_data *regulator_init_data; }; diff --git a/include/linux/platform_data/sky81452-backlight.h b/include/linux/platform_data/sky81452-backlight.h deleted file mode 100644 index d6f46670d923..000000000000 --- a/include/linux/platform_data/sky81452-backlight.h +++ /dev/null @@ -1,37 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * sky81452.h SKY81452 backlight driver - * - * Copyright 2014 Skyworks Solutions Inc. - * Author : Gyungoh Yoo - */ - -#ifndef _SKY81452_BACKLIGHT_H -#define _SKY81452_BACKLIGHT_H - -#include - -/** - * struct sky81452_platform_data - * @name: backlight driver name. - If it is not defined, default name is lcd-backlight. - * @gpios_enable:GPIO descriptor which control EN pin - * @enable: Enable mask for current sink channel 1, 2, 3, 4, 5 and 6. - * @ignore_pwm: true if DPWMI should be ignored. - * @dpwm_mode: true is DPWM dimming mode, otherwise Analog dimming mode. - * @phase_shift:true is phase shift mode. - * @short_detecion_threshold: It should be one of 4, 5, 6 and 7V. - * @boost_current_limit: It should be one of 2300, 2750mA. - */ -struct sky81452_bl_platform_data { - const char *name; - struct gpio_desc *gpiod_enable; - unsigned int enable; - bool ignore_pwm; - bool dpwm_mode; - bool phase_shift; - unsigned int short_detection_threshold; - unsigned int boost_current_limit; -}; - -#endif From e994734fdca7309234a210169c7a7f2f446e430f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 26 Jun 2020 12:25:00 +0200 Subject: [PATCH 045/291] backlight: Delete the OT200 backlight driver This driver has no in-kernel users. The device can only be populated by board files since it does not support device tree nor ACPI, and nothing in the kernel creates a device named "ot200-backlight". This driver has been in the kernel since 2012. If it is used by out-of-tree code that code should have been upstreamed by now, it's been 8 years. It uses the idiomatic forked GPIO of the CS5535 which combines pin control and GPIO into its private custom interface, which causes me a headache because that is not how we do things these days: we creates separate pin control and GPIO drivers. Delete this unused driver. Cc: Christian Gmeiner Signed-off-by: Linus Walleij Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/Kconfig | 7 -- drivers/video/backlight/Makefile | 1 - drivers/video/backlight/ot200_bl.c | 162 ----------------------------- 3 files changed, 170 deletions(-) delete mode 100644 drivers/video/backlight/ot200_bl.c diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig index 7d22d7377606..95c546cc8774 100644 --- a/drivers/video/backlight/Kconfig +++ b/drivers/video/backlight/Kconfig @@ -386,13 +386,6 @@ config BACKLIGHT_LP8788 help This supports TI LP8788 backlight driver. -config BACKLIGHT_OT200 - tristate "Backlight driver for ot200 visualisation device" - depends on CS5535_MFGPT && GPIO_CS5535 - help - To compile this driver as a module, choose M here: the module will be - called ot200_bl. - config BACKLIGHT_PANDORA tristate "Backlight driver for Pandora console" depends on TWL4030_CORE diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile index 0c1a1524627a..2072d21b60f7 100644 --- a/drivers/video/backlight/Makefile +++ b/drivers/video/backlight/Makefile @@ -45,7 +45,6 @@ obj-$(CONFIG_BACKLIGHT_LP8788) += lp8788_bl.o obj-$(CONFIG_BACKLIGHT_LV5207LP) += lv5207lp.o obj-$(CONFIG_BACKLIGHT_MAX8925) += max8925_bl.o obj-$(CONFIG_BACKLIGHT_OMAP1) += omap1_bl.o -obj-$(CONFIG_BACKLIGHT_OT200) += ot200_bl.o obj-$(CONFIG_BACKLIGHT_PANDORA) += pandora_bl.o obj-$(CONFIG_BACKLIGHT_PCF50633) += pcf50633-backlight.o obj-$(CONFIG_BACKLIGHT_PWM) += pwm_bl.o diff --git a/drivers/video/backlight/ot200_bl.c b/drivers/video/backlight/ot200_bl.c deleted file mode 100644 index 23ee7106c72a..000000000000 --- a/drivers/video/backlight/ot200_bl.c +++ /dev/null @@ -1,162 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012 Bachmann electronic GmbH - * Christian Gmeiner - * - * Backlight driver for ot200 visualisation device from - * Bachmann electronic GmbH. - */ - -#include -#include -#include -#include -#include -#include - -static struct cs5535_mfgpt_timer *pwm_timer; - -/* this array defines the mapping of brightness in % to pwm frequency */ -static const u8 dim_table[101] = {0, 0, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, - 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, - 4, 5, 5, 5, 5, 6, 6, 6, 7, 7, 7, 8, 8, 9, 9, - 10, 10, 11, 11, 12, 12, 13, 14, 15, 15, 16, - 17, 18, 19, 20, 21, 22, 23, 24, 26, 27, 28, - 30, 31, 33, 35, 37, 39, 41, 43, 45, 47, 50, - 53, 55, 58, 61, 65, 68, 72, 75, 79, 84, 88, - 93, 97, 103, 108, 114, 120, 126, 133, 140, - 147, 155, 163}; - -struct ot200_backlight_data { - int current_brightness; -}; - -#define GPIO_DIMM 27 -#define SCALE 1 -#define CMP1MODE 0x2 /* compare on GE; output high on compare - * greater than or equal */ -#define PWM_SETUP (SCALE | CMP1MODE << 6 | MFGPT_SETUP_CNTEN) -#define MAX_COMP2 163 - -static int ot200_backlight_update_status(struct backlight_device *bl) -{ - struct ot200_backlight_data *data = bl_get_data(bl); - int brightness = bl->props.brightness; - - if (bl->props.state & BL_CORE_FBBLANK) - brightness = 0; - - /* enable or disable PWM timer */ - if (brightness == 0) - cs5535_mfgpt_write(pwm_timer, MFGPT_REG_SETUP, 0); - else if (data->current_brightness == 0) { - cs5535_mfgpt_write(pwm_timer, MFGPT_REG_COUNTER, 0); - cs5535_mfgpt_write(pwm_timer, MFGPT_REG_SETUP, - MFGPT_SETUP_CNTEN); - } - - /* apply new brightness value */ - cs5535_mfgpt_write(pwm_timer, MFGPT_REG_CMP1, - MAX_COMP2 - dim_table[brightness]); - data->current_brightness = brightness; - - return 0; -} - -static int ot200_backlight_get_brightness(struct backlight_device *bl) -{ - struct ot200_backlight_data *data = bl_get_data(bl); - return data->current_brightness; -} - -static const struct backlight_ops ot200_backlight_ops = { - .update_status = ot200_backlight_update_status, - .get_brightness = ot200_backlight_get_brightness, -}; - -static int ot200_backlight_probe(struct platform_device *pdev) -{ - struct backlight_device *bl; - struct ot200_backlight_data *data; - struct backlight_properties props; - int retval = 0; - - /* request gpio */ - if (devm_gpio_request(&pdev->dev, GPIO_DIMM, - "ot200 backlight dimmer") < 0) { - dev_err(&pdev->dev, "failed to request GPIO %d\n", GPIO_DIMM); - return -ENODEV; - } - - /* request timer */ - pwm_timer = cs5535_mfgpt_alloc_timer(7, MFGPT_DOMAIN_ANY); - if (!pwm_timer) { - dev_err(&pdev->dev, "MFGPT 7 not available\n"); - return -ENODEV; - } - - data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL); - if (!data) { - retval = -ENOMEM; - goto error_devm_kzalloc; - } - - /* setup gpio */ - cs5535_gpio_set(GPIO_DIMM, GPIO_OUTPUT_ENABLE); - cs5535_gpio_set(GPIO_DIMM, GPIO_OUTPUT_AUX1); - - /* setup timer */ - cs5535_mfgpt_write(pwm_timer, MFGPT_REG_CMP1, 0); - cs5535_mfgpt_write(pwm_timer, MFGPT_REG_CMP2, MAX_COMP2); - cs5535_mfgpt_write(pwm_timer, MFGPT_REG_SETUP, PWM_SETUP); - - data->current_brightness = 100; - props.max_brightness = 100; - props.brightness = 100; - props.type = BACKLIGHT_RAW; - - bl = devm_backlight_device_register(&pdev->dev, dev_name(&pdev->dev), - &pdev->dev, data, &ot200_backlight_ops, - &props); - if (IS_ERR(bl)) { - dev_err(&pdev->dev, "failed to register backlight\n"); - retval = PTR_ERR(bl); - goto error_devm_kzalloc; - } - - platform_set_drvdata(pdev, bl); - - return 0; - -error_devm_kzalloc: - cs5535_mfgpt_free_timer(pwm_timer); - return retval; -} - -static int ot200_backlight_remove(struct platform_device *pdev) -{ - /* on module unload set brightness to 100% */ - cs5535_mfgpt_write(pwm_timer, MFGPT_REG_COUNTER, 0); - cs5535_mfgpt_write(pwm_timer, MFGPT_REG_SETUP, MFGPT_SETUP_CNTEN); - cs5535_mfgpt_write(pwm_timer, MFGPT_REG_CMP1, - MAX_COMP2 - dim_table[100]); - - cs5535_mfgpt_free_timer(pwm_timer); - - return 0; -} - -static struct platform_driver ot200_backlight_driver = { - .driver = { - .name = "ot200-backlight", - }, - .probe = ot200_backlight_probe, - .remove = ot200_backlight_remove, -}; - -module_platform_driver(ot200_backlight_driver); - -MODULE_DESCRIPTION("backlight driver for ot200 visualisation device"); -MODULE_AUTHOR("Christian Gmeiner "); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:ot200-backlight"); From f3528630e2e7b1556b0f150f1e205462c66efe8e Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 26 Jun 2020 01:25:12 +0200 Subject: [PATCH 046/291] backlight: lms501kf03: Drop unused include This driver includes but does not use any symbols from that file, drop the include. Signed-off-by: Linus Walleij Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/lms501kf03.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/video/backlight/lms501kf03.c b/drivers/video/backlight/lms501kf03.c index 8ae32e3573c1..52d3ee6c3f7f 100644 --- a/drivers/video/backlight/lms501kf03.c +++ b/drivers/video/backlight/lms501kf03.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include #include From 4605ad8f4581981787ed22b3a755209c8fe5aa24 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 30 Jun 2020 10:31:17 -0600 Subject: [PATCH 047/291] remoteproc: ingenic: Move clock handling to prepare/unprepare callbacks This patch moves clock related operations to the remoteproc prepare() and unprepare() callbacks so that the PM runtime framework doesn't have to be involved needlessly. This provides a simpler approach and requires less code. Based on the work from Paul Cercueil published here: https://lore.kernel.org/linux-remoteproc/20191116170846.67220-4-paul@crapouillou.net/ Reviewed-by: Suman Anna Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200630163118.3830422-2-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/ingenic_rproc.c | 84 +++++++++--------------------- 1 file changed, 26 insertions(+), 58 deletions(-) diff --git a/drivers/remoteproc/ingenic_rproc.c b/drivers/remoteproc/ingenic_rproc.c index 189020d77b25..1c2b21a5d178 100644 --- a/drivers/remoteproc/ingenic_rproc.c +++ b/drivers/remoteproc/ingenic_rproc.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include "remoteproc_internal.h" @@ -62,6 +61,28 @@ struct vpu { struct device *dev; }; +static int ingenic_rproc_prepare(struct rproc *rproc) +{ + struct vpu *vpu = rproc->priv; + int ret; + + /* The clocks must be enabled for the firmware to be loaded in TCSM */ + ret = clk_bulk_prepare_enable(ARRAY_SIZE(vpu->clks), vpu->clks); + if (ret) + dev_err(vpu->dev, "Unable to start clocks: %d\n", ret); + + return ret; +} + +static int ingenic_rproc_unprepare(struct rproc *rproc) +{ + struct vpu *vpu = rproc->priv; + + clk_bulk_disable_unprepare(ARRAY_SIZE(vpu->clks), vpu->clks); + + return 0; +} + static int ingenic_rproc_start(struct rproc *rproc) { struct vpu *vpu = rproc->priv; @@ -115,6 +136,8 @@ static void *ingenic_rproc_da_to_va(struct rproc *rproc, u64 da, size_t len) } static struct rproc_ops ingenic_rproc_ops = { + .prepare = ingenic_rproc_prepare, + .unprepare = ingenic_rproc_unprepare, .start = ingenic_rproc_start, .stop = ingenic_rproc_stop, .kick = ingenic_rproc_kick, @@ -135,16 +158,6 @@ static irqreturn_t vpu_interrupt(int irq, void *data) return rproc_vq_interrupt(rproc, vring); } -static void ingenic_rproc_disable_clks(void *data) -{ - struct vpu *vpu = data; - - pm_runtime_resume(vpu->dev); - pm_runtime_disable(vpu->dev); - - clk_bulk_disable_unprepare(ARRAY_SIZE(vpu->clks), vpu->clks); -} - static int ingenic_rproc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -206,35 +219,13 @@ static int ingenic_rproc_probe(struct platform_device *pdev) disable_irq(vpu->irq); - /* The clocks must be enabled for the firmware to be loaded in TCSM */ - ret = clk_bulk_prepare_enable(ARRAY_SIZE(vpu->clks), vpu->clks); - if (ret) { - dev_err(dev, "Unable to start clocks\n"); - return ret; - } - - pm_runtime_irq_safe(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); - pm_runtime_get_sync(dev); - pm_runtime_use_autosuspend(dev); - - ret = devm_add_action_or_reset(dev, ingenic_rproc_disable_clks, vpu); - if (ret) { - dev_err(dev, "Unable to register action\n"); - goto out_pm_put; - } - ret = devm_rproc_add(dev, rproc); if (ret) { dev_err(dev, "Failed to register remote processor\n"); - goto out_pm_put; + return ret; } -out_pm_put: - pm_runtime_put_autosuspend(dev); - - return ret; + return 0; } static const struct of_device_id ingenic_rproc_of_matches[] = { @@ -243,33 +234,10 @@ static const struct of_device_id ingenic_rproc_of_matches[] = { }; MODULE_DEVICE_TABLE(of, ingenic_rproc_of_matches); -static int __maybe_unused ingenic_rproc_suspend(struct device *dev) -{ - struct vpu *vpu = dev_get_drvdata(dev); - - clk_bulk_disable(ARRAY_SIZE(vpu->clks), vpu->clks); - - return 0; -} - -static int __maybe_unused ingenic_rproc_resume(struct device *dev) -{ - struct vpu *vpu = dev_get_drvdata(dev); - - return clk_bulk_enable(ARRAY_SIZE(vpu->clks), vpu->clks); -} - -static const struct dev_pm_ops __maybe_unused ingenic_rproc_pm = { - SET_RUNTIME_PM_OPS(ingenic_rproc_suspend, ingenic_rproc_resume, NULL) -}; - static struct platform_driver ingenic_rproc_driver = { .probe = ingenic_rproc_probe, .driver = { .name = "ingenic-vpu", -#ifdef CONFIG_PM - .pm = &ingenic_rproc_pm, -#endif .of_match_table = ingenic_rproc_of_matches, }, }; From 49cff1256879d8622d253b6deac2438d6cd33445 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 30 Jun 2020 10:31:18 -0600 Subject: [PATCH 048/291] Revert "remoteproc: Add support for runtime PM" This reverts commit a99a37f6cd5a74d5b22c08544aa6c5890813c8ba. Removing PM runtime operations from the remoteproc core in order to: 1) Keep all power management operations in platform drivers. That way we do not loose flexibility in an area that is very HW specific. 2) Avoid making the support for remote processor managed by external entities more complex that it already is. 3) Fix regression introduced for the Omap remoteproc driver. Acked-by: Suman Anna Tested-by: Suman Anna Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200630163118.3830422-3-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 9f04c30c4aaf..0f95e025ba03 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include #include @@ -1383,12 +1382,6 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) if (ret) return ret; - ret = pm_runtime_get_sync(dev); - if (ret < 0) { - dev_err(dev, "pm_runtime_get_sync failed: %d\n", ret); - return ret; - } - dev_info(dev, "Booting fw image %s, size %zd\n", name, fw->size); /* @@ -1398,7 +1391,7 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) ret = rproc_enable_iommu(rproc); if (ret) { dev_err(dev, "can't enable iommu: %d\n", ret); - goto put_pm_runtime; + return ret; } /* Prepare rproc for firmware loading if needed */ @@ -1452,8 +1445,6 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) rproc_unprepare_device(rproc); disable_iommu: rproc_disable_iommu(rproc); -put_pm_runtime: - pm_runtime_put(dev); return ret; } @@ -1891,8 +1882,6 @@ void rproc_shutdown(struct rproc *rproc) rproc_disable_iommu(rproc); - pm_runtime_put(dev); - /* Free the copy of the resource table */ kfree(rproc->cached_table); rproc->cached_table = NULL; @@ -2183,9 +2172,6 @@ struct rproc *rproc_alloc(struct device *dev, const char *name, rproc->state = RPROC_OFFLINE; - pm_runtime_no_callbacks(&rproc->dev); - pm_runtime_enable(&rproc->dev); - return rproc; put_device: @@ -2205,7 +2191,6 @@ EXPORT_SYMBOL(rproc_alloc); */ void rproc_free(struct rproc *rproc) { - pm_runtime_disable(&rproc->dev); put_device(&rproc->dev); } EXPORT_SYMBOL(rproc_free); From 87ad854dd76ca3534ef2e368265c3566a59e21e0 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 22 Jun 2020 12:19:38 -0700 Subject: [PATCH 049/291] dt-bindings: remoteproc: Add Qualcomm PIL info binding Add a devicetree binding for the Qualcomm peripheral image loader relocation information region found in the IMEM. Reviewed-by: Mathieu Poirier Reviewed-by: Rob Herring Reviewed-by: Stephen Boyd Reviewed-by: Vinod Koul Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200622191942.255460-2-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- .../bindings/remoteproc/qcom,pil-info.yaml | 44 +++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 Documentation/devicetree/bindings/remoteproc/qcom,pil-info.yaml diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,pil-info.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,pil-info.yaml new file mode 100644 index 000000000000..87c52316ddbd --- /dev/null +++ b/Documentation/devicetree/bindings/remoteproc/qcom,pil-info.yaml @@ -0,0 +1,44 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/remoteproc/qcom,pil-info.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm peripheral image loader relocation info binding + +maintainers: + - Bjorn Andersson + +description: + The Qualcomm peripheral image loader relocation memory region, in IMEM, is + used for communicating remoteproc relocation information to post mortem + debugging tools. + +properties: + compatible: + const: qcom,pil-reloc-info + + reg: + maxItems: 1 + +required: + - compatible + - reg + +examples: + - | + imem@146bf000 { + compatible = "syscon", "simple-mfd"; + reg = <0x146bf000 0x1000>; + + #address-cells = <1>; + #size-cells = <1>; + + ranges = <0 0x146bf000 0x1000>; + + pil-reloc@94c { + compatible = "qcom,pil-reloc-info"; + reg = <0x94c 0xc8>; + }; + }; +... From 549b67da660d634e3a4a50a325bd1f5609ddb84b Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 22 Jun 2020 12:19:39 -0700 Subject: [PATCH 050/291] remoteproc: qcom: Introduce helper to store pil info in IMEM A region in IMEM is used to communicate load addresses of remoteproc to post mortem debug tools. Implement a helper function that can be used to store this information in order to enable these tools to process collected ramdumps. Reviewed-by: Mathieu Poirier Reviewed-by: Vinod Koul Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200622191942.255460-3-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/Kconfig | 3 + drivers/remoteproc/Makefile | 1 + drivers/remoteproc/qcom_pil_info.c | 129 +++++++++++++++++++++++++++++ drivers/remoteproc/qcom_pil_info.h | 9 ++ 4 files changed, 142 insertions(+) create mode 100644 drivers/remoteproc/qcom_pil_info.c create mode 100644 drivers/remoteproc/qcom_pil_info.h diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index c4d1731295eb..f4bd96d1a1a3 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -116,6 +116,9 @@ config KEYSTONE_REMOTEPROC It's safe to say N here if you're not interested in the Keystone DSPs or just want to use a bare minimum kernel. +config QCOM_PIL_INFO + tristate + config QCOM_RPROC_COMMON tristate diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile index e8b886e511f0..fe398f82d550 100644 --- a/drivers/remoteproc/Makefile +++ b/drivers/remoteproc/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_OMAP_REMOTEPROC) += omap_remoteproc.o obj-$(CONFIG_WKUP_M3_RPROC) += wkup_m3_rproc.o obj-$(CONFIG_DA8XX_REMOTEPROC) += da8xx_remoteproc.o obj-$(CONFIG_KEYSTONE_REMOTEPROC) += keystone_remoteproc.o +obj-$(CONFIG_QCOM_PIL_INFO) += qcom_pil_info.o obj-$(CONFIG_QCOM_RPROC_COMMON) += qcom_common.o obj-$(CONFIG_QCOM_Q6V5_COMMON) += qcom_q6v5.o obj-$(CONFIG_QCOM_Q6V5_ADSP) += qcom_q6v5_adsp.o diff --git a/drivers/remoteproc/qcom_pil_info.c b/drivers/remoteproc/qcom_pil_info.c new file mode 100644 index 000000000000..0536e3904669 --- /dev/null +++ b/drivers/remoteproc/qcom_pil_info.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2019-2020 Linaro Ltd. + */ +#include +#include +#include +#include +#include "qcom_pil_info.h" + +/* + * The PIL relocation information region is used to communicate memory regions + * occupied by co-processor firmware for post mortem crash analysis. + * + * It consists of an array of entries with an 8 byte textual identifier of the + * region followed by a 64 bit base address and 32 bit size, both little + * endian. + */ +#define PIL_RELOC_NAME_LEN 8 +#define PIL_RELOC_ENTRY_SIZE (PIL_RELOC_NAME_LEN + sizeof(__le64) + sizeof(__le32)) + +struct pil_reloc { + void __iomem *base; + size_t num_entries; +}; + +static struct pil_reloc _reloc __read_mostly; +static DEFINE_MUTEX(pil_reloc_lock); + +static int qcom_pil_info_init(void) +{ + struct device_node *np; + struct resource imem; + void __iomem *base; + int ret; + + /* Already initialized? */ + if (_reloc.base) + return 0; + + np = of_find_compatible_node(NULL, NULL, "qcom,pil-reloc-info"); + if (!np) + return -ENOENT; + + ret = of_address_to_resource(np, 0, &imem); + of_node_put(np); + if (ret < 0) + return ret; + + base = ioremap(imem.start, resource_size(&imem)); + if (!base) { + pr_err("failed to map PIL relocation info region\n"); + return -ENOMEM; + } + + memset_io(base, 0, resource_size(&imem)); + + _reloc.base = base; + _reloc.num_entries = resource_size(&imem) / PIL_RELOC_ENTRY_SIZE; + + return 0; +} + +/** + * qcom_pil_info_store() - store PIL information of image in IMEM + * @image: name of the image + * @base: base address of the loaded image + * @size: size of the loaded image + * + * Return: 0 on success, negative errno on failure + */ +int qcom_pil_info_store(const char *image, phys_addr_t base, size_t size) +{ + char buf[PIL_RELOC_NAME_LEN]; + void __iomem *entry; + int ret; + int i; + + mutex_lock(&pil_reloc_lock); + ret = qcom_pil_info_init(); + if (ret < 0) { + mutex_unlock(&pil_reloc_lock); + return ret; + } + + for (i = 0; i < _reloc.num_entries; i++) { + entry = _reloc.base + i * PIL_RELOC_ENTRY_SIZE; + + memcpy_fromio(buf, entry, PIL_RELOC_NAME_LEN); + + /* + * An empty record means we didn't find it, given that the + * records are packed. + */ + if (!buf[0]) + goto found_unused; + + if (!strncmp(buf, image, PIL_RELOC_NAME_LEN)) + goto found_existing; + } + + pr_warn("insufficient PIL info slots\n"); + mutex_unlock(&pil_reloc_lock); + return -ENOMEM; + +found_unused: + memcpy_toio(entry, image, PIL_RELOC_NAME_LEN); +found_existing: + /* Use two writel() as base is only aligned to 4 bytes on odd entries */ + writel(base, entry + PIL_RELOC_NAME_LEN); + writel(base >> 32, entry + PIL_RELOC_NAME_LEN + 4); + writel(size, entry + PIL_RELOC_NAME_LEN + sizeof(__le64)); + mutex_unlock(&pil_reloc_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(qcom_pil_info_store); + +static void __exit pil_reloc_exit(void) +{ + mutex_lock(&pil_reloc_lock); + iounmap(_reloc.base); + _reloc.base = NULL; + mutex_unlock(&pil_reloc_lock); +} +module_exit(pil_reloc_exit); + +MODULE_DESCRIPTION("Qualcomm PIL relocation info"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/remoteproc/qcom_pil_info.h b/drivers/remoteproc/qcom_pil_info.h new file mode 100644 index 000000000000..0dce6142935e --- /dev/null +++ b/drivers/remoteproc/qcom_pil_info.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __QCOM_PIL_INFO_H__ +#define __QCOM_PIL_INFO_H__ + +#include + +int qcom_pil_info_store(const char *image, phys_addr_t base, size_t size); + +#endif From d4c78d2167913b3f7af0d2189fd3d76f6614a1bf Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 22 Jun 2020 12:19:40 -0700 Subject: [PATCH 051/291] remoteproc: qcom: Update PIL relocation info on load Update the PIL relocation information in IMEM with information about where the firmware for various remoteprocs are loaded. Reviewed-by: Vinod Koul Reviewed-by: Stephen Boyd Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200622191942.255460-4-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/Kconfig | 5 +++++ drivers/remoteproc/qcom_q6v5_adsp.c | 16 +++++++++++++--- drivers/remoteproc/qcom_q6v5_mss.c | 3 +++ drivers/remoteproc/qcom_q6v5_pas.c | 15 ++++++++++++--- drivers/remoteproc/qcom_q6v5_wcss.c | 14 +++++++++++--- drivers/remoteproc/qcom_wcnss.c | 14 +++++++++++--- 6 files changed, 55 insertions(+), 12 deletions(-) diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index f4bd96d1a1a3..3e8d5d1a2b9e 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -135,6 +135,7 @@ config QCOM_Q6V5_ADSP depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SYSMON || QCOM_SYSMON=n select MFD_SYSCON + select QCOM_PIL_INFO select QCOM_MDT_LOADER select QCOM_Q6V5_COMMON select QCOM_RPROC_COMMON @@ -151,6 +152,7 @@ config QCOM_Q6V5_MSS depends on QCOM_SYSMON || QCOM_SYSMON=n select MFD_SYSCON select QCOM_MDT_LOADER + select QCOM_PIL_INFO select QCOM_Q6V5_COMMON select QCOM_Q6V5_IPA_NOTIFY select QCOM_RPROC_COMMON @@ -167,6 +169,7 @@ config QCOM_Q6V5_PAS depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SYSMON || QCOM_SYSMON=n select MFD_SYSCON + select QCOM_PIL_INFO select QCOM_MDT_LOADER select QCOM_Q6V5_COMMON select QCOM_RPROC_COMMON @@ -185,6 +188,7 @@ config QCOM_Q6V5_WCSS depends on QCOM_SYSMON || QCOM_SYSMON=n select MFD_SYSCON select QCOM_MDT_LOADER + select QCOM_PIL_INFO select QCOM_Q6V5_COMMON select QCOM_RPROC_COMMON select QCOM_SCM @@ -218,6 +222,7 @@ config QCOM_WCNSS_PIL depends on QCOM_SMEM depends on QCOM_SYSMON || QCOM_SYSMON=n select QCOM_MDT_LOADER + select QCOM_PIL_INFO select QCOM_RPROC_COMMON select QCOM_SCM help diff --git a/drivers/remoteproc/qcom_q6v5_adsp.c b/drivers/remoteproc/qcom_q6v5_adsp.c index d2a2574dcf35..efb2c1aa80a3 100644 --- a/drivers/remoteproc/qcom_q6v5_adsp.c +++ b/drivers/remoteproc/qcom_q6v5_adsp.c @@ -26,6 +26,7 @@ #include #include "qcom_common.h" +#include "qcom_pil_info.h" #include "qcom_q6v5.h" #include "remoteproc_internal.h" @@ -82,6 +83,7 @@ struct qcom_adsp { unsigned int halt_lpass; int crash_reason_smem; + const char *info_name; struct completion start_done; struct completion stop_done; @@ -164,10 +166,17 @@ static int qcom_adsp_shutdown(struct qcom_adsp *adsp) static int adsp_load(struct rproc *rproc, const struct firmware *fw) { struct qcom_adsp *adsp = (struct qcom_adsp *)rproc->priv; + int ret; - return qcom_mdt_load_no_init(adsp->dev, fw, rproc->firmware, 0, - adsp->mem_region, adsp->mem_phys, adsp->mem_size, - &adsp->mem_reloc); + ret = qcom_mdt_load_no_init(adsp->dev, fw, rproc->firmware, 0, + adsp->mem_region, adsp->mem_phys, + adsp->mem_size, &adsp->mem_reloc); + if (ret) + return ret; + + qcom_pil_info_store(adsp->info_name, adsp->mem_phys, adsp->mem_size); + + return 0; } static int adsp_start(struct rproc *rproc) @@ -436,6 +445,7 @@ static int adsp_probe(struct platform_device *pdev) adsp = (struct qcom_adsp *)rproc->priv; adsp->dev = &pdev->dev; adsp->rproc = rproc; + adsp->info_name = desc->sysmon_name; platform_set_drvdata(pdev, adsp); ret = adsp_alloc_memory_region(adsp); diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index feb70283b6a2..dd37e462ed61 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -29,6 +29,7 @@ #include "remoteproc_internal.h" #include "qcom_common.h" +#include "qcom_pil_info.h" #include "qcom_q6v5.h" #include @@ -1189,6 +1190,8 @@ static int q6v5_mpss_load(struct q6v5 *qproc) else if (ret < 0) dev_err(qproc->dev, "MPSS authentication failed: %d\n", ret); + qcom_pil_info_store("modem", qproc->mpss_phys, qproc->mpss_size); + release_firmware: release_firmware(fw); out: diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c index 61791a03f648..3837f23995e0 100644 --- a/drivers/remoteproc/qcom_q6v5_pas.c +++ b/drivers/remoteproc/qcom_q6v5_pas.c @@ -25,6 +25,7 @@ #include #include "qcom_common.h" +#include "qcom_pil_info.h" #include "qcom_q6v5.h" #include "remoteproc_internal.h" @@ -64,6 +65,7 @@ struct qcom_adsp { int pas_id; int crash_reason_smem; bool has_aggre2_clk; + const char *info_name; struct completion start_done; struct completion stop_done; @@ -117,11 +119,17 @@ static void adsp_pds_disable(struct qcom_adsp *adsp, struct device **pds, static int adsp_load(struct rproc *rproc, const struct firmware *fw) { struct qcom_adsp *adsp = (struct qcom_adsp *)rproc->priv; + int ret; - return qcom_mdt_load(adsp->dev, fw, rproc->firmware, adsp->pas_id, - adsp->mem_region, adsp->mem_phys, adsp->mem_size, - &adsp->mem_reloc); + ret = qcom_mdt_load(adsp->dev, fw, rproc->firmware, adsp->pas_id, + adsp->mem_region, adsp->mem_phys, adsp->mem_size, + &adsp->mem_reloc); + if (ret) + return ret; + qcom_pil_info_store(adsp->info_name, adsp->mem_phys, adsp->mem_size); + + return 0; } static int adsp_start(struct rproc *rproc) @@ -405,6 +413,7 @@ static int adsp_probe(struct platform_device *pdev) adsp->rproc = rproc; adsp->pas_id = desc->pas_id; adsp->has_aggre2_clk = desc->has_aggre2_clk; + adsp->info_name = desc->sysmon_name; platform_set_drvdata(pdev, adsp); device_wakeup_enable(adsp->dev); diff --git a/drivers/remoteproc/qcom_q6v5_wcss.c b/drivers/remoteproc/qcom_q6v5_wcss.c index 88c76b9417fa..8846ef0b0f1a 100644 --- a/drivers/remoteproc/qcom_q6v5_wcss.c +++ b/drivers/remoteproc/qcom_q6v5_wcss.c @@ -14,6 +14,7 @@ #include #include #include "qcom_common.h" +#include "qcom_pil_info.h" #include "qcom_q6v5.h" #define WCSS_CRASH_REASON 421 @@ -424,10 +425,17 @@ static void *q6v5_wcss_da_to_va(struct rproc *rproc, u64 da, size_t len) static int q6v5_wcss_load(struct rproc *rproc, const struct firmware *fw) { struct q6v5_wcss *wcss = rproc->priv; + int ret; - return qcom_mdt_load_no_init(wcss->dev, fw, rproc->firmware, - 0, wcss->mem_region, wcss->mem_phys, - wcss->mem_size, &wcss->mem_reloc); + ret = qcom_mdt_load_no_init(wcss->dev, fw, rproc->firmware, + 0, wcss->mem_region, wcss->mem_phys, + wcss->mem_size, &wcss->mem_reloc); + if (ret) + return ret; + + qcom_pil_info_store("wcnss", wcss->mem_phys, wcss->mem_size); + + return ret; } static const struct rproc_ops q6v5_wcss_ops = { diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c index 5d65e1a9329a..e2573f79a137 100644 --- a/drivers/remoteproc/qcom_wcnss.c +++ b/drivers/remoteproc/qcom_wcnss.c @@ -27,6 +27,7 @@ #include "qcom_common.h" #include "remoteproc_internal.h" +#include "qcom_pil_info.h" #include "qcom_wcnss.h" #define WCNSS_CRASH_REASON_SMEM 422 @@ -145,10 +146,17 @@ void qcom_wcnss_assign_iris(struct qcom_wcnss *wcnss, static int wcnss_load(struct rproc *rproc, const struct firmware *fw) { struct qcom_wcnss *wcnss = (struct qcom_wcnss *)rproc->priv; + int ret; - return qcom_mdt_load(wcnss->dev, fw, rproc->firmware, WCNSS_PAS_ID, - wcnss->mem_region, wcnss->mem_phys, - wcnss->mem_size, &wcnss->mem_reloc); + ret = qcom_mdt_load(wcnss->dev, fw, rproc->firmware, WCNSS_PAS_ID, + wcnss->mem_region, wcnss->mem_phys, + wcnss->mem_size, &wcnss->mem_reloc); + if (ret) + return ret; + + qcom_pil_info_store("wcnss", wcnss->mem_phys, wcnss->mem_size); + + return 0; } static void wcnss_indicate_nv_download(struct qcom_wcnss *wcnss) From 81357f818f3e21963aa7630874bfc941330ef4d4 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 23 Jun 2020 12:16:37 +0100 Subject: [PATCH 052/291] backlight: lms501kf03: Remove unused const variables MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit W=1 kernel build reports: drivers/video/backlight/lms501kf03.c:96:28: warning: ‘seq_sleep_in’ defined but not used [-Wunused-const-variable=] 96 | static const unsigned char seq_sleep_in[] = { | ^~~~~~~~~~~~ drivers/video/backlight/lms501kf03.c:92:28: warning: ‘seq_up_dn’ defined but not used [-Wunused-const-variable=] 92 | static const unsigned char seq_up_dn[] = { | ^~~~~~~~~ Either 'seq_sleep_in' nor 'seq_up_dn' have been used since the driver first landed in 2013. Cc: Bartlomiej Zolnierkiewicz Signed-off-by: Lee Jones Reviewed-by: Daniel Thompson Reviewed-by: Sam Ravnborg Signed-off-by: Lee Jones --- drivers/video/backlight/lms501kf03.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/video/backlight/lms501kf03.c b/drivers/video/backlight/lms501kf03.c index 52d3ee6c3f7f..f949b66dce1b 100644 --- a/drivers/video/backlight/lms501kf03.c +++ b/drivers/video/backlight/lms501kf03.c @@ -88,14 +88,6 @@ static const unsigned char seq_rgb_gamma[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, }; -static const unsigned char seq_up_dn[] = { - 0x36, 0x10, -}; - -static const unsigned char seq_sleep_in[] = { - 0x10, -}; - static const unsigned char seq_sleep_out[] = { 0x11, }; From 4160ebacd3579651c5fd9cb1d27dc2205adb13d7 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 23 Jun 2020 12:27:10 +0100 Subject: [PATCH 053/291] backlight: lcd: Add missing kerneldoc entry for 'struct device parent' This has been missing since the conversion to 'struct device' in 2007. Cc: Bartlomiej Zolnierkiewicz Cc: Jamey Hicks Cc: Andrew Zabolotny Signed-off-by: Lee Jones Reviewed-by: Daniel Thompson Reviewed-by: Sam Ravnborg Signed-off-by: Lee Jones --- drivers/video/backlight/lcd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/video/backlight/lcd.c b/drivers/video/backlight/lcd.c index 78b033358625..db56e465aaff 100644 --- a/drivers/video/backlight/lcd.c +++ b/drivers/video/backlight/lcd.c @@ -179,6 +179,7 @@ ATTRIBUTE_GROUPS(lcd_device); * lcd_device_register - register a new object of lcd_device class. * @name: the name of the new object(must be the same as the name of the * respective framebuffer device). + * @parent: pointer to the parent's struct device . * @devdata: an optional pointer to be stored in the device. The * methods may retrieve it by using lcd_get_data(ld). * @ops: the lcd operations structure. From 0e0428be20fac07989bdccc4c2836cdfe2ff5ec4 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 23 Jun 2020 12:41:34 +0100 Subject: [PATCH 054/291] backlight: ili922x: Add missing kerneldoc descriptions for CHECK_FREQ_REG() args Kerneldoc syntax is used, but not complete. Descriptions required. Prevents warnings like: drivers/video/backlight/ili922x.c:116: warning: Function parameter or member 's' not described in 'CHECK_FREQ_REG' drivers/video/backlight/ili922x.c:116: warning: Function parameter or member 'x' not described in 'CHECK_FREQ_REG' Cc: Bartlomiej Zolnierkiewicz Cc: Software Engineering Signed-off-by: Lee Jones Reviewed-by: Daniel Thompson Reviewed-by: Sam Ravnborg Signed-off-by: Lee Jones --- drivers/video/backlight/ili922x.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/video/backlight/ili922x.c b/drivers/video/backlight/ili922x.c index 9c5aa3fbb284..5914147b2c4b 100644 --- a/drivers/video/backlight/ili922x.c +++ b/drivers/video/backlight/ili922x.c @@ -107,6 +107,8 @@ * lower frequency when the registers are read/written. * The macro sets the frequency in the spi_transfer structure if * the frequency exceeds the maximum value. + * @s: pointer to an SPI device + * @x: pointer to the read/write buffer pair */ #define CHECK_FREQ_REG(s, x) \ do { \ From ee555c1dbe69d7de80d11ebbe5c9589726e12ed9 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 23 Jun 2020 12:44:05 +0100 Subject: [PATCH 055/291] backlight: ili922x: Remove invalid use of kerneldoc syntax Kerneldoc is for documenting function arguments and return values. Prevents warnings like: drivers/video/backlight/ili922x.c:127: warning: cannot understand function prototype: 'int ili922x_id = 1; ' drivers/video/backlight/ili922x.c:136: warning: cannot understand function prototype: 'struct ili922x ' Cc: Bartlomiej Zolnierkiewicz Cc: Software Engineering Signed-off-by: Lee Jones Reviewed-by: Daniel Thompson Reviewed-by: Sam Ravnborg Signed-off-by: Lee Jones --- drivers/video/backlight/ili922x.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/video/backlight/ili922x.c b/drivers/video/backlight/ili922x.c index 5914147b2c4b..fe03fb058ef0 100644 --- a/drivers/video/backlight/ili922x.c +++ b/drivers/video/backlight/ili922x.c @@ -123,7 +123,7 @@ #define set_tx_byte(b) (tx_invert ? ~(b) : b) -/** +/* * ili922x_id - id as set by manufacturer */ static int ili922x_id = 1; @@ -132,7 +132,7 @@ module_param(ili922x_id, int, 0); static int tx_invert; module_param(tx_invert, int, 0); -/** +/* * driver's private structure */ struct ili922x { From 7099c930fa71438f1b46350f693e3e6d7e627482 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 23 Jun 2020 12:48:41 +0100 Subject: [PATCH 056/291] backlight: ili922x: Add missing kerneldoc description for ili922x_reg_dump()'s arg Kerneldoc syntax is used, but not complete. Descriptions required. Prevents warnings like: drivers/video/backlight/ili922x.c:298: warning: Function parameter or member 'spi' not described in 'ili922x_reg_dump' Cc: Bartlomiej Zolnierkiewicz Cc: Software Engineering Signed-off-by: Lee Jones Reviewed-by: Daniel Thompson Reviewed-by: Sam Ravnborg Signed-off-by: Lee Jones --- drivers/video/backlight/ili922x.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/video/backlight/ili922x.c b/drivers/video/backlight/ili922x.c index fe03fb058ef0..328aba9cddad 100644 --- a/drivers/video/backlight/ili922x.c +++ b/drivers/video/backlight/ili922x.c @@ -295,6 +295,8 @@ static int ili922x_write(struct spi_device *spi, u8 reg, u16 value) #ifdef DEBUG /** * ili922x_reg_dump - dump all registers + * + * @spi: pointer to an SPI device */ static void ili922x_reg_dump(struct spi_device *spi) { From 6c05632d6341ced4c2cb431ed0e5f617cc83f5bb Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 23 Jun 2020 15:04:36 +0100 Subject: [PATCH 057/291] backlight: backlight: Supply description for function args in existing Kerneldocs Kerneldoc syntax is used, but not complete. Descriptions required. Prevents warnings like: drivers/video/backlight/backlight.c:329: warning: Function parameter or member 'reason' not described in 'backlight_force_update' drivers/video/backlight/backlight.c:354: warning: Function parameter or member 'props' not described in 'backlight_device_register' Cc: Bartlomiej Zolnierkiewicz Cc: Jamey Hicks Cc: Andrew Zabolotny Signed-off-by: Lee Jones Reviewed-by: Daniel Thompson Reviewed-by: Sam Ravnborg Signed-off-by: Lee Jones --- drivers/video/backlight/backlight.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c index 92d80aa0c0ef..744ba58488e0 100644 --- a/drivers/video/backlight/backlight.c +++ b/drivers/video/backlight/backlight.c @@ -320,6 +320,7 @@ ATTRIBUTE_GROUPS(bl_device); * backlight_force_update - tell the backlight subsystem that hardware state * has changed * @bd: the backlight device to update + * @reason: reason for update * * Updates the internal state of the backlight in response to a hardware event, * and generate a uevent to notify userspace @@ -344,6 +345,7 @@ EXPORT_SYMBOL(backlight_force_update); * @devdata: an optional pointer to be stored for private driver use. The * methods may retrieve it by using bl_get_data(bd). * @ops: the backlight operations structure. + * @props: pointer to backlight's properties structure. * * Creates and registers new backlight device. Returns either an * ERR_PTR() or a pointer to the newly allocated device. From 3e799ccda3651a43ef3b366f70101e16e5054865 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 23 Jun 2020 15:37:50 +0100 Subject: [PATCH 058/291] backlight: lm3630a_bl: Remove invalid checks for unsigned int < 0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit unsigned ints 'sources' and 'bank' cannot be less than LM3630A_SINK_0 (0) and LM3630A_BANK_0 (0) respecitively, so change the logic to only check for thier two possible valid values. Fixes W=1 warnings: drivers/video/backlight/lm3630a_bl.c: In function ‘lm3630a_parse_led_sources’: drivers/video/backlight/lm3630a_bl.c:394:18: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits] 394 | if (sources[i] < LM3630A_SINK_0 || sources[i] > LM3630A_SINK_1) | ^ drivers/video/backlight/lm3630a_bl.c: In function ‘lm3630a_parse_bank’: drivers/video/backlight/lm3630a_bl.c:415:11: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits] 415 | if (bank < LM3630A_BANK_0 || bank > LM3630A_BANK_1) | ^ Cc: Bartlomiej Zolnierkiewicz Cc: Daniel Jeong Cc: LDD MLP Signed-off-by: Lee Jones Reviewed-by: Daniel Thompson Reviewed-by: Sam Ravnborg Signed-off-by: Lee Jones --- drivers/video/backlight/lm3630a_bl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/video/backlight/lm3630a_bl.c b/drivers/video/backlight/lm3630a_bl.c index ee320883b710..e88a2b0e5904 100644 --- a/drivers/video/backlight/lm3630a_bl.c +++ b/drivers/video/backlight/lm3630a_bl.c @@ -391,7 +391,7 @@ static int lm3630a_parse_led_sources(struct fwnode_handle *node, return ret; for (i = 0; i < num_sources; i++) { - if (sources[i] < LM3630A_SINK_0 || sources[i] > LM3630A_SINK_1) + if (sources[i] != LM3630A_SINK_0 && sources[i] != LM3630A_SINK_1) return -EINVAL; ret |= BIT(sources[i]); @@ -412,7 +412,7 @@ static int lm3630a_parse_bank(struct lm3630a_platform_data *pdata, if (ret) return ret; - if (bank < LM3630A_BANK_0 || bank > LM3630A_BANK_1) + if (bank != LM3630A_BANK_0 && bank != LM3630A_BANK_1) return -EINVAL; led_sources = lm3630a_parse_led_sources(node, BIT(bank)); From e17c7461a28ce7f0cc2c1aec307584dccd04a847 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 23 Jun 2020 15:47:02 +0100 Subject: [PATCH 059/291] backlight: qcom-wled: Remove unused configs for LED3 and LED4 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes W=1 warnings: drivers/video/backlight/qcom-wled.c:1294:34: warning: ‘wled4_string_cfg’ defined but not used [-Wunused-const-variable=] 1294 | static const struct wled_var_cfg wled4_string_cfg = { | ^~~~~~~~~~~~~~~~ drivers/video/backlight/qcom-wled.c:1290:34: warning: ‘wled3_string_cfg’ defined but not used [-Wunused-const-variable=] 1290 | static const struct wled_var_cfg wled3_string_cfg = { | ^~~~~~~~~~~~~~~~ Cc: Andy Gross Cc: Bjorn Andersson Cc: Bartlomiej Zolnierkiewicz Cc: linux-arm-msm@vger.kernel.org Signed-off-by: Lee Jones Reviewed-by: Daniel Thompson Reviewed-by: Sam Ravnborg Signed-off-by: Lee Jones --- drivers/video/backlight/qcom-wled.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/video/backlight/qcom-wled.c b/drivers/video/backlight/qcom-wled.c index 4c8c34b99441..c25c31199952 100644 --- a/drivers/video/backlight/qcom-wled.c +++ b/drivers/video/backlight/qcom-wled.c @@ -1287,14 +1287,6 @@ static const struct wled_var_cfg wled4_string_i_limit_cfg = { .size = ARRAY_SIZE(wled4_string_i_limit_values), }; -static const struct wled_var_cfg wled3_string_cfg = { - .size = 8, -}; - -static const struct wled_var_cfg wled4_string_cfg = { - .size = 16, -}; - static const struct wled_var_cfg wled5_mod_sel_cfg = { .size = 2, }; From c847e429db9de0a214401477c7292066e599a7c9 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 6 Jul 2020 08:44:21 +0100 Subject: [PATCH 060/291] video: backlight: sky81452-backlight: Fix some kerneldoc issues Firstly, all lines must begin with a '*'. Secondly, arg descriptions must be spelt correctly, so fix misspelling of 'gpioD_enable' and 'short_detecTion_threshold' Fixes the following W=1 kernel build warning(s): drivers/video/backlight/sky81452-backlight.c:46: warning: bad line: If it is not defined, default name is lcd-backlight. drivers/video/backlight/sky81452-backlight.c:64: warning: Function parameter or member 'gpiod_enable' not described in 'sky81452_bl_platform_data' drivers/video/backlight/sky81452-backlight.c:64: warning: Function parameter or member 'short_detection_threshold' not described in 'sky81452_bl_platform_data' Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/sky81452-backlight.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/video/backlight/sky81452-backlight.c b/drivers/video/backlight/sky81452-backlight.c index 83ccb3d940fa..0ce181585008 100644 --- a/drivers/video/backlight/sky81452-backlight.c +++ b/drivers/video/backlight/sky81452-backlight.c @@ -43,13 +43,13 @@ /** * struct sky81452_platform_data * @name: backlight driver name. - If it is not defined, default name is lcd-backlight. - * @gpios_enable:GPIO descriptor which control EN pin + * If it is not defined, default name is lcd-backlight. + * @gpiod_enable:GPIO descriptor which control EN pin * @enable: Enable mask for current sink channel 1, 2, 3, 4, 5 and 6. * @ignore_pwm: true if DPWMI should be ignored. * @dpwm_mode: true is DPWM dimming mode, otherwise Analog dimming mode. * @phase_shift:true is phase shift mode. - * @short_detecion_threshold: It should be one of 4, 5, 6 and 7V. + * @short_detection_threshold: It should be one of 4, 5, 6 and 7V. * @boost_current_limit: It should be one of 2300, 2750mA. */ struct sky81452_bl_platform_data { From ecd7274fb4cd2d6c035a52d59ca3d6ec936a07be Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 4 Jun 2020 18:11:15 +0100 Subject: [PATCH 061/291] iommu: Remove unused IOMMU_SYS_CACHE_ONLY flag The IOMMU_SYS_CACHE_ONLY flag was never exposed via the DMA API and has no in-tree users. Remove it. Cc: Robin Murphy Cc: "Isaac J. Manjarres" Cc: Joerg Roedel Cc: Rob Clark Reviewed-by: Christoph Hellwig Reviewed-by: Sai Prakash Ranjan Signed-off-by: Will Deacon --- drivers/iommu/io-pgtable-arm.c | 3 --- include/linux/iommu.h | 6 ------ 2 files changed, 9 deletions(-) diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 04fbd4bf0ff9..8f175c02f8e3 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -438,9 +438,6 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, else if (prot & IOMMU_CACHE) pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE << ARM_LPAE_PTE_ATTRINDX_SHIFT); - else if (prot & IOMMU_SYS_CACHE_ONLY) - pte |= (ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE - << ARM_LPAE_PTE_ATTRINDX_SHIFT); } if (prot & IOMMU_CACHE) diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 5f0b7859d2eb..bee1a8fa1fb1 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -31,12 +31,6 @@ * if the IOMMU page table format is equivalent. */ #define IOMMU_PRIV (1 << 5) -/* - * Non-coherent masters can use this page protection flag to set cacheable - * memory attributes for only a transparent outer level of cache, also known as - * the last-level or system cache. - */ -#define IOMMU_SYS_CACHE_ONLY (1 << 6) struct iommu_ops; struct iommu_group; From 976492922a6a9c06f6f61436848adf2f03702e5c Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 24 Jun 2020 11:24:51 +0100 Subject: [PATCH 062/291] iommu/arm-smmu: Update impl quirks comment The comment about implementation and integration quirks being mutually-exclusive is out of date, and in fact the code is already structured for the case it anticipates, so document that properly. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/1e742177e084621f3454fbaf768325a6c215656a.1592994291.git.robin.murphy@arm.com Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-impl.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c index c75b9d957b70..1fb4bb994dbf 100644 --- a/drivers/iommu/arm-smmu-impl.c +++ b/drivers/iommu/arm-smmu-impl.c @@ -153,10 +153,9 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu) const struct device_node *np = smmu->dev->of_node; /* - * We will inevitably have to combine model-specific implementation - * quirks with platform-specific integration quirks, but everything - * we currently support happens to work out as straightforward - * mutually-exclusive assignments. + * Set the impl for model-specific implementation quirks first, + * such that platform integration quirks can pick it up and + * inherit from it if necessary. */ switch (smmu->model) { case ARM_MMU500: @@ -168,6 +167,7 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu) break; } + /* This is implicitly MMU-400 */ if (of_property_read_bool(np, "calxeda,smmu-secure-config-access")) smmu->impl = &calxeda_impl; From 5abfe5cf0b8358b8ad0da99e4188c2519839d67c Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Tue, 23 Jun 2020 19:23:27 -0700 Subject: [PATCH 063/291] remoteproc: qcom: Add per subsystem SSR notification Currently there is a single notification chain which is called whenever any remoteproc shuts down. This leads to all the listeners being notified, and is not an optimal design as kernel drivers might only be interested in listening to notifications from a particular remoteproc. Create a global list of remoteproc notification info data structures. This will hold the name and notifier_list information for a particular remoteproc. The API to register for notifications will use name argument to retrieve the notification info data structure and the notifier block will be added to that data structure's notification chain. Also move from blocking notifier to srcu notifer based implementation to support dynamic notifier head creation. Reviewed-by: Alex Elder Co-developed-by: Siddharth Gupta Signed-off-by: Siddharth Gupta Signed-off-by: Rishabh Bhatnagar Link: https://lore.kernel.org/r/1592965408-16908-2-git-send-email-rishabhb@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_common.c | 90 +++++++++++++++++++++++---- drivers/remoteproc/qcom_common.h | 5 +- include/linux/remoteproc/qcom_rproc.h | 20 ++++-- 3 files changed, 95 insertions(+), 20 deletions(-) diff --git a/drivers/remoteproc/qcom_common.c b/drivers/remoteproc/qcom_common.c index 9028cea2d81e..48b399af9c83 100644 --- a/drivers/remoteproc/qcom_common.c +++ b/drivers/remoteproc/qcom_common.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -23,7 +24,14 @@ #define to_smd_subdev(d) container_of(d, struct qcom_rproc_subdev, subdev) #define to_ssr_subdev(d) container_of(d, struct qcom_rproc_ssr, subdev) -static BLOCKING_NOTIFIER_HEAD(ssr_notifiers); +struct qcom_ssr_subsystem { + const char *name; + struct srcu_notifier_head notifier_list; + struct list_head list; +}; + +static LIST_HEAD(qcom_ssr_subsystem_list); +static DEFINE_MUTEX(qcom_ssr_subsys_lock); static int glink_subdev_start(struct rproc_subdev *subdev) { @@ -189,37 +197,83 @@ void qcom_remove_smd_subdev(struct rproc *rproc, struct qcom_rproc_subdev *smd) } EXPORT_SYMBOL_GPL(qcom_remove_smd_subdev); +static struct qcom_ssr_subsystem *qcom_ssr_get_subsys(const char *name) +{ + struct qcom_ssr_subsystem *info; + + mutex_lock(&qcom_ssr_subsys_lock); + /* Match in the global qcom_ssr_subsystem_list with name */ + list_for_each_entry(info, &qcom_ssr_subsystem_list, list) + if (!strcmp(info->name, name)) + goto out; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) { + info = ERR_PTR(-ENOMEM); + goto out; + } + info->name = kstrdup_const(name, GFP_KERNEL); + srcu_init_notifier_head(&info->notifier_list); + + /* Add to global notification list */ + list_add_tail(&info->list, &qcom_ssr_subsystem_list); + +out: + mutex_unlock(&qcom_ssr_subsys_lock); + return info; +} + /** * qcom_register_ssr_notifier() - register SSR notification handler - * @nb: notifier_block to notify for restart notifications + * @name: Subsystem's SSR name + * @nb: notifier_block to be invoked upon subsystem's state change * - * Returns 0 on success, negative errno on failure. + * This registers the @nb notifier block as part the notifier chain for a + * remoteproc associated with @name. The notifier block's callback + * will be invoked when the remote processor's SSR events occur + * (pre/post startup and pre/post shutdown). * - * This register the @notify function as handler for restart notifications. As - * remote processors are stopped this function will be called, with the SSR - * name passed as a parameter. + * Return: a subsystem cookie on success, ERR_PTR on failure. */ -int qcom_register_ssr_notifier(struct notifier_block *nb) +void *qcom_register_ssr_notifier(const char *name, struct notifier_block *nb) { - return blocking_notifier_chain_register(&ssr_notifiers, nb); + struct qcom_ssr_subsystem *info; + + info = qcom_ssr_get_subsys(name); + if (IS_ERR(info)) + return info; + + srcu_notifier_chain_register(&info->notifier_list, nb); + + return &info->notifier_list; } EXPORT_SYMBOL_GPL(qcom_register_ssr_notifier); /** * qcom_unregister_ssr_notifier() - unregister SSR notification handler + * @notify: subsystem cookie returned from qcom_register_ssr_notifier * @nb: notifier_block to unregister + * + * This function will unregister the notifier from the particular notifier + * chain. + * + * Return: 0 on success, %ENOENT otherwise. */ -void qcom_unregister_ssr_notifier(struct notifier_block *nb) +int qcom_unregister_ssr_notifier(void *notify, struct notifier_block *nb) { - blocking_notifier_chain_unregister(&ssr_notifiers, nb); + return srcu_notifier_chain_unregister(notify, nb); } EXPORT_SYMBOL_GPL(qcom_unregister_ssr_notifier); static void ssr_notify_unprepare(struct rproc_subdev *subdev) { struct qcom_rproc_ssr *ssr = to_ssr_subdev(subdev); + struct qcom_ssr_notify_data data = { + .name = ssr->info->name, + .crashed = false, + }; - blocking_notifier_call_chain(&ssr_notifiers, 0, (void *)ssr->name); + srcu_notifier_call_chain(&ssr->info->notifier_list, 0, &data); } /** @@ -229,12 +283,21 @@ static void ssr_notify_unprepare(struct rproc_subdev *subdev) * @ssr_name: identifier to use for notifications originating from @rproc * * As the @ssr is registered with the @rproc SSR events will be sent to all - * registered listeners in the system as the remoteproc is shut down. + * registered listeners for the remoteproc when it's SSR events occur + * (pre/post startup and pre/post shutdown). */ void qcom_add_ssr_subdev(struct rproc *rproc, struct qcom_rproc_ssr *ssr, const char *ssr_name) { - ssr->name = ssr_name; + struct qcom_ssr_subsystem *info; + + info = qcom_ssr_get_subsys(ssr_name); + if (IS_ERR(info)) { + dev_err(&rproc->dev, "Failed to add ssr subdevice\n"); + return; + } + + ssr->info = info; ssr->subdev.unprepare = ssr_notify_unprepare; rproc_add_subdev(rproc, &ssr->subdev); @@ -249,6 +312,7 @@ EXPORT_SYMBOL_GPL(qcom_add_ssr_subdev); void qcom_remove_ssr_subdev(struct rproc *rproc, struct qcom_rproc_ssr *ssr) { rproc_remove_subdev(rproc, &ssr->subdev); + ssr->info = NULL; } EXPORT_SYMBOL_GPL(qcom_remove_ssr_subdev); diff --git a/drivers/remoteproc/qcom_common.h b/drivers/remoteproc/qcom_common.h index 34e5188187dc..dfc641c3a98b 100644 --- a/drivers/remoteproc/qcom_common.h +++ b/drivers/remoteproc/qcom_common.h @@ -26,10 +26,11 @@ struct qcom_rproc_subdev { struct qcom_smd_edge *edge; }; +struct qcom_ssr_subsystem; + struct qcom_rproc_ssr { struct rproc_subdev subdev; - - const char *name; + struct qcom_ssr_subsystem *info; }; void qcom_add_glink_subdev(struct rproc *rproc, struct qcom_rproc_glink *glink, diff --git a/include/linux/remoteproc/qcom_rproc.h b/include/linux/remoteproc/qcom_rproc.h index fa8e38681b4b..2a1d6d0249d9 100644 --- a/include/linux/remoteproc/qcom_rproc.h +++ b/include/linux/remoteproc/qcom_rproc.h @@ -5,18 +5,28 @@ struct notifier_block; #if IS_ENABLED(CONFIG_QCOM_RPROC_COMMON) -int qcom_register_ssr_notifier(struct notifier_block *nb); -void qcom_unregister_ssr_notifier(struct notifier_block *nb); +struct qcom_ssr_notify_data { + const char *name; + bool crashed; +}; + +void *qcom_register_ssr_notifier(const char *name, struct notifier_block *nb); +int qcom_unregister_ssr_notifier(void *notify, struct notifier_block *nb); #else -static inline int qcom_register_ssr_notifier(struct notifier_block *nb) +static inline void *qcom_register_ssr_notifier(const char *name, + struct notifier_block *nb) +{ + return NULL; +} + +static inline int qcom_unregister_ssr_notifier(void *notify, + struct notifier_block *nb) { return 0; } -static inline void qcom_unregister_ssr_notifier(struct notifier_block *nb) {} - #endif #endif From 62495d778439a4e47571293511a785cba754874c Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Tue, 23 Jun 2020 19:23:28 -0700 Subject: [PATCH 064/291] remoteproc: qcom: Add notification types to SSR The SSR subdevice only adds callback for the unprepare event. Add callbacks for prepare, start and prepare events. The client driver for a particular remoteproc might be interested in knowing the status of the remoteproc while undergoing SSR, not just when the remoteproc has finished shutting down. Reviewed-by: Alex Elder Signed-off-by: Siddharth Gupta Signed-off-by: Rishabh Bhatnagar Link: https://lore.kernel.org/r/1592965408-16908-3-git-send-email-rishabhb@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_common.c | 44 ++++++++++++++++++++++++++- include/linux/remoteproc/qcom_rproc.h | 16 ++++++++++ 2 files changed, 59 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/qcom_common.c b/drivers/remoteproc/qcom_common.c index 48b399af9c83..2f45f0c79914 100644 --- a/drivers/remoteproc/qcom_common.c +++ b/drivers/remoteproc/qcom_common.c @@ -265,6 +265,44 @@ int qcom_unregister_ssr_notifier(void *notify, struct notifier_block *nb) } EXPORT_SYMBOL_GPL(qcom_unregister_ssr_notifier); +static int ssr_notify_prepare(struct rproc_subdev *subdev) +{ + struct qcom_rproc_ssr *ssr = to_ssr_subdev(subdev); + struct qcom_ssr_notify_data data = { + .name = ssr->info->name, + .crashed = false, + }; + + srcu_notifier_call_chain(&ssr->info->notifier_list, + QCOM_SSR_BEFORE_POWERUP, &data); + return 0; +} + +static int ssr_notify_start(struct rproc_subdev *subdev) +{ + struct qcom_rproc_ssr *ssr = to_ssr_subdev(subdev); + struct qcom_ssr_notify_data data = { + .name = ssr->info->name, + .crashed = false, + }; + + srcu_notifier_call_chain(&ssr->info->notifier_list, + QCOM_SSR_AFTER_POWERUP, &data); + return 0; +} + +static void ssr_notify_stop(struct rproc_subdev *subdev, bool crashed) +{ + struct qcom_rproc_ssr *ssr = to_ssr_subdev(subdev); + struct qcom_ssr_notify_data data = { + .name = ssr->info->name, + .crashed = crashed, + }; + + srcu_notifier_call_chain(&ssr->info->notifier_list, + QCOM_SSR_BEFORE_SHUTDOWN, &data); +} + static void ssr_notify_unprepare(struct rproc_subdev *subdev) { struct qcom_rproc_ssr *ssr = to_ssr_subdev(subdev); @@ -273,7 +311,8 @@ static void ssr_notify_unprepare(struct rproc_subdev *subdev) .crashed = false, }; - srcu_notifier_call_chain(&ssr->info->notifier_list, 0, &data); + srcu_notifier_call_chain(&ssr->info->notifier_list, + QCOM_SSR_AFTER_SHUTDOWN, &data); } /** @@ -298,6 +337,9 @@ void qcom_add_ssr_subdev(struct rproc *rproc, struct qcom_rproc_ssr *ssr, } ssr->info = info; + ssr->subdev.prepare = ssr_notify_prepare; + ssr->subdev.start = ssr_notify_start; + ssr->subdev.stop = ssr_notify_stop; ssr->subdev.unprepare = ssr_notify_unprepare; rproc_add_subdev(rproc, &ssr->subdev); diff --git a/include/linux/remoteproc/qcom_rproc.h b/include/linux/remoteproc/qcom_rproc.h index 2a1d6d0249d9..647051662174 100644 --- a/include/linux/remoteproc/qcom_rproc.h +++ b/include/linux/remoteproc/qcom_rproc.h @@ -5,6 +5,22 @@ struct notifier_block; #if IS_ENABLED(CONFIG_QCOM_RPROC_COMMON) +/** + * enum qcom_ssr_notify_type - Startup/Shutdown events related to a remoteproc + * processor. + * + * @QCOM_SSR_BEFORE_POWERUP: Remoteproc about to start (prepare stage) + * @QCOM_SSR_AFTER_POWERUP: Remoteproc is running (start stage) + * @QCOM_SSR_BEFORE_SHUTDOWN: Remoteproc crashed or shutting down (stop stage) + * @QCOM_SSR_AFTER_SHUTDOWN: Remoteproc is down (unprepare stage) + */ +enum qcom_ssr_notify_type { + QCOM_SSR_BEFORE_POWERUP, + QCOM_SSR_AFTER_POWERUP, + QCOM_SSR_BEFORE_SHUTDOWN, + QCOM_SSR_AFTER_SHUTDOWN, +}; + struct qcom_ssr_notify_data { const char *name; bool crashed; From 7b6b70d88b10c61af7050820ca041ff9e73482ae Mon Sep 17 00:00:00 2001 From: Jonathan Marek Date: Tue, 9 Jun 2020 15:40:19 -0400 Subject: [PATCH 065/291] dt-bindings: arm-smmu: Add sm8150 and sm8250 compatible strings Add compatible strings for sm8150 and sm8250 iommus to documentation. Signed-off-by: Jonathan Marek Acked-by: Rob Herring Link: https://lore.kernel.org/r/20200609194030.17756-2-jonathan@marek.ca Signed-off-by: Will Deacon --- Documentation/devicetree/bindings/iommu/arm,smmu.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index d7ceb4c34423..3ac741236c8b 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -37,6 +37,8 @@ properties: - enum: - qcom,sc7180-smmu-500 - qcom,sdm845-smmu-500 + - qcom,sm8150-smmu-500 + - qcom,sm8250-smmu-500 - const: arm,mmu-500 - items: - const: arm,mmu-500 From 2c5c3cfb2da577bb23c3d9d771cc08300dec3559 Mon Sep 17 00:00:00 2001 From: Jonathan Marek Date: Tue, 9 Jun 2020 15:40:20 -0400 Subject: [PATCH 066/291] iommu: arm-smmu-impl: Use qcom impl for sm8150 and sm8250 compatibles Use the qcom implementation for IOMMU hardware on sm8150 and sm8250 SoCs. Signed-off-by: Jonathan Marek Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200609194030.17756-3-jonathan@marek.ca Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-impl.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c index 1fb4bb994dbf..22a9acd76955 100644 --- a/drivers/iommu/arm-smmu-impl.c +++ b/drivers/iommu/arm-smmu-impl.c @@ -172,7 +172,9 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu) smmu->impl = &calxeda_impl; if (of_device_is_compatible(np, "qcom,sdm845-smmu-500") || - of_device_is_compatible(np, "qcom,sc7180-smmu-500")) + of_device_is_compatible(np, "qcom,sc7180-smmu-500") || + of_device_is_compatible(np, "qcom,sm8150-smmu-500") || + of_device_is_compatible(np, "qcom,sm8250-smmu-500")) return qcom_smmu_impl_init(smmu); return smmu; From b4ceb4a5359ed1c9ba4a20acf3a70d4bbead3248 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 3 Jul 2020 17:03:19 +0100 Subject: [PATCH 067/291] iommu: Tidy up Kconfig for SoC IOMMUs Wacky COMPILE_TEST dependencies based on who used to define dev_archdata.iommu can go. Dependencies on ARM or ARM64 already implied by the ARCH_* platform selection can go. The entire IOMMU_SUPPORT menu already depends on MMU, so those can go. IOMMU_DMA is for the architecture's DMA API implementation to choose, and its interface to IOMMU drivers is properly stubbed out if disabled, so dependencies on or selections of that can go (AMD_IOMMU is the current exception since the x86 drivers have to provide their own entire dma_map_ops implementation). Since commit ed6ccf10f24b ("dma-mapping: properly stub out the DMA API for !CONFIG_HAS_DMA"), drivers which simply use the dma-mapping API should not need to depend on HAS_DMA, so those can go. And a long-dead option for code removed from the MSM driver 4 years ago can also go. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/7fb9c74dc6bd12a4619ca44c92408e91352f1be0.1593791968.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/Kconfig | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 6dc49ed8377a..4dcd85bbff99 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -128,10 +128,6 @@ config MSM_IOMMU If unsure, say N here. -config IOMMU_PGTABLES_L2 - def_bool y - depends on MSM_IOMMU && MMU && SMP && CPU_DCACHE_DISABLE=n - # AMD IOMMU support config AMD_IOMMU bool "AMD IOMMU support" @@ -274,7 +270,6 @@ config IRQ_REMAP # OMAP IOMMU support config OMAP_IOMMU bool "OMAP IOMMU Support" - depends on ARM && MMU || (COMPILE_TEST && (ARM || ARM64 || IA64 || SPARC)) depends on ARCH_OMAP2PLUS || COMPILE_TEST select IOMMU_API help @@ -292,7 +287,6 @@ config OMAP_IOMMU_DEBUG config ROCKCHIP_IOMMU bool "Rockchip IOMMU Support" - depends on ARM || ARM64 || (COMPILE_TEST && (ARM64 || IA64 || SPARC)) depends on ARCH_ROCKCHIP || COMPILE_TEST select IOMMU_API select ARM_DMA_USE_IOMMU @@ -308,7 +302,6 @@ config SUN50I_IOMMU depends on ARCH_SUNXI || COMPILE_TEST select ARM_DMA_USE_IOMMU select IOMMU_API - select IOMMU_DMA help Support for the IOMMU introduced in the Allwinner H6 SoCs. @@ -335,7 +328,7 @@ config TEGRA_IOMMU_SMMU config EXYNOS_IOMMU bool "Exynos IOMMU Support" - depends on ARCH_EXYNOS && MMU || (COMPILE_TEST && (ARM || ARM64 || IA64 || SPARC)) + depends on ARCH_EXYNOS || COMPILE_TEST depends on !CPU_BIG_ENDIAN # revisit driver if we can enable big-endian ptes select IOMMU_API select ARM_DMA_USE_IOMMU @@ -358,7 +351,7 @@ config EXYNOS_IOMMU_DEBUG config IPMMU_VMSA bool "Renesas VMSA-compatible IPMMU" - depends on ARM || IOMMU_DMA + depends on ARM || ARM64 depends on ARCH_RENESAS || (COMPILE_TEST && !GENERIC_ATOMIC64) select IOMMU_API select IOMMU_IO_PGTABLE_LPAE @@ -380,7 +373,7 @@ config SPAPR_TCE_IOMMU # ARM IOMMU support config ARM_SMMU tristate "ARM Ltd. System MMU (SMMU) Support" - depends on (ARM64 || ARM || (COMPILE_TEST && !GENERIC_ATOMIC64)) && MMU + depends on ARM64 || ARM || (COMPILE_TEST && !GENERIC_ATOMIC64) select IOMMU_API select IOMMU_IO_PGTABLE_LPAE select ARM_DMA_USE_IOMMU if ARM @@ -466,11 +459,9 @@ config S390_AP_IOMMU config MTK_IOMMU bool "MTK IOMMU Support" - depends on HAS_DMA depends on ARCH_MEDIATEK || COMPILE_TEST select ARM_DMA_USE_IOMMU select IOMMU_API - select IOMMU_DMA select IOMMU_IO_PGTABLE_ARMV7S select MEMORY select MTK_SMI From 97215a7df4351fdd9141418568be872fb1032d6e Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 3 Jul 2020 17:03:20 +0100 Subject: [PATCH 068/291] iommu/renesas: Expand COMPILE_TEST coverage This driver shouldn't need anything architecture-specific (that isn't under CONFIG_ARM protection already), and has already been accessible from certain x86 configurations by virtue of the previously-cleaned-up "ARM || IOMMU_DMA" dependency. Allow COMPILE_TEST for all architectures. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/1fe2006aa98f008a2e689adba6e8c96e9197f903.1593791968.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 4dcd85bbff99..af6c081d164f 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -351,7 +351,6 @@ config EXYNOS_IOMMU_DEBUG config IPMMU_VMSA bool "Renesas VMSA-compatible IPMMU" - depends on ARM || ARM64 depends on ARCH_RENESAS || (COMPILE_TEST && !GENERIC_ATOMIC64) select IOMMU_API select IOMMU_IO_PGTABLE_LPAE From 349b00c9c0a052af6720552919c9812dad9013e7 Mon Sep 17 00:00:00 2001 From: Chao Hao Date: Fri, 3 Jul 2020 12:41:18 +0800 Subject: [PATCH 069/291] dt-bindings: mediatek: Add bindings for MT6779 This patch adds description for MT6779 IOMMU. MT6779 has two iommus, they are mm_iommu and apu_iommu which both use ARM Short-Descriptor translation format. In addition, mm_iommu and apu_iommu are two independent HW instance , we need to set them separately. The MT6779 IOMMU hardware diagram is as below, it is only a brief diagram about iommu, it don't focus on the part of smi_larb, so I don't describe the smi_larb detailedly. EMI | -------------------------------------- | | MM_IOMMU APU_IOMMU | | SMI_COMMOM----------- APU_BUS | | | SMI_LARB(0~11) | | | | | | | -------------- | | | | | Multimedia engine CCU VPU MDLA EMDA All the connections are hardware fixed, software can not adjust it. Signed-off-by: Chao Hao Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20200703044127.27438-2-chao.hao@mediatek.com Signed-off-by: Joerg Roedel --- .../bindings/iommu/mediatek,iommu.txt | 2 + include/dt-bindings/memory/mt6779-larb-port.h | 206 ++++++++++++++++++ 2 files changed, 208 insertions(+) create mode 100644 include/dt-bindings/memory/mt6779-larb-port.h diff --git a/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt b/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt index ce59a505f5a4..c1ccd8582eb2 100644 --- a/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt +++ b/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt @@ -58,6 +58,7 @@ Required properties: - compatible : must be one of the following string: "mediatek,mt2701-m4u" for mt2701 which uses generation one m4u HW. "mediatek,mt2712-m4u" for mt2712 which uses generation two m4u HW. + "mediatek,mt6779-m4u" for mt6779 which uses generation two m4u HW. "mediatek,mt7623-m4u", "mediatek,mt2701-m4u" for mt7623 which uses generation one m4u HW. "mediatek,mt8173-m4u" for mt8173 which uses generation two m4u HW. @@ -78,6 +79,7 @@ Required properties: Specifies the mtk_m4u_id as defined in dt-binding/memory/mt2701-larb-port.h for mt2701, mt7623 dt-binding/memory/mt2712-larb-port.h for mt2712, + dt-binding/memory/mt6779-larb-port.h for mt6779, dt-binding/memory/mt8173-larb-port.h for mt8173, and dt-binding/memory/mt8183-larb-port.h for mt8183. diff --git a/include/dt-bindings/memory/mt6779-larb-port.h b/include/dt-bindings/memory/mt6779-larb-port.h new file mode 100644 index 000000000000..2ad0899fbf2f --- /dev/null +++ b/include/dt-bindings/memory/mt6779-larb-port.h @@ -0,0 +1,206 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2019 MediaTek Inc. + * Author: Chao Hao + */ + +#ifndef _DTS_IOMMU_PORT_MT6779_H_ +#define _DTS_IOMMU_PORT_MT6779_H_ + +#define MTK_M4U_ID(larb, port) (((larb) << 5) | (port)) + +#define M4U_LARB0_ID 0 +#define M4U_LARB1_ID 1 +#define M4U_LARB2_ID 2 +#define M4U_LARB3_ID 3 +#define M4U_LARB4_ID 4 +#define M4U_LARB5_ID 5 +#define M4U_LARB6_ID 6 +#define M4U_LARB7_ID 7 +#define M4U_LARB8_ID 8 +#define M4U_LARB9_ID 9 +#define M4U_LARB10_ID 10 +#define M4U_LARB11_ID 11 + +/* larb0 */ +#define M4U_PORT_DISP_POSTMASK0 MTK_M4U_ID(M4U_LARB0_ID, 0) +#define M4U_PORT_DISP_OVL0_HDR MTK_M4U_ID(M4U_LARB0_ID, 1) +#define M4U_PORT_DISP_OVL1_HDR MTK_M4U_ID(M4U_LARB0_ID, 2) +#define M4U_PORT_DISP_OVL0 MTK_M4U_ID(M4U_LARB0_ID, 3) +#define M4U_PORT_DISP_OVL1 MTK_M4U_ID(M4U_LARB0_ID, 4) +#define M4U_PORT_DISP_PVRIC0 MTK_M4U_ID(M4U_LARB0_ID, 5) +#define M4U_PORT_DISP_RDMA0 MTK_M4U_ID(M4U_LARB0_ID, 6) +#define M4U_PORT_DISP_WDMA0 MTK_M4U_ID(M4U_LARB0_ID, 7) +#define M4U_PORT_DISP_FAKE0 MTK_M4U_ID(M4U_LARB0_ID, 8) + +/* larb1 */ +#define M4U_PORT_DISP_OVL0_2L_HDR MTK_M4U_ID(M4U_LARB1_ID, 0) +#define M4U_PORT_DISP_OVL1_2L_HDR MTK_M4U_ID(M4U_LARB1_ID, 1) +#define M4U_PORT_DISP_OVL0_2L MTK_M4U_ID(M4U_LARB1_ID, 2) +#define M4U_PORT_DISP_OVL1_2L MTK_M4U_ID(M4U_LARB1_ID, 3) +#define M4U_PORT_DISP_RDMA1 MTK_M4U_ID(M4U_LARB1_ID, 4) +#define M4U_PORT_MDP_PVRIC0 MTK_M4U_ID(M4U_LARB1_ID, 5) +#define M4U_PORT_MDP_PVRIC1 MTK_M4U_ID(M4U_LARB1_ID, 6) +#define M4U_PORT_MDP_RDMA0 MTK_M4U_ID(M4U_LARB1_ID, 7) +#define M4U_PORT_MDP_RDMA1 MTK_M4U_ID(M4U_LARB1_ID, 8) +#define M4U_PORT_MDP_WROT0_R MTK_M4U_ID(M4U_LARB1_ID, 9) +#define M4U_PORT_MDP_WROT0_W MTK_M4U_ID(M4U_LARB1_ID, 10) +#define M4U_PORT_MDP_WROT1_R MTK_M4U_ID(M4U_LARB1_ID, 11) +#define M4U_PORT_MDP_WROT1_W MTK_M4U_ID(M4U_LARB1_ID, 12) +#define M4U_PORT_DISP_FAKE1 MTK_M4U_ID(M4U_LARB1_ID, 13) + +/* larb2-VDEC */ +#define M4U_PORT_HW_VDEC_MC_EXT MTK_M4U_ID(M4U_LARB2_ID, 0) +#define M4U_PORT_HW_VDEC_UFO_EXT MTK_M4U_ID(M4U_LARB2_ID, 1) +#define M4U_PORT_HW_VDEC_PP_EXT MTK_M4U_ID(M4U_LARB2_ID, 2) +#define M4U_PORT_HW_VDEC_PRED_RD_EXT MTK_M4U_ID(M4U_LARB2_ID, 3) +#define M4U_PORT_HW_VDEC_PRED_WR_EXT MTK_M4U_ID(M4U_LARB2_ID, 4) +#define M4U_PORT_HW_VDEC_PPWRAP_EXT MTK_M4U_ID(M4U_LARB2_ID, 5) +#define M4U_PORT_HW_VDEC_TILE_EXT MTK_M4U_ID(M4U_LARB2_ID, 6) +#define M4U_PORT_HW_VDEC_VLD_EXT MTK_M4U_ID(M4U_LARB2_ID, 7) +#define M4U_PORT_HW_VDEC_VLD2_EXT MTK_M4U_ID(M4U_LARB2_ID, 8) +#define M4U_PORT_HW_VDEC_AVC_MV_EXT MTK_M4U_ID(M4U_LARB2_ID, 9) +#define M4U_PORT_HW_VDEC_UFO_ENC_EXT MTK_M4U_ID(M4U_LARB2_ID, 10) +#define M4U_PORT_HW_VDEC_RG_CTRL_DMA_EXT MTK_M4U_ID(M4U_LARB2_ID, 11) + +/* larb3-VENC */ +#define M4U_PORT_VENC_RCPU MTK_M4U_ID(M4U_LARB3_ID, 0) +#define M4U_PORT_VENC_REC MTK_M4U_ID(M4U_LARB3_ID, 1) +#define M4U_PORT_VENC_BSDMA MTK_M4U_ID(M4U_LARB3_ID, 2) +#define M4U_PORT_VENC_SV_COMV MTK_M4U_ID(M4U_LARB3_ID, 3) +#define M4U_PORT_VENC_RD_COMV MTK_M4U_ID(M4U_LARB3_ID, 4) +#define M4U_PORT_VENC_NBM_RDMA MTK_M4U_ID(M4U_LARB3_ID, 5) +#define M4U_PORT_VENC_NBM_RDMA_LITE MTK_M4U_ID(M4U_LARB3_ID, 6) +#define M4U_PORT_JPGENC_Y_RDMA MTK_M4U_ID(M4U_LARB3_ID, 7) +#define M4U_PORT_JPGENC_C_RDMA MTK_M4U_ID(M4U_LARB3_ID, 8) +#define M4U_PORT_JPGENC_Q_TABLE MTK_M4U_ID(M4U_LARB3_ID, 9) +#define M4U_PORT_JPGENC_BSDMA MTK_M4U_ID(M4U_LARB3_ID, 10) +#define M4U_PORT_JPGDEC_WDMA MTK_M4U_ID(M4U_LARB3_ID, 11) +#define M4U_PORT_JPGDEC_BSDMA MTK_M4U_ID(M4U_LARB3_ID, 12) +#define M4U_PORT_VENC_NBM_WDMA MTK_M4U_ID(M4U_LARB3_ID, 13) +#define M4U_PORT_VENC_NBM_WDMA_LITE MTK_M4U_ID(M4U_LARB3_ID, 14) +#define M4U_PORT_VENC_CUR_LUMA MTK_M4U_ID(M4U_LARB3_ID, 15) +#define M4U_PORT_VENC_CUR_CHROMA MTK_M4U_ID(M4U_LARB3_ID, 16) +#define M4U_PORT_VENC_REF_LUMA MTK_M4U_ID(M4U_LARB3_ID, 17) +#define M4U_PORT_VENC_REF_CHROMA MTK_M4U_ID(M4U_LARB3_ID, 18) + +/* larb4-dummy */ + +/* larb5-IMG */ +#define M4U_PORT_IMGI_D1 MTK_M4U_ID(M4U_LARB5_ID, 0) +#define M4U_PORT_IMGBI_D1 MTK_M4U_ID(M4U_LARB5_ID, 1) +#define M4U_PORT_DMGI_D1 MTK_M4U_ID(M4U_LARB5_ID, 2) +#define M4U_PORT_DEPI_D1 MTK_M4U_ID(M4U_LARB5_ID, 3) +#define M4U_PORT_LCEI_D1 MTK_M4U_ID(M4U_LARB5_ID, 4) +#define M4U_PORT_SMTI_D1 MTK_M4U_ID(M4U_LARB5_ID, 5) +#define M4U_PORT_SMTO_D2 MTK_M4U_ID(M4U_LARB5_ID, 6) +#define M4U_PORT_SMTO_D1 MTK_M4U_ID(M4U_LARB5_ID, 7) +#define M4U_PORT_CRZO_D1 MTK_M4U_ID(M4U_LARB5_ID, 8) +#define M4U_PORT_IMG3O_D1 MTK_M4U_ID(M4U_LARB5_ID, 9) +#define M4U_PORT_VIPI_D1 MTK_M4U_ID(M4U_LARB5_ID, 10) +#define M4U_PORT_WPE_RDMA1 MTK_M4U_ID(M4U_LARB5_ID, 11) +#define M4U_PORT_WPE_RDMA0 MTK_M4U_ID(M4U_LARB5_ID, 12) +#define M4U_PORT_WPE_WDMA MTK_M4U_ID(M4U_LARB5_ID, 13) +#define M4U_PORT_TIMGO_D1 MTK_M4U_ID(M4U_LARB5_ID, 14) +#define M4U_PORT_MFB_RDMA0 MTK_M4U_ID(M4U_LARB5_ID, 15) +#define M4U_PORT_MFB_RDMA1 MTK_M4U_ID(M4U_LARB5_ID, 16) +#define M4U_PORT_MFB_RDMA2 MTK_M4U_ID(M4U_LARB5_ID, 17) +#define M4U_PORT_MFB_RDMA3 MTK_M4U_ID(M4U_LARB5_ID, 18) +#define M4U_PORT_MFB_WDMA MTK_M4U_ID(M4U_LARB5_ID, 19) +#define M4U_PORT_RESERVE1 MTK_M4U_ID(M4U_LARB5_ID, 20) +#define M4U_PORT_RESERVE2 MTK_M4U_ID(M4U_LARB5_ID, 21) +#define M4U_PORT_RESERVE3 MTK_M4U_ID(M4U_LARB5_ID, 22) +#define M4U_PORT_RESERVE4 MTK_M4U_ID(M4U_LARB5_ID, 23) +#define M4U_PORT_RESERVE5 MTK_M4U_ID(M4U_LARB5_ID, 24) +#define M4U_PORT_RESERVE6 MTK_M4U_ID(M4U_LARB5_ID, 25) + +/* larb6-IMG-VPU */ +#define M4U_PORT_IMG_IPUO MTK_M4U_ID(M4U_LARB6_ID, 0) +#define M4U_PORT_IMG_IPU3O MTK_M4U_ID(M4U_LARB6_ID, 1) +#define M4U_PORT_IMG_IPUI MTK_M4U_ID(M4U_LARB6_ID, 2) + +/* larb7-DVS */ +#define M4U_PORT_DVS_RDMA MTK_M4U_ID(M4U_LARB7_ID, 0) +#define M4U_PORT_DVS_WDMA MTK_M4U_ID(M4U_LARB7_ID, 1) +#define M4U_PORT_DVP_RDMA MTK_M4U_ID(M4U_LARB7_ID, 2) +#define M4U_PORT_DVP_WDMA MTK_M4U_ID(M4U_LARB7_ID, 3) + +/* larb8-IPESYS */ +#define M4U_PORT_FDVT_RDA MTK_M4U_ID(M4U_LARB8_ID, 0) +#define M4U_PORT_FDVT_RDB MTK_M4U_ID(M4U_LARB8_ID, 1) +#define M4U_PORT_FDVT_WRA MTK_M4U_ID(M4U_LARB8_ID, 2) +#define M4U_PORT_FDVT_WRB MTK_M4U_ID(M4U_LARB8_ID, 3) +#define M4U_PORT_FE_RD0 MTK_M4U_ID(M4U_LARB8_ID, 4) +#define M4U_PORT_FE_RD1 MTK_M4U_ID(M4U_LARB8_ID, 5) +#define M4U_PORT_FE_WR0 MTK_M4U_ID(M4U_LARB8_ID, 6) +#define M4U_PORT_FE_WR1 MTK_M4U_ID(M4U_LARB8_ID, 7) +#define M4U_PORT_RSC_RDMA0 MTK_M4U_ID(M4U_LARB8_ID, 8) +#define M4U_PORT_RSC_WDMA MTK_M4U_ID(M4U_LARB8_ID, 9) + +/* larb9-CAM */ +#define M4U_PORT_CAM_IMGO_R1_C MTK_M4U_ID(M4U_LARB9_ID, 0) +#define M4U_PORT_CAM_RRZO_R1_C MTK_M4U_ID(M4U_LARB9_ID, 1) +#define M4U_PORT_CAM_LSCI_R1_C MTK_M4U_ID(M4U_LARB9_ID, 2) +#define M4U_PORT_CAM_BPCI_R1_C MTK_M4U_ID(M4U_LARB9_ID, 3) +#define M4U_PORT_CAM_YUVO_R1_C MTK_M4U_ID(M4U_LARB9_ID, 4) +#define M4U_PORT_CAM_UFDI_R2_C MTK_M4U_ID(M4U_LARB9_ID, 5) +#define M4U_PORT_CAM_RAWI_R2_C MTK_M4U_ID(M4U_LARB9_ID, 6) +#define M4U_PORT_CAM_RAWI_R5_C MTK_M4U_ID(M4U_LARB9_ID, 7) +#define M4U_PORT_CAM_CAMSV_1 MTK_M4U_ID(M4U_LARB9_ID, 8) +#define M4U_PORT_CAM_CAMSV_2 MTK_M4U_ID(M4U_LARB9_ID, 9) +#define M4U_PORT_CAM_CAMSV_3 MTK_M4U_ID(M4U_LARB9_ID, 10) +#define M4U_PORT_CAM_CAMSV_4 MTK_M4U_ID(M4U_LARB9_ID, 11) +#define M4U_PORT_CAM_CAMSV_5 MTK_M4U_ID(M4U_LARB9_ID, 12) +#define M4U_PORT_CAM_CAMSV_6 MTK_M4U_ID(M4U_LARB9_ID, 13) +#define M4U_PORT_CAM_AAO_R1_C MTK_M4U_ID(M4U_LARB9_ID, 14) +#define M4U_PORT_CAM_AFO_R1_C MTK_M4U_ID(M4U_LARB9_ID, 15) +#define M4U_PORT_CAM_FLKO_R1_C MTK_M4U_ID(M4U_LARB9_ID, 16) +#define M4U_PORT_CAM_LCESO_R1_C MTK_M4U_ID(M4U_LARB9_ID, 17) +#define M4U_PORT_CAM_CRZO_R1_C MTK_M4U_ID(M4U_LARB9_ID, 18) +#define M4U_PORT_CAM_LTMSO_R1_C MTK_M4U_ID(M4U_LARB9_ID, 19) +#define M4U_PORT_CAM_RSSO_R1_C MTK_M4U_ID(M4U_LARB9_ID, 20) +#define M4U_PORT_CAM_CCUI MTK_M4U_ID(M4U_LARB9_ID, 21) +#define M4U_PORT_CAM_CCUO MTK_M4U_ID(M4U_LARB9_ID, 22) +#define M4U_PORT_CAM_FAKE MTK_M4U_ID(M4U_LARB9_ID, 23) + +/* larb10-CAM_A */ +#define M4U_PORT_CAM_IMGO_R1_A MTK_M4U_ID(M4U_LARB10_ID, 0) +#define M4U_PORT_CAM_RRZO_R1_A MTK_M4U_ID(M4U_LARB10_ID, 1) +#define M4U_PORT_CAM_LSCI_R1_A MTK_M4U_ID(M4U_LARB10_ID, 2) +#define M4U_PORT_CAM_BPCI_R1_A MTK_M4U_ID(M4U_LARB10_ID, 3) +#define M4U_PORT_CAM_YUVO_R1_A MTK_M4U_ID(M4U_LARB10_ID, 4) +#define M4U_PORT_CAM_UFDI_R2_A MTK_M4U_ID(M4U_LARB10_ID, 5) +#define M4U_PORT_CAM_RAWI_R2_A MTK_M4U_ID(M4U_LARB10_ID, 6) +#define M4U_PORT_CAM_RAWI_R5_A MTK_M4U_ID(M4U_LARB10_ID, 7) +#define M4U_PORT_CAM_IMGO_R1_B MTK_M4U_ID(M4U_LARB10_ID, 8) +#define M4U_PORT_CAM_RRZO_R1_B MTK_M4U_ID(M4U_LARB10_ID, 9) +#define M4U_PORT_CAM_LSCI_R1_B MTK_M4U_ID(M4U_LARB10_ID, 10) +#define M4U_PORT_CAM_BPCI_R1_B MTK_M4U_ID(M4U_LARB10_ID, 11) +#define M4U_PORT_CAM_YUVO_R1_B MTK_M4U_ID(M4U_LARB10_ID, 12) +#define M4U_PORT_CAM_UFDI_R2_B MTK_M4U_ID(M4U_LARB10_ID, 13) +#define M4U_PORT_CAM_RAWI_R2_B MTK_M4U_ID(M4U_LARB10_ID, 14) +#define M4U_PORT_CAM_RAWI_R5_B MTK_M4U_ID(M4U_LARB10_ID, 15) +#define M4U_PORT_CAM_CAMSV_0 MTK_M4U_ID(M4U_LARB10_ID, 16) +#define M4U_PORT_CAM_AAO_R1_A MTK_M4U_ID(M4U_LARB10_ID, 17) +#define M4U_PORT_CAM_AFO_R1_A MTK_M4U_ID(M4U_LARB10_ID, 18) +#define M4U_PORT_CAM_FLKO_R1_A MTK_M4U_ID(M4U_LARB10_ID, 19) +#define M4U_PORT_CAM_LCESO_R1_A MTK_M4U_ID(M4U_LARB10_ID, 20) +#define M4U_PORT_CAM_CRZO_R1_A MTK_M4U_ID(M4U_LARB10_ID, 21) +#define M4U_PORT_CAM_AAO_R1_B MTK_M4U_ID(M4U_LARB10_ID, 22) +#define M4U_PORT_CAM_AFO_R1_B MTK_M4U_ID(M4U_LARB10_ID, 23) +#define M4U_PORT_CAM_FLKO_R1_B MTK_M4U_ID(M4U_LARB10_ID, 24) +#define M4U_PORT_CAM_LCESO_R1_B MTK_M4U_ID(M4U_LARB10_ID, 25) +#define M4U_PORT_CAM_CRZO_R1_B MTK_M4U_ID(M4U_LARB10_ID, 26) +#define M4U_PORT_CAM_LTMSO_R1_A MTK_M4U_ID(M4U_LARB10_ID, 27) +#define M4U_PORT_CAM_RSSO_R1_A MTK_M4U_ID(M4U_LARB10_ID, 28) +#define M4U_PORT_CAM_LTMSO_R1_B MTK_M4U_ID(M4U_LARB10_ID, 29) +#define M4U_PORT_CAM_RSSO_R1_B MTK_M4U_ID(M4U_LARB10_ID, 30) + +/* larb11-CAM-VPU */ +#define M4U_PORT_CAM_IPUO MTK_M4U_ID(M4U_LARB11_ID, 0) +#define M4U_PORT_CAM_IPU2O MTK_M4U_ID(M4U_LARB11_ID, 1) +#define M4U_PORT_CAM_IPU3O MTK_M4U_ID(M4U_LARB11_ID, 2) +#define M4U_PORT_CAM_IPUI MTK_M4U_ID(M4U_LARB11_ID, 3) +#define M4U_PORT_CAM_IPU2I MTK_M4U_ID(M4U_LARB11_ID, 4) + +#endif From 75eed350877c4cdae2bd9e8410c66292143bd410 Mon Sep 17 00:00:00 2001 From: Chao Hao Date: Fri, 3 Jul 2020 12:41:19 +0800 Subject: [PATCH 070/291] iommu/mediatek: Rename the register STANDARD_AXI_MODE(0x48) to MISC_CTRL For iommu offset=0x48 register, only the previous mt8173/mt8183 use the name STANDARD_AXI_MODE, all the latest SoC extend the register more feature by different bits, for example: axi_mode, in_order_en, coherent_en and so on. So rename REG_MMU_MISC_CTRL may be more proper. This patch only rename the register name, no functional change. Signed-off-by: Chao Hao Reviewed-by: Yong Wu Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20200703044127.27438-3-chao.hao@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 14 +++++++------- drivers/iommu/mtk_iommu.h | 5 ++++- 2 files changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 2be96f1cdbd2..88d3df5b91c2 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -41,7 +41,7 @@ #define F_INVLD_EN0 BIT(0) #define F_INVLD_EN1 BIT(1) -#define REG_MMU_STANDARD_AXI_MODE 0x048 +#define REG_MMU_MISC_CTRL 0x048 #define REG_MMU_DCM_DIS 0x050 #define REG_MMU_CTRL_REG 0x110 @@ -573,8 +573,10 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) } writel_relaxed(0, data->base + REG_MMU_DCM_DIS); - if (data->plat_data->reset_axi) - writel_relaxed(0, data->base + REG_MMU_STANDARD_AXI_MODE); + if (data->plat_data->reset_axi) { + /* The register is called STANDARD_AXI_MODE in this case */ + writel_relaxed(0, data->base + REG_MMU_MISC_CTRL); + } if (devm_request_irq(data->dev, data->irq, mtk_iommu_isr, 0, dev_name(data->dev), (void *)data)) { @@ -718,8 +720,7 @@ static int __maybe_unused mtk_iommu_suspend(struct device *dev) struct mtk_iommu_suspend_reg *reg = &data->reg; void __iomem *base = data->base; - reg->standard_axi_mode = readl_relaxed(base + - REG_MMU_STANDARD_AXI_MODE); + reg->misc_ctrl = readl_relaxed(base + REG_MMU_MISC_CTRL); reg->dcm_dis = readl_relaxed(base + REG_MMU_DCM_DIS); reg->ctrl_reg = readl_relaxed(base + REG_MMU_CTRL_REG); reg->int_control0 = readl_relaxed(base + REG_MMU_INT_CONTROL0); @@ -743,8 +744,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev) dev_err(data->dev, "Failed to enable clk(%d) in resume\n", ret); return ret; } - writel_relaxed(reg->standard_axi_mode, - base + REG_MMU_STANDARD_AXI_MODE); + writel_relaxed(reg->misc_ctrl, base + REG_MMU_MISC_CTRL); writel_relaxed(reg->dcm_dis, base + REG_MMU_DCM_DIS); writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG); writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL0); diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index ea949a324e33..7212e6fcf982 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -18,7 +18,10 @@ #include struct mtk_iommu_suspend_reg { - u32 standard_axi_mode; + union { + u32 standard_axi_mode;/* v1 */ + u32 misc_ctrl;/* v2 */ + }; u32 dcm_dis; u32 ctrl_reg; u32 int_control0; From 6b717796227ec8d4303adcdc574165d06e499f0f Mon Sep 17 00:00:00 2001 From: Chao Hao Date: Fri, 3 Jul 2020 12:41:20 +0800 Subject: [PATCH 071/291] iommu/mediatek: Use a u32 flags to describe different HW features Given the fact that we are adding more and more plat_data bool values, it would make sense to use a u32 flags register and add the appropriate macro definitions to set and check for a flag present. No functional change. Suggested-by: Matthias Brugger Signed-off-by: Chao Hao Reviewed-by: Matthias Brugger Cc: Yong Wu Link: https://lore.kernel.org/r/20200703044127.27438-4-chao.hao@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 28 +++++++++++++++++----------- drivers/iommu/mtk_iommu.h | 7 +------ 2 files changed, 18 insertions(+), 17 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 88d3df5b91c2..40ca564d97af 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -100,6 +100,15 @@ #define MTK_M4U_TO_LARB(id) (((id) >> 5) & 0xf) #define MTK_M4U_TO_PORT(id) ((id) & 0x1f) +#define HAS_4GB_MODE BIT(0) +/* HW will use the EMI clock if there isn't the "bclk". */ +#define HAS_BCLK BIT(1) +#define HAS_VLD_PA_RNG BIT(2) +#define RESET_AXI BIT(3) + +#define MTK_IOMMU_HAS_FLAG(pdata, _x) \ + ((((pdata)->flags) & (_x)) == (_x)) + struct mtk_iommu_domain { struct io_pgtable_cfg cfg; struct io_pgtable_ops *iop; @@ -563,7 +572,8 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) upper_32_bits(data->protect_base); writel_relaxed(regval, data->base + REG_MMU_IVRP_PADDR); - if (data->enable_4GB && data->plat_data->has_vld_pa_rng) { + if (data->enable_4GB && + MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_VLD_PA_RNG)) { /* * If 4GB mode is enabled, the validate PA range is from * 0x1_0000_0000 to 0x1_ffff_ffff. here record bit[32:30]. @@ -573,7 +583,7 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) } writel_relaxed(0, data->base + REG_MMU_DCM_DIS); - if (data->plat_data->reset_axi) { + if (MTK_IOMMU_HAS_FLAG(data->plat_data, RESET_AXI)) { /* The register is called STANDARD_AXI_MODE in this case */ writel_relaxed(0, data->base + REG_MMU_MISC_CTRL); } @@ -618,7 +628,7 @@ static int mtk_iommu_probe(struct platform_device *pdev) /* Whether the current dram is over 4GB */ data->enable_4GB = !!(max_pfn > (BIT_ULL(32) >> PAGE_SHIFT)); - if (!data->plat_data->has_4gb_mode) + if (!MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE)) data->enable_4GB = false; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -631,7 +641,7 @@ static int mtk_iommu_probe(struct platform_device *pdev) if (data->irq < 0) return data->irq; - if (data->plat_data->has_bclk) { + if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_BCLK)) { data->bclk = devm_clk_get(dev, "bclk"); if (IS_ERR(data->bclk)) return PTR_ERR(data->bclk); @@ -763,23 +773,19 @@ static const struct dev_pm_ops mtk_iommu_pm_ops = { static const struct mtk_iommu_plat_data mt2712_data = { .m4u_plat = M4U_MT2712, - .has_4gb_mode = true, - .has_bclk = true, - .has_vld_pa_rng = true, + .flags = HAS_4GB_MODE | HAS_BCLK | HAS_VLD_PA_RNG, .larbid_remap = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9}, }; static const struct mtk_iommu_plat_data mt8173_data = { .m4u_plat = M4U_MT8173, - .has_4gb_mode = true, - .has_bclk = true, - .reset_axi = true, + .flags = HAS_4GB_MODE | HAS_BCLK | RESET_AXI, .larbid_remap = {0, 1, 2, 3, 4, 5}, /* Linear mapping. */ }; static const struct mtk_iommu_plat_data mt8183_data = { .m4u_plat = M4U_MT8183, - .reset_axi = true, + .flags = RESET_AXI, .larbid_remap = {0, 4, 5, 6, 7, 2, 3, 1}, }; diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index 7212e6fcf982..5225a9170aaa 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -39,12 +39,7 @@ enum mtk_iommu_plat { struct mtk_iommu_plat_data { enum mtk_iommu_plat m4u_plat; - bool has_4gb_mode; - - /* HW will use the EMI clock if there isn't the "bclk". */ - bool has_bclk; - bool has_vld_pa_rng; - bool reset_axi; + u32 flags; unsigned char larbid_remap[MTK_LARB_NR_MAX]; }; From 4bb2bf4c6ad36d5aef9fc7ecd01e89ae4f8d7ec7 Mon Sep 17 00:00:00 2001 From: Chao Hao Date: Fri, 3 Jul 2020 12:41:21 +0800 Subject: [PATCH 072/291] iommu/mediatek: Setting MISC_CTRL register Add F_MMU_IN_ORDER_WR_EN_MASK and F_MMU_STANDARD_AXI_MODE_EN_MASK definitions in MISC_CTRL register. F_MMU_STANDARD_AXI_MODE_EN_MASK: If we set F_MMU_STANDARD_AXI_MODE_EN_MASK (bit[3][19] = 0, not follow standard AXI protocol), the iommu will priorize sending of urgent read command over a normal read command. This improves the performance. F_MMU_IN_ORDER_WR_EN_MASK: If we set F_MMU_IN_ORDER_WR_EN_MASK (bit[1][17] = 0, out-of-order write), the iommu will re-order write commands and send the write commands with higher priority. Otherwise the sending of write commands will be done in order. The feature is controlled by OUT_ORDER_WR_EN platform data flag. Suggested-by: Yong Wu Signed-off-by: Chao Hao Reviewed-by: Matthias Brugger Cc: Matthias Brugger Link: https://lore.kernel.org/r/20200703044127.27438-5-chao.hao@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 40ca564d97af..219d7aa6f059 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -42,6 +42,9 @@ #define F_INVLD_EN1 BIT(1) #define REG_MMU_MISC_CTRL 0x048 +#define F_MMU_IN_ORDER_WR_EN_MASK (BIT(1) | BIT(17)) +#define F_MMU_STANDARD_AXI_MODE_MASK (BIT(3) | BIT(19)) + #define REG_MMU_DCM_DIS 0x050 #define REG_MMU_CTRL_REG 0x110 @@ -105,6 +108,7 @@ #define HAS_BCLK BIT(1) #define HAS_VLD_PA_RNG BIT(2) #define RESET_AXI BIT(3) +#define OUT_ORDER_WR_EN BIT(4) #define MTK_IOMMU_HAS_FLAG(pdata, _x) \ ((((pdata)->flags) & (_x)) == (_x)) @@ -585,8 +589,14 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) if (MTK_IOMMU_HAS_FLAG(data->plat_data, RESET_AXI)) { /* The register is called STANDARD_AXI_MODE in this case */ - writel_relaxed(0, data->base + REG_MMU_MISC_CTRL); + regval = 0; + } else { + regval = readl_relaxed(data->base + REG_MMU_MISC_CTRL); + regval &= ~F_MMU_STANDARD_AXI_MODE_MASK; + if (MTK_IOMMU_HAS_FLAG(data->plat_data, OUT_ORDER_WR_EN)) + regval &= ~F_MMU_IN_ORDER_WR_EN_MASK; } + writel_relaxed(regval, data->base + REG_MMU_MISC_CTRL); if (devm_request_irq(data->dev, data->irq, mtk_iommu_isr, 0, dev_name(data->dev), (void *)data)) { From b053bc7183c86dc52e68e9891d269992e79a5251 Mon Sep 17 00:00:00 2001 From: Chao Hao Date: Fri, 3 Jul 2020 12:41:22 +0800 Subject: [PATCH 073/291] iommu/mediatek: Move inv_sel_reg into the plat_data For mt6779, MMU_INV_SEL register's offset is changed from 0x38 to 0x2c, so we can put inv_sel_reg in the plat_data to use it. In addition, we renamed it to REG_MMU_INV_SEL_GEN1 and use it before mt6779. Signed-off-by: Chao Hao Reviewed-by: Matthias Brugger Cc: Yong Wu Link: https://lore.kernel.org/r/20200703044127.27438-6-chao.hao@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 9 ++++++--- drivers/iommu/mtk_iommu.h | 1 + 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 219d7aa6f059..533b8f76f592 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -37,7 +37,7 @@ #define REG_MMU_INVLD_START_A 0x024 #define REG_MMU_INVLD_END_A 0x028 -#define REG_MMU_INV_SEL 0x038 +#define REG_MMU_INV_SEL_GEN1 0x038 #define F_INVLD_EN0 BIT(0) #define F_INVLD_EN1 BIT(1) @@ -178,7 +178,7 @@ static void mtk_iommu_tlb_flush_all(void *cookie) for_each_m4u(data) { writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0, - data->base + REG_MMU_INV_SEL); + data->base + data->plat_data->inv_sel_reg); writel_relaxed(F_ALL_INVLD, data->base + REG_MMU_INVALIDATE); wmb(); /* Make sure the tlb flush all done */ } @@ -195,7 +195,7 @@ static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size, for_each_m4u(data) { spin_lock_irqsave(&data->tlb_lock, flags); writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0, - data->base + REG_MMU_INV_SEL); + data->base + data->plat_data->inv_sel_reg); writel_relaxed(iova, data->base + REG_MMU_INVLD_START_A); writel_relaxed(iova + size - 1, @@ -784,18 +784,21 @@ static const struct dev_pm_ops mtk_iommu_pm_ops = { static const struct mtk_iommu_plat_data mt2712_data = { .m4u_plat = M4U_MT2712, .flags = HAS_4GB_MODE | HAS_BCLK | HAS_VLD_PA_RNG, + .inv_sel_reg = REG_MMU_INV_SEL_GEN1, .larbid_remap = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9}, }; static const struct mtk_iommu_plat_data mt8173_data = { .m4u_plat = M4U_MT8173, .flags = HAS_4GB_MODE | HAS_BCLK | RESET_AXI, + .inv_sel_reg = REG_MMU_INV_SEL_GEN1, .larbid_remap = {0, 1, 2, 3, 4, 5}, /* Linear mapping. */ }; static const struct mtk_iommu_plat_data mt8183_data = { .m4u_plat = M4U_MT8183, .flags = RESET_AXI, + .inv_sel_reg = REG_MMU_INV_SEL_GEN1, .larbid_remap = {0, 4, 5, 6, 7, 2, 3, 1}, }; diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index 5225a9170aaa..cf53f5e80d22 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -40,6 +40,7 @@ enum mtk_iommu_plat { struct mtk_iommu_plat_data { enum mtk_iommu_plat m4u_plat; u32 flags; + u32 inv_sel_reg; unsigned char larbid_remap[MTK_LARB_NR_MAX]; }; From 37276e00da7d3a0d643d325aef81b7283fe23010 Mon Sep 17 00:00:00 2001 From: Chao Hao Date: Fri, 3 Jul 2020 12:41:23 +0800 Subject: [PATCH 074/291] iommu/mediatek: Add sub_comm id in translation fault The max larb number that a iommu HW support is 8(larb0~larb7 in the below diagram). If the larb's number is over 8, we use a sub_common for merging several larbs into one larb. At this case, we will extend larb_id: bit[11:9] means common-id; bit[8:7] means subcommon-id; >From these two variables, we could get the real larb number when translation fault happen. The diagram is as below: EMI | IOMMU | ----------------- | | common1 common0 | | ----------------- | smi common | ------------------------------------ | | | | | | 3'd0 3'd1 3'd2 3'd3 ... 3'd7 <-common_id(max is 8) | | | | | | Larb0 Larb1 | Larb3 ... Larb7 | smi sub common | -------------------------- | | | | 2'd0 2'd1 2'd2 2'd3 <-sub_common_id(max is 4) | | | | Larb8 Larb9 Larb10 Larb11 In this patch we extend larb_remap[] to larb_remap[8][4] for this. larb_remap[x][y]: x means common-id above, y means subcommon_id above. We can also distinguish if the M4U HW has sub_common by HAS_SUB_COMM macro. Signed-off-by: Chao Hao Reviewed-by: Yong Wu Reviewed-by: Matthias Brugger Cc: Matthias Brugger Link: https://lore.kernel.org/r/20200703044127.27438-7-chao.hao@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 21 ++++++++++++++------- drivers/iommu/mtk_iommu.h | 5 ++++- 2 files changed, 18 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 533b8f76f592..0d96dcd8612b 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -91,6 +91,8 @@ #define REG_MMU1_INVLD_PA 0x148 #define REG_MMU0_INT_ID 0x150 #define REG_MMU1_INT_ID 0x154 +#define F_MMU_INT_ID_COMM_ID(a) (((a) >> 9) & 0x7) +#define F_MMU_INT_ID_SUB_COMM_ID(a) (((a) >> 7) & 0x3) #define F_MMU_INT_ID_LARB_ID(a) (((a) >> 7) & 0x7) #define F_MMU_INT_ID_PORT_ID(a) (((a) >> 2) & 0x1f) @@ -109,6 +111,7 @@ #define HAS_VLD_PA_RNG BIT(2) #define RESET_AXI BIT(3) #define OUT_ORDER_WR_EN BIT(4) +#define HAS_SUB_COMM BIT(5) #define MTK_IOMMU_HAS_FLAG(pdata, _x) \ ((((pdata)->flags) & (_x)) == (_x)) @@ -239,7 +242,7 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id) struct mtk_iommu_data *data = dev_id; struct mtk_iommu_domain *dom = data->m4u_dom; u32 int_state, regval, fault_iova, fault_pa; - unsigned int fault_larb, fault_port; + unsigned int fault_larb, fault_port, sub_comm = 0; bool layer, write; /* Read error info from registers */ @@ -255,10 +258,14 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id) } layer = fault_iova & F_MMU_FAULT_VA_LAYER_BIT; write = fault_iova & F_MMU_FAULT_VA_WRITE_BIT; - fault_larb = F_MMU_INT_ID_LARB_ID(regval); fault_port = F_MMU_INT_ID_PORT_ID(regval); - - fault_larb = data->plat_data->larbid_remap[fault_larb]; + if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_SUB_COMM)) { + fault_larb = F_MMU_INT_ID_COMM_ID(regval); + sub_comm = F_MMU_INT_ID_SUB_COMM_ID(regval); + } else { + fault_larb = F_MMU_INT_ID_LARB_ID(regval); + } + fault_larb = data->plat_data->larbid_remap[fault_larb][sub_comm]; if (report_iommu_fault(&dom->domain, data->dev, fault_iova, write ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ)) { @@ -785,21 +792,21 @@ static const struct mtk_iommu_plat_data mt2712_data = { .m4u_plat = M4U_MT2712, .flags = HAS_4GB_MODE | HAS_BCLK | HAS_VLD_PA_RNG, .inv_sel_reg = REG_MMU_INV_SEL_GEN1, - .larbid_remap = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9}, + .larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}, {6}, {7}}, }; static const struct mtk_iommu_plat_data mt8173_data = { .m4u_plat = M4U_MT8173, .flags = HAS_4GB_MODE | HAS_BCLK | RESET_AXI, .inv_sel_reg = REG_MMU_INV_SEL_GEN1, - .larbid_remap = {0, 1, 2, 3, 4, 5}, /* Linear mapping. */ + .larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}}, /* Linear mapping. */ }; static const struct mtk_iommu_plat_data mt8183_data = { .m4u_plat = M4U_MT8183, .flags = RESET_AXI, .inv_sel_reg = REG_MMU_INV_SEL_GEN1, - .larbid_remap = {0, 4, 5, 6, 7, 2, 3, 1}, + .larbid_remap = {{0}, {4}, {5}, {6}, {7}, {2}, {3}, {1}}, }; static const struct of_device_id mtk_iommu_of_ids[] = { diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index cf53f5e80d22..46d0d47b22e1 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -17,6 +17,9 @@ #include #include +#define MTK_LARB_COM_MAX 8 +#define MTK_LARB_SUBCOM_MAX 4 + struct mtk_iommu_suspend_reg { union { u32 standard_axi_mode;/* v1 */ @@ -41,7 +44,7 @@ struct mtk_iommu_plat_data { enum mtk_iommu_plat m4u_plat; u32 flags; u32 inv_sel_reg; - unsigned char larbid_remap[MTK_LARB_NR_MAX]; + unsigned char larbid_remap[MTK_LARB_COM_MAX][MTK_LARB_SUBCOM_MAX]; }; struct mtk_iommu_domain; From 35c1b48d27dac486835435e703749236b14dcd8f Mon Sep 17 00:00:00 2001 From: Chao Hao Date: Fri, 3 Jul 2020 12:41:24 +0800 Subject: [PATCH 075/291] iommu/mediatek: Add REG_MMU_WR_LEN_CTRL register definition Some platforms(ex: mt6779) need to improve performance by setting REG_MMU_WR_LEN_CTRL register. And we can use WR_THROT_EN macro to control whether we need to set the register. If the register uses default value, iommu will send command to EMI without restriction, when the number of commands become more and more, it will drop the EMI performance. So when more than ten_commands(default value) don't be handled for EMI, iommu will stop send command to EMI for keeping EMI's performace by enabling write throttling mechanism(bit[5][21]=0) in MMU_WR_LEN_CTRL register. Signed-off-by: Chao Hao Reviewed-by: Matthias Brugger Cc: Matthias Brugger Link: https://lore.kernel.org/r/20200703044127.27438-8-chao.hao@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 11 +++++++++++ drivers/iommu/mtk_iommu.h | 1 + 2 files changed, 12 insertions(+) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 0d96dcd8612b..5c8e141668fc 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -46,6 +46,8 @@ #define F_MMU_STANDARD_AXI_MODE_MASK (BIT(3) | BIT(19)) #define REG_MMU_DCM_DIS 0x050 +#define REG_MMU_WR_LEN_CTRL 0x054 +#define F_MMU_WR_THROT_DIS_MASK (BIT(5) | BIT(21)) #define REG_MMU_CTRL_REG 0x110 #define F_MMU_TF_PROT_TO_PROGRAM_ADDR (2 << 4) @@ -112,6 +114,7 @@ #define RESET_AXI BIT(3) #define OUT_ORDER_WR_EN BIT(4) #define HAS_SUB_COMM BIT(5) +#define WR_THROT_EN BIT(6) #define MTK_IOMMU_HAS_FLAG(pdata, _x) \ ((((pdata)->flags) & (_x)) == (_x)) @@ -593,6 +596,12 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) writel_relaxed(regval, data->base + REG_MMU_VLD_PA_RNG); } writel_relaxed(0, data->base + REG_MMU_DCM_DIS); + if (MTK_IOMMU_HAS_FLAG(data->plat_data, WR_THROT_EN)) { + /* write command throttling mode */ + regval = readl_relaxed(data->base + REG_MMU_WR_LEN_CTRL); + regval &= ~F_MMU_WR_THROT_DIS_MASK; + writel_relaxed(regval, data->base + REG_MMU_WR_LEN_CTRL); + } if (MTK_IOMMU_HAS_FLAG(data->plat_data, RESET_AXI)) { /* The register is called STANDARD_AXI_MODE in this case */ @@ -747,6 +756,7 @@ static int __maybe_unused mtk_iommu_suspend(struct device *dev) struct mtk_iommu_suspend_reg *reg = &data->reg; void __iomem *base = data->base; + reg->wr_len_ctrl = readl_relaxed(base + REG_MMU_WR_LEN_CTRL); reg->misc_ctrl = readl_relaxed(base + REG_MMU_MISC_CTRL); reg->dcm_dis = readl_relaxed(base + REG_MMU_DCM_DIS); reg->ctrl_reg = readl_relaxed(base + REG_MMU_CTRL_REG); @@ -771,6 +781,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev) dev_err(data->dev, "Failed to enable clk(%d) in resume\n", ret); return ret; } + writel_relaxed(reg->wr_len_ctrl, base + REG_MMU_WR_LEN_CTRL); writel_relaxed(reg->misc_ctrl, base + REG_MMU_MISC_CTRL); writel_relaxed(reg->dcm_dis, base + REG_MMU_DCM_DIS); writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG); diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index 46d0d47b22e1..31edd05e2eb1 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -31,6 +31,7 @@ struct mtk_iommu_suspend_reg { u32 int_main_control; u32 ivrp_paddr; u32 vld_pa_rng; + u32 wr_len_ctrl; }; enum mtk_iommu_plat { From 829316b3bc897a3275a0354505fde3ccd0053936 Mon Sep 17 00:00:00 2001 From: Chao Hao Date: Fri, 3 Jul 2020 12:41:25 +0800 Subject: [PATCH 076/291] iommu/mediatek: Extend protect pa alignment value Starting with mt6779, iommu needs to extend to 256 bytes from 128 bytes which can send the max number of data for memory protection pa alignment. So we can use a separate patch to modify it. Signed-off-by: Chao Hao Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20200703044127.27438-9-chao.hao@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 5c8e141668fc..e71003037ffa 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -98,7 +98,7 @@ #define F_MMU_INT_ID_LARB_ID(a) (((a) >> 7) & 0x7) #define F_MMU_INT_ID_PORT_ID(a) (((a) >> 2) & 0x1f) -#define MTK_PROTECT_PA_ALIGN 128 +#define MTK_PROTECT_PA_ALIGN 256 /* * Get the local arbiter ID and the portid within the larb arbiter From 864444130eed304835b09c86a5bf2ff05bc2f4a2 Mon Sep 17 00:00:00 2001 From: Chao Hao Date: Fri, 3 Jul 2020 12:41:26 +0800 Subject: [PATCH 077/291] iommu/mediatek: Modify MMU_CTRL register setting The MMU_CTRL register of MT8173 is different from other SoCs. The in_order_wr_en is bit[9] which is zero by default. Other SoCs have the vitcim_tlb_en feature mapped to bit[12]. This bit is set to one by default. We need to preserve the bit when setting F_MMU_TF_PROT_TO_PROGRAM_ADDR as otherwise the bit will be cleared and IOMMU performance will drop. Signed-off-by: Chao Hao Reviewed-by: Matthias Brugger Cc: Matthias Brugger Cc: Yong Wu Link: https://lore.kernel.org/r/20200703044127.27438-10-chao.hao@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index e71003037ffa..a816030d00f1 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -555,11 +555,13 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) return ret; } - if (data->plat_data->m4u_plat == M4U_MT8173) + if (data->plat_data->m4u_plat == M4U_MT8173) { regval = F_MMU_PREFETCH_RT_REPLACE_MOD | F_MMU_TF_PROT_TO_PROGRAM_ADDR_MT8173; - else - regval = F_MMU_TF_PROT_TO_PROGRAM_ADDR; + } else { + regval = readl_relaxed(data->base + REG_MMU_CTRL_REG); + regval |= F_MMU_TF_PROT_TO_PROGRAM_ADDR; + } writel_relaxed(regval, data->base + REG_MMU_CTRL_REG); regval = F_L2_MULIT_HIT_EN | From 068c86e92f3fc9df7d95a39710b40be811d861aa Mon Sep 17 00:00:00 2001 From: Chao Hao Date: Fri, 3 Jul 2020 12:41:27 +0800 Subject: [PATCH 078/291] iommu/mediatek: Add mt6779 basic support 1. Start from mt6779, INVLDT_SEL move to offset=0x2c, so we add REG_MMU_INV_SEL_GEN2 definition and mt6779 uses it. 2. Add mt6779_data to support mm_iommu HW init. Signed-off-by: Chao Hao Reviewed-by: Matthias Brugger Cc: Yong Wu Link: https://lore.kernel.org/r/20200703044127.27438-11-chao.hao@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 9 +++++++++ drivers/iommu/mtk_iommu.h | 1 + 2 files changed, 10 insertions(+) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index a816030d00f1..59e5a62a34db 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -37,6 +37,7 @@ #define REG_MMU_INVLD_START_A 0x024 #define REG_MMU_INVLD_END_A 0x028 +#define REG_MMU_INV_SEL_GEN2 0x02c #define REG_MMU_INV_SEL_GEN1 0x038 #define F_INVLD_EN0 BIT(0) #define F_INVLD_EN1 BIT(1) @@ -808,6 +809,13 @@ static const struct mtk_iommu_plat_data mt2712_data = { .larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}, {6}, {7}}, }; +static const struct mtk_iommu_plat_data mt6779_data = { + .m4u_plat = M4U_MT6779, + .flags = HAS_SUB_COMM | OUT_ORDER_WR_EN | WR_THROT_EN, + .inv_sel_reg = REG_MMU_INV_SEL_GEN2, + .larbid_remap = {{0}, {1}, {2}, {3}, {5}, {7, 8}, {10}, {9}}, +}; + static const struct mtk_iommu_plat_data mt8173_data = { .m4u_plat = M4U_MT8173, .flags = HAS_4GB_MODE | HAS_BCLK | RESET_AXI, @@ -824,6 +832,7 @@ static const struct mtk_iommu_plat_data mt8183_data = { static const struct of_device_id mtk_iommu_of_ids[] = { { .compatible = "mediatek,mt2712-m4u", .data = &mt2712_data}, + { .compatible = "mediatek,mt6779-m4u", .data = &mt6779_data}, { .compatible = "mediatek,mt8173-m4u", .data = &mt8173_data}, { .compatible = "mediatek,mt8183-m4u", .data = &mt8183_data}, {} diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index 31edd05e2eb1..214898578026 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -37,6 +37,7 @@ struct mtk_iommu_suspend_reg { enum mtk_iommu_plat { M4U_MT2701, M4U_MT2712, + M4U_MT6779, M4U_MT8173, M4U_MT8183, }; From f512eefc9bf94e4f943c95833518bdbc80c93f0e Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Wed, 8 Jul 2020 23:04:34 +0200 Subject: [PATCH 079/291] iommu/omap: 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 Link: https://lore.kernel.org/r/20200708210434.22518-1-grandmaster@al2klimov.de Signed-off-by: Joerg Roedel --- drivers/iommu/omap-iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index c8282cc212cb..ec1c8cd0e419 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -3,7 +3,7 @@ * omap iommu: tlb and pagetable primitives * * Copyright (C) 2008-2010 Nokia Corporation - * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2013-2017 Texas Instruments Incorporated - https://www.ti.com/ * * Written by Hiroshi DOYU , * Paul Mundt and Toshihiro Kobayashi From 397e18b4bb2d27389361ceaf154a7acced648a72 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 13 Jul 2020 12:16:48 +0200 Subject: [PATCH 080/291] iommu/mediatek: Include liunx/dma-mapping.h This fixes a compile error when cross-compiling the driver on x86-32. Signed-off-by: Joerg Roedel Link: https://lore.kernel.org/r/20200713101648.32056-1-joro@8bytes.org --- drivers/iommu/mtk_iommu.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index 214898578026..6253e98d810c 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #define MTK_LARB_COM_MAX 8 From d724794b4534105e4169f8c9641235541bc7b74f Mon Sep 17 00:00:00 2001 From: Ming-Fan Chen Date: Wed, 8 Jan 2020 14:41:29 +0800 Subject: [PATCH 081/291] dt-bindings: mediatek: Add binding for MT6779 SMI This patch add description for MT6779 SMI. There are GALS in smi-larb but without clock of GALS alone. changelog since v2: Add GALS for mt6779 in smi-common.txt Signed-off-by: Ming-Fan Chen Acked-by: Rob Herring Link: https://lore.kernel.org/r/1578465691-30692-3-git-send-email-ming-fan.chen@mediatek.com Signed-off-by: Joerg Roedel --- .../bindings/memory-controllers/mediatek,smi-common.txt | 5 +++-- .../bindings/memory-controllers/mediatek,smi-larb.txt | 3 ++- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt b/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt index b478ade4da65..b64573680b42 100644 --- a/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt +++ b/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt @@ -5,7 +5,7 @@ The hardware block diagram please check bindings/iommu/mediatek,iommu.txt Mediatek SMI have two generations of HW architecture, here is the list which generation the SoCs use: generation 1: mt2701 and mt7623. -generation 2: mt2712, mt8173 and mt8183. +generation 2: mt2712, mt6779, mt8173 and mt8183. There's slight differences between the two SMI, for generation 2, the register which control the iommu port is at each larb's register base. But @@ -18,6 +18,7 @@ Required properties: - compatible : must be one of : "mediatek,mt2701-smi-common" "mediatek,mt2712-smi-common" + "mediatek,mt6779-smi-common" "mediatek,mt7623-smi-common", "mediatek,mt2701-smi-common" "mediatek,mt8173-smi-common" "mediatek,mt8183-smi-common" @@ -35,7 +36,7 @@ Required properties: and these 2 option clocks for generation 2 smi HW: - "gals0": the path0 clock of GALS(Global Async Local Sync). - "gals1": the path1 clock of GALS(Global Async Local Sync). - Here is the list which has this GALS: mt8183. + Here is the list which has this GALS: mt6779 and mt8183. Example: smi_common: smi@14022000 { diff --git a/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt b/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt index 4b369b3e1a69..8f19dfe7d80e 100644 --- a/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt +++ b/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt @@ -6,6 +6,7 @@ Required properties: - compatible : must be one of : "mediatek,mt2701-smi-larb" "mediatek,mt2712-smi-larb" + "mediatek,mt6779-smi-larb" "mediatek,mt7623-smi-larb", "mediatek,mt2701-smi-larb" "mediatek,mt8173-smi-larb" "mediatek,mt8183-smi-larb" @@ -21,7 +22,7 @@ Required properties: - "gals": the clock for GALS(Global Async Local Sync). Here is the list which has this GALS: mt8183. -Required property for mt2701, mt2712 and mt7623: +Required property for mt2701, mt2712, mt6779 and mt7623: - mediatek,larb-id :the hardware id of this larb. Example: From fc492f339f766591d6399d380edb89b2ab8bc89c Mon Sep 17 00:00:00 2001 From: Ming-Fan Chen Date: Wed, 8 Jan 2020 14:41:30 +0800 Subject: [PATCH 082/291] memory: mtk-smi: Add basic support for MT6779 Add smi-larb and smi-common nodes and config_port for MT6779. changelog since v2: Split basic nodes and config_port support from initial golden setting patch Signed-off-by: Ming-Fan Chen Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/1578465691-30692-4-git-send-email-ming-fan.chen@mediatek.com Signed-off-by: Joerg Roedel --- drivers/memory/mtk-smi.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/drivers/memory/mtk-smi.c b/drivers/memory/mtk-smi.c index a113e811faab..109c7e51d551 100644 --- a/drivers/memory/mtk-smi.c +++ b/drivers/memory/mtk-smi.c @@ -239,6 +239,13 @@ static const struct mtk_smi_larb_gen mtk_smi_larb_mt2712 = { .larb_direct_to_common_mask = BIT(8) | BIT(9), /* bdpsys */ }; +static const struct mtk_smi_larb_gen mtk_smi_larb_mt6779 = { + .config_port = mtk_smi_larb_config_port_gen2_general, + .larb_direct_to_common_mask = + BIT(4) | BIT(6) | BIT(11) | BIT(12) | BIT(13), + /* DUMMY | IPU0 | IPU1 | CCU | MDLA */ +}; + static const struct mtk_smi_larb_gen mtk_smi_larb_mt8183 = { .has_gals = true, .config_port = mtk_smi_larb_config_port_gen2_general, @@ -259,6 +266,10 @@ static const struct of_device_id mtk_smi_larb_of_ids[] = { .compatible = "mediatek,mt2712-smi-larb", .data = &mtk_smi_larb_mt2712 }, + { + .compatible = "mediatek,mt6779-smi-larb", + .data = &mtk_smi_larb_mt6779 + }, { .compatible = "mediatek,mt8183-smi-larb", .data = &mtk_smi_larb_mt8183 @@ -388,6 +399,13 @@ static const struct mtk_smi_common_plat mtk_smi_common_gen2 = { .gen = MTK_SMI_GEN2, }; +static const struct mtk_smi_common_plat mtk_smi_common_mt6779 = { + .gen = MTK_SMI_GEN2, + .has_gals = true, + .bus_sel = F_MMU1_LARB(1) | F_MMU1_LARB(2) | F_MMU1_LARB(4) | + F_MMU1_LARB(5) | F_MMU1_LARB(6) | F_MMU1_LARB(7), +}; + static const struct mtk_smi_common_plat mtk_smi_common_mt8183 = { .gen = MTK_SMI_GEN2, .has_gals = true, @@ -408,6 +426,10 @@ static const struct of_device_id mtk_smi_common_of_ids[] = { .compatible = "mediatek,mt2712-smi-common", .data = &mtk_smi_common_gen2, }, + { + .compatible = "mediatek,mt6779-smi-common", + .data = &mtk_smi_common_mt6779, + }, { .compatible = "mediatek,mt8183-smi-common", .data = &mtk_smi_common_mt8183, From 0cf17702d872128fc2bec79a9578b5cb00d54a11 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 13 Jul 2020 10:00:03 +0800 Subject: [PATCH 083/291] remoteproc: qcom: Add missing slab.h drivers/remoteproc/qcom_common.c: In function 'qcom_ssr_get_subsys': drivers/remoteproc/qcom_common.c:210:9: error: implicit declaration of function 'kzalloc'; did you mean 'vzalloc'? [-Werror=implicit-function-declaration] info = kzalloc(sizeof(*info), GFP_KERNEL); ^~~~~~~ vzalloc kzalloc() is declared in linux/slab.h, add include to fix build issue. Tested-by: Alex Elder Reported-by: Hulk Robot Signed-off-by: Kefeng Wang Link: https://lore.kernel.org/r/20200713020003.134039-1-wangkefeng.wang@huawei.com Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_common.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/remoteproc/qcom_common.c b/drivers/remoteproc/qcom_common.c index 2f45f0c79914..085fd73fa23a 100644 --- a/drivers/remoteproc/qcom_common.c +++ b/drivers/remoteproc/qcom_common.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include "remoteproc_internal.h" From a7541de9abed7cee7df0012214b1962e892885cc Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 22 Jun 2020 00:59:53 -0700 Subject: [PATCH 084/291] dt-bindings: hwlock: qcom: Migrate binding to YAML Migrate the Qualcomm TCSR mutex binding to YAML to allow validation. Reviewed-by: Vinod Koul Reviewed-by: Rob Herring Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200622075956.171058-2-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- .../bindings/hwlock/qcom-hwspinlock.txt | 39 -------------- .../bindings/hwlock/qcom-hwspinlock.yaml | 51 +++++++++++++++++++ 2 files changed, 51 insertions(+), 39 deletions(-) delete mode 100644 Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.txt create mode 100644 Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml diff --git a/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.txt b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.txt deleted file mode 100644 index 4563f524556b..000000000000 --- a/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.txt +++ /dev/null @@ -1,39 +0,0 @@ -Qualcomm Hardware Mutex Block: - -The hardware block provides mutexes utilized between different processors on -the SoC as part of the communication protocol used by these processors. - -- compatible: - Usage: required - Value type: - Definition: must be one of: - "qcom,sfpb-mutex", - "qcom,tcsr-mutex" - -- syscon: - Usage: required - Value type: - Definition: one cell containing: - syscon phandle - offset of the hwmutex block within the syscon - stride of the hwmutex registers - -- #hwlock-cells: - Usage: required - Value type: - Definition: must be 1, the specified cell represent the lock id - (hwlock standard property, see hwlock.txt) - -Example: - - tcsr_mutex_block: syscon@fd484000 { - compatible = "syscon"; - reg = <0xfd484000 0x2000>; - }; - - hwlock@fd484000 { - compatible = "qcom,tcsr-mutex"; - syscon = <&tcsr_mutex_block 0 0x80>; - - #hwlock-cells = <1>; - }; diff --git a/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml new file mode 100644 index 000000000000..71e63b52edd5 --- /dev/null +++ b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml @@ -0,0 +1,51 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/hwlock/qcom-hwspinlock.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Hardware Mutex Block + +maintainers: + - Bjorn Andersson + +description: + The hardware block provides mutexes utilized between different processors on + the SoC as part of the communication protocol used by these processors. + +properties: + compatible: + enum: + - qcom,sfpb-mutex + - qcom,tcsr-mutex + + '#hwlock-cells': + const: 1 + + syscon: + $ref: "/schemas/types.yaml#/definitions/phandle-array" + description: + Should be a triple of phandle referencing the TCSR mutex syscon, offset + of first mutex within the syscon and stride between each mutex. + +required: + - compatible + - '#hwlock-cells' + - syscon + +additionalProperties: false + +examples: + - | + tcsr_mutex_block: syscon@fd484000 { + compatible = "syscon"; + reg = <0xfd484000 0x2000>; + }; + + hwlock { + compatible = "qcom,tcsr-mutex"; + syscon = <&tcsr_mutex_block 0 0x80>; + + #hwlock-cells = <1>; + }; +... From d6a9f0c8f635a9177e39db6386575bd6cdd55931 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 22 Jun 2020 00:59:54 -0700 Subject: [PATCH 085/291] dt-bindings: hwlock: qcom: Allow device on mmio bus In modern Qualcomm platforms the mutex region of the TCSR is forked off into its own block, all with a offset of 0 and stride of 4096, and in some of these platforms no other registers in this region is accessed from Linux. Update the binding to allow the hardware block to be described directly on the mmio bus, in addition to allowing the existing syscon based definition for backwards compatibility. Reviewed-by: Vinod Koul Reviewed-by: Rob Herring Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200622075956.171058-3-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- .../bindings/hwlock/qcom-hwspinlock.yaml | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml index 71e63b52edd5..88f975837588 100644 --- a/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml +++ b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml @@ -19,6 +19,9 @@ properties: - qcom,sfpb-mutex - qcom,tcsr-mutex + reg: + maxItems: 1 + '#hwlock-cells': const: 1 @@ -31,7 +34,12 @@ properties: required: - compatible - '#hwlock-cells' - - syscon + +oneOf: + - required: + - reg + - required: + - syscon additionalProperties: false @@ -46,6 +54,12 @@ examples: compatible = "qcom,tcsr-mutex"; syscon = <&tcsr_mutex_block 0 0x80>; + #hwlock-cells = <1>; + }; + - | + tcsr_mutex: hwlock@1f40000 { + compatible = "qcom,tcsr-mutex"; + reg = <0x01f40000 0x40000>; #hwlock-cells = <1>; }; ... From 7a1e6fb1c606d414320b7498e7f8357d73c972e5 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 22 Jun 2020 00:59:55 -0700 Subject: [PATCH 086/291] hwspinlock: qcom: Allow mmio usage in addition to syscon In modern Qualcomm platforms the mutex region of the TCSR is forked off into its own block, all with a offset of 0 and stride of 4096, and in some of these platforms no other registers in this region is accessed from Linux. So add support for directly memory mapping this register space, to avoid the need to represent this block using a syscon. Reviewed-by: Baolin Wang Reviewed-by: Vinod Koul Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200622075956.171058-4-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- drivers/hwspinlock/qcom_hwspinlock.c | 80 ++++++++++++++++++++-------- 1 file changed, 59 insertions(+), 21 deletions(-) diff --git a/drivers/hwspinlock/qcom_hwspinlock.c b/drivers/hwspinlock/qcom_hwspinlock.c index f0da544b14d2..364710966665 100644 --- a/drivers/hwspinlock/qcom_hwspinlock.c +++ b/drivers/hwspinlock/qcom_hwspinlock.c @@ -70,41 +70,79 @@ static const struct of_device_id qcom_hwspinlock_of_match[] = { }; MODULE_DEVICE_TABLE(of, qcom_hwspinlock_of_match); +static struct regmap *qcom_hwspinlock_probe_syscon(struct platform_device *pdev, + u32 *base, u32 *stride) +{ + struct device_node *syscon; + struct regmap *regmap; + int ret; + + syscon = of_parse_phandle(pdev->dev.of_node, "syscon", 0); + if (!syscon) + return ERR_PTR(-ENODEV); + + regmap = syscon_node_to_regmap(syscon); + of_node_put(syscon); + if (IS_ERR(regmap)) + return regmap; + + ret = of_property_read_u32_index(pdev->dev.of_node, "syscon", 1, base); + if (ret < 0) { + dev_err(&pdev->dev, "no offset in syscon\n"); + return ERR_PTR(-EINVAL); + } + + ret = of_property_read_u32_index(pdev->dev.of_node, "syscon", 2, stride); + if (ret < 0) { + dev_err(&pdev->dev, "no stride syscon\n"); + return ERR_PTR(-EINVAL); + } + + return regmap; +} + +static const struct regmap_config tcsr_mutex_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x40000, + .fast_io = true, +}; + +static struct regmap *qcom_hwspinlock_probe_mmio(struct platform_device *pdev, + u32 *offset, u32 *stride) +{ + struct device *dev = &pdev->dev; + void __iomem *base; + + /* All modern platform has offset 0 and stride of 4k */ + *offset = 0; + *stride = 0x1000; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) + return ERR_CAST(base); + + return devm_regmap_init_mmio(dev, base, &tcsr_mutex_config); +} + static int qcom_hwspinlock_probe(struct platform_device *pdev) { struct hwspinlock_device *bank; - struct device_node *syscon; struct reg_field field; struct regmap *regmap; size_t array_size; u32 stride; u32 base; - int ret; int i; - syscon = of_parse_phandle(pdev->dev.of_node, "syscon", 0); - if (!syscon) { - dev_err(&pdev->dev, "no syscon property\n"); - return -ENODEV; - } + regmap = qcom_hwspinlock_probe_syscon(pdev, &base, &stride); + if (IS_ERR(regmap) && PTR_ERR(regmap) == -ENODEV) + regmap = qcom_hwspinlock_probe_mmio(pdev, &base, &stride); - regmap = syscon_node_to_regmap(syscon); - of_node_put(syscon); if (IS_ERR(regmap)) return PTR_ERR(regmap); - ret = of_property_read_u32_index(pdev->dev.of_node, "syscon", 1, &base); - if (ret < 0) { - dev_err(&pdev->dev, "no offset in syscon\n"); - return -EINVAL; - } - - ret = of_property_read_u32_index(pdev->dev.of_node, "syscon", 2, &stride); - if (ret < 0) { - dev_err(&pdev->dev, "no stride syscon\n"); - return -EINVAL; - } - array_size = QCOM_MUTEX_NUM_LOCKS * sizeof(struct hwspinlock); bank = devm_kzalloc(&pdev->dev, sizeof(*bank) + array_size, GFP_KERNEL); if (!bank) From 7e05c8de132308da0c2a5b17842b808d99a00ca8 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 15 Jul 2020 13:35:50 +0100 Subject: [PATCH 087/291] remoteproc: remoteproc_core: Use 'gnu_printf' format notation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes the following W=1 kernel build warning(s): drivers/remoteproc/remoteproc_core.c: In function ‘rproc_find_carveout_by_name’: drivers/remoteproc/remoteproc_core.c:257:2: warning: function ‘rproc_find_carveout_by_name’ might be a candidate for ‘gnu_printf’ format attribute [-Wsuggest-attribute=format] 257 | vsnprintf(_name, sizeof(_name), name, args); | ^~~~~~~~~ drivers/remoteproc/remoteproc_core.c: In function ‘rproc_mem_entry_init’: drivers/remoteproc/remoteproc_core.c:993:2: warning: function ‘rproc_mem_entry_init’ might be a candidate for ‘gnu_printf’ format attribute [-Wsuggest-attribute=format] 993 | vsnprintf(mem->name, sizeof(mem->name), name, args); | ^~~~~~~~~ drivers/remoteproc/remoteproc_core.c: In function ‘rproc_of_resm_mem_entry_init’: drivers/remoteproc/remoteproc_core.c:1029:2: warning: function ‘rproc_of_resm_mem_entry_init’ might be a candidate for ‘gnu_printf’ format attribute [-Wsuggest-attribute=format] 1029 | vsnprintf(mem->name, sizeof(mem->name), name, args); | ^~~~~~~~~ Cc: Brian Swetland Cc: Mark Grosen Cc: Guzman Lugo Cc: Suman Anna Cc: Robert Tivy Cc: De Leon Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20200715123551.4011154-1-lee.jones@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 0f95e025ba03..e00dff425c96 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -243,6 +243,7 @@ EXPORT_SYMBOL(rproc_da_to_va); * * Return: a valid pointer on carveout entry on success or NULL on failure. */ +__printf(2, 3) struct rproc_mem_entry * rproc_find_carveout_by_name(struct rproc *rproc, const char *name, ...) { @@ -966,6 +967,7 @@ EXPORT_SYMBOL(rproc_add_carveout); * This function allocates a rproc_mem_entry struct and fill it with parameters * provided by client. */ +__printf(8, 9) struct rproc_mem_entry * rproc_mem_entry_init(struct device *dev, void *va, dma_addr_t dma, size_t len, u32 da, @@ -1009,6 +1011,7 @@ EXPORT_SYMBOL(rproc_mem_entry_init); * This function allocates a rproc_mem_entry struct and fill it with parameters * provided by client. */ +__printf(5, 6) struct rproc_mem_entry * rproc_of_resm_mem_entry_init(struct device *dev, u32 of_resm_idx, size_t len, u32 da, const char *name, ...) From 5b435ca38b2ce785b60b4d3c230f0a21121d6728 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 15 Jul 2020 13:35:51 +0100 Subject: [PATCH 088/291] remoteproc: qcom_sysmon: Solve function header bitrot issues Looks as though 'name' has now been moved into 'struct sysmod_event' which is passed in instead. However, the parameter descriptions were not updated at the same time. Let's do that now. Fixes the following W=1 kernel build warning(s): drivers/remoteproc/qcom_sysmon.c:78: warning: Function parameter or member 'event' not described in 'sysmon_send_event' drivers/remoteproc/qcom_sysmon.c:78: warning: Excess function parameter 'name' description in 'sysmon_send_event' drivers/remoteproc/qcom_sysmon.c:350: warning: Function parameter or member 'event' not described in 'ssctl_send_event' drivers/remoteproc/qcom_sysmon.c:350: warning: Excess function parameter 'name' description in 'ssctl_send_event' Cc: Andy Gross Cc: linux-arm-msm@vger.kernel.org Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20200715123551.4011154-2-lee.jones@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_sysmon.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/remoteproc/qcom_sysmon.c b/drivers/remoteproc/qcom_sysmon.c index 8d8996d714f0..9eb2f6bccea6 100644 --- a/drivers/remoteproc/qcom_sysmon.c +++ b/drivers/remoteproc/qcom_sysmon.c @@ -71,7 +71,7 @@ static LIST_HEAD(sysmon_list); /** * sysmon_send_event() - send notification of other remote's SSR event * @sysmon: sysmon context - * @name: other remote's name + * @event: sysmon event context */ static void sysmon_send_event(struct qcom_sysmon *sysmon, const struct sysmon_event *event) @@ -343,7 +343,7 @@ static void ssctl_request_shutdown(struct qcom_sysmon *sysmon) /** * ssctl_send_event() - send notification of other remote's SSR event * @sysmon: sysmon context - * @name: other remote's name + * @event: sysmon event context */ static void ssctl_send_event(struct qcom_sysmon *sysmon, const struct sysmon_event *event) From 6a79a5a3842b6a9f639fe2874dd6ae0bd4b24d1a Mon Sep 17 00:00:00 2001 From: Tomasz Nowicki Date: Wed, 15 Jul 2020 09:06:46 +0200 Subject: [PATCH 089/291] iommu/arm-smmu: Call configuration impl hook before consuming features 'cfg_probe' hook is called at the very end of configuration probing procedure and therefore features override and workaround may become complex like for ID register fixups. In preparation for adding Marvell errata move 'cfg_probe' a bit earlier to have chance to adjust the detected features before we start consuming them. Since the Cavium quirk (the only user) does not alter features it is safe to do so. Suggested-by: Robin Murphy Signed-off-by: Tomasz Nowicki Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20200715070649.18733-2-tn@semihalf.com Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 243bc4cb2705..19f906de6420 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1728,7 +1728,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) unsigned int size; u32 id; bool cttw_reg, cttw_fw = smmu->features & ARM_SMMU_FEAT_COHERENT_WALK; - int i; + int i, ret; dev_notice(smmu->dev, "probing hardware configuration...\n"); dev_notice(smmu->dev, "SMMUv%d with:\n", @@ -1891,6 +1891,12 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K; } + if (smmu->impl && smmu->impl->cfg_probe) { + ret = smmu->impl->cfg_probe(smmu); + if (ret) + return ret; + } + /* Now we've corralled the various formats, what'll it do? */ if (smmu->features & ARM_SMMU_FEAT_FMT_AARCH32_S) smmu->pgsize_bitmap |= SZ_4K | SZ_64K | SZ_1M | SZ_16M; @@ -1918,9 +1924,6 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) dev_notice(smmu->dev, "\tStage-2: %lu-bit IPA -> %lu-bit PA\n", smmu->ipa_size, smmu->pa_size); - if (smmu->impl && smmu->impl->cfg_probe) - return smmu->impl->cfg_probe(smmu); - return 0; } From f2d9848aeb9fa71523bbfb226203ffb7d50877d2 Mon Sep 17 00:00:00 2001 From: Hanna Hawa Date: Wed, 15 Jul 2020 09:06:47 +0200 Subject: [PATCH 090/291] iommu/arm-smmu: Workaround for Marvell Armada-AP806 SoC erratum #582743 Due to erratum #582743, the Marvell Armada-AP806 can't access 64bit to ARM SMMUv2 registers. Provide implementation relevant hooks: - split the writeq/readq to two accesses of writel/readl. - mask the MMU_IDR2.PTFSv8 fields to not use AArch64 format (but only AARCH32_L) since with AArch64 format 32 bits access is not supported. Note that most 64-bit registers like TTBRn can be accessed as two 32-bit halves without issue, and AArch32 format ensures that the register writes which must be atomic (for TLBI etc.) need only be 32-bit. Signed-off-by: Hanna Hawa Signed-off-by: Gregory CLEMENT Signed-off-by: Tomasz Nowicki Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20200715070649.18733-3-tn@semihalf.com Signed-off-by: Will Deacon --- Documentation/arm64/silicon-errata.rst | 3 ++ drivers/iommu/arm-smmu-impl.c | 45 ++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 936cf2a59ca4..157214d3abe1 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -125,6 +125,9 @@ stable kernels. | Cavium | ThunderX2 Core | #219 | CAVIUM_TX2_ERRATUM_219 | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ +| Marvell | ARM-MMU-500 | #582743 | N/A | ++----------------+-----------------+-----------------+-----------------------------+ ++----------------+-----------------+-----------------+-----------------------------+ | Freescale/NXP | LS2080A/LS1043A | A-008585 | FSL_ERRATUM_A008585 | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c index 22a9acd76955..c87d825f651e 100644 --- a/drivers/iommu/arm-smmu-impl.c +++ b/drivers/iommu/arm-smmu-impl.c @@ -147,6 +147,48 @@ static const struct arm_smmu_impl arm_mmu500_impl = { .reset = arm_mmu500_reset, }; +static u64 mrvl_mmu500_readq(struct arm_smmu_device *smmu, int page, int off) +{ + /* + * Marvell Armada-AP806 erratum #582743. + * Split all the readq to double readl + */ + return hi_lo_readq_relaxed(arm_smmu_page(smmu, page) + off); +} + +static void mrvl_mmu500_writeq(struct arm_smmu_device *smmu, int page, int off, + u64 val) +{ + /* + * Marvell Armada-AP806 erratum #582743. + * Split all the writeq to double writel + */ + hi_lo_writeq_relaxed(val, arm_smmu_page(smmu, page) + off); +} + +static int mrvl_mmu500_cfg_probe(struct arm_smmu_device *smmu) +{ + + /* + * Armada-AP806 erratum #582743. + * Hide the SMMU_IDR2.PTFSv8 fields to sidestep the AArch64 + * formats altogether and allow using 32 bits access on the + * interconnect. + */ + smmu->features &= ~(ARM_SMMU_FEAT_FMT_AARCH64_4K | + ARM_SMMU_FEAT_FMT_AARCH64_16K | + ARM_SMMU_FEAT_FMT_AARCH64_64K); + + return 0; +} + +static const struct arm_smmu_impl mrvl_mmu500_impl = { + .read_reg64 = mrvl_mmu500_readq, + .write_reg64 = mrvl_mmu500_writeq, + .cfg_probe = mrvl_mmu500_cfg_probe, + .reset = arm_mmu500_reset, +}; + struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu) { @@ -177,5 +219,8 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu) of_device_is_compatible(np, "qcom,sm8250-smmu-500")) return qcom_smmu_impl_init(smmu); + if (of_device_is_compatible(np, "marvell,ap806-smmu-500")) + smmu->impl = &mrvl_mmu500_impl; + return smmu; } From e85e84d19b9dac3d3ac92c9f6a24d034691f1243 Mon Sep 17 00:00:00 2001 From: Tomasz Nowicki Date: Wed, 15 Jul 2020 09:06:48 +0200 Subject: [PATCH 091/291] dt-bindings: arm-smmu: add compatible string for Marvell Armada-AP806 SMMU-500 Add specific compatible string for Marvell usage due to errata of accessing 64bits registers of ARM SMMU, in AP806. AP806 SoC uses the generic ARM-MMU500, and there's no specific implementation of Marvell, this compatible is used for errata only. Signed-off-by: Hanna Hawa Signed-off-by: Gregory CLEMENT Signed-off-by: Tomasz Nowicki Reviewed-by: Rob Herring Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20200715070649.18733-4-tn@semihalf.com Signed-off-by: Will Deacon --- Documentation/devicetree/bindings/iommu/arm,smmu.yaml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index 3ac741236c8b..93fb9fe068b9 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -40,6 +40,10 @@ properties: - qcom,sm8150-smmu-500 - qcom,sm8250-smmu-500 - const: arm,mmu-500 + - description: Marvell SoCs implementing "arm,mmu-500" + items: + - const: marvell,ap806-smmu-500 + - const: arm,mmu-500 - items: - const: arm,mmu-500 - const: arm,smmu-v2 From 49fbb25030265c660de732513f18275d88ff99d3 Mon Sep 17 00:00:00 2001 From: John Garry Date: Tue, 23 Jun 2020 01:28:37 +0800 Subject: [PATCH 092/291] iommu/arm-smmu-v3: Fix trivial typo Set "cmq" -> "cmdq". Signed-off-by: John Garry Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index f578677a5c41..a8e814c652fe 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1479,7 +1479,7 @@ static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu, } /* - * Try to unlock the cmq lock. This will fail if we're the last + * Try to unlock the cmdq lock. This will fail if we're the last * reader, in which case we can safely update cmdq->q.llq.cons */ if (!arm_smmu_cmdq_shared_tryunlock(cmdq)) { From 90ec257c380ebdcebf332b698f3e809cd1157202 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 15 Jul 2020 22:48:17 -0700 Subject: [PATCH 093/291] remoteproc: qcom: pil-info: Fix shift overflow On platforms with 32-bit phys_addr_t the shift to get the upper word of the base address of the memory region is invalid. Cast the base to 64 bit to resolv this. Fixes: 549b67da660d ("remoteproc: qcom: Introduce helper to store pil info in IMEM") Tested-by: Nathan Chancellor # build Reported-by: Lee Jones Reported-by: Nathan Chancellor Link: https://lore.kernel.org/r/20200716054817.157608-1-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_pil_info.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/remoteproc/qcom_pil_info.c b/drivers/remoteproc/qcom_pil_info.c index 0536e3904669..5521c4437ffa 100644 --- a/drivers/remoteproc/qcom_pil_info.c +++ b/drivers/remoteproc/qcom_pil_info.c @@ -108,7 +108,7 @@ int qcom_pil_info_store(const char *image, phys_addr_t base, size_t size) found_existing: /* Use two writel() as base is only aligned to 4 bytes on odd entries */ writel(base, entry + PIL_RELOC_NAME_LEN); - writel(base >> 32, entry + PIL_RELOC_NAME_LEN + 4); + writel((u64)base >> 32, entry + PIL_RELOC_NAME_LEN + 4); writel(size, entry + PIL_RELOC_NAME_LEN + sizeof(__le64)); mutex_unlock(&pil_reloc_lock); From 4e6751a1cfab85b7a1c054cf3d55f12322e1ee3b Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Thu, 16 Jul 2020 17:35:14 +0530 Subject: [PATCH 094/291] remoteproc: qcom_q6v5_mss: Monitor MSS_STATUS for boot completion On secure devices there exists a race condition which could lock the MSS CONFIG AHB bus thus preventing access to BOOT_STATUS register during SSR. Switch to polling the MSS_STATUS register with an additional 10 us delay to reliably track boot completion. Signed-off-by: Sibi Sankar Link: https://lore.kernel.org/r/20200716120514.21588-1-sibis@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_q6v5_mss.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index dd37e462ed61..1fd270a900f4 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -112,8 +112,6 @@ #define QDSP6SS_SLEEP 0x3C #define QDSP6SS_BOOT_CORE_START 0x400 #define QDSP6SS_BOOT_CMD 0x404 -#define QDSP6SS_BOOT_STATUS 0x408 -#define BOOT_STATUS_TIMEOUT_US 200 #define BOOT_FSM_TIMEOUT 10000 struct reg_info { @@ -579,13 +577,15 @@ static int q6v5proc_reset(struct q6v5 *qproc) /* De-assert the Q6 stop core signal */ writel(1, qproc->reg_base + QDSP6SS_BOOT_CORE_START); + /* Wait for 10 us for any staggering logic to settle */ + usleep_range(10, 20); + /* Trigger the boot FSM to start the Q6 out-of-reset sequence */ writel(1, qproc->reg_base + QDSP6SS_BOOT_CMD); - /* Poll the QDSP6SS_BOOT_STATUS for FSM completion */ - ret = readl_poll_timeout(qproc->reg_base + QDSP6SS_BOOT_STATUS, - val, (val & BIT(0)) != 0, 1, - BOOT_STATUS_TIMEOUT_US); + /* Poll the MSS_STATUS for FSM completion */ + ret = readl_poll_timeout(qproc->rmb_base + RMB_MBA_MSS_STATUS, + val, (val & BIT(0)) != 0, 10, BOOT_FSM_TIMEOUT); if (ret) { dev_err(qproc->dev, "Boot FSM failed to complete.\n"); /* Reset the modem so that boot FSM is in reset state */ From e2e5c55eed8023ecfbf4c9b623ef7dec343d1845 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 13:50:27 -0600 Subject: [PATCH 095/291] remoteproc: Add new RPROC_DETACHED state Add a new RPROC_DETACHED state to take into account scenarios where the remoteproc core needs to attach to a remote processor that is booted by another entity. Signed-off-by: Mathieu Poirier Reviewed-by: Bjorn Andersson Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714195035.1426873-2-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_sysfs.c | 1 + include/linux/remoteproc.h | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/remoteproc_sysfs.c b/drivers/remoteproc/remoteproc_sysfs.c index 52b871327b55..264759713934 100644 --- a/drivers/remoteproc/remoteproc_sysfs.c +++ b/drivers/remoteproc/remoteproc_sysfs.c @@ -72,6 +72,7 @@ static const char * const rproc_state_string[] = { [RPROC_RUNNING] = "running", [RPROC_CRASHED] = "crashed", [RPROC_DELETED] = "deleted", + [RPROC_DETACHED] = "detached", [RPROC_LAST] = "invalid", }; diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index e7b7bab8b235..21182ad2d059 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -400,6 +400,8 @@ struct rproc_ops { * @RPROC_RUNNING: device is up and running * @RPROC_CRASHED: device has crashed; need to start recovery * @RPROC_DELETED: device is deleted + * @RPROC_DETACHED: device has been booted by another entity and waiting + * for the core to attach to it * @RPROC_LAST: just keep this one at the end * * Please note that the values of these states are used as indices @@ -414,7 +416,8 @@ enum rproc_state { RPROC_RUNNING = 2, RPROC_CRASHED = 3, RPROC_DELETED = 4, - RPROC_LAST = 5, + RPROC_DETACHED = 5, + RPROC_LAST = 6, }; /** From a6a4f2857524007848f7957af432cddb4d43b593 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 13:50:28 -0600 Subject: [PATCH 096/291] remoteproc: Add new attach() remoteproc operation Add an new attach() operation in order to properly deal with scenarios where the remoteproc core needs to attach to a remote processor that has been booted by another entity. Signed-off-by: Mathieu Poirier Reviewed-by: Bjorn Andersson Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714195035.1426873-3-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_internal.h | 8 ++++++++ include/linux/remoteproc.h | 2 ++ 2 files changed, 10 insertions(+) diff --git a/drivers/remoteproc/remoteproc_internal.h b/drivers/remoteproc/remoteproc_internal.h index 4ba7cb59d3e8..fc710866f8ce 100644 --- a/drivers/remoteproc/remoteproc_internal.h +++ b/drivers/remoteproc/remoteproc_internal.h @@ -79,6 +79,14 @@ static inline int rproc_unprepare_device(struct rproc *rproc) return 0; } +static inline int rproc_attach_device(struct rproc *rproc) +{ + if (rproc->ops->attach) + return rproc->ops->attach(rproc); + + return 0; +} + static inline int rproc_fw_sanity_check(struct rproc *rproc, const struct firmware *fw) { diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 21182ad2d059..bf6a310ba870 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -359,6 +359,7 @@ enum rsc_handling_status { * @unprepare: unprepare device after stop * @start: power on the device and boot it * @stop: power off the device + * @attach: attach to a device that his already powered up * @kick: kick a virtqueue (virtqueue id given as a parameter) * @da_to_va: optional platform hook to perform address translations * @parse_fw: parse firmware to extract information (e.g. resource table) @@ -379,6 +380,7 @@ struct rproc_ops { int (*unprepare)(struct rproc *rproc); int (*start)(struct rproc *rproc); int (*stop)(struct rproc *rproc); + int (*attach)(struct rproc *rproc); void (*kick)(struct rproc *rproc, int vqid); void * (*da_to_va)(struct rproc *rproc, u64 da, size_t len); int (*parse_fw)(struct rproc *rproc, const struct firmware *fw); From d848a4819d858973952de181314de6d05512fb98 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 13:50:29 -0600 Subject: [PATCH 097/291] remoteproc: Introducing function rproc_attach() Introducing function rproc_attach() to enact the same actions as rproc_start(), but without the steps related to the handling of a firmware image. That way we can properly deal with scenarios where the remoteproc core needs to attach with a remote processsor that has been booted by another entity. Signed-off-by: Mathieu Poirier Reviewed-by: Bjorn Andersson Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714195035.1426873-4-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 42 ++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index e00dff425c96..90842c535dc5 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1372,6 +1372,48 @@ static int rproc_start(struct rproc *rproc, const struct firmware *fw) return ret; } +static int __maybe_unused rproc_attach(struct rproc *rproc) +{ + struct device *dev = &rproc->dev; + int ret; + + ret = rproc_prepare_subdevices(rproc); + if (ret) { + dev_err(dev, "failed to prepare subdevices for %s: %d\n", + rproc->name, ret); + goto out; + } + + /* Attach to the remote processor */ + ret = rproc_attach_device(rproc); + if (ret) { + dev_err(dev, "can't attach to rproc %s: %d\n", + rproc->name, ret); + goto unprepare_subdevices; + } + + /* Start any subdevices for the remote processor */ + ret = rproc_start_subdevices(rproc); + if (ret) { + dev_err(dev, "failed to probe subdevices for %s: %d\n", + rproc->name, ret); + goto stop_rproc; + } + + rproc->state = RPROC_RUNNING; + + dev_info(dev, "remote processor %s is now attached\n", rproc->name); + + return 0; + +stop_rproc: + rproc->ops->stop(rproc); +unprepare_subdevices: + rproc_unprepare_subdevices(rproc); +out: + return ret; +} + /* * take a firmware and boot a remote processor with it. */ From fdf0e00ed646fc94ab27e7d46fac983b1533a761 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 13:50:30 -0600 Subject: [PATCH 098/291] remoteproc: Introducing function rproc_actuate() Introduce function rproc_actuate() that provides the same functionatlity as rproc_fw_boot(), but without the steps that involve interaction with the firmware image. That way we can deal with scenarios where the remoteproc core is attaching to a remote processor that has already been started by another entity. Signed-off-by: Mathieu Poirier Reviewed-by: Arnaud Pouliquen Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714195035.1426873-5-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 59 +++++++++++++++++++++++++++- 1 file changed, 58 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 90842c535dc5..a62c4a74094b 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1372,7 +1372,7 @@ static int rproc_start(struct rproc *rproc, const struct firmware *fw) return ret; } -static int __maybe_unused rproc_attach(struct rproc *rproc) +static int rproc_attach(struct rproc *rproc) { struct device *dev = &rproc->dev; int ret; @@ -1493,6 +1493,63 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) return ret; } +/* + * Attach to remote processor - similar to rproc_fw_boot() but without + * the steps that deal with the firmware image. + */ +static int __maybe_unused rproc_actuate(struct rproc *rproc) +{ + struct device *dev = &rproc->dev; + int ret; + + /* + * if enabling an IOMMU isn't relevant for this rproc, this is + * just a nop + */ + ret = rproc_enable_iommu(rproc); + if (ret) { + dev_err(dev, "can't enable iommu: %d\n", ret); + return ret; + } + + /* reset max_notifyid */ + rproc->max_notifyid = -1; + + /* reset handled vdev */ + rproc->nb_vdev = 0; + + /* + * Handle firmware resources required to attach to a remote processor. + * Because we are attaching rather than booting the remote processor, + * we expect the platform driver to properly set rproc->table_ptr. + */ + ret = rproc_handle_resources(rproc, rproc_loading_handlers); + if (ret) { + dev_err(dev, "Failed to process resources: %d\n", ret); + goto disable_iommu; + } + + /* Allocate carveout resources associated to rproc */ + ret = rproc_alloc_registered_carveouts(rproc); + if (ret) { + dev_err(dev, "Failed to allocate associated carveouts: %d\n", + ret); + goto clean_up_resources; + } + + ret = rproc_attach(rproc); + if (ret) + goto clean_up_resources; + + return 0; + +clean_up_resources: + rproc_resource_cleanup(rproc); +disable_iommu: + rproc_disable_iommu(rproc); + return ret; +} + /* * take a firmware and boot it up. * From 88d3a1360755b7dd88a737ef2cd966a54c932682 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 13:50:31 -0600 Subject: [PATCH 099/291] remoteproc: Introducing function rproc_validate() Add a new function to assert the general health of the remote processor before handing it to the remoteproc core. Signed-off-by: Mathieu Poirier Reviewed-by: Arnaud Pouliquen Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714195035.1426873-6-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 41 ++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index a62c4a74094b..7e6b17a23cf2 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -2043,6 +2043,43 @@ struct rproc *rproc_get_by_phandle(phandle phandle) #endif EXPORT_SYMBOL(rproc_get_by_phandle); +static int rproc_validate(struct rproc *rproc) +{ + switch (rproc->state) { + case RPROC_OFFLINE: + /* + * An offline processor without a start() + * function makes no sense. + */ + if (!rproc->ops->start) + return -EINVAL; + break; + case RPROC_DETACHED: + /* + * A remote processor in a detached state without an + * attach() function makes not sense. + */ + if (!rproc->ops->attach) + return -EINVAL; + /* + * When attaching to a remote processor the device memory + * is already available and as such there is no need to have a + * cached table. + */ + if (rproc->cached_table) + return -EINVAL; + break; + default: + /* + * When adding a remote processor, the state of the device + * can be offline or detached, nothing else. + */ + return -EINVAL; + } + + return 0; +} + /** * rproc_add() - register a remote processor * @rproc: the remote processor handle to register @@ -2072,6 +2109,10 @@ int rproc_add(struct rproc *rproc) if (ret < 0) return ret; + ret = rproc_validate(rproc); + if (ret < 0) + return ret; + dev_info(dev, "%s is available\n", rproc->name); /* create debugfs entries */ From 0f9dc562b721aa1c0190ffe9f32aa0fcd7b8f2e8 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 13:50:32 -0600 Subject: [PATCH 100/291] remoteproc: Refactor function rproc_boot() Refactor function rproc_boot() to properly deal with scenarios where the remoteproc core needs to attach with a remote processor that has already been booted by an external entity. Signed-off-by: Mathieu Poirier Reviewed-by: Bjorn Andersson Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714195035.1426873-7-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 30 +++++++++++++++++----------- 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 7e6b17a23cf2..1e9fc3112385 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1497,7 +1497,7 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) * Attach to remote processor - similar to rproc_fw_boot() but without * the steps that deal with the firmware image. */ -static int __maybe_unused rproc_actuate(struct rproc *rproc) +static int rproc_actuate(struct rproc *rproc) { struct device *dev = &rproc->dev; int ret; @@ -1908,25 +1908,31 @@ int rproc_boot(struct rproc *rproc) goto unlock_mutex; } - /* skip the boot process if rproc is already powered up */ + /* skip the boot or attach process if rproc is already powered up */ if (atomic_inc_return(&rproc->power) > 1) { ret = 0; goto unlock_mutex; } - dev_info(dev, "powering up %s\n", rproc->name); + if (rproc->state == RPROC_DETACHED) { + dev_info(dev, "attaching to %s\n", rproc->name); - /* load firmware */ - ret = request_firmware(&firmware_p, rproc->firmware, dev); - if (ret < 0) { - dev_err(dev, "request_firmware failed: %d\n", ret); - goto downref_rproc; + ret = rproc_actuate(rproc); + } else { + dev_info(dev, "powering up %s\n", rproc->name); + + /* load firmware */ + ret = request_firmware(&firmware_p, rproc->firmware, dev); + if (ret < 0) { + dev_err(dev, "request_firmware failed: %d\n", ret); + goto downref_rproc; + } + + ret = rproc_fw_boot(rproc, firmware_p); + + release_firmware(firmware_p); } - ret = rproc_fw_boot(rproc, firmware_p); - - release_firmware(firmware_p); - downref_rproc: if (ret) atomic_dec(&rproc->power); From e3d2193959824e2119996fe361f92b34750de2b0 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 13:50:33 -0600 Subject: [PATCH 101/291] remoteproc: Refactor function rproc_trigger_auto_boot() Refactor function rproc_trigger_auto_boot() to properly deal with scenarios where the remoteproc core needs to attach with a remote processor that has already been booted by an external entity. Signed-off-by: Mathieu Poirier Reviewed-by: Bjorn Andersson Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714195035.1426873-8-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 1e9fc3112385..1f73dc13ca93 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1571,6 +1571,15 @@ static int rproc_trigger_auto_boot(struct rproc *rproc) { int ret; + /* + * Since the remote processor is in a detached state, it has already + * been booted by another entity. As such there is no point in waiting + * for a firmware image to be loaded, we can simply initiate the process + * of attaching to it immediately. + */ + if (rproc->state == RPROC_DETACHED) + return rproc_boot(rproc); + /* * We're initiating an asynchronous firmware loading, so we can * be built-in kernel code, without hanging the boot process. From 4d3ebb3b99905e0e1c83b320764495f5fc3f93fe Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 13:50:34 -0600 Subject: [PATCH 102/291] remoteproc: Refactor function rproc_free_vring() When function rproc_free_vring() clears the virtio device section it does so on the cached resource table rather than the one installed in the remote processor memory. When a remote processor has been booted by another entity there is no need to use a cached table and as such, no need to clear the virtio device section in it. Signed-off-by: Mathieu Poirier Reviewed-by: Bjorn Andersson Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714195035.1426873-9-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 1f73dc13ca93..565778ccb39c 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -411,10 +411,22 @@ void rproc_free_vring(struct rproc_vring *rvring) idr_remove(&rproc->notifyids, rvring->notifyid); - /* reset resource entry info */ - rsc = (void *)rproc->table_ptr + rvring->rvdev->rsc_offset; - rsc->vring[idx].da = 0; - rsc->vring[idx].notifyid = -1; + /* + * At this point rproc_stop() has been called and the installed resource + * table in the remote processor memory may no longer be accessible. As + * such and as per rproc_stop(), rproc->table_ptr points to the cached + * resource table (rproc->cached_table). The cached resource table is + * only available when a remote processor has been booted by the + * remoteproc core, otherwise it is NULL. + * + * Based on the above, reset the virtio device section in the cached + * resource table only if there is one to work with. + */ + if (rproc->table_ptr) { + rsc = (void *)rproc->table_ptr + rvring->rvdev->rsc_offset; + rsc->vring[idx].da = 0; + rsc->vring[idx].notifyid = -1; + } } static int rproc_vdev_do_start(struct rproc_subdev *subdev) From 4a4dca1941fedc1b02635ff0b4ed51b9857d0382 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 13:50:35 -0600 Subject: [PATCH 103/291] remoteproc: Properly handle firmware name when attaching This patch prevents the firmware image name from being displayed when the remoteproc core is attaching to a remote processor. This is needed needed since there is no guarantee about the nature of the firmware image that is loaded by the external entity. Signed-off-by: Mathieu Poirier Reviewed-by: Arnaud Pouliquen Reviewed-by: Bjorn Andersson Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714195035.1426873-10-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 18 ++++++++++++++++++ drivers/remoteproc/remoteproc_sysfs.c | 14 +++++++++++++- include/linux/remoteproc.h | 2 ++ 3 files changed, 33 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 565778ccb39c..1b52004655ab 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1627,6 +1627,14 @@ static int rproc_stop(struct rproc *rproc, bool crashed) rproc->state = RPROC_OFFLINE; + /* + * The remote processor has been stopped and is now offline, which means + * that the next time it is brought back online the remoteproc core will + * be responsible to load its firmware. As such it is no longer + * autonomous. + */ + rproc->autonomous = false; + dev_info(dev, "stopped remote processor %s\n", rproc->name); return 0; @@ -2145,6 +2153,16 @@ int rproc_add(struct rproc *rproc) /* create debugfs entries */ rproc_create_debug_dir(rproc); + /* + * Remind ourselves the remote processor has been attached to rather + * than booted by the remoteproc core. This is important because the + * RPROC_DETACHED state will be lost as soon as the remote processor + * has been attached to. Used in firmware_show() and reset in + * rproc_stop(). + */ + if (rproc->state == RPROC_DETACHED) + rproc->autonomous = true; + /* if rproc is marked always-on, request it to boot */ if (rproc->auto_boot) { ret = rproc_trigger_auto_boot(rproc); diff --git a/drivers/remoteproc/remoteproc_sysfs.c b/drivers/remoteproc/remoteproc_sysfs.c index 264759713934..eea514cec50e 100644 --- a/drivers/remoteproc/remoteproc_sysfs.c +++ b/drivers/remoteproc/remoteproc_sysfs.c @@ -15,8 +15,20 @@ static ssize_t firmware_show(struct device *dev, struct device_attribute *attr, char *buf) { struct rproc *rproc = to_rproc(dev); + const char *firmware = rproc->firmware; - return sprintf(buf, "%s\n", rproc->firmware); + /* + * If the remote processor has been started by an external + * entity we have no idea of what image it is running. As such + * simply display a generic string rather then rproc->firmware. + * + * Here we rely on the autonomous flag because a remote processor + * may have been attached to and currently in a running state. + */ + if (rproc->autonomous) + firmware = "unknown"; + + return sprintf(buf, "%s\n", firmware); } /* Change firmware name via sysfs */ diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index bf6a310ba870..cf5e31556780 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -491,6 +491,7 @@ struct rproc_dump_segment { * @table_sz: size of @cached_table * @has_iommu: flag to indicate if remote processor is behind an MMU * @auto_boot: flag to indicate if remote processor should be auto-started + * @autonomous: true if an external entity has booted the remote processor * @dump_segments: list of segments in the firmware * @nb_vdev: number of vdev currently handled by rproc */ @@ -524,6 +525,7 @@ struct rproc { size_t table_sz; bool has_iommu; bool auto_boot; + bool autonomous; struct list_head dump_segments; int nb_vdev; u8 elf_class; From 7b9f18ca933ae35b90add6fe1787056bbc789a8a Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 14:04:35 -0600 Subject: [PATCH 104/291] remoteproc: stm32: Decouple rproc from memory translation Remove the remote processor from the process of parsing the memory ranges since there is no correlation between them. Acked-by: Arnaud Pouliquen Signed-off-by: Mathieu Poirier Reviewed-by: Loic Pallardy Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200714200445.1427257-2-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/stm32_rproc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index 062797a447c6..2973ba201c1d 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -128,10 +128,10 @@ static int stm32_rproc_mem_release(struct rproc *rproc, return 0; } -static int stm32_rproc_of_memory_translations(struct rproc *rproc) +static int stm32_rproc_of_memory_translations(struct platform_device *pdev, + struct stm32_rproc *ddata) { - struct device *parent, *dev = rproc->dev.parent; - struct stm32_rproc *ddata = rproc->priv; + struct device *parent, *dev = &pdev->dev; struct device_node *np; struct stm32_rproc_mem *p_mems; struct stm32_rproc_mem_ranges *mem_range; @@ -607,7 +607,7 @@ static int stm32_rproc_parse_dt(struct platform_device *pdev) rproc->auto_boot = of_property_read_bool(np, "st,auto-boot"); - return stm32_rproc_of_memory_translations(rproc); + return stm32_rproc_of_memory_translations(pdev, ddata); } static int stm32_rproc_probe(struct platform_device *pdev) From b8631ab137c78f58afacd7e7f822cd3fc296f589 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 14:04:36 -0600 Subject: [PATCH 105/291] remoteproc: stm32: Request IRQ with platform device Request IRQ with platform device rather than remote proc in order to call stm32_rproc_parse_dt() before rproc_alloc(). That way we can know whether we need to synchronise with the MCU or not. Acked-by: Arnaud Pouliquen Signed-off-by: Mathieu Poirier Reviewed-by: Loic Pallardy Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200714200445.1427257-3-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/stm32_rproc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index 2973ba201c1d..c00f60d42ab6 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -262,7 +262,8 @@ static int stm32_rproc_parse_fw(struct rproc *rproc, const struct firmware *fw) static irqreturn_t stm32_rproc_wdg(int irq, void *data) { - struct rproc *rproc = data; + struct platform_device *pdev = data; + struct rproc *rproc = platform_get_drvdata(pdev); rproc_report_crash(rproc, RPROC_WATCHDOG); @@ -554,7 +555,7 @@ static int stm32_rproc_parse_dt(struct platform_device *pdev) if (irq > 0) { err = devm_request_irq(dev, irq, stm32_rproc_wdg, 0, - dev_name(dev), rproc); + dev_name(dev), pdev); if (err) { dev_err(dev, "failed to request wdg irq\n"); return err; From 8210fc873d2f1a550ad41093d21a7c18217f75fb Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 14:04:37 -0600 Subject: [PATCH 106/291] remoteproc: stm32: Decouple rproc from DT parsing Remove the remote processor from the process of parsing the device tree since (1) there is no correlation between them and (2) to use the information that was gathered to make a decision on whether to synchronise with the M4 or not. Acked-by: Arnaud Pouliquen Signed-off-by: Mathieu Poirier Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200714200445.1427257-4-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/stm32_rproc.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index c00f60d42ab6..cbba995a80a2 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -539,12 +539,11 @@ static int stm32_rproc_get_syscon(struct device_node *np, const char *prop, return err; } -static int stm32_rproc_parse_dt(struct platform_device *pdev) +static int stm32_rproc_parse_dt(struct platform_device *pdev, + struct stm32_rproc *ddata, bool *auto_boot) { struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; - struct rproc *rproc = platform_get_drvdata(pdev); - struct stm32_rproc *ddata = rproc->priv; struct stm32_syscon tz; unsigned int tzen; int err, irq; @@ -590,7 +589,7 @@ static int stm32_rproc_parse_dt(struct platform_device *pdev) err = regmap_read(tz.map, tz.reg, &tzen); if (err) { - dev_err(&rproc->dev, "failed to read tzen\n"); + dev_err(dev, "failed to read tzen\n"); return err; } ddata->secured_soc = tzen & tz.mask; @@ -606,7 +605,7 @@ static int stm32_rproc_parse_dt(struct platform_device *pdev) if (err) dev_info(dev, "failed to get pdds\n"); - rproc->auto_boot = of_property_read_bool(np, "st,auto-boot"); + *auto_boot = of_property_read_bool(np, "st,auto-boot"); return stm32_rproc_of_memory_translations(pdev, ddata); } @@ -627,9 +626,15 @@ static int stm32_rproc_probe(struct platform_device *pdev) if (!rproc) return -ENOMEM; - rproc_coredump_set_elf_info(rproc, ELFCLASS32, EM_NONE); - rproc->has_iommu = false; ddata = rproc->priv; + + rproc_coredump_set_elf_info(rproc, ELFCLASS32, EM_NONE); + + ret = stm32_rproc_parse_dt(pdev, ddata, &rproc->auto_boot); + if (ret) + goto free_rproc; + + rproc->has_iommu = false; ddata->workqueue = create_workqueue(dev_name(dev)); if (!ddata->workqueue) { dev_err(dev, "cannot create workqueue\n"); @@ -639,13 +644,9 @@ static int stm32_rproc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rproc); - ret = stm32_rproc_parse_dt(pdev); - if (ret) - goto free_wkq; - ret = stm32_rproc_request_mbox(rproc); if (ret) - goto free_rproc; + goto free_wkq; ret = rproc_add(rproc); if (ret) From 95e32f868aa67cb0d581ca8ced456dc2fac5edf7 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 14:04:38 -0600 Subject: [PATCH 107/291] remoteproc: stm32: Remove memory translation from DT parsing Other than one has to be done after the other, there is no correlation between memory translation and DT parsing. As such move function stm32_rproc_of_memory_translations() to stm32_rproc_probe() so that stm32_rproc_parse_dt() can be extended to look for attach bindings in a clean way. Acked-by: Arnaud Pouliquen Signed-off-by: Mathieu Poirier Reviewed-by: Loic Pallardy Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200714200445.1427257-5-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/stm32_rproc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index cbba995a80a2..986f34a336a7 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -607,7 +607,7 @@ static int stm32_rproc_parse_dt(struct platform_device *pdev, *auto_boot = of_property_read_bool(np, "st,auto-boot"); - return stm32_rproc_of_memory_translations(pdev, ddata); + return 0; } static int stm32_rproc_probe(struct platform_device *pdev) @@ -634,6 +634,10 @@ static int stm32_rproc_probe(struct platform_device *pdev) if (ret) goto free_rproc; + ret = stm32_rproc_of_memory_translations(pdev, ddata); + if (ret) + goto free_rproc; + rproc->has_iommu = false; ddata->workqueue = create_workqueue(dev_name(dev)); if (!ddata->workqueue) { From 9276536f455b38b965ea16958a01f77bfae385f3 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 14:04:39 -0600 Subject: [PATCH 108/291] remoteproc: stm32: Parse syscon that will manage M4 synchronisation Get from the DT the syncon to probe the state of the remote processor and the location of the resource table. Mainly based on the work published by Arnaud Pouliquen [1]. [1]. https://patchwork.kernel.org/project/linux-remoteproc/list/?series=239877 Acked-by: Arnaud Pouliquen Signed-off-by: Mathieu Poirier Reviewed-by: Loic Pallardy Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200714200445.1427257-6-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/stm32_rproc.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index 986f34a336a7..961a53f67ec5 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -71,6 +71,8 @@ struct stm32_rproc { struct reset_control *rst; struct stm32_syscon hold_boot; struct stm32_syscon pdds; + struct stm32_syscon m4_state; + struct stm32_syscon rsctbl; int wdg_irq; u32 nb_rmems; struct stm32_rproc_mem *rmems; @@ -607,6 +609,30 @@ static int stm32_rproc_parse_dt(struct platform_device *pdev, *auto_boot = of_property_read_bool(np, "st,auto-boot"); + /* + * See if we can check the M4 status, i.e if it was started + * from the boot loader or not. + */ + err = stm32_rproc_get_syscon(np, "st,syscfg-m4-state", + &ddata->m4_state); + if (err) { + /* remember this */ + ddata->m4_state.map = NULL; + /* no coprocessor state syscon (optional) */ + dev_warn(dev, "m4 state not supported\n"); + + /* no need to go further */ + return 0; + } + + /* See if we can get the resource table */ + err = stm32_rproc_get_syscon(np, "st,syscfg-rsc-tbl", + &ddata->rsctbl); + if (err) { + /* no rsc table syscon (optional) */ + dev_warn(dev, "rsc tbl syscon not supported\n"); + } + return 0; } From 376ffdc044568fcd9982a89d57eed67874566f85 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 14:04:40 -0600 Subject: [PATCH 109/291] remoteproc: stm32: Properly set co-processor state when attaching Introduce the required mechanic to set the state of the M4 in order to properly deal with scenarios where the co-processor has been started by another entity. Mainly based on the work published by Arnaud Pouliquen [1]. [1]. https://patchwork.kernel.org/project/linux-remoteproc/list/?series=239877 Acked-by: Arnaud Pouliquen Signed-off-by: Mathieu Poirier Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200714200445.1427257-7-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/stm32_rproc.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index 961a53f67ec5..f393f2503106 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -39,6 +39,13 @@ #define STM32_MBX_VQ1_ID 1 #define STM32_MBX_SHUTDOWN "shutdown" +#define M4_STATE_OFF 0 +#define M4_STATE_INI 1 +#define M4_STATE_CRUN 2 +#define M4_STATE_CSTOP 3 +#define M4_STATE_STANDBY 4 +#define M4_STATE_CRASH 5 + struct stm32_syscon { struct regmap *map; u32 reg; @@ -636,12 +643,29 @@ static int stm32_rproc_parse_dt(struct platform_device *pdev, return 0; } +static int stm32_rproc_get_m4_status(struct stm32_rproc *ddata, + unsigned int *state) +{ + /* See stm32_rproc_parse_dt() */ + if (!ddata->m4_state.map) { + /* + * We couldn't get the coprocessor's state, assume + * it is not running. + */ + state = M4_STATE_OFF; + return 0; + } + + return regmap_read(ddata->m4_state.map, ddata->m4_state.reg, state); +} + static int stm32_rproc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct stm32_rproc *ddata; struct device_node *np = dev->of_node; struct rproc *rproc; + unsigned int state; int ret; ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32)); @@ -664,6 +688,13 @@ static int stm32_rproc_probe(struct platform_device *pdev) if (ret) goto free_rproc; + ret = stm32_rproc_get_m4_status(ddata, &state); + if (ret) + goto free_rproc; + + if (state == M4_STATE_CRUN) + rproc->state = RPROC_DETACHED; + rproc->has_iommu = false; ddata->workqueue = create_workqueue(dev_name(dev)); if (!ddata->workqueue) { From d9473cbfb0c5cbb279dfdeaec780934729537d27 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 14:04:41 -0600 Subject: [PATCH 110/291] remoteproc: Make function rproc_resource_cleanup() public Make function rproc_resource_cleanup() public so that it can be used by platform drivers when allocating resources to be used by a detached remote processor. Acked-by: Arnaud Pouliquen Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200714200445.1427257-8-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 3 ++- include/linux/remoteproc.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 1b52004655ab..6fa9f75754b3 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1274,7 +1274,7 @@ static void rproc_coredump_cleanup(struct rproc *rproc) * This function will free all resources acquired for @rproc, and it * is called whenever @rproc either shuts down or fails to boot. */ -static void rproc_resource_cleanup(struct rproc *rproc) +void rproc_resource_cleanup(struct rproc *rproc) { struct rproc_mem_entry *entry, *tmp; struct rproc_debug_trace *trace, *ttmp; @@ -1318,6 +1318,7 @@ static void rproc_resource_cleanup(struct rproc *rproc) rproc_coredump_cleanup(rproc); } +EXPORT_SYMBOL(rproc_resource_cleanup); static int rproc_start(struct rproc *rproc, const struct firmware *fw) { diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index cf5e31556780..7c0567029f7c 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -610,6 +610,7 @@ void rproc_put(struct rproc *rproc); int rproc_add(struct rproc *rproc); int rproc_del(struct rproc *rproc); void rproc_free(struct rproc *rproc); +void rproc_resource_cleanup(struct rproc *rproc); struct rproc *devm_rproc_alloc(struct device *dev, const char *name, const struct rproc_ops *ops, From dadbdb9c304c51038465e0735585538a78e8578b Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 14:04:42 -0600 Subject: [PATCH 111/291] remoteproc: stm32: Parse memory regions when attaching to M4 Split function stm32_rproc_parse_fw() in two parts, the first one to parse the memory regions and the second one to load the resource table. That way parsing of the memory regions can be done without having do deal with the resource table when attaching to a remote processor. Mainly based on the work published by Arnaud Pouliquen [1]. [1]. https://patchwork.kernel.org/project/linux-remoteproc/list/?series=239877 Acked-by: Arnaud Pouliquen Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200714200445.1427257-9-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/stm32_rproc.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index f393f2503106..2a1cccd8d311 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -213,7 +213,7 @@ static int stm32_rproc_elf_load_rsc_table(struct rproc *rproc, return 0; } -static int stm32_rproc_parse_fw(struct rproc *rproc, const struct firmware *fw) +static int stm32_rproc_parse_memory_regions(struct rproc *rproc) { struct device *dev = rproc->dev.parent; struct device_node *np = dev->of_node; @@ -266,6 +266,16 @@ static int stm32_rproc_parse_fw(struct rproc *rproc, const struct firmware *fw) index++; } + return 0; +} + +static int stm32_rproc_parse_fw(struct rproc *rproc, const struct firmware *fw) +{ + int ret = stm32_rproc_parse_memory_regions(rproc); + + if (ret) + return ret; + return stm32_rproc_elf_load_rsc_table(rproc, fw); } @@ -692,15 +702,20 @@ static int stm32_rproc_probe(struct platform_device *pdev) if (ret) goto free_rproc; - if (state == M4_STATE_CRUN) + if (state == M4_STATE_CRUN) { rproc->state = RPROC_DETACHED; + ret = stm32_rproc_parse_memory_regions(rproc); + if (ret) + goto free_resources; + } + rproc->has_iommu = false; ddata->workqueue = create_workqueue(dev_name(dev)); if (!ddata->workqueue) { dev_err(dev, "cannot create workqueue\n"); ret = -ENOMEM; - goto free_rproc; + goto free_resources; } platform_set_drvdata(pdev, rproc); @@ -719,6 +734,8 @@ static int stm32_rproc_probe(struct platform_device *pdev) stm32_rproc_free_mbox(rproc); free_wkq: destroy_workqueue(ddata->workqueue); +free_resources: + rproc_resource_cleanup(rproc); free_rproc: if (device_may_wakeup(dev)) { dev_pm_clear_wake_irq(dev); From 11a7aaa72cc5539591bd34c637ab12e55cb79e1e Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 14:04:43 -0600 Subject: [PATCH 112/291] remoteproc: stm32: Properly handle the resource table when attaching Properly set the remote processor's resource table based on where it was loaded by the external entity when attaching to a remote processor. Mainly based on the work published by Arnaud Pouliquen [1]. [1]. https://patchwork.kernel.org/project/linux-remoteproc/list/?series=239877 Acked-by: Arnaud Pouliquen Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200714200445.1427257-10-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/stm32_rproc.c | 76 ++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index 2a1cccd8d311..882229f3b1c9 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -39,6 +39,8 @@ #define STM32_MBX_VQ1_ID 1 #define STM32_MBX_SHUTDOWN "shutdown" +#define RSC_TBL_SIZE 1024 + #define M4_STATE_OFF 0 #define M4_STATE_INI 1 #define M4_STATE_CRUN 2 @@ -86,6 +88,7 @@ struct stm32_rproc { struct stm32_mbox mb[MBOX_NB_MBX]; struct workqueue_struct *workqueue; bool secured_soc; + void __iomem *rsc_va; }; static int stm32_rproc_pa_to_da(struct rproc *rproc, phys_addr_t pa, u64 *da) @@ -669,6 +672,75 @@ static int stm32_rproc_get_m4_status(struct stm32_rproc *ddata, return regmap_read(ddata->m4_state.map, ddata->m4_state.reg, state); } +static int stm32_rproc_da_to_pa(struct platform_device *pdev, + struct stm32_rproc *ddata, + u64 da, phys_addr_t *pa) +{ + struct device *dev = &pdev->dev; + struct stm32_rproc_mem *p_mem; + unsigned int i; + + for (i = 0; i < ddata->nb_rmems; i++) { + p_mem = &ddata->rmems[i]; + + if (da < p_mem->dev_addr || + da >= p_mem->dev_addr + p_mem->size) + continue; + + *pa = da - p_mem->dev_addr + p_mem->bus_addr; + dev_dbg(dev, "da %llx to pa %#x\n", da, *pa); + + return 0; + } + + dev_err(dev, "can't translate da %llx\n", da); + + return -EINVAL; +} + +static int stm32_rproc_get_loaded_rsc_table(struct platform_device *pdev, + struct rproc *rproc, + struct stm32_rproc *ddata) +{ + struct device *dev = &pdev->dev; + phys_addr_t rsc_pa; + u32 rsc_da; + int err; + + err = regmap_read(ddata->rsctbl.map, ddata->rsctbl.reg, &rsc_da); + if (err) { + dev_err(dev, "failed to read rsc tbl addr\n"); + return err; + } + + if (!rsc_da) + /* no rsc table */ + return 0; + + err = stm32_rproc_da_to_pa(pdev, ddata, rsc_da, &rsc_pa); + if (err) + return err; + + ddata->rsc_va = devm_ioremap_wc(dev, rsc_pa, RSC_TBL_SIZE); + if (IS_ERR_OR_NULL(ddata->rsc_va)) { + dev_err(dev, "Unable to map memory region: %pa+%zx\n", + &rsc_pa, RSC_TBL_SIZE); + ddata->rsc_va = NULL; + return -ENOMEM; + } + + /* + * The resource table is already loaded in device memory, no need + * to work with a cached table. + */ + rproc->cached_table = NULL; + /* Assuming the resource table fits in 1kB is fair */ + rproc->table_sz = RSC_TBL_SIZE; + rproc->table_ptr = (struct resource_table *)ddata->rsc_va; + + return 0; +} + static int stm32_rproc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -708,6 +780,10 @@ static int stm32_rproc_probe(struct platform_device *pdev) ret = stm32_rproc_parse_memory_regions(rproc); if (ret) goto free_resources; + + ret = stm32_rproc_get_loaded_rsc_table(pdev, rproc, ddata); + if (ret) + goto free_resources; } rproc->has_iommu = false; From bee04d4672e0e8f6b82b62b092763b88a395da22 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 14:04:44 -0600 Subject: [PATCH 113/291] remoteproc: stm32: Introduce new attach() operation Introduce new attach function to be used when attaching to a remote processor. Mainly based on the work published by Arnaud Pouliquen [1]. [1]. https://patchwork.kernel.org/project/linux-remoteproc/list/?series=239877 Acked-by: Arnaud Pouliquen Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200714200445.1427257-11-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/stm32_rproc.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index 882229f3b1c9..7145cd49616e 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -460,6 +460,13 @@ static int stm32_rproc_start(struct rproc *rproc) return stm32_rproc_set_hold_boot(rproc, true); } +static int stm32_rproc_attach(struct rproc *rproc) +{ + stm32_rproc_add_coredump_trace(rproc); + + return stm32_rproc_set_hold_boot(rproc, true); +} + static int stm32_rproc_stop(struct rproc *rproc) { struct stm32_rproc *ddata = rproc->priv; @@ -525,6 +532,7 @@ static void stm32_rproc_kick(struct rproc *rproc, int vqid) static struct rproc_ops st_rproc_ops = { .start = stm32_rproc_start, .stop = stm32_rproc_stop, + .attach = stm32_rproc_attach, .kick = stm32_rproc_kick, .load = rproc_elf_load_segments, .parse_fw = stm32_rproc_parse_fw, From efd8626213f6897b416e573e87f4582810086b93 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 14:04:45 -0600 Subject: [PATCH 114/291] remoteproc: stm32: Update M4 state in stm32_rproc_stop() Update the co-processor state in function stm32_rproc_stop() so that it can be used in scenarios where the remoteproc core is attaching to the M4. Mainly based on the work published by Arnaud Pouliquen [1]. [1]. https://patchwork.kernel.org/project/linux-remoteproc/list/?series=239877 Acked-by: Arnaud Pouliquen Signed-off-by: Mathieu Poirier Reviewed-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714200445.1427257-12-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/stm32_rproc.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index 7145cd49616e..f4da42fc0eeb 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -504,6 +504,18 @@ static int stm32_rproc_stop(struct rproc *rproc) } } + /* update coprocessor state to OFF if available */ + if (ddata->m4_state.map) { + err = regmap_update_bits(ddata->m4_state.map, + ddata->m4_state.reg, + ddata->m4_state.mask, + M4_STATE_OFF); + if (err) { + dev_err(&rproc->dev, "failed to set copro state\n"); + return err; + } + } + return 0; } From cd8479cf0de9d1950b51032a216fbf630f8542a4 Mon Sep 17 00:00:00 2001 From: Krishna Reddy Date: Sat, 18 Jul 2020 12:34:53 -0700 Subject: [PATCH 115/291] iommu/arm-smmu: move TLB timeout and spin count macros Move TLB timeout and spin count macros to header file to allow using the same from vendor specific implementations. Signed-off-by: Krishna Reddy Reviewed-by: Jon Hunter Reviewed-by: Nicolin Chen Reviewed-by: Pritesh Raithatha Reviewed-by: Robin Murphy Reviewed-by: Thierry Reding Link: https://lore.kernel.org/r/20200718193457.30046-2-vdumpa@nvidia.com Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu.c | 3 --- drivers/iommu/arm-smmu.h | 2 ++ 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 19f906de6420..cdd15ead9bc4 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -52,9 +52,6 @@ */ #define QCOM_DUMMY_VAL -1 -#define TLB_LOOP_TIMEOUT 1000000 /* 1s! */ -#define TLB_SPIN_COUNT 10 - #define MSI_IOVA_BASE 0x8000000 #define MSI_IOVA_LENGTH 0x100000 diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h index d172c024be61..c7d0122a7c6c 100644 --- a/drivers/iommu/arm-smmu.h +++ b/drivers/iommu/arm-smmu.h @@ -236,6 +236,8 @@ enum arm_smmu_cbar_type { /* Maximum number of context banks per SMMU */ #define ARM_SMMU_MAX_CBS 128 +#define TLB_LOOP_TIMEOUT 1000000 /* 1s! */ +#define TLB_SPIN_COUNT 10 /* Shared driver definitions */ enum arm_smmu_arch_version { From 6c019f4e697ebed2225b20cc5d6276673834853d Mon Sep 17 00:00:00 2001 From: Krishna Reddy Date: Sat, 18 Jul 2020 12:34:54 -0700 Subject: [PATCH 116/291] iommu/arm-smmu: ioremap smmu mmio region before implementation init ioremap smmu mmio region before calling into implementation init. This is necessary to allow mapped address available during vendor specific implementation init. Signed-off-by: Krishna Reddy Reviewed-by: Jon Hunter Reviewed-by: Nicolin Chen Reviewed-by: Pritesh Raithatha Reviewed-by: Robin Murphy Reviewed-by: Thierry Reding Link: https://lore.kernel.org/r/20200718193457.30046-3-vdumpa@nvidia.com Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index cdd15ead9bc4..de520115d3df 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -2123,10 +2123,6 @@ static int arm_smmu_device_probe(struct platform_device *pdev) if (err) return err; - smmu = arm_smmu_impl_init(smmu); - if (IS_ERR(smmu)) - return PTR_ERR(smmu); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); ioaddr = res->start; smmu->base = devm_ioremap_resource(dev, res); @@ -2138,6 +2134,10 @@ static int arm_smmu_device_probe(struct platform_device *pdev) */ smmu->numpage = resource_size(res); + smmu = arm_smmu_impl_init(smmu); + if (IS_ERR(smmu)) + return PTR_ERR(smmu); + num_irqs = 0; while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, num_irqs))) { num_irqs++; From aab5a1c882760a5bc990b14e5c0c2ee4dab5f1ac Mon Sep 17 00:00:00 2001 From: Krishna Reddy Date: Sat, 18 Jul 2020 12:34:55 -0700 Subject: [PATCH 117/291] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage NVIDIA's Tegra194 SoC has three ARM MMU-500 instances. It uses two of the ARM MMU-500s together to interleave IOVA accesses across them and must be programmed identically. This implementation supports programming the two ARM MMU-500s that must be programmed identically. The third ARM MMU-500 instance is supported by standard arm-smmu.c driver itself. Signed-off-by: Krishna Reddy Reviewed-by: Jon Hunter Reviewed-by: Nicolin Chen Reviewed-by: Pritesh Raithatha Reviewed-by: Robin Murphy Reviewed-by: Thierry Reding Link: https://lore.kernel.org/r/20200718193457.30046-4-vdumpa@nvidia.com Signed-off-by: Will Deacon --- MAINTAINERS | 2 + drivers/iommu/Makefile | 2 +- drivers/iommu/arm-smmu-impl.c | 3 + drivers/iommu/arm-smmu-nvidia.c | 179 ++++++++++++++++++++++++++++++++ drivers/iommu/arm-smmu.c | 1 + drivers/iommu/arm-smmu.h | 1 + 6 files changed, 187 insertions(+), 1 deletion(-) create mode 100644 drivers/iommu/arm-smmu-nvidia.c diff --git a/MAINTAINERS b/MAINTAINERS index 496fd4eafb68..ee2c0ba13a0f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16810,8 +16810,10 @@ F: drivers/i2c/busses/i2c-tegra.c TEGRA IOMMU DRIVERS M: Thierry Reding +R: Krishna Reddy L: linux-tegra@vger.kernel.org S: Supported +F: drivers/iommu/arm-smmu-nvidia.c F: drivers/iommu/tegra* TEGRA KBC DRIVER diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 342190196dfb..2b8203db73ec 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -15,7 +15,7 @@ obj-$(CONFIG_AMD_IOMMU) += amd/iommu.o amd/init.o amd/quirks.o obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd/debugfs.o obj-$(CONFIG_AMD_IOMMU_V2) += amd/iommu_v2.o obj-$(CONFIG_ARM_SMMU) += arm_smmu.o -arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o +arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o arm-smmu-qcom.o obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o obj-$(CONFIG_DMAR_TABLE) += intel/dmar.o obj-$(CONFIG_INTEL_IOMMU) += intel/iommu.o intel/pasid.o diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c index c87d825f651e..f4ff124a1967 100644 --- a/drivers/iommu/arm-smmu-impl.c +++ b/drivers/iommu/arm-smmu-impl.c @@ -213,6 +213,9 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu) if (of_property_read_bool(np, "calxeda,smmu-secure-config-access")) smmu->impl = &calxeda_impl; + if (of_device_is_compatible(np, "nvidia,tegra194-smmu")) + return nvidia_smmu_impl_init(smmu); + if (of_device_is_compatible(np, "qcom,sdm845-smmu-500") || of_device_is_compatible(np, "qcom,sc7180-smmu-500") || of_device_is_compatible(np, "qcom,sm8150-smmu-500") || diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c new file mode 100644 index 000000000000..2f55e5793d34 --- /dev/null +++ b/drivers/iommu/arm-smmu-nvidia.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2019-2020 NVIDIA CORPORATION. All rights reserved. + +#include +#include +#include +#include +#include + +#include "arm-smmu.h" + +/* + * Tegra194 has three ARM MMU-500 Instances. + * Two of them are used together and must be programmed identically for + * interleaved IOVA accesses across them and translates accesses from + * non-isochronous HW devices. + * Third one is used for translating accesses from isochronous HW devices. + * This implementation supports programming of the two instances that must + * be programmed identically. + * The third instance usage is through standard arm-smmu driver itself and + * is out of scope of this implementation. + */ +#define NUM_SMMU_INSTANCES 2 + +struct nvidia_smmu { + struct arm_smmu_device smmu; + void __iomem *bases[NUM_SMMU_INSTANCES]; +}; + +static inline void __iomem *nvidia_smmu_page(struct arm_smmu_device *smmu, + unsigned int inst, int page) +{ + struct nvidia_smmu *nvidia_smmu; + + nvidia_smmu = container_of(smmu, struct nvidia_smmu, smmu); + return nvidia_smmu->bases[inst] + (page << smmu->pgshift); +} + +static u32 nvidia_smmu_read_reg(struct arm_smmu_device *smmu, + int page, int offset) +{ + void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset; + + return readl_relaxed(reg); +} + +static void nvidia_smmu_write_reg(struct arm_smmu_device *smmu, + int page, int offset, u32 val) +{ + unsigned int i; + + for (i = 0; i < NUM_SMMU_INSTANCES; i++) { + void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset; + + writel_relaxed(val, reg); + } +} + +static u64 nvidia_smmu_read_reg64(struct arm_smmu_device *smmu, + int page, int offset) +{ + void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset; + + return readq_relaxed(reg); +} + +static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu, + int page, int offset, u64 val) +{ + unsigned int i; + + for (i = 0; i < NUM_SMMU_INSTANCES; i++) { + void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset; + + writeq_relaxed(val, reg); + } +} + +static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page, + int sync, int status) +{ + unsigned int delay; + + arm_smmu_writel(smmu, page, sync, 0); + + for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) { + unsigned int spin_cnt; + + for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) { + u32 val = 0; + unsigned int i; + + for (i = 0; i < NUM_SMMU_INSTANCES; i++) { + void __iomem *reg; + + reg = nvidia_smmu_page(smmu, i, page) + status; + val |= readl_relaxed(reg); + } + + if (!(val & ARM_SMMU_sTLBGSTATUS_GSACTIVE)) + return; + + cpu_relax(); + } + + udelay(delay); + } + + dev_err_ratelimited(smmu->dev, + "TLB sync timed out -- SMMU may be deadlocked\n"); +} + +static int nvidia_smmu_reset(struct arm_smmu_device *smmu) +{ + unsigned int i; + + for (i = 0; i < NUM_SMMU_INSTANCES; i++) { + u32 val; + void __iomem *reg = nvidia_smmu_page(smmu, i, ARM_SMMU_GR0) + + ARM_SMMU_GR0_sGFSR; + + /* clear global FSR */ + val = readl_relaxed(reg); + writel_relaxed(val, reg); + } + + return 0; +} + +static const struct arm_smmu_impl nvidia_smmu_impl = { + .read_reg = nvidia_smmu_read_reg, + .write_reg = nvidia_smmu_write_reg, + .read_reg64 = nvidia_smmu_read_reg64, + .write_reg64 = nvidia_smmu_write_reg64, + .reset = nvidia_smmu_reset, + .tlb_sync = nvidia_smmu_tlb_sync, +}; + +struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu) +{ + struct resource *res; + struct device *dev = smmu->dev; + struct nvidia_smmu *nvidia_smmu; + struct platform_device *pdev = to_platform_device(dev); + + nvidia_smmu = devm_kzalloc(dev, sizeof(*nvidia_smmu), GFP_KERNEL); + if (!nvidia_smmu) + return ERR_PTR(-ENOMEM); + + /* + * Copy the data from struct arm_smmu_device *smmu allocated in + * arm-smmu.c. The smmu from struct nvidia_smmu replaces the smmu + * pointer used in arm-smmu.c once this function returns. + * This is necessary to derive nvidia_smmu from smmu pointer passed + * through arm_smmu_impl function calls subsequently. + */ + nvidia_smmu->smmu = *smmu; + /* Instance 0 is ioremapped by arm-smmu.c. */ + nvidia_smmu->bases[0] = smmu->base; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!res) + return ERR_PTR(-ENODEV); + + nvidia_smmu->bases[1] = devm_ioremap_resource(dev, res); + if (IS_ERR(nvidia_smmu->bases[1])) + return ERR_CAST(nvidia_smmu->bases[1]); + + nvidia_smmu->smmu.impl = &nvidia_smmu_impl; + + /* + * Free the struct arm_smmu_device *smmu allocated in arm-smmu.c. + * Once this function returns, arm-smmu.c would use arm_smmu_device + * allocated as part of struct nvidia_smmu. + */ + devm_kfree(dev, smmu); + + return &nvidia_smmu->smmu; +} diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index de520115d3df..35422a17f610 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1946,6 +1946,7 @@ static const struct of_device_id arm_smmu_of_match[] = { { .compatible = "arm,mmu-401", .data = &arm_mmu401 }, { .compatible = "arm,mmu-500", .data = &arm_mmu500 }, { .compatible = "cavium,smmu-v2", .data = &cavium_smmuv2 }, + { .compatible = "nvidia,smmu-500", .data = &arm_mmu500 }, { .compatible = "qcom,smmu-v2", .data = &qcom_smmuv2 }, { }, }; diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h index c7d0122a7c6c..fad63efa1a72 100644 --- a/drivers/iommu/arm-smmu.h +++ b/drivers/iommu/arm-smmu.h @@ -452,6 +452,7 @@ static inline void arm_smmu_writeq(struct arm_smmu_device *smmu, int page, arm_smmu_writeq((s), ARM_SMMU_CB((s), (n)), (o), (v)) struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu); +struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu); struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu); int arm_mmu500_reset(struct arm_smmu_device *smmu); From 3d2deb0cdb69e85d05760c6c72189d7653709ee1 Mon Sep 17 00:00:00 2001 From: Krishna Reddy Date: Sat, 18 Jul 2020 12:34:56 -0700 Subject: [PATCH 118/291] dt-bindings: arm-smmu: add binding for Tegra194 SMMU Add binding for NVIDIA's Tegra194 SoC SMMU. Signed-off-by: Krishna Reddy Reviewed-by: Jon Hunter Reviewed-by: Rob Herring Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20200718193457.30046-5-vdumpa@nvidia.com Signed-off-by: Will Deacon --- .../devicetree/bindings/iommu/arm,smmu.yaml | 25 ++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index 93fb9fe068b9..503160a7b9a0 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -44,6 +44,11 @@ properties: items: - const: marvell,ap806-smmu-500 - const: arm,mmu-500 + - description: NVIDIA SoCs that program two ARM MMU-500s identically + items: + - enum: + - nvidia,tegra194-smmu + - const: nvidia,smmu-500 - items: - const: arm,mmu-500 - const: arm,smmu-v2 @@ -61,7 +66,8 @@ properties: - cavium,smmu-v2 reg: - maxItems: 1 + minItems: 1 + maxItems: 2 '#global-interrupts': description: The number of global interrupts exposed by the device. @@ -144,6 +150,23 @@ required: additionalProperties: false +allOf: + - if: + properties: + compatible: + contains: + enum: + - nvidia,tegra194-smmu + then: + properties: + reg: + minItems: 2 + maxItems: 2 + else: + properties: + reg: + maxItems: 1 + examples: - |+ /* SMMU with stream matching or stream indexing */ From aa7ec73297df57a86308fee78d2bf86e22ea0bae Mon Sep 17 00:00:00 2001 From: Krishna Reddy Date: Sat, 18 Jul 2020 12:34:57 -0700 Subject: [PATCH 119/291] iommu/arm-smmu: Add global/context fault implementation hooks Add global/context fault hooks to allow vendor specific implementations override default fault interrupt handlers. Update NVIDIA implementation to override the default global/context fault interrupt handlers and handle interrupts across the two ARM MMU-500s that are programmed identically. Signed-off-by: Krishna Reddy Reviewed-by: Jon Hunter Reviewed-by: Nicolin Chen Reviewed-by: Pritesh Raithatha Reviewed-by: Robin Murphy Reviewed-by: Thierry Reding Link: https://lore.kernel.org/r/20200718193457.30046-6-vdumpa@nvidia.com Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-nvidia.c | 99 +++++++++++++++++++++++++++++++++ drivers/iommu/arm-smmu.c | 17 +++++- drivers/iommu/arm-smmu.h | 3 + 3 files changed, 117 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c index 2f55e5793d34..31368057e9be 100644 --- a/drivers/iommu/arm-smmu-nvidia.c +++ b/drivers/iommu/arm-smmu-nvidia.c @@ -127,6 +127,103 @@ static int nvidia_smmu_reset(struct arm_smmu_device *smmu) return 0; } +static irqreturn_t nvidia_smmu_global_fault_inst(int irq, + struct arm_smmu_device *smmu, + int inst) +{ + u32 gfsr, gfsynr0, gfsynr1, gfsynr2; + void __iomem *gr0_base = nvidia_smmu_page(smmu, inst, 0); + + gfsr = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSR); + if (!gfsr) + return IRQ_NONE; + + gfsynr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR0); + gfsynr1 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR1); + gfsynr2 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR2); + + dev_err_ratelimited(smmu->dev, + "Unexpected global fault, this could be serious\n"); + dev_err_ratelimited(smmu->dev, + "\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n", + gfsr, gfsynr0, gfsynr1, gfsynr2); + + writel_relaxed(gfsr, gr0_base + ARM_SMMU_GR0_sGFSR); + return IRQ_HANDLED; +} + +static irqreturn_t nvidia_smmu_global_fault(int irq, void *dev) +{ + unsigned int inst; + irqreturn_t ret = IRQ_NONE; + struct arm_smmu_device *smmu = dev; + + for (inst = 0; inst < NUM_SMMU_INSTANCES; inst++) { + irqreturn_t irq_ret; + + irq_ret = nvidia_smmu_global_fault_inst(irq, smmu, inst); + if (irq_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + + return ret; +} + +static irqreturn_t nvidia_smmu_context_fault_bank(int irq, + struct arm_smmu_device *smmu, + int idx, int inst) +{ + u32 fsr, fsynr, cbfrsynra; + unsigned long iova; + void __iomem *gr1_base = nvidia_smmu_page(smmu, inst, 1); + void __iomem *cb_base = nvidia_smmu_page(smmu, inst, smmu->numpage + idx); + + fsr = readl_relaxed(cb_base + ARM_SMMU_CB_FSR); + if (!(fsr & ARM_SMMU_FSR_FAULT)) + return IRQ_NONE; + + fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0); + iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR); + cbfrsynra = readl_relaxed(gr1_base + ARM_SMMU_GR1_CBFRSYNRA(idx)); + + dev_err_ratelimited(smmu->dev, + "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cbfrsynra=0x%x, cb=%d\n", + fsr, iova, fsynr, cbfrsynra, idx); + + writel_relaxed(fsr, cb_base + ARM_SMMU_CB_FSR); + return IRQ_HANDLED; +} + +static irqreturn_t nvidia_smmu_context_fault(int irq, void *dev) +{ + int idx; + unsigned int inst; + irqreturn_t ret = IRQ_NONE; + struct arm_smmu_device *smmu; + struct iommu_domain *domain = dev; + struct arm_smmu_domain *smmu_domain; + + smmu_domain = container_of(domain, struct arm_smmu_domain, domain); + smmu = smmu_domain->smmu; + + for (inst = 0; inst < NUM_SMMU_INSTANCES; inst++) { + irqreturn_t irq_ret; + + /* + * Interrupt line is shared between all contexts. + * Check for faults across all contexts. + */ + for (idx = 0; idx < smmu->num_context_banks; idx++) { + irq_ret = nvidia_smmu_context_fault_bank(irq, smmu, + idx, inst); + if (irq_ret == IRQ_HANDLED) + ret = IRQ_HANDLED; + } + } + + return ret; +} + static const struct arm_smmu_impl nvidia_smmu_impl = { .read_reg = nvidia_smmu_read_reg, .write_reg = nvidia_smmu_write_reg, @@ -134,6 +231,8 @@ static const struct arm_smmu_impl nvidia_smmu_impl = { .write_reg64 = nvidia_smmu_write_reg64, .reset = nvidia_smmu_reset, .tlb_sync = nvidia_smmu_tlb_sync, + .global_fault = nvidia_smmu_global_fault, + .context_fault = nvidia_smmu_context_fault, }; struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu) diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 35422a17f610..56b7103e1368 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -670,6 +670,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, enum io_pgtable_fmt fmt; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_cfg *cfg = &smmu_domain->cfg; + irqreturn_t (*context_fault)(int irq, void *dev); mutex_lock(&smmu_domain->init_mutex); if (smmu_domain->smmu) @@ -832,7 +833,13 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, * handler seeing a half-initialised domain state. */ irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx]; - ret = devm_request_irq(smmu->dev, irq, arm_smmu_context_fault, + + if (smmu->impl && smmu->impl->context_fault) + context_fault = smmu->impl->context_fault; + else + context_fault = arm_smmu_context_fault; + + ret = devm_request_irq(smmu->dev, irq, context_fault, IRQF_SHARED, "arm-smmu-context-fault", domain); if (ret < 0) { dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n", @@ -2108,6 +2115,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev) struct arm_smmu_device *smmu; struct device *dev = &pdev->dev; int num_irqs, i, err; + irqreturn_t (*global_fault)(int irq, void *dev); smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL); if (!smmu) { @@ -2194,9 +2202,14 @@ static int arm_smmu_device_probe(struct platform_device *pdev) smmu->num_context_irqs = smmu->num_context_banks; } + if (smmu->impl && smmu->impl->global_fault) + global_fault = smmu->impl->global_fault; + else + global_fault = arm_smmu_global_fault; + for (i = 0; i < smmu->num_global_irqs; ++i) { err = devm_request_irq(smmu->dev, smmu->irqs[i], - arm_smmu_global_fault, + global_fault, IRQF_SHARED, "arm-smmu global fault", smmu); diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h index fad63efa1a72..d890a4a968e8 100644 --- a/drivers/iommu/arm-smmu.h +++ b/drivers/iommu/arm-smmu.h @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -389,6 +390,8 @@ struct arm_smmu_impl { void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync, int status); int (*def_domain_type)(struct device *dev); + irqreturn_t (*global_fault)(int irq, void *dev); + irqreturn_t (*context_fault)(int irq, void *dev); }; static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n) From 698d4d35be34385f0b501dde5ea1071d483c9a22 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 15 Jul 2020 16:49:28 -0700 Subject: [PATCH 120/291] platform/chrome: cros_ec_typec: Unregister partner on error When port update is called during probe(), any error with setting the Type C muxes results in an errno being returned to probe(), which promptly returns that itself. Ensure that we unregister any registered partners when doing so, to prevent orphaned partners on the Type C connector class framework. Move the cros_typec_add_partner() and cros_typec_remove_partner() code together to higher up in the file, so that they are together, and we can call cros_typec_remove_partner() from cros_unregister_ports(). Fixes: 7e7def15fa4b ("platform/chrome: cros_ec_typec: Add USB mux control") Signed-off-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_typec.c | 83 +++++++++++++------------ 1 file changed, 42 insertions(+), 41 deletions(-) diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index 3eae01f4c9f7..3fcd27ec9ad8 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -141,6 +141,47 @@ static int cros_typec_get_switch_handles(struct cros_typec_port *port, return -ENODEV; } +static int cros_typec_add_partner(struct cros_typec_data *typec, int port_num, + bool pd_en) +{ + struct cros_typec_port *port = typec->ports[port_num]; + struct typec_partner_desc p_desc = { + .usb_pd = pd_en, + }; + int ret = 0; + + /* + * Fill an initial PD identity, which will then be updated with info + * from the EC. + */ + p_desc.identity = &port->p_identity; + + port->partner = typec_register_partner(port->port, &p_desc); + if (IS_ERR(port->partner)) { + ret = PTR_ERR(port->partner); + port->partner = NULL; + } + + return ret; +} + +static void cros_typec_remove_partner(struct cros_typec_data *typec, + int port_num) +{ + struct cros_typec_port *port = typec->ports[port_num]; + + port->state.alt = NULL; + port->state.mode = TYPEC_STATE_USB; + port->state.data = NULL; + + usb_role_switch_set_role(port->role_sw, USB_ROLE_NONE); + typec_switch_set(port->ori_sw, TYPEC_ORIENTATION_NONE); + typec_mux_set(port->mux, &port->state); + + typec_unregister_partner(port->partner); + port->partner = NULL; +} + static void cros_unregister_ports(struct cros_typec_data *typec) { int i; @@ -148,6 +189,7 @@ static void cros_unregister_ports(struct cros_typec_data *typec) for (i = 0; i < typec->num_ports; i++) { if (!typec->ports[i]) continue; + cros_typec_remove_partner(typec, i); usb_role_switch_put(typec->ports[i]->role_sw); typec_switch_put(typec->ports[i]->ori_sw); typec_mux_put(typec->ports[i]->mux); @@ -286,47 +328,6 @@ static int cros_typec_ec_command(struct cros_typec_data *typec, return ret; } -static int cros_typec_add_partner(struct cros_typec_data *typec, int port_num, - bool pd_en) -{ - struct cros_typec_port *port = typec->ports[port_num]; - struct typec_partner_desc p_desc = { - .usb_pd = pd_en, - }; - int ret = 0; - - /* - * Fill an initial PD identity, which will then be updated with info - * from the EC. - */ - p_desc.identity = &port->p_identity; - - port->partner = typec_register_partner(port->port, &p_desc); - if (IS_ERR(port->partner)) { - ret = PTR_ERR(port->partner); - port->partner = NULL; - } - - return ret; -} - -static void cros_typec_remove_partner(struct cros_typec_data *typec, - int port_num) -{ - struct cros_typec_port *port = typec->ports[port_num]; - - port->state.alt = NULL; - port->state.mode = TYPEC_STATE_USB; - port->state.data = NULL; - - usb_role_switch_set_role(port->role_sw, USB_ROLE_NONE); - typec_switch_set(port->ori_sw, TYPEC_ORIENTATION_NONE); - typec_mux_set(port->mux, &port->state); - - typec_unregister_partner(port->partner); - port->partner = NULL; -} - static void cros_typec_set_port_params_v0(struct cros_typec_data *typec, int port_num, struct ec_response_usb_pd_control *resp) { From 4edfe2248d21d661dbcd735e5d28a36cfa826e11 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:25 +0200 Subject: [PATCH 121/291] backlight: backlight: Refactor fb_notifier_callback() Increase readability of fb_notifier_callback() by removing a few indent levels. No functional change. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- drivers/video/backlight/backlight.c | 43 +++++++++++++++-------------- 1 file changed, 22 insertions(+), 21 deletions(-) diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c index 744ba58488e0..18501956dd87 100644 --- a/drivers/video/backlight/backlight.c +++ b/drivers/video/backlight/backlight.c @@ -58,28 +58,29 @@ static int fb_notifier_callback(struct notifier_block *self, bd = container_of(self, struct backlight_device, fb_notif); mutex_lock(&bd->ops_lock); - if (bd->ops) - if (!bd->ops->check_fb || - bd->ops->check_fb(bd, evdata->info)) { - fb_blank = *(int *)evdata->data; - if (fb_blank == FB_BLANK_UNBLANK && - !bd->fb_bl_on[node]) { - bd->fb_bl_on[node] = true; - if (!bd->use_count++) { - bd->props.state &= ~BL_CORE_FBBLANK; - bd->props.fb_blank = FB_BLANK_UNBLANK; - backlight_update_status(bd); - } - } else if (fb_blank != FB_BLANK_UNBLANK && - bd->fb_bl_on[node]) { - bd->fb_bl_on[node] = false; - if (!(--bd->use_count)) { - bd->props.state |= BL_CORE_FBBLANK; - bd->props.fb_blank = fb_blank; - backlight_update_status(bd); - } - } + + if (!bd->ops) + goto out; + if (bd->ops->check_fb && !bd->ops->check_fb(bd, evdata->info)) + goto out; + + fb_blank = *(int *)evdata->data; + if (fb_blank == FB_BLANK_UNBLANK && !bd->fb_bl_on[node]) { + bd->fb_bl_on[node] = true; + if (!bd->use_count++) { + bd->props.state &= ~BL_CORE_FBBLANK; + bd->props.fb_blank = FB_BLANK_UNBLANK; + backlight_update_status(bd); } + } else if (fb_blank != FB_BLANK_UNBLANK && bd->fb_bl_on[node]) { + bd->fb_bl_on[node] = false; + if (!(--bd->use_count)) { + bd->props.state |= BL_CORE_FBBLANK; + bd->props.fb_blank = fb_blank; + backlight_update_status(bd); + } + } +out: mutex_unlock(&bd->ops_lock); return 0; } From 1c91b46555aa1dd86331025e62d55d92459e0faf Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:26 +0200 Subject: [PATCH 122/291] backlight: backlight: Add backlight_is_blank() The backlight support has three properties that express the state: - power - state - fb_blank It is un-documented and easy to get wrong. Add backlight_is_blank() helper to make it simpler for drivers to get the check of the state correct. A lot of drivers also includes checks for fb_blank. This check is redundant when the state is checked and thus not needed in this helper function. But added anyway to avoid introducing subtle bugs due to the creative use of fb_blank in some drivers. Introducing this helper will for some drivers results in added support for fb_blank. This will be a change in functionality, which will improve the backlight driver. Rolling out this helper to all relevant backlight drivers will eliminate almost all accesses to fb_blank. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Peter Ujfalusi Reviewed-by: Emil Velikov Reviewed-by: Daniel Vetter Signed-off-by: Lee Jones --- include/linux/backlight.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 56e4580d4f55..56e51ebab740 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -175,6 +175,25 @@ static inline void backlight_put(struct backlight_device *bd) put_device(&bd->dev); } +/** + * backlight_is_blank - Return true if display is expected to be blank + * @bd: the backlight device + * + * Display is expected to be blank if any of these is true:: + * + * 1) if power in not UNBLANK + * 2) if fb_blank is not UNBLANK + * 3) if state indicate BLANK or SUSPENDED + * + * Returns true if display is expected to be blank, false otherwise. + */ +static inline bool backlight_is_blank(const struct backlight_device *bd) +{ + return bd->props.power != FB_BLANK_UNBLANK || + bd->props.fb_blank != FB_BLANK_UNBLANK || + bd->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK); +} + extern struct backlight_device *backlight_device_register(const char *name, struct device *dev, void *devdata, const struct backlight_ops *ops, const struct backlight_properties *props); From ca7c20b2132d228ec76df3c96f5d0b5ae3d6f218 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:27 +0200 Subject: [PATCH 123/291] backlight: backlight: Improve backlight_ops documentation Improve the documentation for backlight_ops and adapt it to kernel-doc style. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- include/linux/backlight.h | 59 +++++++++++++++++++++++++++++++++++---- 1 file changed, 53 insertions(+), 6 deletions(-) diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 56e51ebab740..4ff60774ae22 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -55,19 +55,66 @@ enum backlight_scale { struct backlight_device; struct fb_info; +/** + * struct backlight_ops - backlight operations + * + * The backlight operations are specified when the backlight device is registered. + */ struct backlight_ops { + /** + * @options: Configure how operations are called from the core. + * + * The options parameter is used to adjust the behaviour of the core. + * Set BL_CORE_SUSPENDRESUME to get the update_status() operation called + * upon suspend and resume. + */ unsigned int options; #define BL_CORE_SUSPENDRESUME (1 << 0) - /* Notify the backlight driver some property has changed */ + /** + * @update_status: Operation called when properties have changed. + * + * Notify the backlight driver some property has changed. + * The update_status operation is protected by the update_lock. + * + * The backlight driver is expected to use backlight_is_blank() + * to check if the display is blanked and set brightness accordingly. + * update_status() is called when any of the properties has changed. + * + * RETURNS: + * + * 0 on success, negative error code if any failure occurred. + */ int (*update_status)(struct backlight_device *); - /* Return the current backlight brightness (accounting for power, - fb_blank etc.) */ + + /** + * @get_brightness: Return the current backlight brightness. + * + * The driver may implement this as a readback from the HW. + * This operation is optional and if not present then the current + * brightness property value is used. + * + * RETURNS: + * + * A brightness value which is 0 or a positive number. + * On failure a negative error code is returned. + */ int (*get_brightness)(struct backlight_device *); - /* Check if given framebuffer device is the one bound to this backlight; - return 0 if not, !=0 if it is. If NULL, backlight always matches the fb. */ - int (*check_fb)(struct backlight_device *, struct fb_info *); + + /** + * @check_fb: Check the framebuffer device. + * + * Check if given framebuffer device is the one bound to this backlight. + * This operation is optional and if not implemented it is assumed that the + * fbdev is always the one bound to the backlight. + * + * RETURNS: + * + * If info is NULL or the info matches the fbdev bound to the backlight return true. + * If info does not match the fbdev bound to the backlight return false. + */ + int (*check_fb)(struct backlight_device *bd, struct fb_info *info); }; /* This structure defines all the properties of a backlight */ From cabf161335ca9fe695bb87469ed99be881cd08f5 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:28 +0200 Subject: [PATCH 124/291] backlight: backlight: Improve backlight_properties documentation Improve the documentation for backlight_properties and adapt it to kernel-doc style. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- include/linux/backlight.h | 96 ++++++++++++++++++++++++++++++++++----- 1 file changed, 85 insertions(+), 11 deletions(-) diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 4ff60774ae22..3554aef008ea 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -117,28 +117,102 @@ struct backlight_ops { int (*check_fb)(struct backlight_device *bd, struct fb_info *info); }; -/* This structure defines all the properties of a backlight */ +/** + * struct backlight_properties - backlight properties + * + * This structure defines all the properties of a backlight. + */ struct backlight_properties { - /* Current User requested brightness (0 - max_brightness) */ + /** + * @brightness: The current brightness requested by the user. + * + * The backlight core makes sure the range is (0 to max_brightness) + * when the brightness is set via the sysfs attribute: + * /sys/class/backlight//brightness. + * + * This value can be set in the backlight_properties passed + * to devm_backlight_device_register() to set a default brightness + * value. + */ int brightness; - /* Maximal value for brightness (read-only) */ + + /** + * @max_brightness: The maximum brightness value. + * + * This value must be set in the backlight_properties passed to + * devm_backlight_device_register() and shall not be modified by the + * driver after registration. + */ int max_brightness; - /* Current FB Power mode (0: full on, 1..3: power saving - modes; 4: full off), see FB_BLANK_XXX */ + + /** + * @power: The current power mode. + * + * User space can configure the power mode using the sysfs + * attribute: /sys/class/backlight//bl_power + * When the power property is updated update_status() is called. + * + * The possible values are: (0: full on, 1 to 3: power saving + * modes; 4: full off), see FB_BLANK_XXX. + * + * When the backlight device is enabled @power is set + * to FB_BLANK_UNBLANK. When the backlight device is disabled + * @power is set to FB_BLANK_POWERDOWN. + */ int power; - /* FB Blanking active? (values as for power) */ - /* Due to be removed, please use (state & BL_CORE_FBBLANK) */ + + /** + * @fb_blank: The power state from the FBIOBLANK ioctl. + * + * When the FBIOBLANK ioctl is called @fb_blank is set to the + * blank parameter and the update_status() operation is called. + * + * When the backlight device is enabled @fb_blank is set + * to FB_BLANK_UNBLANK. When the backlight device is disabled + * @fb_blank is set to FB_BLANK_POWERDOWN. + * + * Backlight drivers should avoid using this property. It has been + * replaced by state & BL_CORE_FBLANK (although most drivers should + * use backlight_is_blank() as the preferred means to get the blank + * state). + * + * fb_blank is deprecated and will be removed. + */ int fb_blank; - /* Backlight type */ + + /** + * @type: The type of backlight supported. + * + * The backlight type allows userspace to make appropriate + * policy decisions based on the backlight type. + * + * This value must be set in the backlight_properties + * passed to devm_backlight_device_register(). + */ enum backlight_type type; - /* Flags used to signal drivers of state changes */ + + /** + * @state: The state of the backlight core. + * + * The state is a bitmask. BL_CORE_FBBLANK is set when the display + * is expected to be blank. BL_CORE_SUSPENDED is set when the + * driver is suspended. + * + * backlight drivers are expected to use backlight_is_blank() + * in their update_status() operation rather than reading the + * state property. + * + * The state is maintained by the core and drivers may not modify it. + */ unsigned int state; - /* Type of the brightness scale (linear, non-linear, ...) */ - enum backlight_scale scale; #define BL_CORE_SUSPENDED (1 << 0) /* backlight is suspended */ #define BL_CORE_FBBLANK (1 << 1) /* backlight is under an fb blank event */ + /** + * @scale: The type of the brightness scale. + */ + enum backlight_scale scale; }; struct backlight_device { From 6f10cd124c44eea018672d5852708ca5dca4d06d Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:29 +0200 Subject: [PATCH 125/291] backlight: backlight: Improve backlight_device documentation Improve the documentation for backlight_device and adapt it to kernel-doc style. The updated documentation is more strict on how locking is used. With the update neither update_lock nor ops_lock may be used outside the backlight core. This restriction was introduced to keep the locking simple by keeping it in the core. It was verified that this documents the current state by renaming update_lock => bl_update_lock and ops_lock => bl_ops_lock. The rename did not reveal any uses outside the backlight core. The rename is NOT part of this patch. Signed-off-by: Sam Ravnborg Reviewed-by: Emil Velikov Reviewed-by: Daniel Thompson Reviewed-by: Jingoo Han Signed-off-by: Lee Jones --- include/linux/backlight.h | 72 ++++++++++++++++++++++++++------------- 1 file changed, 49 insertions(+), 23 deletions(-) diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 3554aef008ea..cf9977169fe8 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -14,21 +14,6 @@ #include #include -/* Notes on locking: - * - * backlight_device->ops_lock is an internal backlight lock protecting the - * ops pointer and no code outside the core should need to touch it. - * - * Access to update_status() is serialised by the update_lock mutex since - * most drivers seem to need this and historically get it wrong. - * - * Most drivers don't need locking on their get_brightness() method. - * If yours does, you need to implement it in the driver. You can use the - * update_lock mutex if appropriate. - * - * Any other use of the locks below is probably wrong. - */ - enum backlight_update_reason { BACKLIGHT_UPDATE_HOTKEY, BACKLIGHT_UPDATE_SYSFS, @@ -215,30 +200,71 @@ struct backlight_properties { enum backlight_scale scale; }; +/** + * struct backlight_device - backlight device data + * + * This structure holds all data required by a backlight device. + */ struct backlight_device { - /* Backlight properties */ + /** + * @props: Backlight properties + */ struct backlight_properties props; - /* Serialise access to update_status method */ + /** + * @update_lock: The lock used when calling the update_status() operation. + * + * update_lock is an internal backlight lock that serialise access + * to the update_status() operation. The backlight core holds the update_lock + * when calling the update_status() operation. The update_lock shall not + * be used by backlight drivers. + */ struct mutex update_lock; - /* This protects the 'ops' field. If 'ops' is NULL, the driver that - registered this device has been unloaded, and if class_get_devdata() - points to something in the body of that driver, it is also invalid. */ + /** + * @ops_lock: The lock used around everything related to backlight_ops. + * + * ops_lock is an internal backlight lock that protects the ops pointer + * and is used around all accesses to ops and when the operations are + * invoked. The ops_lock shall not be used by backlight drivers. + */ struct mutex ops_lock; + + /** + * @ops: Pointer to the backlight operations. + * + * If ops is NULL, the driver that registered this device has been unloaded, + * and if class_get_devdata() points to something in the body of that driver, + * it is also invalid. + */ const struct backlight_ops *ops; - /* The framebuffer notifier block */ + /** + * @fb_notif: The framebuffer notifier block + */ struct notifier_block fb_notif; - /* list entry of all registered backlight devices */ + /** + * @entry: List entry of all registered backlight devices + */ struct list_head entry; + /** + * @dev: Parent device. + */ struct device dev; - /* Multiple framebuffers may share one backlight device */ + /** + * @fb_bl_on: The state of individual fbdev's. + * + * Multiple fbdev's may share one backlight device. The fb_bl_on + * records the state of the individual fbdev. + */ bool fb_bl_on[FB_MAX]; + /** + * @use_count: The number of uses of fb_bl_on. + */ int use_count; }; From d160fd4e918da33f5ffbcf005cd95888dbbe4f76 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:30 +0200 Subject: [PATCH 126/291] backlight: backlight: Document inline functions in backlight.h Add documentation for the inline functions in backlight.h Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- include/linux/backlight.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/include/linux/backlight.h b/include/linux/backlight.h index cf9977169fe8..99381b5a289d 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -268,6 +268,10 @@ struct backlight_device { int use_count; }; +/** + * backlight_update_status - force an update of the backlight device status + * @bd: the backlight device + */ static inline int backlight_update_status(struct backlight_device *bd) { int ret = -ENOENT; @@ -361,6 +365,18 @@ extern int backlight_device_set_brightness(struct backlight_device *bd, unsigned #define to_backlight_device(obj) container_of(obj, struct backlight_device, dev) +/** + * bl_get_data - access devdata + * @bl_dev: pointer to backlight device + * + * When a backlight device is registered the driver has the possibility + * to supply a void * devdata. bl_get_data() return a pointer to the + * devdata. + * + * RETURNS: + * + * pointer to devdata stored while registering the backlight device. + */ static inline void * bl_get_data(struct backlight_device *bl_dev) { return dev_get_drvdata(&bl_dev->dev); From 2d15bb47f3331db979bd0a1987812ca1a3ff40c6 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:31 +0200 Subject: [PATCH 127/291] backlight: backlight: Document enums in backlight.h Add kernel-doc documentation for the backlight enums Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- include/linux/backlight.h | 72 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 99381b5a289d..1d56b34ff33c 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -14,26 +14,98 @@ #include #include +/** + * enum backlight_update_reason - what method was used to update backlight + * + * A driver indicates the method (reason) used for updating the backlight + * when calling backlight_force_update(). + */ enum backlight_update_reason { + /** + * @BACKLIGHT_UPDATE_HOTKEY: The backlight was updated using a hot-key. + */ BACKLIGHT_UPDATE_HOTKEY, + + /** + * @BACKLIGHT_UPDATE_SYSFS: The backlight was updated using sysfs. + */ BACKLIGHT_UPDATE_SYSFS, }; +/** + * enum backlight_type - the type of backlight control + * + * The type of interface used to control the backlight. + */ enum backlight_type { + /** + * @BACKLIGHT_RAW: + * + * The backlight is controlled using hardware registers. + */ BACKLIGHT_RAW = 1, + + /** + * @BACKLIGHT_PLATFORM: + * + * The backlight is controlled using a platform-specific interface. + */ BACKLIGHT_PLATFORM, + + /** + * @BACKLIGHT_FIRMWARE: + * + * The backlight is controlled using a standard firmware interface. + */ BACKLIGHT_FIRMWARE, + + /** + * @BACKLIGHT_TYPE_MAX: Number of entries. + */ BACKLIGHT_TYPE_MAX, }; +/** + * enum backlight_notification - the type of notification + * + * The notifications that is used for notification sent to the receiver + * that registered notifications using backlight_register_notifier(). + */ enum backlight_notification { + /** + * @BACKLIGHT_REGISTERED: The backlight device is registered. + */ BACKLIGHT_REGISTERED, + + /** + * @BACKLIGHT_UNREGISTERED: The backlight revice is unregistered. + */ BACKLIGHT_UNREGISTERED, }; +/** enum backlight_scale - the type of scale used for brightness values + * + * The type of scale used for brightness values. + */ enum backlight_scale { + /** + * @BACKLIGHT_SCALE_UNKNOWN: The scale is unknown. + */ BACKLIGHT_SCALE_UNKNOWN = 0, + + /** + * @BACKLIGHT_SCALE_LINEAR: The scale is linear. + * + * The linear scale will increase brightness the same for each step. + */ BACKLIGHT_SCALE_LINEAR, + + /** + * @BACKLIGHT_SCALE_NON_LINEAR: The scale is not linear. + * + * This is often used when the brightness values tries to adjust to + * the relative perception of the eye demanding a non-linear scale. + */ BACKLIGHT_SCALE_NON_LINEAR, }; From 7ecdea4a0226f6c5cd0e86859d1b38cf17bc8529 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:32 +0200 Subject: [PATCH 128/291] backlight: generic_bl: Remove this driver as it is unused The backlight_bl driver required initialization using struct generic_bl_info. As there are no more references to this struct there is no users left. So it is safe to delete the driver. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- drivers/video/backlight/Kconfig | 8 -- drivers/video/backlight/Makefile | 1 - drivers/video/backlight/generic_bl.c | 110 --------------------------- include/linux/backlight.h | 9 --- 4 files changed, 128 deletions(-) delete mode 100644 drivers/video/backlight/generic_bl.c diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig index 95c546cc8774..87f9fc238d28 100644 --- a/drivers/video/backlight/Kconfig +++ b/drivers/video/backlight/Kconfig @@ -173,14 +173,6 @@ config BACKLIGHT_EP93XX To compile this driver as a module, choose M here: the module will be called ep93xx_bl. -config BACKLIGHT_GENERIC - tristate "Generic (aka Sharp Corgi) Backlight Driver" - default y - help - Say y to enable the generic platform backlight driver previously - known as the Corgi backlight driver. If you have a Sharp Zaurus - SL-C7xx, SL-Cxx00 or SL-6000x say y. - config BACKLIGHT_IPAQ_MICRO tristate "iPAQ microcontroller backlight driver" depends on MFD_IPAQ_MICRO diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile index 2072d21b60f7..13463b99f1f9 100644 --- a/drivers/video/backlight/Makefile +++ b/drivers/video/backlight/Makefile @@ -31,7 +31,6 @@ obj-$(CONFIG_BACKLIGHT_CLASS_DEVICE) += backlight.o obj-$(CONFIG_BACKLIGHT_DA903X) += da903x_bl.o obj-$(CONFIG_BACKLIGHT_DA9052) += da9052_bl.o obj-$(CONFIG_BACKLIGHT_EP93XX) += ep93xx_bl.o -obj-$(CONFIG_BACKLIGHT_GENERIC) += generic_bl.o obj-$(CONFIG_BACKLIGHT_GPIO) += gpio_backlight.o obj-$(CONFIG_BACKLIGHT_HP680) += hp680_bl.o obj-$(CONFIG_BACKLIGHT_HP700) += jornada720_bl.o diff --git a/drivers/video/backlight/generic_bl.c b/drivers/video/backlight/generic_bl.c deleted file mode 100644 index 8fe63dbc8590..000000000000 --- a/drivers/video/backlight/generic_bl.c +++ /dev/null @@ -1,110 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Generic Backlight Driver - * - * Copyright (c) 2004-2008 Richard Purdie - */ - -#include -#include -#include -#include -#include -#include -#include - -static int genericbl_intensity; -static struct backlight_device *generic_backlight_device; -static struct generic_bl_info *bl_machinfo; - -static int genericbl_send_intensity(struct backlight_device *bd) -{ - int intensity = bd->props.brightness; - - if (bd->props.power != FB_BLANK_UNBLANK) - intensity = 0; - if (bd->props.state & BL_CORE_FBBLANK) - intensity = 0; - if (bd->props.state & BL_CORE_SUSPENDED) - intensity = 0; - - bl_machinfo->set_bl_intensity(intensity); - - genericbl_intensity = intensity; - - if (bl_machinfo->kick_battery) - bl_machinfo->kick_battery(); - - return 0; -} - -static int genericbl_get_intensity(struct backlight_device *bd) -{ - return genericbl_intensity; -} - -static const struct backlight_ops genericbl_ops = { - .options = BL_CORE_SUSPENDRESUME, - .get_brightness = genericbl_get_intensity, - .update_status = genericbl_send_intensity, -}; - -static int genericbl_probe(struct platform_device *pdev) -{ - struct backlight_properties props; - struct generic_bl_info *machinfo = dev_get_platdata(&pdev->dev); - const char *name = "generic-bl"; - struct backlight_device *bd; - - bl_machinfo = machinfo; - if (!machinfo->limit_mask) - machinfo->limit_mask = -1; - - if (machinfo->name) - name = machinfo->name; - - memset(&props, 0, sizeof(struct backlight_properties)); - props.type = BACKLIGHT_RAW; - props.max_brightness = machinfo->max_intensity; - bd = devm_backlight_device_register(&pdev->dev, name, &pdev->dev, - NULL, &genericbl_ops, &props); - if (IS_ERR(bd)) - return PTR_ERR(bd); - - platform_set_drvdata(pdev, bd); - - bd->props.power = FB_BLANK_UNBLANK; - bd->props.brightness = machinfo->default_intensity; - backlight_update_status(bd); - - generic_backlight_device = bd; - - dev_info(&pdev->dev, "Generic Backlight Driver Initialized.\n"); - return 0; -} - -static int genericbl_remove(struct platform_device *pdev) -{ - struct backlight_device *bd = platform_get_drvdata(pdev); - - bd->props.power = 0; - bd->props.brightness = 0; - backlight_update_status(bd); - - dev_info(&pdev->dev, "Generic Backlight Driver Unloaded\n"); - return 0; -} - -static struct platform_driver genericbl_driver = { - .probe = genericbl_probe, - .remove = genericbl_remove, - .driver = { - .name = "generic-bl", - }, -}; - -module_platform_driver(genericbl_driver); - -MODULE_AUTHOR("Richard Purdie "); -MODULE_DESCRIPTION("Generic Backlight Driver"); -MODULE_LICENSE("GPL"); diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 1d56b34ff33c..d0f01dc3b98d 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -454,15 +454,6 @@ static inline void * bl_get_data(struct backlight_device *bl_dev) return dev_get_drvdata(&bl_dev->dev); } -struct generic_bl_info { - const char *name; - int max_intensity; - int default_intensity; - int limit_mask; - void (*set_bl_intensity)(int intensity); - void (*kick_battery)(void); -}; - #ifdef CONFIG_OF struct backlight_device *of_find_backlight_by_node(struct device_node *node); #else From 9c4aa3118bab6f10904b7bc9bc34b501a083751b Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:33 +0200 Subject: [PATCH 129/291] backlight: backlight: Drop extern from prototypes No need to put "extern" in front of prototypes. While touching the prototypes adjust indent to follow the kernel style. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- include/linux/backlight.h | 35 +++++++++++++++++++---------------- 1 file changed, 19 insertions(+), 16 deletions(-) diff --git a/include/linux/backlight.h b/include/linux/backlight.h index d0f01dc3b98d..c1824426fc9e 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -417,23 +417,26 @@ static inline bool backlight_is_blank(const struct backlight_device *bd) bd->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK); } -extern struct backlight_device *backlight_device_register(const char *name, - struct device *dev, void *devdata, const struct backlight_ops *ops, - const struct backlight_properties *props); -extern struct backlight_device *devm_backlight_device_register( - struct device *dev, const char *name, struct device *parent, - void *devdata, const struct backlight_ops *ops, - const struct backlight_properties *props); -extern void backlight_device_unregister(struct backlight_device *bd); -extern void devm_backlight_device_unregister(struct device *dev, - struct backlight_device *bd); -extern void backlight_force_update(struct backlight_device *bd, - enum backlight_update_reason reason); -extern int backlight_register_notifier(struct notifier_block *nb); -extern int backlight_unregister_notifier(struct notifier_block *nb); -extern struct backlight_device *backlight_device_get_by_type(enum backlight_type type); +struct backlight_device * +backlight_device_register(const char *name, struct device *dev, void *devdata, + const struct backlight_ops *ops, + const struct backlight_properties *props); +struct backlight_device * +devm_backlight_device_register(struct device *dev, const char *name, + struct device *parent, void *devdata, + const struct backlight_ops *ops, + const struct backlight_properties *props); +void backlight_device_unregister(struct backlight_device *bd); +void devm_backlight_device_unregister(struct device *dev, + struct backlight_device *bd); +void backlight_force_update(struct backlight_device *bd, + enum backlight_update_reason reason); +int backlight_register_notifier(struct notifier_block *nb); +int backlight_unregister_notifier(struct notifier_block *nb); struct backlight_device *backlight_device_get_by_name(const char *name); -extern int backlight_device_set_brightness(struct backlight_device *bd, unsigned long brightness); +struct backlight_device *backlight_device_get_by_type(enum backlight_type type); +int backlight_device_set_brightness(struct backlight_device *bd, + unsigned long brightness); #define to_backlight_device(obj) container_of(obj, struct backlight_device, dev) From a1230eb2e3f44ebd1b59c547491e0c480b44aff3 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:34 +0200 Subject: [PATCH 130/291] backlight: backlight: Add overview and update existing doc Add overview chapter to backlight.c. Update existing kernel-doc to follow a more consistent style and drop kernel-doc for deprecated functions. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- drivers/video/backlight/backlight.c | 138 +++++++++++++++++++--------- 1 file changed, 97 insertions(+), 41 deletions(-) diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c index 18501956dd87..82dc93ca859a 100644 --- a/drivers/video/backlight/backlight.c +++ b/drivers/video/backlight/backlight.c @@ -22,6 +22,47 @@ #include #endif +/** + * DOC: overview + * + * The backlight core supports implementing backlight drivers. + * + * A backlight driver registers a driver using + * devm_backlight_device_register(). The properties of the backlight + * driver such as type and max_brightness must be specified. + * When the core detect changes in for example brightness or power state + * the update_status() operation is called. The backlight driver shall + * implement this operation and use it to adjust backlight. + * + * Several sysfs attributes are provided by the backlight core:: + * + * - brightness R/W, set the requested brightness level + * - actual_brightness RO, the brightness level used by the HW + * - max_brightness RO, the maximum brightness level supported + * + * See Documentation/ABI/stable/sysfs-class-backlight for the full list. + * + * The backlight can be adjusted using the sysfs interface, and + * the backlight driver may also support adjusting backlight using + * a hot-key or some other platform or firmware specific way. + * + * The driver must implement the get_brightness() operation if + * the HW do not support all the levels that can be specified in + * brightness, thus providing user-space access to the actual level + * via the actual_brightness attribute. + * + * When the backlight changes this is reported to user-space using + * an uevent connected to the actual_brightness attribute. + * When brightness is set by platform specific means, for example + * a hot-key to adjust backlight, the driver must notify the backlight + * core that brightness has changed using backlight_force_update(). + * + * The backlight driver core receives notifications from fbdev and + * if the event is FB_EVENT_BLANK and if the value of blank, from the + * FBIOBLANK ioctrl, results in a change in the backlight state the + * update_status() operation is called. + */ + static struct list_head backlight_dev_list; static struct mutex backlight_dev_list_mutex; static struct blocking_notifier_head backlight_notifier; @@ -40,9 +81,17 @@ static const char *const backlight_scale_types[] = { #if defined(CONFIG_FB) || (defined(CONFIG_FB_MODULE) && \ defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)) -/* This callback gets called when something important happens inside a - * framebuffer driver. We're looking if that important event is blanking, - * and if it is and necessary, we're switching backlight power as well ... +/* + * fb_notifier_callback + * + * This callback gets called when something important happens inside a + * framebuffer driver. The backlight core only cares about FB_BLANK_UNBLANK + * which is reported to the driver using backlight_update_status() + * as a state change. + * + * There may be several fbdev's connected to the backlight device, + * in which case they are kept track of. A state change is only reported + * if there is a change in backlight for the specified fbdev. */ static int fb_notifier_callback(struct notifier_block *self, unsigned long event, void *data) @@ -324,7 +373,10 @@ ATTRIBUTE_GROUPS(bl_device); * @reason: reason for update * * Updates the internal state of the backlight in response to a hardware event, - * and generate a uevent to notify userspace + * and generates an uevent to notify userspace. A backlight driver shall call + * backlight_force_update() when the backlight is changed using, for example, + * a hot-key. The updated brightness is read using get_brightness() and the + * brightness value is reported using an uevent. */ void backlight_force_update(struct backlight_device *bd, enum backlight_update_reason reason) @@ -337,20 +389,7 @@ void backlight_force_update(struct backlight_device *bd, } EXPORT_SYMBOL(backlight_force_update); -/** - * backlight_device_register - create and register a new object of - * backlight_device class. - * @name: the name of the new object(must be the same as the name of the - * respective framebuffer device). - * @parent: a pointer to the parent device - * @devdata: an optional pointer to be stored for private driver use. The - * methods may retrieve it by using bl_get_data(bd). - * @ops: the backlight operations structure. - * @props: pointer to backlight's properties structure. - * - * Creates and registers new backlight device. Returns either an - * ERR_PTR() or a pointer to the newly allocated device. - */ +/* deprecated - use devm_backlight_device_register() */ struct backlight_device *backlight_device_register(const char *name, struct device *parent, void *devdata, const struct backlight_ops *ops, const struct backlight_properties *props) @@ -417,6 +456,15 @@ struct backlight_device *backlight_device_register(const char *name, } EXPORT_SYMBOL(backlight_device_register); +/** backlight_device_get_by_type - find first backlight device of a type + * @type: the type of backlight device + * + * Look up the first backlight device of the specified type + * + * RETURNS: + * + * Pointer to backlight device if any was found. Otherwise NULL. + */ struct backlight_device *backlight_device_get_by_type(enum backlight_type type) { bool found = false; @@ -456,12 +504,7 @@ struct backlight_device *backlight_device_get_by_name(const char *name) } EXPORT_SYMBOL(backlight_device_get_by_name); -/** - * backlight_device_unregister - unregisters a backlight device object. - * @bd: the backlight device object to be unregistered and freed. - * - * Unregisters a previously registered via backlight_device_register object. - */ +/* deprecated - use devm_backlight_device_unregister() */ void backlight_device_unregister(struct backlight_device *bd) { if (!bd) @@ -509,10 +552,12 @@ static int devm_backlight_device_match(struct device *dev, void *res, * backlight_register_notifier - get notified of backlight (un)registration * @nb: notifier block with the notifier to call on backlight (un)registration * - * @return 0 on success, otherwise a negative error code - * * Register a notifier to get notified when backlight devices get registered * or unregistered. + * + * RETURNS: + * + * 0 on success, otherwise a negative error code */ int backlight_register_notifier(struct notifier_block *nb) { @@ -524,10 +569,12 @@ EXPORT_SYMBOL(backlight_register_notifier); * backlight_unregister_notifier - unregister a backlight notifier * @nb: notifier block to unregister * - * @return 0 on success, otherwise a negative error code - * * Register a notifier to get notified when backlight devices get registered * or unregistered. + * + * RETURNS: + * + * 0 on success, otherwise a negative error code */ int backlight_unregister_notifier(struct notifier_block *nb) { @@ -536,19 +583,21 @@ int backlight_unregister_notifier(struct notifier_block *nb) EXPORT_SYMBOL(backlight_unregister_notifier); /** - * devm_backlight_device_register - resource managed backlight_device_register() + * devm_backlight_device_register - register a new backlight device * @dev: the device to register * @name: the name of the device - * @parent: a pointer to the parent device + * @parent: a pointer to the parent device (often the same as @dev) * @devdata: an optional pointer to be stored for private driver use * @ops: the backlight operations structure * @props: the backlight properties * - * @return a struct backlight on success, or an ERR_PTR on error + * Creates and registers new backlight device. When a backlight device + * is registered the configuration must be specified in the @props + * parameter. See description of &backlight_properties. * - * Managed backlight_device_register(). The backlight_device returned - * from this function are automatically freed on driver detach. - * See backlight_device_register() for more information. + * RETURNS: + * + * struct backlight on success, or an ERR_PTR on error */ struct backlight_device *devm_backlight_device_register(struct device *dev, const char *name, struct device *parent, void *devdata, @@ -576,13 +625,13 @@ struct backlight_device *devm_backlight_device_register(struct device *dev, EXPORT_SYMBOL(devm_backlight_device_register); /** - * devm_backlight_device_unregister - resource managed backlight_device_unregister() + * devm_backlight_device_unregister - unregister backlight device * @dev: the device to unregister * @bd: the backlight device to unregister * - * Deallocated a backlight allocated with devm_backlight_device_register(). + * Deallocates a backlight allocated with devm_backlight_device_register(). * Normally this function will not need to be called and the resource management - * code will ensure that the resource is freed. + * code will ensure that the resources are freed. */ void devm_backlight_device_unregister(struct device *dev, struct backlight_device *bd) @@ -673,12 +722,19 @@ static void devm_backlight_release(void *data) } /** - * devm_of_find_backlight - Resource-managed of_find_backlight() - * @dev: Device + * devm_of_find_backlight - find backlight for a device + * @dev: the device * - * Device managed version of of_find_backlight(). - * The reference on the backlight device is automatically + * This function looks for a property named 'backlight' on the DT node + * connected to @dev and looks up the backlight device. The lookup is + * device managed so the reference to the backlight device is automatically * dropped on driver detach. + * + * RETURNS: + * + * A pointer to the backlight device if found. + * Error pointer -EPROBE_DEFER if the DT property is set, but no backlight + * device is found. NULL if there's no backlight property. */ struct backlight_device *devm_of_find_backlight(struct device *dev) { From 5ab4246cfc6f62cd0eb4c95a029e6fa7f29b3984 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:35 +0200 Subject: [PATCH 131/291] doc-rst: Wire-up Backlight kernel-doc documentation Include backlight so the documentation is now generated with make htmldocs and friends. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- Documentation/gpu/backlight.rst | 12 ++++++++++++ Documentation/gpu/index.rst | 1 + 2 files changed, 13 insertions(+) create mode 100644 Documentation/gpu/backlight.rst diff --git a/Documentation/gpu/backlight.rst b/Documentation/gpu/backlight.rst new file mode 100644 index 000000000000..9ebfc9d0aced --- /dev/null +++ b/Documentation/gpu/backlight.rst @@ -0,0 +1,12 @@ +================= +Backlight support +================= + +.. kernel-doc:: drivers/video/backlight/backlight.c + :doc: overview + +.. kernel-doc:: include/linux/backlight.h + :internal: + +.. kernel-doc:: drivers/video/backlight/backlight.c + :export: diff --git a/Documentation/gpu/index.rst b/Documentation/gpu/index.rst index 1fcf8e851e15..c9a51e3bfb5a 100644 --- a/Documentation/gpu/index.rst +++ b/Documentation/gpu/index.rst @@ -12,6 +12,7 @@ Linux GPU Driver Developer's Guide drm-uapi drm-client drivers + backlight vga-switcheroo vgaarbiter todo From 2144d00ed0db28c764513080f95e4c49ea9133b0 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:36 +0200 Subject: [PATCH 132/291] backlight: backlight: Introduce backlight_get_brightness() Based on an idea from Emil Velikov, add a helper that checks backlight_is_blank() and return 0 as brightness if display is blank or the property value if not. This allows us to simplify the update_status() implementation in most of the backlight drivers. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- include/linux/backlight.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/include/linux/backlight.h b/include/linux/backlight.h index c1824426fc9e..26e89a8033f5 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -417,6 +417,25 @@ static inline bool backlight_is_blank(const struct backlight_device *bd) bd->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK); } +/** + * backlight_get_brightness - Returns the current brightness value + * @bd: the backlight device + * + * Returns the current brightness value, taking in consideration the current + * state. If backlight_is_blank() returns true then return 0 as brightness + * otherwise return the current brightness property value. + * + * Backlight drivers are expected to use this function in their update_status() + * operation to get the brightness value. + */ +static inline int backlight_get_brightness(const struct backlight_device *bd) +{ + if (backlight_is_blank(bd)) + return 0; + else + return bd->props.brightness; +} + struct backlight_device * backlight_device_register(const char *name, struct device *dev, void *devdata, const struct backlight_ops *ops, From 5a09765ddedd34f176275c72ffbe567e428e2dfc Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:37 +0200 Subject: [PATCH 133/291] backlight: as3711_bl: Simplify update_status Replaces the open-coded checks of the state, with the backlight_get_brightness() helper. This increases readability of the code and align the functionality across the drivers. Furthermore drop the debug prints in update_status(). If we need debug printing then we can add it to the backlight core. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/as3711_bl.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/video/backlight/as3711_bl.c b/drivers/video/backlight/as3711_bl.c index 33f0f0f2e8b3..3b60019cdc2b 100644 --- a/drivers/video/backlight/as3711_bl.c +++ b/drivers/video/backlight/as3711_bl.c @@ -104,17 +104,10 @@ static int as3711_bl_update_status(struct backlight_device *bl) struct as3711_bl_data *data = bl_get_data(bl); struct as3711_bl_supply *supply = to_supply(data); struct as3711 *as3711 = supply->as3711; - int brightness = bl->props.brightness; + int brightness; int ret = 0; - dev_dbg(&bl->dev, "%s(): brightness %u, pwr %x, blank %x, state %x\n", - __func__, bl->props.brightness, bl->props.power, - bl->props.fb_blank, bl->props.state); - - if (bl->props.power != FB_BLANK_UNBLANK || - bl->props.fb_blank != FB_BLANK_UNBLANK || - bl->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK)) - brightness = 0; + brightness = backlight_get_brightness(bl); if (data->type == AS3711_BL_SU1) { ret = as3711_set_brightness_v(as3711, brightness, From 24d34617c24f9d41953f76f2fbf282334584f5db Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:38 +0200 Subject: [PATCH 134/291] backlight: cr_bllcd: Introduce gpio-backlight semantics cr_bllcd can turn backlight ON or OFF. Fix semantitics so they equals what we know from gpio-backlight. brightness == 0 => backlight off brightness == 1 => backlight on Use the backlight_get_brightness() helper to simplify the code. Signed-off-by: Sam Ravnborg Signed-off-by: Lee Jones --- drivers/video/backlight/cr_bllcd.c | 25 +++++++++---------------- 1 file changed, 9 insertions(+), 16 deletions(-) diff --git a/drivers/video/backlight/cr_bllcd.c b/drivers/video/backlight/cr_bllcd.c index 4624b7b7c6a6..a24d42e1ea3c 100644 --- a/drivers/video/backlight/cr_bllcd.c +++ b/drivers/video/backlight/cr_bllcd.c @@ -63,22 +63,15 @@ static int cr_backlight_set_intensity(struct backlight_device *bd) u32 addr = gpio_bar + CRVML_PANEL_PORT; u32 cur = inl(addr); - if (bd->props.power == FB_BLANK_UNBLANK) - intensity = FB_BLANK_UNBLANK; - if (bd->props.fb_blank == FB_BLANK_UNBLANK) - intensity = FB_BLANK_UNBLANK; - if (bd->props.power == FB_BLANK_POWERDOWN) - intensity = FB_BLANK_POWERDOWN; - if (bd->props.fb_blank == FB_BLANK_POWERDOWN) - intensity = FB_BLANK_POWERDOWN; - - if (intensity == FB_BLANK_UNBLANK) { /* FULL ON */ - cur &= ~CRVML_BACKLIGHT_OFF; - outl(cur, addr); - } else if (intensity == FB_BLANK_POWERDOWN) { /* OFF */ + if (backlight_get_brightness(bd) == 0) { + /* OFF */ cur |= CRVML_BACKLIGHT_OFF; outl(cur, addr); - } /* anything else, don't bother */ + } else { + /* FULL ON */ + cur &= ~CRVML_BACKLIGHT_OFF; + outl(cur, addr); + } return 0; } @@ -90,9 +83,9 @@ static int cr_backlight_get_intensity(struct backlight_device *bd) u8 intensity; if (cur & CRVML_BACKLIGHT_OFF) - intensity = FB_BLANK_POWERDOWN; + intensity = 0; else - intensity = FB_BLANK_UNBLANK; + intensity = 1; return intensity; } From de7b490cdfe46e34e3eb567019b4e3b3747b5c0b Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:39 +0200 Subject: [PATCH 135/291] backlight: gpio_backlight: Simplify update_status() Introduce the use of backlight_get_brightness() to simplify the update_status() operation. With the simpler implementation drop the gpio_backlight_get_next_brightness() helper as it was now a one-liner. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/gpio_backlight.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) diff --git a/drivers/video/backlight/gpio_backlight.c b/drivers/video/backlight/gpio_backlight.c index 75409ddfba3e..6f78d928f054 100644 --- a/drivers/video/backlight/gpio_backlight.c +++ b/drivers/video/backlight/gpio_backlight.c @@ -21,24 +21,11 @@ struct gpio_backlight { struct gpio_desc *gpiod; }; -static int gpio_backlight_get_next_brightness(struct backlight_device *bl) -{ - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK || - bl->props.fb_blank != FB_BLANK_UNBLANK || - bl->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK)) - brightness = 0; - - return brightness; -} - static int gpio_backlight_update_status(struct backlight_device *bl) { struct gpio_backlight *gbl = bl_get_data(bl); - int brightness = gpio_backlight_get_next_brightness(bl); - gpiod_set_value_cansleep(gbl->gpiod, brightness); + gpiod_set_value_cansleep(gbl->gpiod, backlight_get_brightness(bl)); return 0; } @@ -108,7 +95,7 @@ static int gpio_backlight_probe(struct platform_device *pdev) bl->props.brightness = 1; - init_brightness = gpio_backlight_get_next_brightness(bl); + init_brightness = backlight_get_brightness(bl); ret = gpiod_direction_output(gbl->gpiod, init_brightness); if (ret) { dev_err(dev, "failed to set initial brightness\n"); From a00a5feb1e96ff55c24131472db53dc56cc7570b Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:40 +0200 Subject: [PATCH 136/291] backlight: jornada720_bl: Introduce backlight_is_blank() Use the backlight_is_blank() helper to simplify the code a bit. The jornada720_bl driver distinguish between backlight off and brightness set to 0. Thus this driver turn off backlight only when backlight_is_blank() returns true. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/jornada720_bl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/backlight/jornada720_bl.c b/drivers/video/backlight/jornada720_bl.c index f0385f9cf9da..996f7ba3b373 100644 --- a/drivers/video/backlight/jornada720_bl.c +++ b/drivers/video/backlight/jornada720_bl.c @@ -54,7 +54,7 @@ static int jornada_bl_update_status(struct backlight_device *bd) jornada_ssp_start(); /* If backlight is off then really turn it off */ - if ((bd->props.power != FB_BLANK_UNBLANK) || (bd->props.fb_blank != FB_BLANK_UNBLANK)) { + if (backlight_is_blank(bd)) { ret = jornada_ssp_byte(BRIGHTNESSOFF); if (ret != TXDUMMY) { dev_info(&bd->dev, "brightness off timeout\n"); From 51d53e5b06b8e75d02a17bfe678e7be7554a2322 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:41 +0200 Subject: [PATCH 137/291] backlight: Use backlight_get_brightness() throughout Introduce the backlight_get_brightness() helper in all video/backlight/* drivers. This simplifies the code and align the implementation of the update_status() operation across the different backlight drivers. Some of the drivers gains a little extra functionality by the change as they now respect the fb_blank() ioctl. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/88pm860x_bl.c | 13 +------------ drivers/video/backlight/adp5520_bl.c | 10 +--------- drivers/video/backlight/adp8860_bl.c | 10 +--------- drivers/video/backlight/adp8870_bl.c | 10 +--------- drivers/video/backlight/bd6107.c | 7 +------ drivers/video/backlight/corgi_lcd.c | 8 +------- drivers/video/backlight/da903x_bl.c | 13 +------------ drivers/video/backlight/ep93xx_bl.c | 8 +------- drivers/video/backlight/hp680_bl.c | 6 +----- drivers/video/backlight/kb3886_bl.c | 6 +----- drivers/video/backlight/led_bl.c | 7 +------ drivers/video/backlight/lm3533_bl.c | 8 +------- drivers/video/backlight/locomolcd.c | 6 +----- drivers/video/backlight/lv5207lp.c | 7 +------ drivers/video/backlight/max8925_bl.c | 13 +------------ drivers/video/backlight/pwm_bl.c | 7 +------ drivers/video/backlight/qcom-wled.c | 7 +------ drivers/video/backlight/tps65217_bl.c | 10 +--------- drivers/video/backlight/wm831x_bl.c | 13 +------------ 19 files changed, 19 insertions(+), 150 deletions(-) diff --git a/drivers/video/backlight/88pm860x_bl.c b/drivers/video/backlight/88pm860x_bl.c index 20d96a5ac384..25e409bbb1a2 100644 --- a/drivers/video/backlight/88pm860x_bl.c +++ b/drivers/video/backlight/88pm860x_bl.c @@ -121,18 +121,7 @@ static int pm860x_backlight_set(struct backlight_device *bl, int brightness) static int pm860x_backlight_update_status(struct backlight_device *bl) { - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK) - brightness = 0; - - if (bl->props.fb_blank != FB_BLANK_UNBLANK) - brightness = 0; - - if (bl->props.state & BL_CORE_SUSPENDED) - brightness = 0; - - return pm860x_backlight_set(bl, brightness); + return pm860x_backlight_set(bl, backlight_get_brightness(bl)); } static int pm860x_backlight_get_brightness(struct backlight_device *bl) diff --git a/drivers/video/backlight/adp5520_bl.c b/drivers/video/backlight/adp5520_bl.c index 0f63f76723a5..686988c3df3a 100644 --- a/drivers/video/backlight/adp5520_bl.c +++ b/drivers/video/backlight/adp5520_bl.c @@ -65,15 +65,7 @@ static int adp5520_bl_set(struct backlight_device *bl, int brightness) static int adp5520_bl_update_status(struct backlight_device *bl) { - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK) - brightness = 0; - - if (bl->props.fb_blank != FB_BLANK_UNBLANK) - brightness = 0; - - return adp5520_bl_set(bl, brightness); + return adp5520_bl_set(bl, backlight_get_brightness(bl)); } static int adp5520_bl_get_brightness(struct backlight_device *bl) diff --git a/drivers/video/backlight/adp8860_bl.c b/drivers/video/backlight/adp8860_bl.c index 19968104fc47..ddc7f5f0401f 100644 --- a/drivers/video/backlight/adp8860_bl.c +++ b/drivers/video/backlight/adp8860_bl.c @@ -361,15 +361,7 @@ static int adp8860_bl_set(struct backlight_device *bl, int brightness) static int adp8860_bl_update_status(struct backlight_device *bl) { - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK) - brightness = 0; - - if (bl->props.fb_blank != FB_BLANK_UNBLANK) - brightness = 0; - - return adp8860_bl_set(bl, brightness); + return adp8860_bl_set(bl, backlight_get_brightness(bl)); } static int adp8860_bl_get_brightness(struct backlight_device *bl) diff --git a/drivers/video/backlight/adp8870_bl.c b/drivers/video/backlight/adp8870_bl.c index 4c0032010cfe..8b5213a39527 100644 --- a/drivers/video/backlight/adp8870_bl.c +++ b/drivers/video/backlight/adp8870_bl.c @@ -399,15 +399,7 @@ static int adp8870_bl_set(struct backlight_device *bl, int brightness) static int adp8870_bl_update_status(struct backlight_device *bl) { - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK) - brightness = 0; - - if (bl->props.fb_blank != FB_BLANK_UNBLANK) - brightness = 0; - - return adp8870_bl_set(bl, brightness); + return adp8870_bl_set(bl, backlight_get_brightness(bl)); } static int adp8870_bl_get_brightness(struct backlight_device *bl) diff --git a/drivers/video/backlight/bd6107.c b/drivers/video/backlight/bd6107.c index d5d5fb457e78..515184fbe33a 100644 --- a/drivers/video/backlight/bd6107.c +++ b/drivers/video/backlight/bd6107.c @@ -82,12 +82,7 @@ static int bd6107_write(struct bd6107 *bd, u8 reg, u8 data) static int bd6107_backlight_update_status(struct backlight_device *backlight) { struct bd6107 *bd = bl_get_data(backlight); - int brightness = backlight->props.brightness; - - if (backlight->props.power != FB_BLANK_UNBLANK || - backlight->props.fb_blank != FB_BLANK_UNBLANK || - backlight->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK)) - brightness = 0; + int brightness = backlight_get_brightness(backlight); if (brightness) { bd6107_write(bd, BD6107_PORTSEL, BD6107_PORTSEL_LEDM(2) | diff --git a/drivers/video/backlight/corgi_lcd.c b/drivers/video/backlight/corgi_lcd.c index 25ef0cbd7583..33f5d80495e6 100644 --- a/drivers/video/backlight/corgi_lcd.c +++ b/drivers/video/backlight/corgi_lcd.c @@ -420,13 +420,7 @@ static int corgi_bl_set_intensity(struct corgi_lcd *lcd, int intensity) static int corgi_bl_update_status(struct backlight_device *bd) { struct corgi_lcd *lcd = bl_get_data(bd); - int intensity = bd->props.brightness; - - if (bd->props.power != FB_BLANK_UNBLANK) - intensity = 0; - - if (bd->props.fb_blank != FB_BLANK_UNBLANK) - intensity = 0; + int intensity = backlight_get_brightness(bd); if (corgibl_flags & CORGIBL_SUSPENDED) intensity = 0; diff --git a/drivers/video/backlight/da903x_bl.c b/drivers/video/backlight/da903x_bl.c index 62540e4bdedb..71f21bbc7a9f 100644 --- a/drivers/video/backlight/da903x_bl.c +++ b/drivers/video/backlight/da903x_bl.c @@ -77,18 +77,7 @@ static int da903x_backlight_set(struct backlight_device *bl, int brightness) static int da903x_backlight_update_status(struct backlight_device *bl) { - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK) - brightness = 0; - - if (bl->props.fb_blank != FB_BLANK_UNBLANK) - brightness = 0; - - if (bl->props.state & BL_CORE_SUSPENDED) - brightness = 0; - - return da903x_backlight_set(bl, brightness); + return da903x_backlight_set(bl, backlight_get_brightness(bl)); } static int da903x_backlight_get_brightness(struct backlight_device *bl) diff --git a/drivers/video/backlight/ep93xx_bl.c b/drivers/video/backlight/ep93xx_bl.c index 4149e0b2f83c..2387009d452d 100644 --- a/drivers/video/backlight/ep93xx_bl.c +++ b/drivers/video/backlight/ep93xx_bl.c @@ -36,13 +36,7 @@ static int ep93xxbl_set(struct backlight_device *bl, int brightness) static int ep93xxbl_update_status(struct backlight_device *bl) { - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK || - bl->props.fb_blank != FB_BLANK_UNBLANK) - brightness = 0; - - return ep93xxbl_set(bl, brightness); + return ep93xxbl_set(bl, backlight_get_brightness(bl)); } static int ep93xxbl_get_brightness(struct backlight_device *bl) diff --git a/drivers/video/backlight/hp680_bl.c b/drivers/video/backlight/hp680_bl.c index 8ea42b8d9bc8..9123c33def05 100644 --- a/drivers/video/backlight/hp680_bl.c +++ b/drivers/video/backlight/hp680_bl.c @@ -33,12 +33,8 @@ static void hp680bl_send_intensity(struct backlight_device *bd) { unsigned long flags; u16 v; - int intensity = bd->props.brightness; + int intensity = backlight_get_brightness(bd); - if (bd->props.power != FB_BLANK_UNBLANK) - intensity = 0; - if (bd->props.fb_blank != FB_BLANK_UNBLANK) - intensity = 0; if (hp680bl_suspended) intensity = 0; diff --git a/drivers/video/backlight/kb3886_bl.c b/drivers/video/backlight/kb3886_bl.c index 1dfe13c18925..55794b239cff 100644 --- a/drivers/video/backlight/kb3886_bl.c +++ b/drivers/video/backlight/kb3886_bl.c @@ -87,12 +87,8 @@ static const struct dmi_system_id kb3886bl_device_table[] __initconst = { static int kb3886bl_send_intensity(struct backlight_device *bd) { - int intensity = bd->props.brightness; + int intensity = backlight_get_brightness(bd); - if (bd->props.power != FB_BLANK_UNBLANK) - intensity = 0; - if (bd->props.fb_blank != FB_BLANK_UNBLANK) - intensity = 0; if (kb3886bl_flags & KB3886BL_SUSPENDED) intensity = 0; diff --git a/drivers/video/backlight/led_bl.c b/drivers/video/backlight/led_bl.c index 3f66549997c8..f54d256e2d54 100644 --- a/drivers/video/backlight/led_bl.c +++ b/drivers/video/backlight/led_bl.c @@ -54,12 +54,7 @@ static void led_bl_power_off(struct led_bl_data *priv) static int led_bl_update_status(struct backlight_device *bl) { struct led_bl_data *priv = bl_get_data(bl); - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK || - bl->props.fb_blank != FB_BLANK_UNBLANK || - bl->props.state & BL_CORE_FBBLANK) - brightness = 0; + int brightness = backlight_get_brightness(bl); if (brightness > 0) led_bl_set_brightness(priv, brightness); diff --git a/drivers/video/backlight/lm3533_bl.c b/drivers/video/backlight/lm3533_bl.c index 0c7830f793de..1df1b6643c0b 100644 --- a/drivers/video/backlight/lm3533_bl.c +++ b/drivers/video/backlight/lm3533_bl.c @@ -39,14 +39,8 @@ static inline int lm3533_bl_get_ctrlbank_id(struct lm3533_bl *bl) static int lm3533_bl_update_status(struct backlight_device *bd) { struct lm3533_bl *bl = bl_get_data(bd); - int brightness = bd->props.brightness; - if (bd->props.power != FB_BLANK_UNBLANK) - brightness = 0; - if (bd->props.fb_blank != FB_BLANK_UNBLANK) - brightness = 0; - - return lm3533_ctrlbank_set_brightness(&bl->cb, (u8)brightness); + return lm3533_ctrlbank_set_brightness(&bl->cb, backlight_get_brightness(bd)); } static int lm3533_bl_get_brightness(struct backlight_device *bd) diff --git a/drivers/video/backlight/locomolcd.c b/drivers/video/backlight/locomolcd.c index cdc02e04f89d..297ee2e1ab0b 100644 --- a/drivers/video/backlight/locomolcd.c +++ b/drivers/video/backlight/locomolcd.c @@ -111,12 +111,8 @@ static int current_intensity; static int locomolcd_set_intensity(struct backlight_device *bd) { - int intensity = bd->props.brightness; + int intensity = backlight_get_brightness(bd); - if (bd->props.power != FB_BLANK_UNBLANK) - intensity = 0; - if (bd->props.fb_blank != FB_BLANK_UNBLANK) - intensity = 0; if (locomolcd_flags & LOCOMOLCD_SUSPENDED) intensity = 0; diff --git a/drivers/video/backlight/lv5207lp.c b/drivers/video/backlight/lv5207lp.c index c6ad73a784e2..1842ae9a55f8 100644 --- a/drivers/video/backlight/lv5207lp.c +++ b/drivers/video/backlight/lv5207lp.c @@ -46,12 +46,7 @@ static int lv5207lp_write(struct lv5207lp *lv, u8 reg, u8 data) static int lv5207lp_backlight_update_status(struct backlight_device *backlight) { struct lv5207lp *lv = bl_get_data(backlight); - int brightness = backlight->props.brightness; - - if (backlight->props.power != FB_BLANK_UNBLANK || - backlight->props.fb_blank != FB_BLANK_UNBLANK || - backlight->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK)) - brightness = 0; + int brightness = backlight_get_brightness(backlight); if (brightness) { lv5207lp_write(lv, LV5207LP_CTRL1, diff --git a/drivers/video/backlight/max8925_bl.c b/drivers/video/backlight/max8925_bl.c index 97cc260ff9d1..e607ec6fd4bf 100644 --- a/drivers/video/backlight/max8925_bl.c +++ b/drivers/video/backlight/max8925_bl.c @@ -64,18 +64,7 @@ static int max8925_backlight_set(struct backlight_device *bl, int brightness) static int max8925_backlight_update_status(struct backlight_device *bl) { - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK) - brightness = 0; - - if (bl->props.fb_blank != FB_BLANK_UNBLANK) - brightness = 0; - - if (bl->props.state & BL_CORE_SUSPENDED) - brightness = 0; - - return max8925_backlight_set(bl, brightness); + return max8925_backlight_set(bl, backlight_get_brightness(bl)); } static int max8925_backlight_get_brightness(struct backlight_device *bl) diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c index 82b8d7594701..eff64db2e02e 100644 --- a/drivers/video/backlight/pwm_bl.c +++ b/drivers/video/backlight/pwm_bl.c @@ -108,14 +108,9 @@ static int compute_duty_cycle(struct pwm_bl_data *pb, int brightness) static int pwm_backlight_update_status(struct backlight_device *bl) { struct pwm_bl_data *pb = bl_get_data(bl); - int brightness = bl->props.brightness; + int brightness = backlight_get_brightness(bl); struct pwm_state state; - if (bl->props.power != FB_BLANK_UNBLANK || - bl->props.fb_blank != FB_BLANK_UNBLANK || - bl->props.state & BL_CORE_FBBLANK) - brightness = 0; - if (pb->notify) brightness = pb->notify(pb->dev, brightness); diff --git a/drivers/video/backlight/qcom-wled.c b/drivers/video/backlight/qcom-wled.c index c25c31199952..3bc7800eb0a9 100644 --- a/drivers/video/backlight/qcom-wled.c +++ b/drivers/video/backlight/qcom-wled.c @@ -433,14 +433,9 @@ static int wled5_ovp_delay(struct wled *wled) static int wled_update_status(struct backlight_device *bl) { struct wled *wled = bl_get_data(bl); - u16 brightness = bl->props.brightness; + u16 brightness = backlight_get_brightness(bl); int rc = 0; - if (bl->props.power != FB_BLANK_UNBLANK || - bl->props.fb_blank != FB_BLANK_UNBLANK || - bl->props.state & BL_CORE_FBBLANK) - brightness = 0; - mutex_lock(&wled->lock); if (brightness) { rc = wled->wled_set_brightness(wled, brightness); diff --git a/drivers/video/backlight/tps65217_bl.c b/drivers/video/backlight/tps65217_bl.c index 762e3feed097..8457166f357f 100644 --- a/drivers/video/backlight/tps65217_bl.c +++ b/drivers/video/backlight/tps65217_bl.c @@ -77,15 +77,7 @@ static int tps65217_bl_update_status(struct backlight_device *bl) { struct tps65217_bl *tps65217_bl = bl_get_data(bl); int rc; - int brightness = bl->props.brightness; - - if (bl->props.state & BL_CORE_SUSPENDED) - brightness = 0; - - if ((bl->props.power != FB_BLANK_UNBLANK) || - (bl->props.fb_blank != FB_BLANK_UNBLANK)) - /* framebuffer in low power mode or blanking active */ - brightness = 0; + int brightness = backlight_get_brightness(bl); if (brightness > 0) { rc = tps65217_reg_write(tps65217_bl->tps, diff --git a/drivers/video/backlight/wm831x_bl.c b/drivers/video/backlight/wm831x_bl.c index e55977d54c15..c5aaee205bdf 100644 --- a/drivers/video/backlight/wm831x_bl.c +++ b/drivers/video/backlight/wm831x_bl.c @@ -91,18 +91,7 @@ static int wm831x_backlight_set(struct backlight_device *bl, int brightness) static int wm831x_backlight_update_status(struct backlight_device *bl) { - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK) - brightness = 0; - - if (bl->props.fb_blank != FB_BLANK_UNBLANK) - brightness = 0; - - if (bl->props.state & BL_CORE_SUSPENDED) - brightness = 0; - - return wm831x_backlight_set(bl, brightness); + return wm831x_backlight_set(bl, backlight_get_brightness(bl)); } static int wm831x_backlight_get_brightness(struct backlight_device *bl) From 0f6a3256fd810eeca9c56cccafee46359d995138 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:42 +0200 Subject: [PATCH 138/291] backlight: backlight: Drop backlight_put() There are no external users of backlight_put(). Drop it and open code the two users in backlight.c. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/backlight.c | 7 +++++-- include/linux/backlight.h | 10 ---------- 2 files changed, 5 insertions(+), 12 deletions(-) diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c index 82dc93ca859a..cba8505fef5a 100644 --- a/drivers/video/backlight/backlight.c +++ b/drivers/video/backlight/backlight.c @@ -718,7 +718,10 @@ EXPORT_SYMBOL(of_find_backlight); static void devm_backlight_release(void *data) { - backlight_put(data); + struct backlight_device *bd = data; + + if (bd) + put_device(&bd->dev); } /** @@ -746,7 +749,7 @@ struct backlight_device *devm_of_find_backlight(struct device *dev) return bd; ret = devm_add_action(dev, devm_backlight_release, bd); if (ret) { - backlight_put(bd); + put_device(&bd->dev); return ERR_PTR(ret); } return bd; diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 26e89a8033f5..64f91324c911 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -388,16 +388,6 @@ static inline int backlight_disable(struct backlight_device *bd) return backlight_update_status(bd); } -/** - * backlight_put - Drop backlight reference - * @bd: the backlight device to put - */ -static inline void backlight_put(struct backlight_device *bd) -{ - if (bd) - put_device(&bd->dev); -} - /** * backlight_is_blank - Return true if display is expected to be blank * @bd: the backlight device From b6539a11e807c531e51ff7ad9a25c3a1b6ff7340 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:43 +0200 Subject: [PATCH 139/291] backlight: backlight: Make of_find_backlight static There are no external users of of_find_backlight, as they have all changed to use the managed version. Make of_find_backlight static to prevent new external users. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/backlight.c | 18 +----------------- include/linux/backlight.h | 6 ------ 2 files changed, 1 insertion(+), 23 deletions(-) diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c index cba8505fef5a..537fe1b376ad 100644 --- a/drivers/video/backlight/backlight.c +++ b/drivers/video/backlight/backlight.c @@ -673,22 +673,7 @@ struct backlight_device *of_find_backlight_by_node(struct device_node *node) EXPORT_SYMBOL(of_find_backlight_by_node); #endif -/** - * of_find_backlight - Get backlight device - * @dev: Device - * - * This function looks for a property named 'backlight' on the DT node - * connected to @dev and looks up the backlight device. - * - * Call backlight_put() to drop the reference on the backlight device. - * - * Returns: - * A pointer to the backlight device if found. - * Error pointer -EPROBE_DEFER if the DT property is set, but no backlight - * device is found. - * NULL if there's no backlight property. - */ -struct backlight_device *of_find_backlight(struct device *dev) +static struct backlight_device *of_find_backlight(struct device *dev) { struct backlight_device *bd = NULL; struct device_node *np; @@ -714,7 +699,6 @@ struct backlight_device *of_find_backlight(struct device *dev) return bd; } -EXPORT_SYMBOL(of_find_backlight); static void devm_backlight_release(void *data) { diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 64f91324c911..614653e07e3a 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -477,14 +477,8 @@ of_find_backlight_by_node(struct device_node *node) #endif #if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE) -struct backlight_device *of_find_backlight(struct device *dev); struct backlight_device *devm_of_find_backlight(struct device *dev); #else -static inline struct backlight_device *of_find_backlight(struct device *dev) -{ - return NULL; -} - static inline struct backlight_device * devm_of_find_backlight(struct device *dev) { From 7eb99a39ef767644bbfd2b3f12f139d13e3ee8b3 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 21 Jul 2020 08:34:57 +0100 Subject: [PATCH 140/291] video: backlight: cr_bllcd: Remove unused variable 'intensity' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes the following kernel build warning: drivers/video/backlight/cr_bllcd.c: In function ‘cr_backlight_set_intensity’: drivers/video/backlight/cr_bllcd.c:62:6: warning: unused variable ‘intensity’ [-Wunused-variable] 62 | int intensity = bd->props.brightness; | ^~~~~~~~~ Cc: Jingoo Han Cc: Bartlomiej Zolnierkiewicz Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Fixes: 24d34617c24f ("backlight: cr_bllcd: Introduce gpio-backlight semantics") Reviewed-by: Sam Ravnborg Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/cr_bllcd.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/video/backlight/cr_bllcd.c b/drivers/video/backlight/cr_bllcd.c index a24d42e1ea3c..4ad0a72531fe 100644 --- a/drivers/video/backlight/cr_bllcd.c +++ b/drivers/video/backlight/cr_bllcd.c @@ -59,7 +59,6 @@ struct cr_panel { static int cr_backlight_set_intensity(struct backlight_device *bd) { - int intensity = bd->props.brightness; u32 addr = gpio_bar + CRVML_PANEL_PORT; u32 cur = inl(addr); From 2c010cc378cdd89af649119d89adee3f443bfd2f Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Thu, 16 Jul 2020 15:20:31 -0700 Subject: [PATCH 141/291] remoteproc: Move coredump functionality to a new file Move all coredump functionality to an individual file. This is being done so that the current functionality can be extended in future patchsets. Signed-off-by: Rishabh Bhatnagar Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Reviewed-by: Sibi Sankar Tested-by: Sibi Sankar Link: https://lore.kernel.org/r/1594938035-7327-2-git-send-email-rishabhb@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/Makefile | 1 + drivers/remoteproc/remoteproc_core.c | 191 --------------------- drivers/remoteproc/remoteproc_coredump.c | 204 +++++++++++++++++++++++ drivers/remoteproc/remoteproc_internal.h | 4 + 4 files changed, 209 insertions(+), 191 deletions(-) create mode 100644 drivers/remoteproc/remoteproc_coredump.c diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile index fe398f82d550..a4c1397d6367 100644 --- a/drivers/remoteproc/Makefile +++ b/drivers/remoteproc/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_REMOTEPROC) += remoteproc.o remoteproc-y := remoteproc_core.o +remoteproc-y += remoteproc_coredump.o remoteproc-y += remoteproc_debugfs.o remoteproc-y += remoteproc_sysfs.o remoteproc-y += remoteproc_virtio.o diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 6fa9f75754b3..7f0d55fceb02 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include @@ -40,7 +39,6 @@ #include #include "remoteproc_internal.h" -#include "remoteproc_elf_helpers.h" #define HIGH_BITS_MASK 0xFFFFFFFF00000000ULL @@ -1253,19 +1251,6 @@ static int rproc_alloc_registered_carveouts(struct rproc *rproc) return 0; } -/** - * rproc_coredump_cleanup() - clean up dump_segments list - * @rproc: the remote processor handle - */ -static void rproc_coredump_cleanup(struct rproc *rproc) -{ - struct rproc_dump_segment *entry, *tmp; - - list_for_each_entry_safe(entry, tmp, &rproc->dump_segments, node) { - list_del(&entry->node); - kfree(entry); - } -} /** * rproc_resource_cleanup() - clean up and free all acquired resources @@ -1641,182 +1626,6 @@ static int rproc_stop(struct rproc *rproc, bool crashed) return 0; } -/** - * rproc_coredump_add_segment() - add segment of device memory to coredump - * @rproc: handle of a remote processor - * @da: device address - * @size: size of segment - * - * Add device memory to the list of segments to be included in a coredump for - * the remoteproc. - * - * Return: 0 on success, negative errno on error. - */ -int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size) -{ - struct rproc_dump_segment *segment; - - segment = kzalloc(sizeof(*segment), GFP_KERNEL); - if (!segment) - return -ENOMEM; - - segment->da = da; - segment->size = size; - - list_add_tail(&segment->node, &rproc->dump_segments); - - return 0; -} -EXPORT_SYMBOL(rproc_coredump_add_segment); - -/** - * rproc_coredump_add_custom_segment() - add custom coredump segment - * @rproc: handle of a remote processor - * @da: device address - * @size: size of segment - * @dumpfn: custom dump function called for each segment during coredump - * @priv: private data - * - * Add device memory to the list of segments to be included in the coredump - * and associate the segment with the given custom dump function and private - * data. - * - * Return: 0 on success, negative errno on error. - */ -int rproc_coredump_add_custom_segment(struct rproc *rproc, - dma_addr_t da, size_t size, - void (*dumpfn)(struct rproc *rproc, - struct rproc_dump_segment *segment, - void *dest), - void *priv) -{ - struct rproc_dump_segment *segment; - - segment = kzalloc(sizeof(*segment), GFP_KERNEL); - if (!segment) - return -ENOMEM; - - segment->da = da; - segment->size = size; - segment->priv = priv; - segment->dump = dumpfn; - - list_add_tail(&segment->node, &rproc->dump_segments); - - return 0; -} -EXPORT_SYMBOL(rproc_coredump_add_custom_segment); - -/** - * rproc_coredump_set_elf_info() - set coredump elf information - * @rproc: handle of a remote processor - * @class: elf class for coredump elf file - * @machine: elf machine for coredump elf file - * - * Set elf information which will be used for coredump elf file. - * - * Return: 0 on success, negative errno on error. - */ -int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine) -{ - if (class != ELFCLASS64 && class != ELFCLASS32) - return -EINVAL; - - rproc->elf_class = class; - rproc->elf_machine = machine; - - return 0; -} -EXPORT_SYMBOL(rproc_coredump_set_elf_info); - -/** - * rproc_coredump() - perform coredump - * @rproc: rproc handle - * - * This function will generate an ELF header for the registered segments - * and create a devcoredump device associated with rproc. - */ -static void rproc_coredump(struct rproc *rproc) -{ - struct rproc_dump_segment *segment; - void *phdr; - void *ehdr; - size_t data_size; - size_t offset; - void *data; - void *ptr; - u8 class = rproc->elf_class; - int phnum = 0; - - if (list_empty(&rproc->dump_segments)) - return; - - if (class == ELFCLASSNONE) { - dev_err(&rproc->dev, "Elf class is not set\n"); - return; - } - - data_size = elf_size_of_hdr(class); - list_for_each_entry(segment, &rproc->dump_segments, node) { - data_size += elf_size_of_phdr(class) + segment->size; - - phnum++; - } - - data = vmalloc(data_size); - if (!data) - return; - - ehdr = data; - - memset(ehdr, 0, elf_size_of_hdr(class)); - /* e_ident field is common for both elf32 and elf64 */ - elf_hdr_init_ident(ehdr, class); - - elf_hdr_set_e_type(class, ehdr, ET_CORE); - elf_hdr_set_e_machine(class, ehdr, rproc->elf_machine); - elf_hdr_set_e_version(class, ehdr, EV_CURRENT); - elf_hdr_set_e_entry(class, ehdr, rproc->bootaddr); - elf_hdr_set_e_phoff(class, ehdr, elf_size_of_hdr(class)); - elf_hdr_set_e_ehsize(class, ehdr, elf_size_of_hdr(class)); - elf_hdr_set_e_phentsize(class, ehdr, elf_size_of_phdr(class)); - elf_hdr_set_e_phnum(class, ehdr, phnum); - - phdr = data + elf_hdr_get_e_phoff(class, ehdr); - offset = elf_hdr_get_e_phoff(class, ehdr); - offset += elf_size_of_phdr(class) * elf_hdr_get_e_phnum(class, ehdr); - - list_for_each_entry(segment, &rproc->dump_segments, node) { - memset(phdr, 0, elf_size_of_phdr(class)); - elf_phdr_set_p_type(class, phdr, PT_LOAD); - elf_phdr_set_p_offset(class, phdr, offset); - elf_phdr_set_p_vaddr(class, phdr, segment->da); - elf_phdr_set_p_paddr(class, phdr, segment->da); - elf_phdr_set_p_filesz(class, phdr, segment->size); - elf_phdr_set_p_memsz(class, phdr, segment->size); - elf_phdr_set_p_flags(class, phdr, PF_R | PF_W | PF_X); - elf_phdr_set_p_align(class, phdr, 0); - - if (segment->dump) { - segment->dump(rproc, segment, data + offset); - } else { - ptr = rproc_da_to_va(rproc, segment->da, segment->size); - if (!ptr) { - dev_err(&rproc->dev, - "invalid coredump segment (%pad, %zu)\n", - &segment->da, segment->size); - memset(data + offset, 0xff, segment->size); - } else { - memcpy(data + offset, ptr, segment->size); - } - } - - offset += elf_phdr_get_p_filesz(class, phdr); - phdr += elf_size_of_phdr(class); - } - - dev_coredumpv(&rproc->dev, data, data_size, GFP_KERNEL); -} /** * rproc_trigger_recovery() - recover a remoteproc diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c new file mode 100644 index 000000000000..ded02442374a --- /dev/null +++ b/drivers/remoteproc/remoteproc_coredump.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Coredump functionality for Remoteproc framework. + * + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + */ + +#include +#include +#include +#include +#include "remoteproc_internal.h" +#include "remoteproc_elf_helpers.h" + +/** + * rproc_coredump_cleanup() - clean up dump_segments list + * @rproc: the remote processor handle + */ +void rproc_coredump_cleanup(struct rproc *rproc) +{ + struct rproc_dump_segment *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &rproc->dump_segments, node) { + list_del(&entry->node); + kfree(entry); + } +} + +/** + * rproc_coredump_add_segment() - add segment of device memory to coredump + * @rproc: handle of a remote processor + * @da: device address + * @size: size of segment + * + * Add device memory to the list of segments to be included in a coredump for + * the remoteproc. + * + * Return: 0 on success, negative errno on error. + */ +int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size) +{ + struct rproc_dump_segment *segment; + + segment = kzalloc(sizeof(*segment), GFP_KERNEL); + if (!segment) + return -ENOMEM; + + segment->da = da; + segment->size = size; + + list_add_tail(&segment->node, &rproc->dump_segments); + + return 0; +} +EXPORT_SYMBOL(rproc_coredump_add_segment); + +/** + * rproc_coredump_add_custom_segment() - add custom coredump segment + * @rproc: handle of a remote processor + * @da: device address + * @size: size of segment + * @dumpfn: custom dump function called for each segment during coredump + * @priv: private data + * + * Add device memory to the list of segments to be included in the coredump + * and associate the segment with the given custom dump function and private + * data. + * + * Return: 0 on success, negative errno on error. + */ +int rproc_coredump_add_custom_segment(struct rproc *rproc, + dma_addr_t da, size_t size, + void (*dumpfn)(struct rproc *rproc, + struct rproc_dump_segment *segment, + void *dest), + void *priv) +{ + struct rproc_dump_segment *segment; + + segment = kzalloc(sizeof(*segment), GFP_KERNEL); + if (!segment) + return -ENOMEM; + + segment->da = da; + segment->size = size; + segment->priv = priv; + segment->dump = dumpfn; + + list_add_tail(&segment->node, &rproc->dump_segments); + + return 0; +} +EXPORT_SYMBOL(rproc_coredump_add_custom_segment); + +/** + * rproc_coredump_set_elf_info() - set coredump elf information + * @rproc: handle of a remote processor + * @class: elf class for coredump elf file + * @machine: elf machine for coredump elf file + * + * Set elf information which will be used for coredump elf file. + * + * Return: 0 on success, negative errno on error. + */ +int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine) +{ + if (class != ELFCLASS64 && class != ELFCLASS32) + return -EINVAL; + + rproc->elf_class = class; + rproc->elf_machine = machine; + + return 0; +} +EXPORT_SYMBOL(rproc_coredump_set_elf_info); + +/** + * rproc_coredump() - perform coredump + * @rproc: rproc handle + * + * This function will generate an ELF header for the registered segments + * and create a devcoredump device associated with rproc. + */ +void rproc_coredump(struct rproc *rproc) +{ + struct rproc_dump_segment *segment; + void *phdr; + void *ehdr; + size_t data_size; + size_t offset; + void *data; + void *ptr; + u8 class = rproc->elf_class; + int phnum = 0; + + if (list_empty(&rproc->dump_segments)) + return; + + if (class == ELFCLASSNONE) { + dev_err(&rproc->dev, "Elf class is not set\n"); + return; + } + + data_size = elf_size_of_hdr(class); + list_for_each_entry(segment, &rproc->dump_segments, node) { + data_size += elf_size_of_phdr(class) + segment->size; + + phnum++; + } + + data = vmalloc(data_size); + if (!data) + return; + + ehdr = data; + + memset(ehdr, 0, elf_size_of_hdr(class)); + /* e_ident field is common for both elf32 and elf64 */ + elf_hdr_init_ident(ehdr, class); + + elf_hdr_set_e_type(class, ehdr, ET_CORE); + elf_hdr_set_e_machine(class, ehdr, rproc->elf_machine); + elf_hdr_set_e_version(class, ehdr, EV_CURRENT); + elf_hdr_set_e_entry(class, ehdr, rproc->bootaddr); + elf_hdr_set_e_phoff(class, ehdr, elf_size_of_hdr(class)); + elf_hdr_set_e_ehsize(class, ehdr, elf_size_of_hdr(class)); + elf_hdr_set_e_phentsize(class, ehdr, elf_size_of_phdr(class)); + elf_hdr_set_e_phnum(class, ehdr, phnum); + + phdr = data + elf_hdr_get_e_phoff(class, ehdr); + offset = elf_hdr_get_e_phoff(class, ehdr); + offset += elf_size_of_phdr(class) * elf_hdr_get_e_phnum(class, ehdr); + + list_for_each_entry(segment, &rproc->dump_segments, node) { + memset(phdr, 0, elf_size_of_phdr(class)); + elf_phdr_set_p_type(class, phdr, PT_LOAD); + elf_phdr_set_p_offset(class, phdr, offset); + elf_phdr_set_p_vaddr(class, phdr, segment->da); + elf_phdr_set_p_paddr(class, phdr, segment->da); + elf_phdr_set_p_filesz(class, phdr, segment->size); + elf_phdr_set_p_memsz(class, phdr, segment->size); + elf_phdr_set_p_flags(class, phdr, PF_R | PF_W | PF_X); + elf_phdr_set_p_align(class, phdr, 0); + + if (segment->dump) { + segment->dump(rproc, segment, data + offset); + } else { + ptr = rproc_da_to_va(rproc, segment->da, segment->size); + if (!ptr) { + dev_err(&rproc->dev, + "invalid coredump segment (%pad, %zu)\n", + &segment->da, segment->size); + memset(data + offset, 0xff, segment->size); + } else { + memcpy(data + offset, ptr, segment->size); + } + } + + offset += elf_phdr_get_p_filesz(class, phdr); + phdr += elf_size_of_phdr(class); + } + + dev_coredumpv(&rproc->dev, data, data_size, GFP_KERNEL); +} diff --git a/drivers/remoteproc/remoteproc_internal.h b/drivers/remoteproc/remoteproc_internal.h index fc710866f8ce..26fe012e6803 100644 --- a/drivers/remoteproc/remoteproc_internal.h +++ b/drivers/remoteproc/remoteproc_internal.h @@ -47,6 +47,10 @@ extern struct class rproc_class; int rproc_init_sysfs(void); void rproc_exit_sysfs(void); +/* from remoteproc_coredump.c */ +void rproc_coredump_cleanup(struct rproc *rproc); +void rproc_coredump(struct rproc *rproc); + void rproc_free_vring(struct rproc_vring *rvring); int rproc_alloc_vring(struct rproc_vdev *rvdev, int i); From 7ac516d39dd35450596a2dbb9dedea2c85eab1ea Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Thu, 16 Jul 2020 15:20:32 -0700 Subject: [PATCH 142/291] remoteproc: qcom_q6v5_mss: Replace mask based tracking with size In order to land inline coredump support for mss, the dump_segment function would need to support granularities less than the segment size. This is achieved by replacing mask based tracking with size. Reviewed-by: Bjorn Andersson Signed-off-by: Sibi Sankar Signed-off-by: Rishabh Bhatnagar Link: https://lore.kernel.org/r/1594938035-7327-3-git-send-email-rishabhb@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_q6v5_mss.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index 1fd270a900f4..1ee809b772ff 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -180,8 +180,8 @@ struct q6v5 { bool running; bool dump_mba_loaded; - unsigned long dump_segment_mask; - unsigned long dump_complete_mask; + size_t current_dump_size; + size_t total_dump_size; phys_addr_t mba_phys; void *mba_region; @@ -1206,7 +1206,6 @@ static void qcom_q6v5_dump_segment(struct rproc *rproc, { int ret = 0; struct q6v5 *qproc = rproc->priv; - unsigned long mask = BIT((unsigned long)segment->priv); int offset = segment->da - qproc->mpss_reloc; void *ptr = NULL; @@ -1232,10 +1231,10 @@ static void qcom_q6v5_dump_segment(struct rproc *rproc, memset(dest, 0xff, segment->size); } - qproc->dump_segment_mask |= mask; + qproc->current_dump_size += segment->size; /* Reclaim mba after copying segments */ - if (qproc->dump_segment_mask == qproc->dump_complete_mask) { + if (qproc->current_dump_size == qproc->total_dump_size) { if (qproc->dump_mba_loaded) { /* Try to reset ownership back to Q6 */ q6v5_xfer_mem_ownership(qproc, &qproc->mpss_perm, @@ -1277,7 +1276,7 @@ static int q6v5_start(struct rproc *rproc) "Failed to reclaim mba buffer system may become unstable\n"); /* Reset Dump Segment Mask */ - qproc->dump_segment_mask = 0; + qproc->current_dump_size = 0; qproc->running = true; return 0; @@ -1326,7 +1325,7 @@ static int qcom_q6v5_register_dump_segments(struct rproc *rproc, ehdr = (struct elf32_hdr *)fw->data; phdrs = (struct elf32_phdr *)(ehdr + 1); - qproc->dump_complete_mask = 0; + qproc->total_dump_size = 0; for (i = 0; i < ehdr->e_phnum; i++) { phdr = &phdrs[i]; @@ -1337,11 +1336,11 @@ static int qcom_q6v5_register_dump_segments(struct rproc *rproc, ret = rproc_coredump_add_custom_segment(rproc, phdr->p_paddr, phdr->p_memsz, qcom_q6v5_dump_segment, - (void *)i); + NULL); if (ret) break; - qproc->dump_complete_mask |= BIT(i); + qproc->total_dump_size += phdr->p_memsz; } release_firmware(fw); From 76abf9cea6c8215ea45b9359f11f0e30127c544a Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Thu, 16 Jul 2020 15:20:33 -0700 Subject: [PATCH 143/291] remoteproc: Pass size and offset as arguments to segment dump function Change the segment dump API signature to include size and offset arguments. Refactor the qcom_q6v5_mss driver to use these arguments while copying the segment. Doing this lays the ground work for "inline" coredump functionality being added in the next patch. Tested-by: Sibi Sankar Reviewed-by: Bjorn Andersson Reviewed-by: Sibi Sankar Reviewed-by: Mathieu Poirier Signed-off-by: Rishabh Bhatnagar Link: https://lore.kernel.org/r/1594938035-7327-4-git-send-email-rishabhb@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_q6v5_mss.c | 10 +++++----- drivers/remoteproc/remoteproc_coredump.c | 5 +++-- include/linux/remoteproc.h | 5 +++-- 3 files changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index 1ee809b772ff..a3c412a3f143 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -1202,7 +1202,7 @@ static int q6v5_mpss_load(struct q6v5 *qproc) static void qcom_q6v5_dump_segment(struct rproc *rproc, struct rproc_dump_segment *segment, - void *dest) + void *dest, size_t cp_offset, size_t size) { int ret = 0; struct q6v5 *qproc = rproc->priv; @@ -1222,16 +1222,16 @@ static void qcom_q6v5_dump_segment(struct rproc *rproc, } if (!ret) - ptr = ioremap_wc(qproc->mpss_phys + offset, segment->size); + ptr = ioremap_wc(qproc->mpss_phys + offset + cp_offset, size); if (ptr) { - memcpy(dest, ptr, segment->size); + memcpy(dest, ptr, size); iounmap(ptr); } else { - memset(dest, 0xff, segment->size); + memset(dest, 0xff, size); } - qproc->current_dump_size += segment->size; + qproc->current_dump_size += size; /* Reclaim mba after copying segments */ if (qproc->current_dump_size == qproc->total_dump_size) { diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c index ded02442374a..390f563ec019 100644 --- a/drivers/remoteproc/remoteproc_coredump.c +++ b/drivers/remoteproc/remoteproc_coredump.c @@ -72,7 +72,8 @@ int rproc_coredump_add_custom_segment(struct rproc *rproc, dma_addr_t da, size_t size, void (*dumpfn)(struct rproc *rproc, struct rproc_dump_segment *segment, - void *dest), + void *dest, size_t offset, + size_t size), void *priv) { struct rproc_dump_segment *segment; @@ -183,7 +184,7 @@ void rproc_coredump(struct rproc *rproc) elf_phdr_set_p_align(class, phdr, 0); if (segment->dump) { - segment->dump(rproc, segment, data + offset); + segment->dump(rproc, segment, data + offset, 0, segment->size); } else { ptr = rproc_da_to_va(rproc, segment->da, segment->size); if (!ptr) { diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 7c0567029f7c..5dab13b6baae 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -456,7 +456,7 @@ struct rproc_dump_segment { void *priv; void (*dump)(struct rproc *rproc, struct rproc_dump_segment *segment, - void *dest); + void *dest, size_t offset, size_t size); loff_t offset; }; @@ -638,7 +638,8 @@ int rproc_coredump_add_custom_segment(struct rproc *rproc, dma_addr_t da, size_t size, void (*dumpfn)(struct rproc *rproc, struct rproc_dump_segment *segment, - void *dest), + void *dest, size_t offset, + size_t size), void *priv); int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine); From c97319881c9116dc7c56dd30115567b4078c4ba6 Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Thu, 16 Jul 2020 15:20:34 -0700 Subject: [PATCH 144/291] remoteproc: Add inline coredump functionality The current coredump implementation uses vmalloc area to copy all the segments. But this might put strain on low memory targets as the firmware size sometimes is in tens of MBs. The situation becomes worse if there are multiple remote processors undergoing recovery at the same time. This patch adds inline coredump functionality that avoids extra memory usage. This requires recovery to be halted until data is read by userspace and free function is called. Reviewed-by: Bjorn Andersson Reviewed-by: Sibi Sankar Reviewed-by: Mathieu Poirier Signed-off-by: Rishabh Bhatnagar Tested-by: Sibi Sankar Link: https://lore.kernel.org/r/1594938035-7327-5-git-send-email-rishabhb@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_coredump.c | 156 ++++++++++++++++++++--- include/linux/remoteproc.h | 16 +++ 2 files changed, 154 insertions(+), 18 deletions(-) diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c index 390f563ec019..bb15a29038e8 100644 --- a/drivers/remoteproc/remoteproc_coredump.c +++ b/drivers/remoteproc/remoteproc_coredump.c @@ -5,6 +5,7 @@ * Copyright (c) 2020, The Linux Foundation. All rights reserved. */ +#include #include #include #include @@ -12,6 +13,12 @@ #include "remoteproc_internal.h" #include "remoteproc_elf_helpers.h" +struct rproc_coredump_state { + struct rproc *rproc; + void *header; + struct completion dump_done; +}; + /** * rproc_coredump_cleanup() - clean up dump_segments list * @rproc: the remote processor handle @@ -115,12 +122,110 @@ int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine) } EXPORT_SYMBOL(rproc_coredump_set_elf_info); +static void rproc_coredump_free(void *data) +{ + struct rproc_coredump_state *dump_state = data; + + vfree(dump_state->header); + complete(&dump_state->dump_done); +} + +static void *rproc_coredump_find_segment(loff_t user_offset, + struct list_head *segments, + size_t *data_left) +{ + struct rproc_dump_segment *segment; + + list_for_each_entry(segment, segments, node) { + if (user_offset < segment->size) { + *data_left = segment->size - user_offset; + return segment; + } + user_offset -= segment->size; + } + + *data_left = 0; + return NULL; +} + +static void rproc_copy_segment(struct rproc *rproc, void *dest, + struct rproc_dump_segment *segment, + size_t offset, size_t size) +{ + void *ptr; + + if (segment->dump) { + segment->dump(rproc, segment, dest, offset, size); + } else { + ptr = rproc_da_to_va(rproc, segment->da + offset, size); + if (!ptr) { + dev_err(&rproc->dev, + "invalid copy request for segment %pad with offset %zu and size %zu)\n", + &segment->da, offset, size); + memset(dest, 0xff, size); + } else { + memcpy(dest, ptr, size); + } + } +} + +static ssize_t rproc_coredump_read(char *buffer, loff_t offset, size_t count, + void *data, size_t header_sz) +{ + size_t seg_data, bytes_left = count; + ssize_t copy_sz; + struct rproc_dump_segment *seg; + struct rproc_coredump_state *dump_state = data; + struct rproc *rproc = dump_state->rproc; + void *elfcore = dump_state->header; + + /* Copy the vmalloc'ed header first. */ + if (offset < header_sz) { + copy_sz = memory_read_from_buffer(buffer, count, &offset, + elfcore, header_sz); + + return copy_sz; + } + + /* + * Find out the segment memory chunk to be copied based on offset. + * Keep copying data until count bytes are read. + */ + while (bytes_left) { + seg = rproc_coredump_find_segment(offset - header_sz, + &rproc->dump_segments, + &seg_data); + /* EOF check */ + if (!seg) { + dev_info(&rproc->dev, "Ramdump done, %lld bytes read", + offset); + break; + } + + copy_sz = min_t(size_t, bytes_left, seg_data); + + rproc_copy_segment(rproc, buffer, seg, seg->size - seg_data, + copy_sz); + + offset += copy_sz; + buffer += copy_sz; + bytes_left -= copy_sz; + } + + return count - bytes_left; +} + /** * rproc_coredump() - perform coredump * @rproc: rproc handle * * This function will generate an ELF header for the registered segments - * and create a devcoredump device associated with rproc. + * and create a devcoredump device associated with rproc. Based on the + * coredump configuration this function will directly copy the segments + * from device memory to userspace or copy segments from device memory to + * a separate buffer, which can then be read by userspace. + * The first approach avoids using extra vmalloc memory. But it will stall + * recovery flow until dump is read by userspace. */ void rproc_coredump(struct rproc *rproc) { @@ -130,11 +235,13 @@ void rproc_coredump(struct rproc *rproc) size_t data_size; size_t offset; void *data; - void *ptr; u8 class = rproc->elf_class; int phnum = 0; + struct rproc_coredump_state dump_state; + enum rproc_dump_mechanism dump_conf = rproc->dump_conf; - if (list_empty(&rproc->dump_segments)) + if (list_empty(&rproc->dump_segments) || + dump_conf == RPROC_COREDUMP_DISABLED) return; if (class == ELFCLASSNONE) { @@ -144,7 +251,14 @@ void rproc_coredump(struct rproc *rproc) data_size = elf_size_of_hdr(class); list_for_each_entry(segment, &rproc->dump_segments, node) { - data_size += elf_size_of_phdr(class) + segment->size; + /* + * For default configuration buffer includes headers & segments. + * For inline dump buffer just includes headers as segments are + * directly read from device memory. + */ + data_size += elf_size_of_phdr(class); + if (dump_conf == RPROC_COREDUMP_DEFAULT) + data_size += segment->size; phnum++; } @@ -183,23 +297,29 @@ void rproc_coredump(struct rproc *rproc) elf_phdr_set_p_flags(class, phdr, PF_R | PF_W | PF_X); elf_phdr_set_p_align(class, phdr, 0); - if (segment->dump) { - segment->dump(rproc, segment, data + offset, 0, segment->size); - } else { - ptr = rproc_da_to_va(rproc, segment->da, segment->size); - if (!ptr) { - dev_err(&rproc->dev, - "invalid coredump segment (%pad, %zu)\n", - &segment->da, segment->size); - memset(data + offset, 0xff, segment->size); - } else { - memcpy(data + offset, ptr, segment->size); - } - } + if (dump_conf == RPROC_COREDUMP_DEFAULT) + rproc_copy_segment(rproc, data + offset, segment, 0, + segment->size); offset += elf_phdr_get_p_filesz(class, phdr); phdr += elf_size_of_phdr(class); } + if (dump_conf == RPROC_COREDUMP_DEFAULT) { + dev_coredumpv(&rproc->dev, data, data_size, GFP_KERNEL); + return; + } - dev_coredumpv(&rproc->dev, data, data_size, GFP_KERNEL); + /* Initialize the dump state struct to be used by rproc_coredump_read */ + dump_state.rproc = rproc; + dump_state.header = data; + init_completion(&dump_state.dump_done); + + dev_coredumpm(&rproc->dev, NULL, &dump_state, data_size, GFP_KERNEL, + rproc_coredump_read, rproc_coredump_free); + + /* + * Wait until the dump is read and free is called. Data is freed + * by devcoredump framework automatically after 5 minutes. + */ + wait_for_completion(&dump_state.dump_done); } diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 5dab13b6baae..0e8d2ff575b4 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -439,6 +439,20 @@ enum rproc_crash_type { RPROC_FATAL_ERROR, }; +/** + * enum rproc_dump_mechanism - Coredump options for core + * @RPROC_COREDUMP_DEFAULT: Copy dump to separate buffer and carry on with + recovery + * @RPROC_COREDUMP_INLINE: Read segments directly from device memory. Stall + recovery until all segments are read + * @RPROC_COREDUMP_DISABLED: Don't perform any dump + */ +enum rproc_dump_mechanism { + RPROC_COREDUMP_DEFAULT, + RPROC_COREDUMP_INLINE, + RPROC_COREDUMP_DISABLED, +}; + /** * struct rproc_dump_segment - segment info from ELF header * @node: list node related to the rproc segment list @@ -471,6 +485,7 @@ struct rproc_dump_segment { * @dev: virtual device for refcounting and common remoteproc behavior * @power: refcount of users who need this rproc powered up * @state: state of the device + * @dump_conf: Currently selected coredump configuration * @lock: lock which protects concurrent manipulations of the rproc * @dbg_dir: debugfs directory of this rproc device * @traces: list of trace buffers @@ -505,6 +520,7 @@ struct rproc { struct device dev; atomic_t power; unsigned int state; + enum rproc_dump_mechanism dump_conf; struct mutex lock; struct dentry *dbg_dir; struct list_head traces; From 3afdc59e4390487f04f2435b7e8a6289984e0a1e Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Thu, 16 Jul 2020 15:20:35 -0700 Subject: [PATCH 145/291] remoteproc: Add coredump debugfs entry Add coredump debugfs entry to configure the type of dump that will be collected during recovery. User can select between default or inline coredump functionality. Also coredump collection can be disabled through this interface. This functionality can be configured differently for different remote processors. Signed-off-by: Rishabh Bhatnagar Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Tested-by: Sibi Sankar Reviewed-by: Sibi Sankar Link: https://lore.kernel.org/r/1594938035-7327-6-git-send-email-rishabhb@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_debugfs.c | 90 +++++++++++++++++++++++++ 1 file changed, 90 insertions(+) diff --git a/drivers/remoteproc/remoteproc_debugfs.c b/drivers/remoteproc/remoteproc_debugfs.c index 732770e92b99..2e3b3e22e1d0 100644 --- a/drivers/remoteproc/remoteproc_debugfs.c +++ b/drivers/remoteproc/remoteproc_debugfs.c @@ -27,6 +27,94 @@ /* remoteproc debugfs parent dir */ static struct dentry *rproc_dbg; +/* + * A coredump-configuration-to-string lookup table, for exposing a + * human readable configuration via debugfs. Always keep in sync with + * enum rproc_coredump_mechanism + */ +static const char * const rproc_coredump_str[] = { + [RPROC_COREDUMP_DEFAULT] = "default", + [RPROC_COREDUMP_INLINE] = "inline", + [RPROC_COREDUMP_DISABLED] = "disabled", +}; + +/* Expose the current coredump configuration via debugfs */ +static ssize_t rproc_coredump_read(struct file *filp, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct rproc *rproc = filp->private_data; + char buf[20]; + int len; + + len = scnprintf(buf, sizeof(buf), "%s\n", + rproc_coredump_str[rproc->dump_conf]); + + return simple_read_from_buffer(userbuf, count, ppos, buf, len); +} + +/* + * By writing to the 'coredump' debugfs entry, we control the behavior of the + * coredump mechanism dynamically. The default value of this entry is "default". + * + * The 'coredump' debugfs entry supports these commands: + * + * default: This is the default coredump mechanism. When the remoteproc + * crashes the entire coredump will be copied to a separate buffer + * and exposed to userspace. + * + * inline: The coredump will not be copied to a separate buffer and the + * recovery process will have to wait until data is read by + * userspace. But this avoid usage of extra memory. + * + * disabled: This will disable coredump. Recovery will proceed without + * collecting any dump. + */ +static ssize_t rproc_coredump_write(struct file *filp, + const char __user *user_buf, size_t count, + loff_t *ppos) +{ + struct rproc *rproc = filp->private_data; + int ret, err = 0; + char buf[20]; + + if (count > sizeof(buf)) + return -EINVAL; + + ret = copy_from_user(buf, user_buf, count); + if (ret) + return -EFAULT; + + /* remove end of line */ + if (buf[count - 1] == '\n') + buf[count - 1] = '\0'; + + if (rproc->state == RPROC_CRASHED) { + dev_err(&rproc->dev, "can't change coredump configuration\n"); + err = -EBUSY; + goto out; + } + + if (!strncmp(buf, "disable", count)) { + rproc->dump_conf = RPROC_COREDUMP_DISABLED; + } else if (!strncmp(buf, "inline", count)) { + rproc->dump_conf = RPROC_COREDUMP_INLINE; + } else if (!strncmp(buf, "default", count)) { + rproc->dump_conf = RPROC_COREDUMP_DEFAULT; + } else { + dev_err(&rproc->dev, "Invalid coredump configuration\n"); + err = -EINVAL; + } +out: + return err ? err : count; +} + +static const struct file_operations rproc_coredump_fops = { + .read = rproc_coredump_read, + .write = rproc_coredump_write, + .open = simple_open, + .llseek = generic_file_llseek, +}; + /* * Some remote processors may support dumping trace logs into a shared * memory buffer. We expose this trace buffer using debugfs, so users @@ -337,6 +425,8 @@ void rproc_create_debug_dir(struct rproc *rproc) rproc, &rproc_rsc_table_fops); debugfs_create_file("carveout_memories", 0400, rproc->dbg_dir, rproc, &rproc_carveouts_fops); + debugfs_create_file("coredump", 0600, rproc->dbg_dir, + rproc, &rproc_coredump_fops); } void __init rproc_init_debugfs(void) From 111d1089700cdb752681ef44f54ab6137736f5c2 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Tue, 21 Jul 2020 10:56:38 +0200 Subject: [PATCH 146/291] rpmsg: virtio: add endianness conversions According to the VirtIO 1.0 spec data, sent over virtual queues must be in little-endian format. Update the RPMsg VirtIO implementation to enforce that but let legacy configurations continue use native endianness. Acked-by: Michael S. Tsirkin Signed-off-by: Guennadi Liakhovetski Reviewed-by: Mathieu Poirier Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200721085638.GA3815@ubuntu Signed-off-by: Bjorn Andersson --- drivers/rpmsg/virtio_rpmsg_bus.c | 63 +++++++++++++++++--------------- 1 file changed, 34 insertions(+), 29 deletions(-) diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 07d4f3374098..9006fc7f73d0 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -84,11 +85,11 @@ struct virtproc_info { * Every message sent(/received) on the rpmsg bus begins with this header. */ struct rpmsg_hdr { - u32 src; - u32 dst; - u32 reserved; - u16 len; - u16 flags; + __virtio32 src; + __virtio32 dst; + __virtio32 reserved; + __virtio16 len; + __virtio16 flags; u8 data[]; } __packed; @@ -106,8 +107,8 @@ struct rpmsg_hdr { */ struct rpmsg_ns_msg { char name[RPMSG_NAME_SIZE]; - u32 addr; - u32 flags; + __virtio32 addr; + __virtio32 flags; } __packed; /** @@ -335,8 +336,8 @@ static int virtio_rpmsg_announce_create(struct rpmsg_device *rpdev) struct rpmsg_ns_msg nsm; strncpy(nsm.name, rpdev->id.name, RPMSG_NAME_SIZE); - nsm.addr = rpdev->ept->addr; - nsm.flags = RPMSG_NS_CREATE; + nsm.addr = cpu_to_virtio32(vrp->vdev, rpdev->ept->addr); + nsm.flags = cpu_to_virtio32(vrp->vdev, RPMSG_NS_CREATE); err = rpmsg_sendto(rpdev->ept, &nsm, sizeof(nsm), RPMSG_NS_ADDR); if (err) @@ -359,8 +360,8 @@ static int virtio_rpmsg_announce_destroy(struct rpmsg_device *rpdev) struct rpmsg_ns_msg nsm; strncpy(nsm.name, rpdev->id.name, RPMSG_NAME_SIZE); - nsm.addr = rpdev->ept->addr; - nsm.flags = RPMSG_NS_DESTROY; + nsm.addr = cpu_to_virtio32(vrp->vdev, rpdev->ept->addr); + nsm.flags = cpu_to_virtio32(vrp->vdev, RPMSG_NS_DESTROY); err = rpmsg_sendto(rpdev->ept, &nsm, sizeof(nsm), RPMSG_NS_ADDR); if (err) @@ -612,18 +613,18 @@ static int rpmsg_send_offchannel_raw(struct rpmsg_device *rpdev, } } - msg->len = len; + msg->len = cpu_to_virtio16(vrp->vdev, len); msg->flags = 0; - msg->src = src; - msg->dst = dst; + msg->src = cpu_to_virtio32(vrp->vdev, src); + msg->dst = cpu_to_virtio32(vrp->vdev, dst); msg->reserved = 0; memcpy(msg->data, data, len); dev_dbg(dev, "TX From 0x%x, To 0x%x, Len %d, Flags %d, Reserved %d\n", - msg->src, msg->dst, msg->len, msg->flags, msg->reserved); + src, dst, len, msg->flags, msg->reserved); #if defined(CONFIG_DYNAMIC_DEBUG) dynamic_hex_dump("rpmsg_virtio TX: ", DUMP_PREFIX_NONE, 16, 1, - msg, sizeof(*msg) + msg->len, true); + msg, sizeof(*msg) + len, true); #endif rpmsg_sg_init(&sg, msg, sizeof(*msg) + len); @@ -704,13 +705,17 @@ static int rpmsg_recv_single(struct virtproc_info *vrp, struct device *dev, { struct rpmsg_endpoint *ept; struct scatterlist sg; + unsigned int msg_len = virtio16_to_cpu(vrp->vdev, msg->len); int err; dev_dbg(dev, "From: 0x%x, To: 0x%x, Len: %d, Flags: %d, Reserved: %d\n", - msg->src, msg->dst, msg->len, msg->flags, msg->reserved); + virtio32_to_cpu(vrp->vdev, msg->src), + virtio32_to_cpu(vrp->vdev, msg->dst), msg_len, + virtio16_to_cpu(vrp->vdev, msg->flags), + virtio32_to_cpu(vrp->vdev, msg->reserved)); #if defined(CONFIG_DYNAMIC_DEBUG) dynamic_hex_dump("rpmsg_virtio RX: ", DUMP_PREFIX_NONE, 16, 1, - msg, sizeof(*msg) + msg->len, true); + msg, sizeof(*msg) + msg_len, true); #endif /* @@ -718,15 +723,15 @@ static int rpmsg_recv_single(struct virtproc_info *vrp, struct device *dev, * the reported payload length. */ if (len > vrp->buf_size || - msg->len > (len - sizeof(struct rpmsg_hdr))) { - dev_warn(dev, "inbound msg too big: (%d, %d)\n", len, msg->len); + msg_len > (len - sizeof(struct rpmsg_hdr))) { + dev_warn(dev, "inbound msg too big: (%d, %d)\n", len, msg_len); return -EINVAL; } /* use the dst addr to fetch the callback of the appropriate user */ mutex_lock(&vrp->endpoints_lock); - ept = idr_find(&vrp->endpoints, msg->dst); + ept = idr_find(&vrp->endpoints, virtio32_to_cpu(vrp->vdev, msg->dst)); /* let's make sure no one deallocates ept while we use it */ if (ept) @@ -739,8 +744,8 @@ static int rpmsg_recv_single(struct virtproc_info *vrp, struct device *dev, mutex_lock(&ept->cb_lock); if (ept->cb) - ept->cb(ept->rpdev, msg->data, msg->len, ept->priv, - msg->src); + ept->cb(ept->rpdev, msg->data, msg_len, ept->priv, + virtio32_to_cpu(vrp->vdev, msg->src)); mutex_unlock(&ept->cb_lock); @@ -846,15 +851,15 @@ static int rpmsg_ns_cb(struct rpmsg_device *rpdev, void *data, int len, /* don't trust the remote processor for null terminating the name */ msg->name[RPMSG_NAME_SIZE - 1] = '\0'; - dev_info(dev, "%sing channel %s addr 0x%x\n", - msg->flags & RPMSG_NS_DESTROY ? "destroy" : "creat", - msg->name, msg->addr); - strncpy(chinfo.name, msg->name, sizeof(chinfo.name)); chinfo.src = RPMSG_ADDR_ANY; - chinfo.dst = msg->addr; + chinfo.dst = virtio32_to_cpu(vrp->vdev, msg->addr); - if (msg->flags & RPMSG_NS_DESTROY) { + dev_info(dev, "%sing channel %s addr 0x%x\n", + virtio32_to_cpu(vrp->vdev, msg->flags) & RPMSG_NS_DESTROY ? + "destroy" : "creat", msg->name, chinfo.dst); + + if (virtio32_to_cpu(vrp->vdev, msg->flags) & RPMSG_NS_DESTROY) { ret = rpmsg_unregister_device(&vrp->vdev->dev, &chinfo); if (ret) dev_err(dev, "rpmsg_destroy_channel failed: %d\n", ret); From 318130cc9362570f3e9587fab54482683aacbc8f Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Tue, 21 Jul 2020 16:59:35 +0530 Subject: [PATCH 147/291] remoteproc: qcom_q6v5_mss: Add MBA log extraction support On SC7180 the MBA firmware stores the bootup text logs in a 4K segment at the beginning of the MBA region. Add support to extract the logs which will be useful to debug mba boot/authentication issues. Reviewed-by: Bjorn Andersson Signed-off-by: Sibi Sankar Link: https://lore.kernel.org/r/20200721112935.25716-3-sibis@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_q6v5_mss.c | 38 +++++++++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index a3c412a3f143..03d7f3d702b3 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -36,6 +37,8 @@ #define MPSS_CRASH_REASON_SMEM 421 +#define MBA_LOG_SIZE SZ_4K + /* RMB Status Register Values */ #define RMB_PBL_SUCCESS 0x1 @@ -138,6 +141,7 @@ struct rproc_hexagon_res { int version; bool need_mem_protection; bool has_alt_reset; + bool has_mba_logs; bool has_spare_reg; }; @@ -198,6 +202,7 @@ struct q6v5 { struct qcom_sysmon *sysmon; bool need_mem_protection; bool has_alt_reset; + bool has_mba_logs; bool has_spare_reg; int mpss_perm; int mba_perm; @@ -509,6 +514,26 @@ static int q6v5_rmb_mba_wait(struct q6v5 *qproc, u32 status, int ms) return val; } +static void q6v5_dump_mba_logs(struct q6v5 *qproc) +{ + struct rproc *rproc = qproc->rproc; + void *data; + + if (!qproc->has_mba_logs) + return; + + if (q6v5_xfer_mem_ownership(qproc, &qproc->mba_perm, true, false, qproc->mba_phys, + qproc->mba_size)) + return; + + data = vmalloc(MBA_LOG_SIZE); + if (!data) + return; + + memcpy(data, qproc->mba_region, MBA_LOG_SIZE); + dev_coredumpv(&rproc->dev, data, MBA_LOG_SIZE, GFP_KERNEL); +} + static int q6v5proc_reset(struct q6v5 *qproc) { u32 val; @@ -829,6 +854,7 @@ static int q6v5_mba_load(struct q6v5 *qproc) { int ret; int xfermemop_ret; + bool mba_load_err = false; qcom_q6v5_prepare(&qproc->q6v5); @@ -918,7 +944,7 @@ static int q6v5_mba_load(struct q6v5 *qproc) q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_q6); q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_modem); q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_nc); - + mba_load_err = true; reclaim_mba: xfermemop_ret = q6v5_xfer_mem_ownership(qproc, &qproc->mba_perm, true, false, qproc->mba_phys, @@ -926,6 +952,8 @@ static int q6v5_mba_load(struct q6v5 *qproc) if (xfermemop_ret) { dev_err(qproc->dev, "Failed to reclaim mba buffer, system may become unstable\n"); + } else if (mba_load_err) { + q6v5_dump_mba_logs(qproc); } disable_active_clks: @@ -1283,6 +1311,7 @@ static int q6v5_start(struct rproc *rproc) reclaim_mpss: q6v5_mba_reclaim(qproc); + q6v5_dump_mba_logs(qproc); return ret; } @@ -1702,6 +1731,7 @@ static int q6v5_probe(struct platform_device *pdev) qproc->version = desc->version; qproc->need_mem_protection = desc->need_mem_protection; + qproc->has_mba_logs = desc->has_mba_logs; ret = qcom_q6v5_init(&qproc->q6v5, pdev, rproc, MPSS_CRASH_REASON_SMEM, qcom_msa_handover); @@ -1793,6 +1823,7 @@ static const struct rproc_hexagon_res sc7180_mss = { }, .need_mem_protection = true, .has_alt_reset = false, + .has_mba_logs = true, .has_spare_reg = true, .version = MSS_SC7180, }; @@ -1828,6 +1859,7 @@ static const struct rproc_hexagon_res sdm845_mss = { }, .need_mem_protection = true, .has_alt_reset = true, + .has_mba_logs = false, .has_spare_reg = false, .version = MSS_SDM845, }; @@ -1855,6 +1887,7 @@ static const struct rproc_hexagon_res msm8998_mss = { }, .need_mem_protection = true, .has_alt_reset = false, + .has_mba_logs = false, .has_spare_reg = false, .version = MSS_MSM8998, }; @@ -1885,6 +1918,7 @@ static const struct rproc_hexagon_res msm8996_mss = { }, .need_mem_protection = true, .has_alt_reset = false, + .has_mba_logs = false, .has_spare_reg = false, .version = MSS_MSM8996, }; @@ -1918,6 +1952,7 @@ static const struct rproc_hexagon_res msm8916_mss = { }, .need_mem_protection = false, .has_alt_reset = false, + .has_mba_logs = false, .has_spare_reg = false, .version = MSS_MSM8916, }; @@ -1959,6 +1994,7 @@ static const struct rproc_hexagon_res msm8974_mss = { }, .need_mem_protection = false, .has_alt_reset = false, + .has_mba_logs = false, .has_spare_reg = false, .version = MSS_MSM8974, }; From 4b2aa7a6f9b793cadbda898476c8a16d374f1b3a Mon Sep 17 00:00:00 2001 From: Marian-Cristian Rotariu Date: Tue, 14 Jul 2020 11:20:54 +0100 Subject: [PATCH 148/291] iommu/ipmmu-vmsa: Hook up R8A774E1 DT matching code Add support for RZ/G2H (R8A774E1) SoC IPMMUs. Signed-off-by: Marian-Cristian Rotariu Signed-off-by: Lad Prabhakar Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/1594722055-9298-2-git-send-email-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Joerg Roedel --- drivers/iommu/ipmmu-vmsa.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index b57b1f213a48..8072db8b379b 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -740,6 +740,7 @@ static const struct soc_device_attribute soc_rcar_gen3[] = { { .soc_id = "r8a774a1", }, { .soc_id = "r8a774b1", }, { .soc_id = "r8a774c0", }, + { .soc_id = "r8a774e1", }, { .soc_id = "r8a7795", }, { .soc_id = "r8a7796", }, { .soc_id = "r8a77965", }, @@ -752,6 +753,7 @@ static const struct soc_device_attribute soc_rcar_gen3[] = { static const struct soc_device_attribute soc_rcar_gen3_whitelist[] = { { .soc_id = "r8a774b1", }, { .soc_id = "r8a774c0", }, + { .soc_id = "r8a774e1", }, { .soc_id = "r8a7795", .revision = "ES3.*" }, { .soc_id = "r8a77961", }, { .soc_id = "r8a77965", }, @@ -964,6 +966,9 @@ static const struct of_device_id ipmmu_of_ids[] = { }, { .compatible = "renesas,ipmmu-r8a774c0", .data = &ipmmu_features_rcar_gen3, + }, { + .compatible = "renesas,ipmmu-r8a774e1", + .data = &ipmmu_features_rcar_gen3, }, { .compatible = "renesas,ipmmu-r8a7795", .data = &ipmmu_features_rcar_gen3, From f3e048b78ad37dff3ba81243f2533f336a240072 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Tue, 14 Jul 2020 11:20:55 +0100 Subject: [PATCH 149/291] iommu/ipmmu-vmsa: Add an entry for r8a77961 in soc_rcar_gen3[] Add an entry for r8a77961 in soc_rcar_gen3[] list so that we dont enable iommu unconditionally. Fixes: 17fe161816398 ("iommu/renesas: Add support for r8a77961") Signed-off-by: Lad Prabhakar Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/1594722055-9298-3-git-send-email-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Joerg Roedel --- drivers/iommu/ipmmu-vmsa.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 8072db8b379b..d411dc50f719 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -742,6 +742,7 @@ static const struct soc_device_attribute soc_rcar_gen3[] = { { .soc_id = "r8a774c0", }, { .soc_id = "r8a774e1", }, { .soc_id = "r8a7795", }, + { .soc_id = "r8a77961", }, { .soc_id = "r8a7796", }, { .soc_id = "r8a77965", }, { .soc_id = "r8a77970", }, From 9314006dc3324cd449db90f23745c4f3e275d2d4 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Tue, 14 Jul 2020 12:59:28 +0100 Subject: [PATCH 150/291] iommu/exynos: Rename update_pte() The name "update_pte" is a little too generic, and can end up clashing with architecture pagetable code leaked out of common mm headers. Rename it to something more appropriately namespaced. Reported-by: kernel test robot Acked-by: Marek Szyprowski Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/829bb5dc18e734870b75db673ddce86e7e37fc73.1594727968.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/exynos-iommu.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 60c8a56e4a3f..75cdd37fae38 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -721,7 +721,7 @@ static struct platform_driver exynos_sysmmu_driver __refdata = { } }; -static inline void update_pte(sysmmu_pte_t *ent, sysmmu_pte_t val) +static inline void exynos_iommu_set_pte(sysmmu_pte_t *ent, sysmmu_pte_t val) { dma_sync_single_for_cpu(dma_dev, virt_to_phys(ent), sizeof(*ent), DMA_TO_DEVICE); @@ -933,7 +933,7 @@ static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *domain, if (!pent) return ERR_PTR(-ENOMEM); - update_pte(sent, mk_lv1ent_page(virt_to_phys(pent))); + exynos_iommu_set_pte(sent, mk_lv1ent_page(virt_to_phys(pent))); kmemleak_ignore(pent); *pgcounter = NUM_LV2ENTRIES; handle = dma_map_single(dma_dev, pent, LV2TABLE_SIZE, @@ -994,7 +994,7 @@ static int lv1set_section(struct exynos_iommu_domain *domain, *pgcnt = 0; } - update_pte(sent, mk_lv1ent_sect(paddr, prot)); + exynos_iommu_set_pte(sent, mk_lv1ent_sect(paddr, prot)); spin_lock(&domain->lock); if (lv1ent_page_zero(sent)) { @@ -1018,7 +1018,7 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size, if (WARN_ON(!lv2ent_fault(pent))) return -EADDRINUSE; - update_pte(pent, mk_lv2ent_spage(paddr, prot)); + exynos_iommu_set_pte(pent, mk_lv2ent_spage(paddr, prot)); *pgcnt -= 1; } else { /* size == LPAGE_SIZE */ int i; @@ -1150,7 +1150,7 @@ static size_t exynos_iommu_unmap(struct iommu_domain *iommu_domain, } /* workaround for h/w bug in System MMU v3.3 */ - update_pte(ent, ZERO_LV2LINK); + exynos_iommu_set_pte(ent, ZERO_LV2LINK); size = SECT_SIZE; goto done; } @@ -1171,7 +1171,7 @@ static size_t exynos_iommu_unmap(struct iommu_domain *iommu_domain, } if (lv2ent_small(ent)) { - update_pte(ent, 0); + exynos_iommu_set_pte(ent, 0); size = SPAGE_SIZE; domain->lv2entcnt[lv1ent_offset(iova)] += 1; goto done; From dee9d154f40c58d02f69acdaa5cfd1eae6ebc28b Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 14 Jul 2020 20:22:11 +0100 Subject: [PATCH 151/291] iommu/omap: Check for failure of a call to omap_iommu_dump_ctx It is possible for the call to omap_iommu_dump_ctx to return a negative error number, so check for the failure and return the error number rather than pass the negative value to simple_read_from_buffer. Fixes: 14e0e6796a0d ("OMAP: iommu: add initial debugfs support") Signed-off-by: Colin Ian King Link: https://lore.kernel.org/r/20200714192211.744776-1-colin.king@canonical.com Addresses-Coverity: ("Improper use of negative value") Signed-off-by: Joerg Roedel --- drivers/iommu/omap-iommu-debug.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c index 8e19bfa94121..a99afb5d9011 100644 --- a/drivers/iommu/omap-iommu-debug.c +++ b/drivers/iommu/omap-iommu-debug.c @@ -98,8 +98,11 @@ static ssize_t debug_read_regs(struct file *file, char __user *userbuf, mutex_lock(&iommu_debug_lock); bytes = omap_iommu_dump_ctx(obj, p, count); + if (bytes < 0) + goto err; bytes = simple_read_from_buffer(userbuf, count, ppos, buf, bytes); +err: mutex_unlock(&iommu_debug_lock); kfree(buf); From 092550eacd040a349917a6bbe90ad543258e1695 Mon Sep 17 00:00:00 2001 From: Libing Zhou Date: Wed, 22 Jul 2020 14:44:50 +0800 Subject: [PATCH 152/291] iommu/amd: Remove double zero check The free_pages() does zero check, therefore remove double zero check here. Signed-off-by: Libing Zhou Link: https://lore.kernel.org/r/20200722064450.GA63618@hzling02.china.nsn-net.net Signed-off-by: Joerg Roedel --- drivers/iommu/amd/init.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 232683ea10e0..958050c213f9 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -720,21 +720,14 @@ static void iommu_enable_ppr_log(struct amd_iommu *iommu) static void __init free_ppr_log(struct amd_iommu *iommu) { - if (iommu->ppr_log == NULL) - return; - free_pages((unsigned long)iommu->ppr_log, get_order(PPR_LOG_SIZE)); } static void free_ga_log(struct amd_iommu *iommu) { #ifdef CONFIG_IRQ_REMAP - if (iommu->ga_log) - free_pages((unsigned long)iommu->ga_log, - get_order(GA_LOG_SIZE)); - if (iommu->ga_log_tail) - free_pages((unsigned long)iommu->ga_log_tail, - get_order(8)); + free_pages((unsigned long)iommu->ga_log, get_order(GA_LOG_SIZE)); + free_pages((unsigned long)iommu->ga_log_tail, get_order(8)); #endif } From 1b0b2a84c979347f5385a8cb3901d3a46569d57c Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Mon, 13 Jul 2020 22:25:42 +0800 Subject: [PATCH 153/291] iommu: Make some functions static The sparse tool complains as follows: drivers/iommu/iommu.c:386:5: warning: symbol 'iommu_insert_resv_region' was not declared. Should it be static? drivers/iommu/iommu.c:2182:5: warning: symbol '__iommu_map' was not declared. Should it be static? Those functions are not used outside of iommu.c, so mark them static. Reported-by: Hulk Robot Signed-off-by: Wei Yongjun Link: https://lore.kernel.org/r/20200713142542.50294-1-weiyongjun1@huawei.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 1ed1e14a1f0c..40947f5bc6c5 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -383,8 +383,8 @@ static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf) * Elements are sorted by start address and overlapping segments * of the same type are merged. */ -int iommu_insert_resv_region(struct iommu_resv_region *new, - struct list_head *regions) +static int iommu_insert_resv_region(struct iommu_resv_region *new, + struct list_head *regions) { struct iommu_resv_region *iter, *tmp, *nr, *top; LIST_HEAD(stack); @@ -2179,8 +2179,8 @@ static size_t iommu_pgsize(struct iommu_domain *domain, return pgsize; } -int __iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot, gfp_t gfp) +static int __iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { const struct iommu_ops *ops = domain->ops; unsigned long orig_iova = iova; From 29bf2617e33b0dfbc87e41981c7960c8e2dbcf1e Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 22 Jul 2020 17:09:26 +0200 Subject: [PATCH 154/291] rpmsg: update documentation rpmsg_create_ept() takes struct rpmsg_channel_info chinfo as its last argument, not a u32 value. The first two arguments are also updated. Signed-off-by: Guennadi Liakhovetski Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200722150927.15587-4-guennadi.liakhovetski@linux.intel.com Signed-off-by: Bjorn Andersson --- Documentation/rpmsg.txt | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/rpmsg.txt b/Documentation/rpmsg.txt index 24b7a9e1a5f9..1ce353cb232a 100644 --- a/Documentation/rpmsg.txt +++ b/Documentation/rpmsg.txt @@ -192,9 +192,9 @@ Returns 0 on success and an appropriate error value on failure. :: - struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_channel *rpdev, - void (*cb)(struct rpmsg_channel *, void *, int, void *, u32), - void *priv, u32 addr); + struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_device *rpdev, + rpmsg_rx_cb_t cb, void *priv, + struct rpmsg_channel_info chinfo); every rpmsg address in the system is bound to an rx callback (so when inbound messages arrive, they are dispatched by the rpmsg bus using the From c1e18d4fb9590268105e724444792656fcb3927d Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Mon, 15 Jun 2020 22:35:21 +0200 Subject: [PATCH 155/291] platform/chrome: cros_ec_proto: Do not export cros_ec_cmd_xfer() Now that all the remaining users of cros_ec_cmd_xfer() has been removed, make this function private to the cros_ec_proto module. Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_proto.c | 5 ++--- include/linux/platform_data/cros_ec_proto.h | 3 --- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 3e745e0fe092..11a2db7cd0f7 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -496,8 +496,8 @@ EXPORT_SYMBOL(cros_ec_query_all); * * Return: 0 on success or negative error code. */ -int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, - struct cros_ec_command *msg) +static int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, + struct cros_ec_command *msg) { int ret; @@ -541,7 +541,6 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, return ret; } -EXPORT_SYMBOL(cros_ec_cmd_xfer); /** * cros_ec_cmd_xfer_status() - Send a command to the ChromeOS EC. diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 383243326676..4a415ae851ef 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -216,9 +216,6 @@ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, int cros_ec_check_result(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, - struct cros_ec_command *msg); - int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); From 5f77d6ca5ca74e4b4a5e2e010f7ff50c45dea326 Mon Sep 17 00:00:00 2001 From: Liu Yi L Date: Fri, 24 Jul 2020 09:49:14 +0800 Subject: [PATCH 156/291] iommu/vt-d: Enforce PASID devTLB field mask Set proper masks to avoid invalid input spillover to reserved bits. Signed-off-by: Liu Yi L Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200724014925.15523-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 3e8fa1c7a1e6..311117b50e93 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -381,8 +381,8 @@ enum { #define QI_DEV_EIOTLB_ADDR(a) ((u64)(a) & VTD_PAGE_MASK) #define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) -#define QI_DEV_EIOTLB_GLOB(g) ((u64)g) -#define QI_DEV_EIOTLB_PASID(p) (((u64)p) << 32) +#define QI_DEV_EIOTLB_GLOB(g) ((u64)(g) & 0x1) +#define QI_DEV_EIOTLB_PASID(p) ((u64)((p) & 0xfffff) << 32) #define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) #define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) #define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ From 78df6c86f0691f5b6e325006aeb470de443351ea Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 24 Jul 2020 09:49:15 +0800 Subject: [PATCH 157/291] iommu/vt-d: Remove global page support in devTLB flush Global pages support is removed from VT-d spec 3.0 for dev TLB invalidation. This patch is to remove the bits for vSVA. Similar change already made for the native SVA. See the link below. Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/linux-iommu/20190830142919.GE11578@8bytes.org/T/ Link: https://lore.kernel.org/r/20200724014925.15523-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 4 +--- drivers/iommu/intel/iommu.c | 4 ++-- include/linux/intel-iommu.h | 3 +-- 3 files changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 683b812c5c47..9be08b9400ee 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1438,8 +1438,7 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, /* PASID-based device IOTLB Invalidate */ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, - u32 pasid, u16 qdep, u64 addr, - unsigned int size_order, u64 granu) + u32 pasid, u16 qdep, u64 addr, unsigned int size_order) { unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size_order - 1); struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0}; @@ -1447,7 +1446,6 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, desc.qw0 = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) | QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE | QI_DEV_IOTLB_PFSID(pfsid); - desc.qw1 = QI_DEV_EIOTLB_GLOB(granu); /* * If S bit is 0, we only flush a single page. If S bit is set, diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index d759e7234e98..bdd1e7d81178 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -5474,7 +5474,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev, info->pfsid, pasid, info->ats_qdep, inv_info->addr_info.addr, - size, granu); + size); break; case IOMMU_CACHE_INV_TYPE_DEV_IOTLB: if (info->ats_enabled) @@ -5482,7 +5482,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev, info->pfsid, pasid, info->ats_qdep, inv_info->addr_info.addr, - size, granu); + size); else pr_warn_ratelimited("Passdown device IOTLB flush w/o ATS!\n"); break; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 311117b50e93..c7a8aae36771 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -381,7 +381,6 @@ enum { #define QI_DEV_EIOTLB_ADDR(a) ((u64)(a) & VTD_PAGE_MASK) #define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) -#define QI_DEV_EIOTLB_GLOB(g) ((u64)(g) & 0x1) #define QI_DEV_EIOTLB_PASID(p) ((u64)((p) & 0xfffff) << 32) #define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) #define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) @@ -705,7 +704,7 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, u32 pasid, u16 qdep, u64 addr, - unsigned int size_order, u64 granu); + unsigned int size_order); void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, int pasid); From e7e69461a83264dbce2b4ff480f858f3f1454db7 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 24 Jul 2020 09:49:16 +0800 Subject: [PATCH 158/291] iommu/vt-d: Fix PASID devTLB invalidation DevTLB flush can be used for both DMA request with and without PASIDs. The former uses PASID#0 (RID2PASID), latter uses non-zero PASID for SVA usage. This patch adds a check for PASID value such that devTLB flush with PASID is used for SVA case. This is more efficient in that multiple PASIDs can be used by a single device, when tearing down a PASID entry we shall flush only the devTLB specific to a PASID. Fixes: 6f7db75e1c46 ("iommu/vt-d: Add second level page table") Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200724014925.15523-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/pasid.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index c81f0f17c6ba..fa0154cce537 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -486,7 +486,16 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu, qdep = info->ats_qdep; pfsid = info->pfsid; - qi_flush_dev_iotlb(iommu, sid, pfsid, qdep, 0, 64 - VTD_PAGE_SHIFT); + /* + * When PASID 0 is used, it indicates RID2PASID(DMA request w/o PASID), + * devTLB flush w/o PASID should be used. For non-zero PASID under + * SVA usage, device could do DMA with multiple PASIDs. It is more + * efficient to flush devTLB specific to the PASID. + */ + if (pasid == PASID_RID2PASID) + qi_flush_dev_iotlb(iommu, sid, pfsid, qdep, 0, 64 - VTD_PAGE_SHIFT); + else + qi_flush_dev_iotlb_pasid(iommu, sid, pfsid, pasid, qdep, 0, 64 - VTD_PAGE_SHIFT); } void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev, From 288d08e78008828416ffaa85ef274b4e29ef3dae Mon Sep 17 00:00:00 2001 From: Liu Yi L Date: Fri, 24 Jul 2020 09:49:17 +0800 Subject: [PATCH 159/291] iommu/vt-d: Handle non-page aligned address Address information for device TLB invalidation comes from userspace when device is directly assigned to a guest with vIOMMU support. VT-d requires page aligned address. This patch checks and enforce address to be page aligned, otherwise reserved bits can be set in the invalidation descriptor. Unrecoverable fault will be reported due to non-zero value in the reserved bits. Fixes: 61a06a16e36d8 ("iommu/vt-d: Support flushing more translation cache types") Signed-off-by: Liu Yi L Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200724014925.15523-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 9be08b9400ee..f6cbe3f95c8d 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1456,9 +1456,26 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, * Max Invs Pending (MIP) is set to 0 for now until we have DIT in * ECAP. */ - desc.qw1 |= addr & ~mask; - if (size_order) + if (addr & GENMASK_ULL(size_order + VTD_PAGE_SHIFT, 0)) + pr_warn_ratelimited("Invalidate non-aligned address %llx, order %d\n", + addr, size_order); + + /* Take page address */ + desc.qw1 = QI_DEV_EIOTLB_ADDR(addr); + + if (size_order) { + /* + * Existing 0s in address below size_order may be the least + * significant bit, we must set them to 1s to avoid having + * smaller size than desired. + */ + desc.qw1 |= GENMASK_ULL(size_order + VTD_PAGE_SHIFT - 1, + VTD_PAGE_SHIFT); + /* Clear size_order bit to indicate size */ + desc.qw1 &= ~mask; + /* Set the S bit to indicate flushing more than 1 page */ desc.qw1 |= QI_DEV_EIOTLB_SIZE; + } qi_submit_sync(iommu, &desc, 1, 0); } From 0fa1a15fa9b37be3899d7fec552c77b67baa8ac7 Mon Sep 17 00:00:00 2001 From: Liu Yi L Date: Fri, 24 Jul 2020 09:49:18 +0800 Subject: [PATCH 160/291] iommu/vt-d: Fix devTLB flush for vSVA For guest SVA usage, in order to optimize for less VMEXIT, guest request of IOTLB flush also includes device TLB. On the host side, IOMMU driver performs IOTLB and implicit devTLB invalidation. When PASID-selective granularity is requested by the guest we need to derive the equivalent address range for devTLB instead of using the address information in the UAPI data. The reason for that is, unlike IOTLB flush, devTLB flush does not support PASID-selective granularity. This is to say, we need to set the following in the PASID based devTLB invalidation descriptor: - entire 64 bit range in address ~(0x1 << 63) - S bit = 1 (VT-d CH 6.5.2.6). Without this fix, device TLB flush range is not set properly for PASID selective granularity. This patch also merged devTLB flush code for both implicit and explicit cases. Fixes: 6ee1b77ba3ac ("iommu/vt-d: Add svm/sva invalidate function") Signed-off-by: Liu Yi L Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200724014925.15523-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 31 +++++++++++++++++++++---------- 1 file changed, 21 insertions(+), 10 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index bdd1e7d81178..34a0ebfc2fcf 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -5416,7 +5416,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev, sid = PCI_DEVID(bus, devfn); /* Size is only valid in address selective invalidation */ - if (inv_info->granularity != IOMMU_INV_GRANU_PASID) + if (inv_info->granularity == IOMMU_INV_GRANU_ADDR) size = to_vtd_size(inv_info->addr_info.granule_size, inv_info->addr_info.nb_granules); @@ -5425,6 +5425,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev, IOMMU_CACHE_INV_TYPE_NR) { int granu = 0; u64 pasid = 0; + u64 addr = 0; granu = to_vtd_granularity(cache_type, inv_info->granularity); if (granu == -EINVAL) { @@ -5464,24 +5465,34 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev, (granu == QI_GRAN_NONG_PASID) ? -1 : 1 << size, inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF); + if (!info->ats_enabled) + break; /* * Always flush device IOTLB if ATS is enabled. vIOMMU * in the guest may assume IOTLB flush is inclusive, * which is more efficient. */ - if (info->ats_enabled) - qi_flush_dev_iotlb_pasid(iommu, sid, - info->pfsid, pasid, - info->ats_qdep, - inv_info->addr_info.addr, - size); - break; + fallthrough; case IOMMU_CACHE_INV_TYPE_DEV_IOTLB: + /* + * PASID based device TLB invalidation does not support + * IOMMU_INV_GRANU_PASID granularity but only supports + * IOMMU_INV_GRANU_ADDR. + * The equivalent of that is we set the size to be the + * entire range of 64 bit. User only provides PASID info + * without address info. So we set addr to 0. + */ + if (inv_info->granularity == IOMMU_INV_GRANU_PASID) { + size = 64 - VTD_PAGE_SHIFT; + addr = 0; + } else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR) { + addr = inv_info->addr_info.addr; + } + if (info->ats_enabled) qi_flush_dev_iotlb_pasid(iommu, sid, info->pfsid, pasid, - info->ats_qdep, - inv_info->addr_info.addr, + info->ats_qdep, addr, size); else pr_warn_ratelimited("Passdown device IOTLB flush w/o ATS!\n"); From 1ff00279655d95ae9c285c39878aedf9ff008d25 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 24 Jul 2020 09:49:19 +0800 Subject: [PATCH 161/291] iommu/vt-d: Warn on out-of-range invalidation address For guest requested IOTLB invalidation, address and mask are provided as part of the invalidation data. VT-d HW silently ignores any address bits below the mask. SW shall also allow such case but give warning if address does not align with the mask. This patch relax the fault handling from error to warning and proceed with invalidation request with the given mask. Fixes: 6ee1b77ba3ac0 ("iommu/vt-d: Add svm/sva invalidate function") Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200724014925.15523-7-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 34a0ebfc2fcf..0a4831532442 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -5447,13 +5447,12 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev, switch (BIT(cache_type)) { case IOMMU_CACHE_INV_TYPE_IOTLB: + /* HW will ignore LSB bits based on address mask */ if (inv_info->granularity == IOMMU_INV_GRANU_ADDR && size && (inv_info->addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) { - pr_err_ratelimited("Address out of range, 0x%llx, size order %llu\n", + pr_err_ratelimited("User address not aligned, 0x%llx, size order %llu\n", inv_info->addr_info.addr, size); - ret = -ERANGE; - goto out_unlock; } /* From d315e9e684d1efd4cb2e8cd70b8d71dec02fcf1f Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 24 Jul 2020 09:49:20 +0800 Subject: [PATCH 162/291] iommu/vt-d: Disable multiple GPASID-dev bind For the unlikely use case where multiple aux domains from the same pdev are attached to a single guest and then bound to a single process (thus same PASID) within that guest, we cannot easily support this case by refcounting the number of users. As there is only one SL page table per PASID while we have multiple aux domains thus multiple SL page tables for the same PASID. Extra unbinding guest PASID can happen due to race between normal and exception cases. Termination of one aux domain may affect others unless we actively track and switch aux domains to ensure the validity of SL page tables and TLB states in the shared PASID entry. Support for sharing second level PGDs across domains can reduce the complexity but this is not available due to the limitations on VFIO container architecture. We can revisit this decision once sharing PGDs are available. Overall, the complexity and potential glitch do not warrant this unlikely use case thereby removed by this patch. Fixes: 56722a4398a30 ("iommu/vt-d: Add bind guest PASID support") Signed-off-by: Liu Yi L Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Cc: Kevin Tian Link: https://lore.kernel.org/r/20200724014925.15523-8-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/svm.c | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 6c87c807a0ab..d386853121a2 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -277,20 +277,16 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, goto out; } + /* + * Do not allow multiple bindings of the same device-PASID since + * there is only one SL page tables per PASID. We may revisit + * once sharing PGD across domains are supported. + */ for_each_svm_dev(sdev, svm, dev) { - /* - * For devices with aux domains, we should allow - * multiple bind calls with the same PASID and pdev. - */ - if (iommu_dev_feature_enabled(dev, - IOMMU_DEV_FEAT_AUX)) { - sdev->users++; - } else { - dev_warn_ratelimited(dev, - "Already bound with PASID %u\n", - svm->pasid); - ret = -EBUSY; - } + dev_warn_ratelimited(dev, + "Already bound with PASID %u\n", + svm->pasid); + ret = -EBUSY; goto out; } } else { From dd6692f1b883bac46036000a1e3a0b3785f89e87 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Fri, 24 Jul 2020 09:49:21 +0800 Subject: [PATCH 163/291] iommu/vt-d: Refactor device_to_iommu() helper It is refactored in two ways: - Make it global so that it could be used in other files. - Make bus/devfn optional so that callers could ignore these two returned values when they only want to get the coresponding iommu pointer. Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20200724014925.15523-9-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 55 +++++++++++-------------------------- drivers/iommu/intel/svm.c | 8 +++--- include/linux/intel-iommu.h | 3 +- 3 files changed, 21 insertions(+), 45 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 0a4831532442..ce8458e8119c 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -778,16 +778,16 @@ is_downstream_to_pci_bridge(struct device *dev, struct device *bridge) return false; } -static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn) +struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn) { struct dmar_drhd_unit *drhd = NULL; + struct pci_dev *pdev = NULL; struct intel_iommu *iommu; struct device *tmp; - struct pci_dev *pdev = NULL; u16 segment = 0; int i; - if (iommu_dummy(dev)) + if (!dev || iommu_dummy(dev)) return NULL; if (dev_is_pci(dev)) { @@ -818,8 +818,10 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf if (pdev && pdev->is_virtfn) goto got_pdev; - *bus = drhd->devices[i].bus; - *devfn = drhd->devices[i].devfn; + if (bus && devfn) { + *bus = drhd->devices[i].bus; + *devfn = drhd->devices[i].devfn; + } goto out; } @@ -829,8 +831,10 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf if (pdev && drhd->include_all) { got_pdev: - *bus = pdev->bus->number; - *devfn = pdev->devfn; + if (bus && devfn) { + *bus = pdev->bus->number; + *devfn = pdev->devfn; + } goto out; } } @@ -5146,11 +5150,10 @@ static int aux_domain_add_dev(struct dmar_domain *domain, struct device *dev) { int ret; - u8 bus, devfn; unsigned long flags; struct intel_iommu *iommu; - iommu = device_to_iommu(dev, &bus, &devfn); + iommu = device_to_iommu(dev, NULL, NULL); if (!iommu) return -ENODEV; @@ -5236,9 +5239,8 @@ static int prepare_domain_attach_device(struct iommu_domain *domain, struct dmar_domain *dmar_domain = to_dmar_domain(domain); struct intel_iommu *iommu; int addr_width; - u8 bus, devfn; - iommu = device_to_iommu(dev, &bus, &devfn); + iommu = device_to_iommu(dev, NULL, NULL); if (!iommu) return -ENODEV; @@ -5668,9 +5670,8 @@ static bool intel_iommu_capable(enum iommu_cap cap) static struct iommu_device *intel_iommu_probe_device(struct device *dev) { struct intel_iommu *iommu; - u8 bus, devfn; - iommu = device_to_iommu(dev, &bus, &devfn); + iommu = device_to_iommu(dev, NULL, NULL); if (!iommu) return ERR_PTR(-ENODEV); @@ -5683,9 +5684,8 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) static void intel_iommu_release_device(struct device *dev) { struct intel_iommu *iommu; - u8 bus, devfn; - iommu = device_to_iommu(dev, &bus, &devfn); + iommu = device_to_iommu(dev, NULL, NULL); if (!iommu) return; @@ -5835,37 +5835,14 @@ static struct iommu_group *intel_iommu_device_group(struct device *dev) return generic_device_group(dev); } -#ifdef CONFIG_INTEL_IOMMU_SVM -struct intel_iommu *intel_svm_device_to_iommu(struct device *dev) -{ - struct intel_iommu *iommu; - u8 bus, devfn; - - if (iommu_dummy(dev)) { - dev_warn(dev, - "No IOMMU translation for device; cannot enable SVM\n"); - return NULL; - } - - iommu = device_to_iommu(dev, &bus, &devfn); - if ((!iommu)) { - dev_err(dev, "No IOMMU for device; cannot enable SVM\n"); - return NULL; - } - - return iommu; -} -#endif /* CONFIG_INTEL_IOMMU_SVM */ - static int intel_iommu_enable_auxd(struct device *dev) { struct device_domain_info *info; struct intel_iommu *iommu; unsigned long flags; - u8 bus, devfn; int ret; - iommu = device_to_iommu(dev, &bus, &devfn); + iommu = device_to_iommu(dev, NULL, NULL); if (!iommu || dmar_disabled) return -EINVAL; diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index d386853121a2..65d2327dcd0d 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -231,7 +231,7 @@ static LIST_HEAD(global_svm_list); int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, struct iommu_gpasid_bind_data *data) { - struct intel_iommu *iommu = intel_svm_device_to_iommu(dev); + struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL); struct dmar_domain *dmar_domain; struct intel_svm_dev *sdev; struct intel_svm *svm; @@ -369,7 +369,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, int intel_svm_unbind_gpasid(struct device *dev, int pasid) { - struct intel_iommu *iommu = intel_svm_device_to_iommu(dev); + struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL); struct intel_svm_dev *sdev; struct intel_svm *svm; int ret = -EINVAL; @@ -426,7 +426,7 @@ static int intel_svm_bind_mm(struct device *dev, int flags, struct svm_dev_ops *ops, struct mm_struct *mm, struct intel_svm_dev **sd) { - struct intel_iommu *iommu = intel_svm_device_to_iommu(dev); + struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL); struct device_domain_info *info; struct intel_svm_dev *sdev; struct intel_svm *svm = NULL; @@ -604,7 +604,7 @@ static int intel_svm_unbind_mm(struct device *dev, int pasid) struct intel_svm *svm; int ret = -EINVAL; - iommu = intel_svm_device_to_iommu(dev); + iommu = device_to_iommu(dev, NULL, NULL); if (!iommu) goto out; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index c7a8aae36771..a57ffbcc84c7 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -727,6 +727,7 @@ void iommu_flush_write_buffer(struct intel_iommu *iommu); int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev); struct dmar_domain *find_domain(struct device *dev); struct device_domain_info *get_domain_info(struct device *dev); +struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); #ifdef CONFIG_INTEL_IOMMU_SVM extern void intel_svm_check(struct intel_iommu *iommu); @@ -765,8 +766,6 @@ struct intel_svm { struct list_head devs; struct list_head list; }; - -extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev); #else static inline void intel_svm_check(struct intel_iommu *iommu) {} #endif From 19abcf70c2b16834a607db515b26a32b233c79eb Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Fri, 24 Jul 2020 09:49:22 +0800 Subject: [PATCH 164/291] iommu/vt-d: Add a helper to get svm and sdev for pasid There are several places in the code that need to get the pointers of svm and sdev according to a pasid and device. Add a helper to achieve this for code consolidation and readability. Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20200724014925.15523-10-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/svm.c | 115 +++++++++++++++++++++----------------- 1 file changed, 65 insertions(+), 50 deletions(-) diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 65d2327dcd0d..c104a50a625c 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -228,13 +228,57 @@ static LIST_HEAD(global_svm_list); list_for_each_entry((sdev), &(svm)->devs, list) \ if ((d) != (sdev)->dev) {} else +static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid, + struct intel_svm **rsvm, + struct intel_svm_dev **rsdev) +{ + struct intel_svm_dev *d, *sdev = NULL; + struct intel_svm *svm; + + /* The caller should hold the pasid_mutex lock */ + if (WARN_ON(!mutex_is_locked(&pasid_mutex))) + return -EINVAL; + + if (pasid == INVALID_IOASID || pasid >= PASID_MAX) + return -EINVAL; + + svm = ioasid_find(NULL, pasid, NULL); + if (IS_ERR(svm)) + return PTR_ERR(svm); + + if (!svm) + goto out; + + /* + * If we found svm for the PASID, there must be at least one device + * bond. + */ + if (WARN_ON(list_empty(&svm->devs))) + return -EINVAL; + + rcu_read_lock(); + list_for_each_entry_rcu(d, &svm->devs, list) { + if (d->dev == dev) { + sdev = d; + break; + } + } + rcu_read_unlock(); + +out: + *rsvm = svm; + *rsdev = sdev; + + return 0; +} + int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, struct iommu_gpasid_bind_data *data) { struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL); + struct intel_svm_dev *sdev = NULL; struct dmar_domain *dmar_domain; - struct intel_svm_dev *sdev; - struct intel_svm *svm; + struct intel_svm *svm = NULL; int ret = 0; if (WARN_ON(!iommu) || !data) @@ -261,35 +305,23 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, dmar_domain = to_dmar_domain(domain); mutex_lock(&pasid_mutex); - svm = ioasid_find(NULL, data->hpasid, NULL); - if (IS_ERR(svm)) { - ret = PTR_ERR(svm); + ret = pasid_to_svm_sdev(dev, data->hpasid, &svm, &sdev); + if (ret) goto out; - } - - if (svm) { - /* - * If we found svm for the PASID, there must be at - * least one device bond, otherwise svm should be freed. - */ - if (WARN_ON(list_empty(&svm->devs))) { - ret = -EINVAL; - goto out; - } + if (sdev) { /* * Do not allow multiple bindings of the same device-PASID since * there is only one SL page tables per PASID. We may revisit * once sharing PGD across domains are supported. */ - for_each_svm_dev(sdev, svm, dev) { - dev_warn_ratelimited(dev, - "Already bound with PASID %u\n", - svm->pasid); - ret = -EBUSY; - goto out; - } - } else { + dev_warn_ratelimited(dev, "Already bound with PASID %u\n", + svm->pasid); + ret = -EBUSY; + goto out; + } + + if (!svm) { /* We come here when PASID has never been bond to a device. */ svm = kzalloc(sizeof(*svm), GFP_KERNEL); if (!svm) { @@ -372,25 +404,17 @@ int intel_svm_unbind_gpasid(struct device *dev, int pasid) struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL); struct intel_svm_dev *sdev; struct intel_svm *svm; - int ret = -EINVAL; + int ret; if (WARN_ON(!iommu)) return -EINVAL; mutex_lock(&pasid_mutex); - svm = ioasid_find(NULL, pasid, NULL); - if (!svm) { - ret = -EINVAL; + ret = pasid_to_svm_sdev(dev, pasid, &svm, &sdev); + if (ret) goto out; - } - if (IS_ERR(svm)) { - ret = PTR_ERR(svm); - goto out; - } - - for_each_svm_dev(sdev, svm, dev) { - ret = 0; + if (sdev) { if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX)) sdev->users--; if (!sdev->users) { @@ -414,7 +438,6 @@ int intel_svm_unbind_gpasid(struct device *dev, int pasid) kfree(svm); } } - break; } out: mutex_unlock(&pasid_mutex); @@ -592,7 +615,7 @@ intel_svm_bind_mm(struct device *dev, int flags, struct svm_dev_ops *ops, if (sd) *sd = sdev; ret = 0; - out: +out: return ret; } @@ -608,17 +631,11 @@ static int intel_svm_unbind_mm(struct device *dev, int pasid) if (!iommu) goto out; - svm = ioasid_find(NULL, pasid, NULL); - if (!svm) + ret = pasid_to_svm_sdev(dev, pasid, &svm, &sdev); + if (ret) goto out; - if (IS_ERR(svm)) { - ret = PTR_ERR(svm); - goto out; - } - - for_each_svm_dev(sdev, svm, dev) { - ret = 0; + if (sdev) { sdev->users--; if (!sdev->users) { list_del_rcu(&sdev->list); @@ -647,10 +664,8 @@ static int intel_svm_unbind_mm(struct device *dev, int pasid) kfree(svm); } } - break; } - out: - +out: return ret; } From eb8d93ea3c1d35b0baf693dd0b7c87ec62358fc9 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Fri, 24 Jul 2020 09:49:23 +0800 Subject: [PATCH 165/291] iommu/vt-d: Report page request faults for guest SVA A pasid might be bound to a page table from a VM guest via the iommu ops.sva_bind_gpasid. In this case, when a DMA page fault is detected on the physical IOMMU, we need to inject the page fault request into the guest. After the guest completes handling the page fault, a page response need to be sent back via the iommu ops.page_response(). This adds support to report a page request fault. Any external module which is interested in handling this fault should regiester a notifier with iommu_register_device_fault_handler(). Co-developed-by: Jacob Pan Co-developed-by: Liu Yi L Signed-off-by: Jacob Pan Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20200724014925.15523-11-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/svm.c | 103 +++++++++++++++++++++++++++++++------- 1 file changed, 85 insertions(+), 18 deletions(-) diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index c104a50a625c..140114ab1375 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -811,8 +811,63 @@ static void intel_svm_drain_prq(struct device *dev, int pasid) } } +static int prq_to_iommu_prot(struct page_req_dsc *req) +{ + int prot = 0; + + if (req->rd_req) + prot |= IOMMU_FAULT_PERM_READ; + if (req->wr_req) + prot |= IOMMU_FAULT_PERM_WRITE; + if (req->exe_req) + prot |= IOMMU_FAULT_PERM_EXEC; + if (req->pm_req) + prot |= IOMMU_FAULT_PERM_PRIV; + + return prot; +} + +static int +intel_svm_prq_report(struct device *dev, struct page_req_dsc *desc) +{ + struct iommu_fault_event event; + + if (!dev || !dev_is_pci(dev)) + return -ENODEV; + + /* Fill in event data for device specific processing */ + memset(&event, 0, sizeof(struct iommu_fault_event)); + event.fault.type = IOMMU_FAULT_PAGE_REQ; + event.fault.prm.addr = desc->addr; + event.fault.prm.pasid = desc->pasid; + event.fault.prm.grpid = desc->prg_index; + event.fault.prm.perm = prq_to_iommu_prot(desc); + + if (desc->lpig) + event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE; + if (desc->pasid_present) { + event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID; + event.fault.prm.flags |= IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID; + } + if (desc->priv_data_present) { + /* + * Set last page in group bit if private data is present, + * page response is required as it does for LPIG. + * iommu_report_device_fault() doesn't understand this vendor + * specific requirement thus we set last_page as a workaround. + */ + event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE; + event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA; + memcpy(event.fault.prm.private_data, desc->priv_data, + sizeof(desc->priv_data)); + } + + return iommu_report_device_fault(dev, &event); +} + static irqreturn_t prq_event_thread(int irq, void *d) { + struct intel_svm_dev *sdev = NULL; struct intel_iommu *iommu = d; struct intel_svm *svm = NULL; int head, tail, handled = 0; @@ -824,7 +879,6 @@ static irqreturn_t prq_event_thread(int irq, void *d) tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK; head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK; while (head != tail) { - struct intel_svm_dev *sdev; struct vm_area_struct *vma; struct page_req_dsc *req; struct qi_desc resp; @@ -860,6 +914,20 @@ static irqreturn_t prq_event_thread(int irq, void *d) } } + if (!sdev || sdev->sid != req->rid) { + struct intel_svm_dev *t; + + sdev = NULL; + rcu_read_lock(); + list_for_each_entry_rcu(t, &svm->devs, list) { + if (t->sid == req->rid) { + sdev = t; + break; + } + } + rcu_read_unlock(); + } + result = QI_RESP_INVALID; /* Since we're using init_mm.pgd directly, we should never take * any faults on kernel addresses. */ @@ -870,6 +938,17 @@ static irqreturn_t prq_event_thread(int irq, void *d) if (!is_canonical_address(address)) goto bad_req; + /* + * If prq is to be handled outside iommu driver via receiver of + * the fault notifiers, we skip the page response here. + */ + if (svm->flags & SVM_FLAG_GUEST_MODE) { + if (sdev && !intel_svm_prq_report(sdev->dev, req)) + goto prq_advance; + else + goto bad_req; + } + /* If the mm is already defunct, don't handle faults. */ if (!mmget_not_zero(svm->mm)) goto bad_req; @@ -888,24 +967,11 @@ static irqreturn_t prq_event_thread(int irq, void *d) goto invalid; result = QI_RESP_SUCCESS; - invalid: +invalid: mmap_read_unlock(svm->mm); mmput(svm->mm); - bad_req: - /* Accounting for major/minor faults? */ - rcu_read_lock(); - list_for_each_entry_rcu(sdev, &svm->devs, list) { - if (sdev->sid == req->rid) - break; - } - /* Other devices can go away, but the drivers are not permitted - * to unbind while any page faults might be in flight. So it's - * OK to drop the 'lock' here now we have it. */ - rcu_read_unlock(); - - if (WARN_ON(&sdev->list == &svm->devs)) - sdev = NULL; - +bad_req: + WARN_ON(!sdev); if (sdev && sdev->ops && sdev->ops->fault_cb) { int rwxp = (req->rd_req << 3) | (req->wr_req << 2) | (req->exe_req << 1) | (req->pm_req); @@ -916,7 +982,7 @@ static irqreturn_t prq_event_thread(int irq, void *d) and these can be NULL. Do not use them below this point! */ sdev = NULL; svm = NULL; - no_pasid: +no_pasid: if (req->lpig || req->priv_data_present) { /* * Per VT-d spec. v3.0 ch7.7, system software must @@ -941,6 +1007,7 @@ static irqreturn_t prq_event_thread(int irq, void *d) resp.qw3 = 0; qi_submit_sync(iommu, &resp, 1, 0); } +prq_advance: head = (head + sizeof(*req)) & PRQ_RING_MASK; } From 8b73712115ebd603b75876f7d96d59e41d9107ad Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Fri, 24 Jul 2020 09:49:24 +0800 Subject: [PATCH 166/291] iommu/vt-d: Add page response ops support After page requests are handled, software must respond to the device which raised the page request with the result. This is done through the iommu ops.page_response if the request was reported to outside of vendor iommu driver through iommu_report_device_fault(). This adds the VT-d implementation of page_response ops. Co-developed-by: Jacob Pan Co-developed-by: Liu Yi L Signed-off-by: Jacob Pan Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20200724014925.15523-12-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 1 + drivers/iommu/intel/svm.c | 99 +++++++++++++++++++++++++++++++++++++ include/linux/intel-iommu.h | 3 ++ 3 files changed, 103 insertions(+) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index ce8458e8119c..1cb3a2a050c3 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -6067,6 +6067,7 @@ const struct iommu_ops intel_iommu_ops = { .sva_bind = intel_svm_bind, .sva_unbind = intel_svm_unbind, .sva_get_pasid = intel_svm_get_pasid, + .page_response = intel_svm_page_response, #endif }; diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 140114ab1375..85ce8daa3177 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -1078,3 +1078,102 @@ int intel_svm_get_pasid(struct iommu_sva *sva) return pasid; } + +int intel_svm_page_response(struct device *dev, + struct iommu_fault_event *evt, + struct iommu_page_response *msg) +{ + struct iommu_fault_page_request *prm; + struct intel_svm_dev *sdev = NULL; + struct intel_svm *svm = NULL; + struct intel_iommu *iommu; + bool private_present; + bool pasid_present; + bool last_page; + u8 bus, devfn; + int ret = 0; + u16 sid; + + if (!dev || !dev_is_pci(dev)) + return -ENODEV; + + iommu = device_to_iommu(dev, &bus, &devfn); + if (!iommu) + return -ENODEV; + + if (!msg || !evt) + return -EINVAL; + + mutex_lock(&pasid_mutex); + + prm = &evt->fault.prm; + sid = PCI_DEVID(bus, devfn); + pasid_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID; + private_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA; + last_page = prm->flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE; + + if (!pasid_present) { + ret = -EINVAL; + goto out; + } + + if (prm->pasid == 0 || prm->pasid >= PASID_MAX) { + ret = -EINVAL; + goto out; + } + + ret = pasid_to_svm_sdev(dev, prm->pasid, &svm, &sdev); + if (ret || !sdev) { + ret = -ENODEV; + goto out; + } + + /* + * For responses from userspace, need to make sure that the + * pasid has been bound to its mm. + */ + if (svm->flags & SVM_FLAG_GUEST_MODE) { + struct mm_struct *mm; + + mm = get_task_mm(current); + if (!mm) { + ret = -EINVAL; + goto out; + } + + if (mm != svm->mm) { + ret = -ENODEV; + mmput(mm); + goto out; + } + + mmput(mm); + } + + /* + * Per VT-d spec. v3.0 ch7.7, system software must respond + * with page group response if private data is present (PDP) + * or last page in group (LPIG) bit is set. This is an + * additional VT-d requirement beyond PCI ATS spec. + */ + if (last_page || private_present) { + struct qi_desc desc; + + desc.qw0 = QI_PGRP_PASID(prm->pasid) | QI_PGRP_DID(sid) | + QI_PGRP_PASID_P(pasid_present) | + QI_PGRP_PDP(private_present) | + QI_PGRP_RESP_CODE(msg->code) | + QI_PGRP_RESP_TYPE; + desc.qw1 = QI_PGRP_IDX(prm->grpid) | QI_PGRP_LPIG(last_page); + desc.qw2 = 0; + desc.qw3 = 0; + if (private_present) + memcpy(&desc.qw2, prm->private_data, + sizeof(prm->private_data)); + + qi_submit_sync(iommu, &desc, 1, 0); + } +out: + mutex_unlock(&pasid_mutex); + return ret; +} diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index a57ffbcc84c7..9ff5e340948b 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -740,6 +740,9 @@ struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata); void intel_svm_unbind(struct iommu_sva *handle); int intel_svm_get_pasid(struct iommu_sva *handle); +int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt, + struct iommu_page_response *msg); + struct svm_dev_ops; struct intel_svm_dev { From 02f3effddfd04f3f08a24d23a82d1c1c6d89b777 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Fri, 24 Jul 2020 09:49:25 +0800 Subject: [PATCH 167/291] iommu/vt-d: Rename intel-pasid.h to pasid.h As Intel VT-d files have been moved to its own subdirectory, the prefix makes no sense. No functional changes. Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20200724014925.15523-13-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/debugfs.c | 2 +- drivers/iommu/intel/iommu.c | 2 +- drivers/iommu/intel/pasid.c | 2 +- drivers/iommu/intel/{intel-pasid.h => pasid.h} | 2 +- drivers/iommu/intel/svm.c | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) rename drivers/iommu/intel/{intel-pasid.h => pasid.h} (98%) diff --git a/drivers/iommu/intel/debugfs.c b/drivers/iommu/intel/debugfs.c index cf1ebb98e418..efea7f02abd9 100644 --- a/drivers/iommu/intel/debugfs.c +++ b/drivers/iommu/intel/debugfs.c @@ -15,7 +15,7 @@ #include -#include "intel-pasid.h" +#include "pasid.h" struct tbl_walk { u16 bus; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 1cb3a2a050c3..b3faf99457a6 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -48,7 +48,7 @@ #include #include "../irq_remapping.h" -#include "intel-pasid.h" +#include "pasid.h" #define ROOT_SIZE VTD_PAGE_SIZE #define CONTEXT_SIZE VTD_PAGE_SIZE diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index fa0154cce537..e6faedf42fd4 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -19,7 +19,7 @@ #include #include -#include "intel-pasid.h" +#include "pasid.h" /* * Intel IOMMU system wide PASID name space: diff --git a/drivers/iommu/intel/intel-pasid.h b/drivers/iommu/intel/pasid.h similarity index 98% rename from drivers/iommu/intel/intel-pasid.h rename to drivers/iommu/intel/pasid.h index c5318d40e0fa..c9850766c3a9 100644 --- a/drivers/iommu/intel/intel-pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * intel-pasid.h - PASID idr, table and entry header + * pasid.h - PASID idr, table and entry header * * Copyright (C) 2018 Intel Corporation * diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 85ce8daa3177..442623ac4b47 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -20,7 +20,7 @@ #include #include -#include "intel-pasid.h" +#include "pasid.h" static irqreturn_t prq_event_thread(int irq, void *d); static void intel_svm_drain_prq(struct device *dev, int pasid); From 9930264fd997dad4c2cd8914cec7acab7c0ed984 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 12 Jun 2020 11:39:54 +0800 Subject: [PATCH 168/291] iommu: Mark __iommu_map_sg() as static Now __iommu_map_sg() is used only in iommu.c file, so mark it static. Signed-off-by: Baolin Wang Acked-by: Will Deacon Link: https://lore.kernel.org/r/ab722e9970739929738066777b8ee7930e32abd5.1591930156.git.baolin.wang@linux.alibaba.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 40947f5bc6c5..15ce5ec3edb2 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2330,9 +2330,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_unmap_fast); -size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot, - gfp_t gfp) +static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot, + gfp_t gfp) { size_t len = 0, mapped = 0; phys_addr_t start; From f34ce7a7018c2f71d78fc7f512f6daf01e487114 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 12 Jun 2020 11:39:55 +0800 Subject: [PATCH 169/291] iommu: Add gfp parameter to io_pgtable_ops->map() Now the ARM page tables are always allocated by GFP_ATOMIC parameter, but the iommu_ops->map() function has been added a gfp_t parameter by commit 781ca2de89ba ("iommu: Add gfp parameter to iommu_ops::map"), thus io_pgtable_ops->map() should use the gfp parameter passed from iommu_ops->map() to allocate page pages, which can avoid wasting the memory allocators atomic pools for some non-atomic contexts. Signed-off-by: Baolin Wang Acked-by: Will Deacon Link: https://lore.kernel.org/r/3093df4cb95497aaf713fca623ce4ecebb197c2e.1591930156.git.baolin.wang@linux.alibaba.com Signed-off-by: Joerg Roedel --- drivers/gpu/drm/panfrost/panfrost_mmu.c | 2 +- drivers/iommu/arm-smmu-v3.c | 2 +- drivers/iommu/arm-smmu.c | 2 +- drivers/iommu/io-pgtable-arm-v7s.c | 18 +++++++++--------- drivers/iommu/io-pgtable-arm.c | 18 +++++++++--------- drivers/iommu/ipmmu-vmsa.c | 2 +- drivers/iommu/msm_iommu.c | 2 +- drivers/iommu/mtk_iommu.c | 2 +- drivers/iommu/qcom_iommu.c | 2 +- include/linux/io-pgtable.h | 2 +- 10 files changed, 26 insertions(+), 26 deletions(-) diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index ed28aeba6d59..5a39eee8cf83 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -262,7 +262,7 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu, while (len) { size_t pgsize = get_pgsize(iova | paddr, len); - ops->map(ops, iova, paddr, pgsize, prot); + ops->map(ops, iova, paddr, pgsize, prot, GFP_KERNEL); iova += pgsize; paddr += pgsize; len -= pgsize; diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index f578677a5c41..7b59f06b3913 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -2850,7 +2850,7 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, if (!ops) return -ENODEV; - return ops->map(ops, iova, paddr, size, prot); + return ops->map(ops, iova, paddr, size, prot, gfp); } static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 243bc4cb2705..dc1d2535798a 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1227,7 +1227,7 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, return -ENODEV; arm_smmu_rpm_get(smmu); - ret = ops->map(ops, iova, paddr, size, prot); + ret = ops->map(ops, iova, paddr, size, prot, gfp); arm_smmu_rpm_put(smmu); return ret; diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 4272fe4e17f4..a688f22cbe3b 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -470,7 +470,7 @@ static arm_v7s_iopte arm_v7s_install_table(arm_v7s_iopte *table, static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova, phys_addr_t paddr, size_t size, int prot, - int lvl, arm_v7s_iopte *ptep) + int lvl, arm_v7s_iopte *ptep, gfp_t gfp) { struct io_pgtable_cfg *cfg = &data->iop.cfg; arm_v7s_iopte pte, *cptep; @@ -491,7 +491,7 @@ static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova, /* Grab a pointer to the next level */ pte = READ_ONCE(*ptep); if (!pte) { - cptep = __arm_v7s_alloc_table(lvl + 1, GFP_ATOMIC, data); + cptep = __arm_v7s_alloc_table(lvl + 1, gfp, data); if (!cptep) return -ENOMEM; @@ -512,11 +512,11 @@ static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova, } /* Rinse, repeat */ - return __arm_v7s_map(data, iova, paddr, size, prot, lvl + 1, cptep); + return __arm_v7s_map(data, iova, paddr, size, prot, lvl + 1, cptep, gfp); } static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops); struct io_pgtable *iop = &data->iop; @@ -530,7 +530,7 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova, paddr >= (1ULL << data->iop.cfg.oas))) return -ERANGE; - ret = __arm_v7s_map(data, iova, paddr, size, prot, 1, data->pgd); + ret = __arm_v7s_map(data, iova, paddr, size, prot, 1, data->pgd, gfp); /* * Synchronise all PTE updates for the new mapping before there's * a chance for anything to kick off a table walk for the new iova. @@ -922,12 +922,12 @@ static int __init arm_v7s_do_selftests(void) if (ops->map(ops, iova, iova, size, IOMMU_READ | IOMMU_WRITE | IOMMU_NOEXEC | - IOMMU_CACHE)) + IOMMU_CACHE, GFP_KERNEL)) return __FAIL(ops); /* Overlapping mappings */ if (!ops->map(ops, iova, iova + size, size, - IOMMU_READ | IOMMU_NOEXEC)) + IOMMU_READ | IOMMU_NOEXEC, GFP_KERNEL)) return __FAIL(ops); if (ops->iova_to_phys(ops, iova + 42) != (iova + 42)) @@ -946,7 +946,7 @@ static int __init arm_v7s_do_selftests(void) return __FAIL(ops); /* Remap of partial unmap */ - if (ops->map(ops, iova_start + size, size, size, IOMMU_READ)) + if (ops->map(ops, iova_start + size, size, size, IOMMU_READ, GFP_KERNEL)) return __FAIL(ops); if (ops->iova_to_phys(ops, iova_start + size + 42) @@ -967,7 +967,7 @@ static int __init arm_v7s_do_selftests(void) return __FAIL(ops); /* Remap full block */ - if (ops->map(ops, iova, iova, size, IOMMU_WRITE)) + if (ops->map(ops, iova, iova, size, IOMMU_WRITE, GFP_KERNEL)) return __FAIL(ops); if (ops->iova_to_phys(ops, iova + 42) != (iova + 42)) diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 04fbd4bf0ff9..4a5a7b083a9b 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -355,7 +355,7 @@ static arm_lpae_iopte arm_lpae_install_table(arm_lpae_iopte *table, static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova, phys_addr_t paddr, size_t size, arm_lpae_iopte prot, - int lvl, arm_lpae_iopte *ptep) + int lvl, arm_lpae_iopte *ptep, gfp_t gfp) { arm_lpae_iopte *cptep, pte; size_t block_size = ARM_LPAE_BLOCK_SIZE(lvl, data); @@ -376,7 +376,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova, /* Grab a pointer to the next level */ pte = READ_ONCE(*ptep); if (!pte) { - cptep = __arm_lpae_alloc_pages(tblsz, GFP_ATOMIC, cfg); + cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg); if (!cptep) return -ENOMEM; @@ -396,7 +396,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova, } /* Rinse, repeat */ - return __arm_lpae_map(data, iova, paddr, size, prot, lvl + 1, cptep); + return __arm_lpae_map(data, iova, paddr, size, prot, lvl + 1, cptep, gfp); } static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, @@ -461,7 +461,7 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, } static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova, - phys_addr_t paddr, size_t size, int iommu_prot) + phys_addr_t paddr, size_t size, int iommu_prot, gfp_t gfp) { struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); struct io_pgtable_cfg *cfg = &data->iop.cfg; @@ -483,7 +483,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova, return -ERANGE; prot = arm_lpae_prot_to_pte(data, iommu_prot); - ret = __arm_lpae_map(data, iova, paddr, size, prot, lvl, ptep); + ret = __arm_lpae_map(data, iova, paddr, size, prot, lvl, ptep, gfp); /* * Synchronise all PTE updates for the new mapping before there's * a chance for anything to kick off a table walk for the new iova. @@ -1178,12 +1178,12 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg) if (ops->map(ops, iova, iova, size, IOMMU_READ | IOMMU_WRITE | IOMMU_NOEXEC | - IOMMU_CACHE)) + IOMMU_CACHE, GFP_KERNEL)) return __FAIL(ops, i); /* Overlapping mappings */ if (!ops->map(ops, iova, iova + size, size, - IOMMU_READ | IOMMU_NOEXEC)) + IOMMU_READ | IOMMU_NOEXEC, GFP_KERNEL)) return __FAIL(ops, i); if (ops->iova_to_phys(ops, iova + 42) != (iova + 42)) @@ -1198,7 +1198,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg) return __FAIL(ops, i); /* Remap of partial unmap */ - if (ops->map(ops, SZ_1G + size, size, size, IOMMU_READ)) + if (ops->map(ops, SZ_1G + size, size, size, IOMMU_READ, GFP_KERNEL)) return __FAIL(ops, i); if (ops->iova_to_phys(ops, SZ_1G + size + 42) != (size + 42)) @@ -1216,7 +1216,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg) return __FAIL(ops, i); /* Remap full block */ - if (ops->map(ops, iova, iova, size, IOMMU_WRITE)) + if (ops->map(ops, iova, iova, size, IOMMU_WRITE, GFP_KERNEL)) return __FAIL(ops, i); if (ops->iova_to_phys(ops, iova + 42) != (iova + 42)) diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 4c2972f3153b..87475b2f7ef1 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -687,7 +687,7 @@ static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova, if (!domain) return -ENODEV; - return domain->iop->map(domain->iop, iova, paddr, size, prot); + return domain->iop->map(domain->iop, iova, paddr, size, prot, gfp); } static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova, diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index f773cc85f311..3615cd6241c4 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -491,7 +491,7 @@ static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova, int ret; spin_lock_irqsave(&priv->pgtlock, flags); - ret = priv->iop->map(priv->iop, iova, pa, len, prot); + ret = priv->iop->map(priv->iop, iova, pa, len, prot, GFP_ATOMIC); spin_unlock_irqrestore(&priv->pgtlock, flags); return ret; diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 2be96f1cdbd2..b7b16414a217 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -397,7 +397,7 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, paddr |= BIT_ULL(32); /* Synchronize with the tlb_lock */ - return dom->iop->map(dom->iop, iova, paddr, size, prot); + return dom->iop->map(dom->iop, iova, paddr, size, prot, gfp); } static size_t mtk_iommu_unmap(struct iommu_domain *domain, diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index c3e1fbd1988c..cfcfd7553b30 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -441,7 +441,7 @@ static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova, return -ENODEV; spin_lock_irqsave(&qcom_domain->pgtbl_lock, flags); - ret = ops->map(ops, iova, paddr, size, prot); + ret = ops->map(ops, iova, paddr, size, prot, GFP_ATOMIC); spin_unlock_irqrestore(&qcom_domain->pgtbl_lock, flags); return ret; } diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 53d53c6c2be9..23285ba645db 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -155,7 +155,7 @@ struct io_pgtable_cfg { */ struct io_pgtable_ops { int (*map)(struct io_pgtable_ops *ops, unsigned long iova, - phys_addr_t paddr, size_t size, int prot); + phys_addr_t paddr, size_t size, int prot, gfp_t gfp); size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova, size_t size, struct iommu_iotlb_gather *gather); phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops, From b1012ca8dc4f9b1a1fe8e2cb1590dd6d43ea3849 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 23 Jul 2020 09:34:37 +0800 Subject: [PATCH 170/291] iommu/vt-d: Skip TE disabling on quirky gfx dedicated iommu The VT-d spec requires (10.4.4 Global Command Register, TE field) that: Hardware implementations supporting DMA draining must drain any in-flight DMA read/write requests queued within the Root-Complex before completing the translation enable command and reflecting the status of the command through the TES field in the Global Status register. Unfortunately, some integrated graphic devices fail to do so after some kind of power state transition. As the result, the system might stuck in iommu_disable_translation(), waiting for the completion of TE transition. This provides a quirk list for those devices and skips TE disabling if the qurik hits. Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=208363 Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=206571 Signed-off-by: Lu Baolu Tested-by: Koba Ko Tested-by: Jun Miao Cc: Ashok Raj Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200723013437.2268-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 1 + drivers/iommu/intel/iommu.c | 27 +++++++++++++++++++++++++++ include/linux/dmar.h | 1 + include/linux/intel-iommu.h | 2 ++ 4 files changed, 31 insertions(+) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index f6cbe3f95c8d..93e6345f3414 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1102,6 +1102,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) } drhd->iommu = iommu; + iommu->drhd = drhd; return 0; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index b3faf99457a6..0c2d582ff8cd 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -356,6 +356,7 @@ static int intel_iommu_strict; static int intel_iommu_superpage = 1; static int iommu_identity_mapping; static int intel_no_bounce; +static int iommu_skip_te_disable; #define IDENTMAP_GFX 2 #define IDENTMAP_AZALIA 4 @@ -1633,6 +1634,10 @@ static void iommu_disable_translation(struct intel_iommu *iommu) u32 sts; unsigned long flag; + if (iommu_skip_te_disable && iommu->drhd->gfx_dedicated && + (cap_read_drain(iommu->cap) || cap_write_drain(iommu->cap))) + return; + raw_spin_lock_irqsave(&iommu->register_lock, flag); iommu->gcmd &= ~DMA_GCMD_TE; writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG); @@ -4043,6 +4048,7 @@ static void __init init_no_remapping_devices(void) /* This IOMMU has *only* gfx devices. Either bypass it or set the gfx_mapped flag, as appropriate */ + drhd->gfx_dedicated = 1; if (!dmar_map_gfx) { drhd->ignored = 1; for_each_active_dev_scope(drhd->devices, @@ -6170,6 +6176,27 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_g DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt); +static void quirk_igfx_skip_te_disable(struct pci_dev *dev) +{ + unsigned short ver; + + if (!IS_GFX_DEVICE(dev)) + return; + + ver = (dev->device >> 8) & 0xff; + if (ver != 0x45 && ver != 0x46 && ver != 0x4c && + ver != 0x4e && ver != 0x8a && ver != 0x98 && + ver != 0x9a) + return; + + if (risky_device(dev)) + return; + + pci_info(dev, "Skip IOMMU disabling for graphics\n"); + iommu_skip_te_disable = 1; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, quirk_igfx_skip_te_disable); + /* On Tylersburg chipsets, some BIOSes have been known to enable the ISOCH DMAR unit for the Azalia sound device, but not give it any TLB entries, which causes it to deadlock. Check for that. We do diff --git a/include/linux/dmar.h b/include/linux/dmar.h index d7bf029df737..65565820328a 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -48,6 +48,7 @@ struct dmar_drhd_unit { u16 segment; /* PCI domain */ u8 ignored:1; /* ignore drhd */ u8 include_all:1; + u8 gfx_dedicated:1; /* graphic dedicated */ struct intel_iommu *iommu; }; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 9ff5e340948b..b1ed2f25f7c0 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -599,6 +599,8 @@ struct intel_iommu { struct iommu_device iommu; /* IOMMU core code handle */ int node; u32 flags; /* Software defined flags */ + + struct dmar_drhd_unit *drhd; }; /* PCI domain-device relationship */ From 92fe2aa859f52ce6aa595ca97fec110dc7100e63 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:07:30 -0700 Subject: [PATCH 171/291] libnvdimm: Validate command family indices The ND_CMD_CALL format allows for a general passthrough of passlisted commands targeting a given command set. However there is no validation of the family index relative to what the bus supports. - Update the NFIT bus implementation (the only one that supports ND_CMD_CALL passthrough) to also passlist the valid set of command family indices. - Update the generic __nd_ioctl() path to validate that field on behalf of all implementations. Fixes: 31eca76ba2fc ("nfit, libnvdimm: limited/whitelisted dimm command marshaling mechanism") Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- drivers/acpi/nfit/core.c | 11 +++++++++-- drivers/acpi/nfit/nfit.h | 1 - drivers/nvdimm/bus.c | 16 ++++++++++++++++ include/linux/libnvdimm.h | 2 ++ include/uapi/linux/ndctl.h | 4 ++++ 5 files changed, 31 insertions(+), 3 deletions(-) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 7c138a4edc03..1f72ce1a782b 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1823,6 +1823,7 @@ static void populate_shutdown_status(struct nfit_mem *nfit_mem) static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, u32 device_handle) { + struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc; struct acpi_device *adev, *adev_dimm; struct device *dev = acpi_desc->dev; unsigned long dsm_mask, label_mask; @@ -1834,6 +1835,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, /* nfit test assumes 1:1 relationship between commands and dsms */ nfit_mem->dsm_mask = acpi_desc->dimm_cmd_force_en; nfit_mem->family = NVDIMM_FAMILY_INTEL; + set_bit(NVDIMM_FAMILY_INTEL, &nd_desc->dimm_family_mask); if (dcr->valid_fields & ACPI_NFIT_CONTROL_MFG_INFO_VALID) sprintf(nfit_mem->id, "%04x-%02x-%04x-%08x", @@ -1886,10 +1888,13 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, * Note, that checking for function0 (bit0) tells us if any commands * are reachable through this GUID. */ + clear_bit(NVDIMM_FAMILY_INTEL, &nd_desc->dimm_family_mask); for (i = 0; i <= NVDIMM_FAMILY_MAX; i++) - if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1)) + if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1)) { + set_bit(i, &nd_desc->dimm_family_mask); if (family < 0 || i == default_dsm_family) family = i; + } /* limit the supported commands to those that are publicly documented */ nfit_mem->family = family; @@ -2153,6 +2158,9 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) nd_desc->cmd_mask = acpi_desc->bus_cmd_force_en; nd_desc->bus_dsm_mask = acpi_desc->bus_nfit_cmd_force_en; + set_bit(ND_CMD_CALL, &nd_desc->cmd_mask); + set_bit(NVDIMM_BUS_FAMILY_NFIT, &nd_desc->bus_family_mask); + adev = to_acpi_dev(acpi_desc); if (!adev) return; @@ -2160,7 +2168,6 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) for (i = ND_CMD_ARS_CAP; i <= ND_CMD_CLEAR_ERROR; i++) if (acpi_check_dsm(adev->handle, guid, 1, 1ULL << i)) set_bit(i, &nd_desc->cmd_mask); - set_bit(ND_CMD_CALL, &nd_desc->cmd_mask); dsm_mask = (1 << ND_CMD_ARS_CAP) | diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index f5525f8bb770..5c5e7ebba8dc 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -33,7 +33,6 @@ | ACPI_NFIT_MEM_RESTORE_FAILED | ACPI_NFIT_MEM_FLUSH_FAILED \ | ACPI_NFIT_MEM_NOT_ARMED | ACPI_NFIT_MEM_MAP_FAILED) -#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_HYPERV #define NVDIMM_CMD_MAX 31 #define NVDIMM_STANDARD_CMDMASK \ diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 09087c38fabd..955265656b96 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -1037,9 +1037,25 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, dimm_name = "bus"; } + /* Validate command family support against bus declared support */ if (cmd == ND_CMD_CALL) { + unsigned long *mask; + if (copy_from_user(&pkg, p, sizeof(pkg))) return -EFAULT; + + if (nvdimm) { + if (pkg.nd_family > NVDIMM_FAMILY_MAX) + return -EINVAL; + mask = &nd_desc->dimm_family_mask; + } else { + if (pkg.nd_family > NVDIMM_BUS_FAMILY_MAX) + return -EINVAL; + mask = &nd_desc->bus_family_mask; + } + + if (!test_bit(pkg.nd_family, mask)) + return -EINVAL; } if (!desc || diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 18da4059be09..bd39a2cf7972 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -78,6 +78,8 @@ struct nvdimm_bus_descriptor { const struct attribute_group **attr_groups; unsigned long bus_dsm_mask; unsigned long cmd_mask; + unsigned long dimm_family_mask; + unsigned long bus_family_mask; struct module *module; char *provider_name; struct device_node *of_node; diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 0e09dc5cec19..e9468b9332bd 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -245,6 +245,10 @@ struct nd_cmd_pkg { #define NVDIMM_FAMILY_MSFT 3 #define NVDIMM_FAMILY_HYPERV 4 #define NVDIMM_FAMILY_PAPR 5 +#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_PAPR + +#define NVDIMM_BUS_FAMILY_NFIT 0 +#define NVDIMM_BUS_FAMILY_MAX NVDIMM_BUS_FAMILY_NFIT #define ND_IOCTL_CALL _IOWR(ND_IOCTL, ND_CMD_CALL,\ struct nd_cmd_pkg) From d46e6a2176f8edf7030db34aeb54a4f016fabe0a Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:07:35 -0700 Subject: [PATCH 172/291] ACPI: NFIT: Move bus_dsm_mask out of generic nvdimm_bus_descriptor DSMs are strictly an ACPI mechanism, evict the bus_dsm_mask concept from the generic 'struct nvdimm_bus_descriptor' object. As a side effect the test facility ->bus_nfit_cmd_force_en is no longer necessary. The test infrastructure can communicate that information directly in ->bus_dsm_mask. Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- drivers/acpi/nfit/core.c | 8 ++++---- drivers/acpi/nfit/nfit.h | 2 +- include/linux/libnvdimm.h | 1 - tools/testing/nvdimm/test/nfit.c | 16 ++++++++-------- 4 files changed, 13 insertions(+), 14 deletions(-) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 1f72ce1a782b..9fdd655bdf0e 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -478,7 +478,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, cmd_name = nvdimm_bus_cmd_name(cmd); cmd_mask = nd_desc->cmd_mask; - dsm_mask = nd_desc->bus_dsm_mask; + dsm_mask = acpi_desc->bus_dsm_mask; desc = nd_cmd_bus_desc(cmd); guid = to_nfit_uuid(NFIT_DEV_BUS); handle = adev->handle; @@ -1238,8 +1238,9 @@ static ssize_t bus_dsm_mask_show(struct device *dev, { struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus); + struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); - return sprintf(buf, "%#lx\n", nd_desc->bus_dsm_mask); + return sprintf(buf, "%#lx\n", acpi_desc->bus_dsm_mask); } static struct device_attribute dev_attr_bus_dsm_mask = __ATTR(dsm_mask, 0444, bus_dsm_mask_show, NULL); @@ -2157,7 +2158,6 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) int i; nd_desc->cmd_mask = acpi_desc->bus_cmd_force_en; - nd_desc->bus_dsm_mask = acpi_desc->bus_nfit_cmd_force_en; set_bit(ND_CMD_CALL, &nd_desc->cmd_mask); set_bit(NVDIMM_BUS_FAMILY_NFIT, &nd_desc->bus_family_mask); @@ -2180,7 +2180,7 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) (1 << NFIT_CMD_ARS_INJECT_GET); for_each_set_bit(i, &dsm_mask, BITS_PER_LONG) if (acpi_check_dsm(adev->handle, guid, 1, 1ULL << i)) - set_bit(i, &nd_desc->bus_dsm_mask); + set_bit(i, &acpi_desc->bus_dsm_mask); } static ssize_t range_index_show(struct device *dev, diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 5c5e7ebba8dc..da097149d94d 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -237,7 +237,7 @@ struct acpi_nfit_desc { unsigned long scrub_flags; unsigned long dimm_cmd_force_en; unsigned long bus_cmd_force_en; - unsigned long bus_nfit_cmd_force_en; + unsigned long bus_dsm_mask; unsigned int platform_cap; unsigned int scrub_tmo; int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index bd39a2cf7972..ad9898ece7d3 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -76,7 +76,6 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc, struct device_node; struct nvdimm_bus_descriptor { const struct attribute_group **attr_groups; - unsigned long bus_dsm_mask; unsigned long cmd_mask; unsigned long dimm_family_mask; unsigned long bus_family_mask; diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index a8ee5c4d41eb..a59174ba1d2a 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -2507,10 +2507,10 @@ static void nfit_test0_setup(struct nfit_test *t) set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en); set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en); set_bit(ND_CMD_CALL, &acpi_desc->bus_cmd_force_en); - set_bit(NFIT_CMD_TRANSLATE_SPA, &acpi_desc->bus_nfit_cmd_force_en); - set_bit(NFIT_CMD_ARS_INJECT_SET, &acpi_desc->bus_nfit_cmd_force_en); - set_bit(NFIT_CMD_ARS_INJECT_CLEAR, &acpi_desc->bus_nfit_cmd_force_en); - set_bit(NFIT_CMD_ARS_INJECT_GET, &acpi_desc->bus_nfit_cmd_force_en); + set_bit(NFIT_CMD_TRANSLATE_SPA, &acpi_desc->bus_dsm_mask); + set_bit(NFIT_CMD_ARS_INJECT_SET, &acpi_desc->bus_dsm_mask); + set_bit(NFIT_CMD_ARS_INJECT_CLEAR, &acpi_desc->bus_dsm_mask); + set_bit(NFIT_CMD_ARS_INJECT_GET, &acpi_desc->bus_dsm_mask); set_bit(ND_INTEL_FW_GET_INFO, &acpi_desc->dimm_cmd_force_en); set_bit(ND_INTEL_FW_START_UPDATE, &acpi_desc->dimm_cmd_force_en); set_bit(ND_INTEL_FW_SEND_DATA, &acpi_desc->dimm_cmd_force_en); @@ -2731,11 +2731,11 @@ static int nfit_ctl_test(struct device *dev) .module = THIS_MODULE, .provider_name = "ACPI.NFIT", .ndctl = acpi_nfit_ctl, - .bus_dsm_mask = 1UL << NFIT_CMD_TRANSLATE_SPA - | 1UL << NFIT_CMD_ARS_INJECT_SET - | 1UL << NFIT_CMD_ARS_INJECT_CLEAR - | 1UL << NFIT_CMD_ARS_INJECT_GET, }, + .bus_dsm_mask = 1UL << NFIT_CMD_TRANSLATE_SPA + | 1UL << NFIT_CMD_ARS_INJECT_SET + | 1UL << NFIT_CMD_ARS_INJECT_CLEAR + | 1UL << NFIT_CMD_ARS_INJECT_GET, .dev = &adev->dev, }; From 6450ddbd5d8e83ea9927c7f9076a21f829699e0f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:07:40 -0700 Subject: [PATCH 173/291] ACPI: NFIT: Define runtime firmware activation commands Platform reboots are expensive. Towards reducing downtime to apply firmware updates the Intel NVDIMM command definition is growing support for applying live firmware updates that only require temporarily suspending memory traffic instead of a full reboot. Follow-on commits add support for triggering firmware activation, this patch only defines the commands, adds probe support, and validates that they are blocked via the ioctl path. The ioctl-path block ensures that the OS is in charge since these commands have side effects only the OS can handle. Specifically firmware activation may cause the memory controller to be quiesced on the order of 100s of milliseconds. In that case Linux ensure the activation only takes place while the OS is in a suspend state. Link: https://pmem.io/documents/IntelOptanePMem_DSM_Interface-V2.0.pdf Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Cc: "Rafael J. Wysocki" Cc: Len Brown Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- drivers/acpi/nfit/core.c | 86 +++++++++++++++++++++++++------------- drivers/acpi/nfit/intel.h | 53 +++++++++++++++++++++++ drivers/acpi/nfit/nfit.h | 25 ++++++++++- include/uapi/linux/ndctl.h | 3 +- 4 files changed, 137 insertions(+), 30 deletions(-) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 9fdd655bdf0e..78cc9e2d2aa3 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -73,6 +73,18 @@ const guid_t *to_nfit_uuid(enum nfit_uuids id) } EXPORT_SYMBOL(to_nfit_uuid); +static const guid_t *to_nfit_bus_uuid(int family) +{ + if (WARN_ONCE(family == NVDIMM_BUS_FAMILY_NFIT, + "only secondary bus families can be translated\n")) + return NULL; + /* + * The index of bus UUIDs starts immediately following the last + * NVDIMM/leaf family. + */ + return to_nfit_uuid(family + NVDIMM_FAMILY_MAX); +} + static struct acpi_device *to_acpi_dev(struct acpi_nfit_desc *acpi_desc) { struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc; @@ -362,24 +374,8 @@ static u8 nfit_dsm_revid(unsigned family, unsigned func) { static const u8 revid_table[NVDIMM_FAMILY_MAX+1][NVDIMM_CMD_MAX+1] = { [NVDIMM_FAMILY_INTEL] = { - [NVDIMM_INTEL_GET_MODES] = 2, - [NVDIMM_INTEL_GET_FWINFO] = 2, - [NVDIMM_INTEL_START_FWUPDATE] = 2, - [NVDIMM_INTEL_SEND_FWUPDATE] = 2, - [NVDIMM_INTEL_FINISH_FWUPDATE] = 2, - [NVDIMM_INTEL_QUERY_FWUPDATE] = 2, - [NVDIMM_INTEL_SET_THRESHOLD] = 2, - [NVDIMM_INTEL_INJECT_ERROR] = 2, - [NVDIMM_INTEL_GET_SECURITY_STATE] = 2, - [NVDIMM_INTEL_SET_PASSPHRASE] = 2, - [NVDIMM_INTEL_DISABLE_PASSPHRASE] = 2, - [NVDIMM_INTEL_UNLOCK_UNIT] = 2, - [NVDIMM_INTEL_FREEZE_LOCK] = 2, - [NVDIMM_INTEL_SECURE_ERASE] = 2, - [NVDIMM_INTEL_OVERWRITE] = 2, - [NVDIMM_INTEL_QUERY_OVERWRITE] = 2, - [NVDIMM_INTEL_SET_MASTER_PASSPHRASE] = 2, - [NVDIMM_INTEL_MASTER_SECURE_ERASE] = 2, + [NVDIMM_INTEL_GET_MODES ... + NVDIMM_INTEL_FW_ACTIVATE_ARM] = 2, }, }; u8 id; @@ -406,7 +402,7 @@ static bool payload_dumpable(struct nvdimm *nvdimm, unsigned int func) } static int cmd_to_func(struct nfit_mem *nfit_mem, unsigned int cmd, - struct nd_cmd_pkg *call_pkg) + struct nd_cmd_pkg *call_pkg, int *family) { if (call_pkg) { int i; @@ -417,6 +413,7 @@ static int cmd_to_func(struct nfit_mem *nfit_mem, unsigned int cmd, for (i = 0; i < ARRAY_SIZE(call_pkg->nd_reserved2); i++) if (call_pkg->nd_reserved2[i]) return -EINVAL; + *family = call_pkg->nd_family; return call_pkg->nd_command; } @@ -450,13 +447,14 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, acpi_handle handle; const guid_t *guid; int func, rc, i; + int family = 0; if (cmd_rc) *cmd_rc = -EINVAL; if (cmd == ND_CMD_CALL) call_pkg = buf; - func = cmd_to_func(nfit_mem, cmd, call_pkg); + func = cmd_to_func(nfit_mem, cmd, call_pkg, &family); if (func < 0) return func; @@ -478,9 +476,17 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, cmd_name = nvdimm_bus_cmd_name(cmd); cmd_mask = nd_desc->cmd_mask; - dsm_mask = acpi_desc->bus_dsm_mask; + if (cmd == ND_CMD_CALL && call_pkg->nd_family) { + family = call_pkg->nd_family; + if (!test_bit(family, &nd_desc->bus_family_mask)) + return -EINVAL; + dsm_mask = acpi_desc->family_dsm_mask[family]; + guid = to_nfit_bus_uuid(family); + } else { + dsm_mask = acpi_desc->bus_dsm_mask; + guid = to_nfit_uuid(NFIT_DEV_BUS); + } desc = nd_cmd_bus_desc(cmd); - guid = to_nfit_uuid(NFIT_DEV_BUS); handle = adev->handle; dimm_name = "bus"; } @@ -516,8 +522,8 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, in_buf.buffer.length = call_pkg->nd_size_in; } - dev_dbg(dev, "%s cmd: %d: func: %d input length: %d\n", - dimm_name, cmd, func, in_buf.buffer.length); + dev_dbg(dev, "%s cmd: %d: family: %d func: %d input length: %d\n", + dimm_name, cmd, family, func, in_buf.buffer.length); if (payload_dumpable(nvdimm, func)) print_hex_dump_debug("nvdimm in ", DUMP_PREFIX_OFFSET, 4, 4, in_buf.buffer.pointer, @@ -2153,14 +2159,21 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) { struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc; const guid_t *guid = to_nfit_uuid(NFIT_DEV_BUS); + unsigned long dsm_mask, *mask; struct acpi_device *adev; - unsigned long dsm_mask; int i; - nd_desc->cmd_mask = acpi_desc->bus_cmd_force_en; set_bit(ND_CMD_CALL, &nd_desc->cmd_mask); set_bit(NVDIMM_BUS_FAMILY_NFIT, &nd_desc->bus_family_mask); + /* enable nfit_test to inject bus command emulation */ + if (acpi_desc->bus_cmd_force_en) { + nd_desc->cmd_mask = acpi_desc->bus_cmd_force_en; + mask = &nd_desc->bus_family_mask; + if (acpi_desc->family_dsm_mask[NVDIMM_BUS_FAMILY_INTEL]) + set_bit(NVDIMM_BUS_FAMILY_INTEL, mask); + } + adev = to_acpi_dev(acpi_desc); if (!adev) return; @@ -2181,6 +2194,14 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) for_each_set_bit(i, &dsm_mask, BITS_PER_LONG) if (acpi_check_dsm(adev->handle, guid, 1, 1ULL << i)) set_bit(i, &acpi_desc->bus_dsm_mask); + + /* Enumerate allowed NVDIMM_BUS_FAMILY_INTEL commands */ + dsm_mask = NVDIMM_BUS_INTEL_FW_ACTIVATE_CMDMASK; + guid = to_nfit_bus_uuid(NVDIMM_BUS_FAMILY_INTEL); + mask = &acpi_desc->family_dsm_mask[NVDIMM_BUS_FAMILY_INTEL]; + for_each_set_bit(i, &dsm_mask, BITS_PER_LONG) + if (acpi_check_dsm(adev->handle, guid, 1, 1ULL << i)) + set_bit(i, mask); } static ssize_t range_index_show(struct device *dev, @@ -3492,7 +3513,10 @@ static int __acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc, return 0; } -/* prevent security commands from being issued via ioctl */ +/* + * Prevent security and firmware activate commands from being issued via + * ioctl. + */ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, unsigned int cmd, void *buf) { @@ -3503,10 +3527,15 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc, call_pkg->nd_family == NVDIMM_FAMILY_INTEL) { func = call_pkg->nd_command; if (func > NVDIMM_CMD_MAX || - (1 << func) & NVDIMM_INTEL_SECURITY_CMDMASK) + (1 << func) & NVDIMM_INTEL_DENY_CMDMASK) return -EOPNOTSUPP; } + /* block all non-nfit bus commands */ + if (!nvdimm && cmd == ND_CMD_CALL && + call_pkg->nd_family != NVDIMM_BUS_FAMILY_NFIT) + return -EOPNOTSUPP; + return __acpi_nfit_clear_to_send(nd_desc, nvdimm, cmd); } @@ -3798,6 +3827,7 @@ static __init int nfit_init(void) guid_parse(UUID_NFIT_DIMM_N_HPE2, &nfit_uuid[NFIT_DEV_DIMM_N_HPE2]); guid_parse(UUID_NFIT_DIMM_N_MSFT, &nfit_uuid[NFIT_DEV_DIMM_N_MSFT]); guid_parse(UUID_NFIT_DIMM_N_HYPERV, &nfit_uuid[NFIT_DEV_DIMM_N_HYPERV]); + guid_parse(UUID_INTEL_BUS, &nfit_uuid[NFIT_BUS_INTEL]); nfit_wq = create_singlethread_workqueue("nfit"); if (!nfit_wq) diff --git a/drivers/acpi/nfit/intel.h b/drivers/acpi/nfit/intel.h index 0aca682ab9d7..868d073731cc 100644 --- a/drivers/acpi/nfit/intel.h +++ b/drivers/acpi/nfit/intel.h @@ -111,4 +111,57 @@ struct nd_intel_master_secure_erase { u8 passphrase[ND_INTEL_PASSPHRASE_SIZE]; u32 status; } __packed; + +#define ND_INTEL_FWA_IDLE 0 +#define ND_INTEL_FWA_ARMED 1 +#define ND_INTEL_FWA_BUSY 2 + +#define ND_INTEL_DIMM_FWA_NONE 0 +#define ND_INTEL_DIMM_FWA_NOTSTAGED 1 +#define ND_INTEL_DIMM_FWA_SUCCESS 2 +#define ND_INTEL_DIMM_FWA_NEEDRESET 3 +#define ND_INTEL_DIMM_FWA_MEDIAFAILED 4 +#define ND_INTEL_DIMM_FWA_ABORT 5 +#define ND_INTEL_DIMM_FWA_NOTSUPP 6 +#define ND_INTEL_DIMM_FWA_ERROR 7 + +struct nd_intel_fw_activate_dimminfo { + u32 status; + u16 result; + u8 state; + u8 reserved[7]; +} __packed; + +struct nd_intel_fw_activate_arm { + u8 activate_arm; + u32 status; +} __packed; + +/* Root device command payloads */ +#define ND_INTEL_BUS_FWA_CAP_FWQUIESCE (1 << 0) +#define ND_INTEL_BUS_FWA_CAP_OSQUIESCE (1 << 1) +#define ND_INTEL_BUS_FWA_CAP_RESET (1 << 2) + +struct nd_intel_bus_fw_activate_businfo { + u32 status; + u16 reserved; + u8 state; + u8 capability; + u64 activate_tmo; + u64 cpu_quiesce_tmo; + u64 io_quiesce_tmo; + u64 max_quiesce_tmo; +} __packed; + +#define ND_INTEL_BUS_FWA_STATUS_NOARM (6 | 1 << 16) +#define ND_INTEL_BUS_FWA_STATUS_BUSY (6 | 2 << 16) +#define ND_INTEL_BUS_FWA_STATUS_NOFW (6 | 3 << 16) +#define ND_INTEL_BUS_FWA_STATUS_TMO (6 | 4 << 16) +#define ND_INTEL_BUS_FWA_STATUS_NOIDLE (6 | 5 << 16) +#define ND_INTEL_BUS_FWA_STATUS_ABORT (6 | 6 << 16) + +struct nd_intel_bus_fw_activate { + u8 iodev_state; + u32 status; +} __packed; #endif diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index da097149d94d..97c122628975 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -18,6 +18,7 @@ /* http://pmem.io/documents/NVDIMM_DSM_Interface-V1.6.pdf */ #define UUID_NFIT_DIMM "4309ac30-0d11-11e4-9191-0800200c9a66" +#define UUID_INTEL_BUS "c7d8acd4-2df8-4b82-9f65-a325335af149" /* https://github.com/HewlettPackard/hpe-nvm/blob/master/Documentation/ */ #define UUID_NFIT_DIMM_N_HPE1 "9002c334-acf3-4c0e-9642-a235f0d53bc6" @@ -65,6 +66,13 @@ enum nvdimm_family_cmds { NVDIMM_INTEL_QUERY_OVERWRITE = 26, NVDIMM_INTEL_SET_MASTER_PASSPHRASE = 27, NVDIMM_INTEL_MASTER_SECURE_ERASE = 28, + NVDIMM_INTEL_FW_ACTIVATE_DIMMINFO = 29, + NVDIMM_INTEL_FW_ACTIVATE_ARM = 30, +}; + +enum nvdimm_bus_family_cmds { + NVDIMM_BUS_INTEL_FW_ACTIVATE_BUSINFO = 1, + NVDIMM_BUS_INTEL_FW_ACTIVATE = 2, }; #define NVDIMM_INTEL_SECURITY_CMDMASK \ @@ -75,13 +83,22 @@ enum nvdimm_family_cmds { | 1 << NVDIMM_INTEL_SET_MASTER_PASSPHRASE \ | 1 << NVDIMM_INTEL_MASTER_SECURE_ERASE) +#define NVDIMM_INTEL_FW_ACTIVATE_CMDMASK \ +(1 << NVDIMM_INTEL_FW_ACTIVATE_DIMMINFO | 1 << NVDIMM_INTEL_FW_ACTIVATE_ARM) + +#define NVDIMM_BUS_INTEL_FW_ACTIVATE_CMDMASK \ +(1 << NVDIMM_BUS_INTEL_FW_ACTIVATE_BUSINFO | 1 << NVDIMM_BUS_INTEL_FW_ACTIVATE) + #define NVDIMM_INTEL_CMDMASK \ (NVDIMM_STANDARD_CMDMASK | 1 << NVDIMM_INTEL_GET_MODES \ | 1 << NVDIMM_INTEL_GET_FWINFO | 1 << NVDIMM_INTEL_START_FWUPDATE \ | 1 << NVDIMM_INTEL_SEND_FWUPDATE | 1 << NVDIMM_INTEL_FINISH_FWUPDATE \ | 1 << NVDIMM_INTEL_QUERY_FWUPDATE | 1 << NVDIMM_INTEL_SET_THRESHOLD \ | 1 << NVDIMM_INTEL_INJECT_ERROR | 1 << NVDIMM_INTEL_LATCH_SHUTDOWN \ - | NVDIMM_INTEL_SECURITY_CMDMASK) + | NVDIMM_INTEL_SECURITY_CMDMASK | NVDIMM_INTEL_FW_ACTIVATE_CMDMASK) + +#define NVDIMM_INTEL_DENY_CMDMASK \ +(NVDIMM_INTEL_SECURITY_CMDMASK | NVDIMM_INTEL_FW_ACTIVATE_CMDMASK) enum nfit_uuids { /* for simplicity alias the uuid index with the family id */ @@ -90,6 +107,11 @@ enum nfit_uuids { NFIT_DEV_DIMM_N_HPE2 = NVDIMM_FAMILY_HPE2, NFIT_DEV_DIMM_N_MSFT = NVDIMM_FAMILY_MSFT, NFIT_DEV_DIMM_N_HYPERV = NVDIMM_FAMILY_HYPERV, + /* + * to_nfit_bus_uuid() expects to translate bus uuid family ids + * to a UUID index using NVDIMM_FAMILY_MAX as an offset + */ + NFIT_BUS_INTEL = NVDIMM_FAMILY_MAX + NVDIMM_BUS_FAMILY_INTEL, NFIT_SPA_VOLATILE, NFIT_SPA_PM, NFIT_SPA_DCR, @@ -238,6 +260,7 @@ struct acpi_nfit_desc { unsigned long dimm_cmd_force_en; unsigned long bus_cmd_force_en; unsigned long bus_dsm_mask; + unsigned long family_dsm_mask[NVDIMM_BUS_FAMILY_MAX + 1]; unsigned int platform_cap; unsigned int scrub_tmo; int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index e9468b9332bd..8cf1e4884fd5 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -248,7 +248,8 @@ struct nd_cmd_pkg { #define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_PAPR #define NVDIMM_BUS_FAMILY_NFIT 0 -#define NVDIMM_BUS_FAMILY_MAX NVDIMM_BUS_FAMILY_NFIT +#define NVDIMM_BUS_FAMILY_INTEL 1 +#define NVDIMM_BUS_FAMILY_MAX NVDIMM_BUS_FAMILY_INTEL #define ND_IOCTL_CALL _IOWR(ND_IOCTL, ND_CMD_CALL,\ struct nd_cmd_pkg) From 24770658dc03bc568dd217b470cba827aeaed582 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:07:46 -0700 Subject: [PATCH 174/291] tools/testing/nvdimm: Cleanup dimm index passing The ND_CMD_CALL path only applies to the nfit_test0 emulated DIMMs. Cleanup occurrences of (i - t->dcr_idx) since that offset fixup only applies to cases where nfit_test1 needs a bus-local index. Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- tools/testing/nvdimm/test/nfit.c | 34 +++++++++++++++++--------------- 1 file changed, 18 insertions(+), 16 deletions(-) diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index a59174ba1d2a..ddf9b3095bfa 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1224,6 +1224,11 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc, i = get_dimm(nfit_mem, func); if (i < 0) return i; + if (i >= NUM_DCR) { + dev_WARN_ONCE(&t->pdev.dev, 1, + "ND_CMD_CALL only valid for nfit_test0\n"); + return -EINVAL; + } switch (func) { case NVDIMM_INTEL_GET_SECURITY_STATE: @@ -1252,11 +1257,11 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc, break; case NVDIMM_INTEL_OVERWRITE: rc = nd_intel_test_cmd_overwrite(t, - buf, buf_len, i - t->dcr_idx); + buf, buf_len, i); break; case NVDIMM_INTEL_QUERY_OVERWRITE: rc = nd_intel_test_cmd_query_overwrite(t, - buf, buf_len, i - t->dcr_idx); + buf, buf_len, i); break; case NVDIMM_INTEL_SET_MASTER_PASSPHRASE: rc = nd_intel_test_cmd_master_set_pass(t, @@ -1272,48 +1277,45 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc, break; case ND_INTEL_FW_GET_INFO: rc = nd_intel_test_get_fw_info(t, buf, - buf_len, i - t->dcr_idx); + buf_len, i); break; case ND_INTEL_FW_START_UPDATE: rc = nd_intel_test_start_update(t, buf, - buf_len, i - t->dcr_idx); + buf_len, i); break; case ND_INTEL_FW_SEND_DATA: rc = nd_intel_test_send_data(t, buf, - buf_len, i - t->dcr_idx); + buf_len, i); break; case ND_INTEL_FW_FINISH_UPDATE: rc = nd_intel_test_finish_fw(t, buf, - buf_len, i - t->dcr_idx); + buf_len, i); break; case ND_INTEL_FW_FINISH_QUERY: rc = nd_intel_test_finish_query(t, buf, - buf_len, i - t->dcr_idx); + buf_len, i); break; case ND_INTEL_SMART: rc = nfit_test_cmd_smart(buf, buf_len, - &t->smart[i - t->dcr_idx]); + &t->smart[i]); break; case ND_INTEL_SMART_THRESHOLD: rc = nfit_test_cmd_smart_threshold(buf, buf_len, - &t->smart_threshold[i - - t->dcr_idx]); + &t->smart_threshold[i]); break; case ND_INTEL_SMART_SET_THRESHOLD: rc = nfit_test_cmd_smart_set_threshold(buf, buf_len, - &t->smart_threshold[i - - t->dcr_idx], - &t->smart[i - t->dcr_idx], + &t->smart_threshold[i], + &t->smart[i], &t->pdev.dev, t->dimm_dev[i]); break; case ND_INTEL_SMART_INJECT: rc = nfit_test_cmd_smart_inject(buf, buf_len, - &t->smart_threshold[i - - t->dcr_idx], - &t->smart[i - t->dcr_idx], + &t->smart_threshold[i], + &t->smart[i], &t->pdev.dev, t->dimm_dev[i]); break; default: From 0d47c4dfe5431abd04951a65845b3d989a704f63 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:07:51 -0700 Subject: [PATCH 175/291] tools/testing/nvdimm: Add command debug messages Arrange the for nfit_test_ctl() path to dump command payloads similarly to the acpi_nfit_ctl() path. This is useful for comparing the sequence of command events between an emulated ACPI-NFIT platform and a real one. Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- tools/testing/nvdimm/test/nfit.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index ddf9b3095bfa..9c6f475befe4 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1192,6 +1192,29 @@ static int get_dimm(struct nfit_mem *nfit_mem, unsigned int func) return i; } +static void nfit_ctl_dbg(struct acpi_nfit_desc *acpi_desc, + struct nvdimm *nvdimm, unsigned int cmd, void *buf, + unsigned int len) +{ + struct nfit_test *t = container_of(acpi_desc, typeof(*t), acpi_desc); + unsigned int func = cmd; + unsigned int family = 0; + + if (cmd == ND_CMD_CALL) { + struct nd_cmd_pkg *pkg = buf; + + len = pkg->nd_size_in; + family = pkg->nd_family; + buf = pkg->nd_payload; + func = pkg->nd_command; + } + dev_dbg(&t->pdev.dev, "%s family: %d cmd: %d: func: %d input length: %d\n", + nvdimm ? nvdimm_name(nvdimm) : "bus", family, cmd, func, + len); + print_hex_dump_debug("nvdimm in ", DUMP_PREFIX_OFFSET, 16, 4, + buf, min(len, 256u), true); +} + static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc) @@ -1205,6 +1228,8 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc, cmd_rc = &__cmd_rc; *cmd_rc = 0; + nfit_ctl_dbg(acpi_desc, nvdimm, cmd, buf, buf_len); + if (nvdimm) { struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm); unsigned long cmd_mask = nvdimm_cmd_mask(nvdimm); From abfd4d9c828b9e1d5ff38c19eed036f707e4e213 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:07:57 -0700 Subject: [PATCH 176/291] tools/testing/nvdimm: Prepare nfit_ctl_test() for ND_CMD_CALL emulation In preparation for adding a mocked implementation of the firmware-activate bus-info command, rework nfit_ctl_test() to operate on a local command payload wrapped in a 'struct nd_cmd_pkg'. Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- tools/testing/nvdimm/test/nfit.c | 83 +++++++++++++++++--------------- 1 file changed, 43 insertions(+), 40 deletions(-) diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 9c6f475befe4..2b0bfbfc0abb 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -2726,14 +2726,17 @@ static int nfit_ctl_test(struct device *dev) struct acpi_nfit_desc *acpi_desc; const u64 test_val = 0x0123456789abcdefULL; unsigned long mask, cmd_size, offset; - union { - struct nd_cmd_get_config_size cfg_size; - struct nd_cmd_clear_error clear_err; - struct nd_cmd_ars_status ars_stat; - struct nd_cmd_ars_cap ars_cap; - char buf[sizeof(struct nd_cmd_ars_status) - + sizeof(struct nd_ars_record)]; - } cmds; + struct nfit_ctl_test_cmd { + struct nd_cmd_pkg pkg; + union { + struct nd_cmd_get_config_size cfg_size; + struct nd_cmd_clear_error clear_err; + struct nd_cmd_ars_status ars_stat; + struct nd_cmd_ars_cap ars_cap; + char buf[sizeof(struct nd_cmd_ars_status) + + sizeof(struct nd_ars_record)]; + }; + } cmd; adev = devm_kzalloc(dev, sizeof(*adev), GFP_KERNEL); if (!adev) @@ -2793,21 +2796,21 @@ static int nfit_ctl_test(struct device *dev) /* basic checkout of a typical 'get config size' command */ - cmd_size = sizeof(cmds.cfg_size); - cmds.cfg_size = (struct nd_cmd_get_config_size) { + cmd_size = sizeof(cmd.cfg_size); + cmd.cfg_size = (struct nd_cmd_get_config_size) { .status = 0, .config_size = SZ_128K, .max_xfer = SZ_4K, }; - rc = setup_result(cmds.buf, cmd_size); + rc = setup_result(cmd.buf, cmd_size); if (rc) return rc; rc = acpi_nfit_ctl(&acpi_desc->nd_desc, nvdimm, ND_CMD_GET_CONFIG_SIZE, - cmds.buf, cmd_size, &cmd_rc); + cmd.buf, cmd_size, &cmd_rc); - if (rc < 0 || cmd_rc || cmds.cfg_size.status != 0 - || cmds.cfg_size.config_size != SZ_128K - || cmds.cfg_size.max_xfer != SZ_4K) { + if (rc < 0 || cmd_rc || cmd.cfg_size.status != 0 + || cmd.cfg_size.config_size != SZ_128K + || cmd.cfg_size.max_xfer != SZ_4K) { dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", __func__, __LINE__, rc, cmd_rc); return -EIO; @@ -2816,14 +2819,14 @@ static int nfit_ctl_test(struct device *dev) /* test ars_status with zero output */ cmd_size = offsetof(struct nd_cmd_ars_status, address); - cmds.ars_stat = (struct nd_cmd_ars_status) { + cmd.ars_stat = (struct nd_cmd_ars_status) { .out_length = 0, }; - rc = setup_result(cmds.buf, cmd_size); + rc = setup_result(cmd.buf, cmd_size); if (rc) return rc; rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_STATUS, - cmds.buf, cmd_size, &cmd_rc); + cmd.buf, cmd_size, &cmd_rc); if (rc < 0 || cmd_rc) { dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", @@ -2833,16 +2836,16 @@ static int nfit_ctl_test(struct device *dev) /* test ars_cap with benign extended status */ - cmd_size = sizeof(cmds.ars_cap); - cmds.ars_cap = (struct nd_cmd_ars_cap) { + cmd_size = sizeof(cmd.ars_cap); + cmd.ars_cap = (struct nd_cmd_ars_cap) { .status = ND_ARS_PERSISTENT << 16, }; offset = offsetof(struct nd_cmd_ars_cap, status); - rc = setup_result(cmds.buf + offset, cmd_size - offset); + rc = setup_result(cmd.buf + offset, cmd_size - offset); if (rc) return rc; rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_CAP, - cmds.buf, cmd_size, &cmd_rc); + cmd.buf, cmd_size, &cmd_rc); if (rc < 0 || cmd_rc) { dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", @@ -2852,19 +2855,19 @@ static int nfit_ctl_test(struct device *dev) /* test ars_status with 'status' trimmed from 'out_length' */ - cmd_size = sizeof(cmds.ars_stat) + sizeof(struct nd_ars_record); - cmds.ars_stat = (struct nd_cmd_ars_status) { + cmd_size = sizeof(cmd.ars_stat) + sizeof(struct nd_ars_record); + cmd.ars_stat = (struct nd_cmd_ars_status) { .out_length = cmd_size - 4, }; - record = &cmds.ars_stat.records[0]; + record = &cmd.ars_stat.records[0]; *record = (struct nd_ars_record) { .length = test_val, }; - rc = setup_result(cmds.buf, cmd_size); + rc = setup_result(cmd.buf, cmd_size); if (rc) return rc; rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_STATUS, - cmds.buf, cmd_size, &cmd_rc); + cmd.buf, cmd_size, &cmd_rc); if (rc < 0 || cmd_rc || record->length != test_val) { dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", @@ -2874,19 +2877,19 @@ static int nfit_ctl_test(struct device *dev) /* test ars_status with 'Output (Size)' including 'status' */ - cmd_size = sizeof(cmds.ars_stat) + sizeof(struct nd_ars_record); - cmds.ars_stat = (struct nd_cmd_ars_status) { + cmd_size = sizeof(cmd.ars_stat) + sizeof(struct nd_ars_record); + cmd.ars_stat = (struct nd_cmd_ars_status) { .out_length = cmd_size, }; - record = &cmds.ars_stat.records[0]; + record = &cmd.ars_stat.records[0]; *record = (struct nd_ars_record) { .length = test_val, }; - rc = setup_result(cmds.buf, cmd_size); + rc = setup_result(cmd.buf, cmd_size); if (rc) return rc; rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_STATUS, - cmds.buf, cmd_size, &cmd_rc); + cmd.buf, cmd_size, &cmd_rc); if (rc < 0 || cmd_rc || record->length != test_val) { dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", @@ -2896,15 +2899,15 @@ static int nfit_ctl_test(struct device *dev) /* test extended status for get_config_size results in failure */ - cmd_size = sizeof(cmds.cfg_size); - cmds.cfg_size = (struct nd_cmd_get_config_size) { + cmd_size = sizeof(cmd.cfg_size); + cmd.cfg_size = (struct nd_cmd_get_config_size) { .status = 1 << 16, }; - rc = setup_result(cmds.buf, cmd_size); + rc = setup_result(cmd.buf, cmd_size); if (rc) return rc; rc = acpi_nfit_ctl(&acpi_desc->nd_desc, nvdimm, ND_CMD_GET_CONFIG_SIZE, - cmds.buf, cmd_size, &cmd_rc); + cmd.buf, cmd_size, &cmd_rc); if (rc < 0 || cmd_rc >= 0) { dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", @@ -2913,16 +2916,16 @@ static int nfit_ctl_test(struct device *dev) } /* test clear error */ - cmd_size = sizeof(cmds.clear_err); - cmds.clear_err = (struct nd_cmd_clear_error) { + cmd_size = sizeof(cmd.clear_err); + cmd.clear_err = (struct nd_cmd_clear_error) { .length = 512, .cleared = 512, }; - rc = setup_result(cmds.buf, cmd_size); + rc = setup_result(cmd.buf, cmd_size); if (rc) return rc; rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_CLEAR_ERROR, - cmds.buf, cmd_size, &cmd_rc); + cmd.buf, cmd_size, &cmd_rc); if (rc < 0 || cmd_rc) { dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", __func__, __LINE__, rc, cmd_rc); From 916566ae78462636fe4de59b3f59a4a0c8f70205 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:08:02 -0700 Subject: [PATCH 177/291] tools/testing/nvdimm: Emulate firmware activation commands Augment the existing firmware update emulation to track activations and validate proper update vs activate sequencing. The DIMM firmware activate capability has a concept of a maximum amount of time platform firmware will quiesce the system relative to how many DIMMs are being activated in parallel. Simulate that DIMM activation happens serially, 1 second per-DIMM, and limit the max at 3 seconds. The nfit_test0 bus emulates 5 DIMMs so it will take 2 activations to update all DIMMs. Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Reported-by: Andy Shevchenko Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- drivers/acpi/nfit/intel.h | 5 + tools/testing/nvdimm/test/nfit.c | 209 ++++++++++++++++++++++++++++++- 2 files changed, 210 insertions(+), 4 deletions(-) diff --git a/drivers/acpi/nfit/intel.h b/drivers/acpi/nfit/intel.h index 868d073731cc..49a598623024 100644 --- a/drivers/acpi/nfit/intel.h +++ b/drivers/acpi/nfit/intel.h @@ -132,6 +132,9 @@ struct nd_intel_fw_activate_dimminfo { u8 reserved[7]; } __packed; +#define ND_INTEL_DIMM_FWA_ARM 1 +#define ND_INTEL_DIMM_FWA_DISARM 0 + struct nd_intel_fw_activate_arm { u8 activate_arm; u32 status; @@ -160,6 +163,8 @@ struct nd_intel_bus_fw_activate_businfo { #define ND_INTEL_BUS_FWA_STATUS_NOIDLE (6 | 5 << 16) #define ND_INTEL_BUS_FWA_STATUS_ABORT (6 | 6 << 16) +#define ND_INTEL_BUS_FWA_IODEV_FORCE_IDLE (0) +#define ND_INTEL_BUS_FWA_IODEV_OS_IDLE (1) struct nd_intel_bus_fw_activate { u8 iodev_state; u32 status; diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 2b0bfbfc0abb..a1a5dc645b40 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -173,6 +173,9 @@ struct nfit_test_fw { u64 version; u32 size_received; u64 end_time; + bool armed; + bool missed_activate; + unsigned long last_activate; }; struct nfit_test { @@ -345,7 +348,7 @@ static int nd_intel_test_finish_fw(struct nfit_test *t, __func__, t, nd_cmd, buf_len, idx); if (fw->state == FW_STATE_UPDATED) { - /* update already done, need cold boot */ + /* update already done, need activation */ nd_cmd->status = 0x20007; return 0; } @@ -430,6 +433,7 @@ static int nd_intel_test_finish_query(struct nfit_test *t, } dev_dbg(dev, "%s: transition out verify\n", __func__); fw->state = FW_STATE_UPDATED; + fw->missed_activate = false; /* fall through */ case FW_STATE_UPDATED: nd_cmd->status = 0; @@ -1178,6 +1182,134 @@ static int nd_intel_test_cmd_master_secure_erase(struct nfit_test *t, return 0; } +static unsigned long last_activate; + +static int nvdimm_bus_intel_fw_activate_businfo(struct nfit_test *t, + struct nd_intel_bus_fw_activate_businfo *nd_cmd, + unsigned int buf_len) +{ + int i, armed = 0; + int state; + u64 tmo; + + for (i = 0; i < NUM_DCR; i++) { + struct nfit_test_fw *fw = &t->fw[i]; + + if (fw->armed) + armed++; + } + + /* + * Emulate 3 second activation max, and 1 second incremental + * quiesce time per dimm requiring multiple activates to get all + * DIMMs updated. + */ + if (armed) + state = ND_INTEL_FWA_ARMED; + else if (!last_activate || time_after(jiffies, last_activate + 3 * HZ)) + state = ND_INTEL_FWA_IDLE; + else + state = ND_INTEL_FWA_BUSY; + + tmo = armed * USEC_PER_SEC; + *nd_cmd = (struct nd_intel_bus_fw_activate_businfo) { + .capability = ND_INTEL_BUS_FWA_CAP_FWQUIESCE + | ND_INTEL_BUS_FWA_CAP_OSQUIESCE + | ND_INTEL_BUS_FWA_CAP_RESET, + .state = state, + .activate_tmo = tmo, + .cpu_quiesce_tmo = tmo, + .io_quiesce_tmo = tmo, + .max_quiesce_tmo = 3 * USEC_PER_SEC, + }; + + return 0; +} + +static int nvdimm_bus_intel_fw_activate(struct nfit_test *t, + struct nd_intel_bus_fw_activate *nd_cmd, + unsigned int buf_len) +{ + struct nd_intel_bus_fw_activate_businfo info; + u32 status = 0; + int i; + + nvdimm_bus_intel_fw_activate_businfo(t, &info, sizeof(info)); + if (info.state == ND_INTEL_FWA_BUSY) + status = ND_INTEL_BUS_FWA_STATUS_BUSY; + else if (info.activate_tmo > info.max_quiesce_tmo) + status = ND_INTEL_BUS_FWA_STATUS_TMO; + else if (info.state == ND_INTEL_FWA_IDLE) + status = ND_INTEL_BUS_FWA_STATUS_NOARM; + + dev_dbg(&t->pdev.dev, "status: %d\n", status); + nd_cmd->status = status; + if (status && status != ND_INTEL_BUS_FWA_STATUS_TMO) + return 0; + + last_activate = jiffies; + for (i = 0; i < NUM_DCR; i++) { + struct nfit_test_fw *fw = &t->fw[i]; + + if (!fw->armed) + continue; + if (fw->state != FW_STATE_UPDATED) + fw->missed_activate = true; + else + fw->state = FW_STATE_NEW; + fw->armed = false; + fw->last_activate = last_activate; + } + + return 0; +} + +static int nd_intel_test_cmd_fw_activate_dimminfo(struct nfit_test *t, + struct nd_intel_fw_activate_dimminfo *nd_cmd, + unsigned int buf_len, int dimm) +{ + struct nd_intel_bus_fw_activate_businfo info; + struct nfit_test_fw *fw = &t->fw[dimm]; + u32 result, state; + + nvdimm_bus_intel_fw_activate_businfo(t, &info, sizeof(info)); + + if (info.state == ND_INTEL_FWA_BUSY) + state = ND_INTEL_FWA_BUSY; + else if (info.state == ND_INTEL_FWA_IDLE) + state = ND_INTEL_FWA_IDLE; + else if (fw->armed) + state = ND_INTEL_FWA_ARMED; + else + state = ND_INTEL_FWA_IDLE; + + result = ND_INTEL_DIMM_FWA_NONE; + if (last_activate && fw->last_activate == last_activate && + state == ND_INTEL_FWA_IDLE) { + if (fw->missed_activate) + result = ND_INTEL_DIMM_FWA_NOTSTAGED; + else + result = ND_INTEL_DIMM_FWA_SUCCESS; + } + + *nd_cmd = (struct nd_intel_fw_activate_dimminfo) { + .result = result, + .state = state, + }; + + return 0; +} + +static int nd_intel_test_cmd_fw_activate_arm(struct nfit_test *t, + struct nd_intel_fw_activate_arm *nd_cmd, + unsigned int buf_len, int dimm) +{ + struct nfit_test_fw *fw = &t->fw[dimm]; + + fw->armed = nd_cmd->activate_arm == ND_INTEL_DIMM_FWA_ARM; + nd_cmd->status = 0; + return 0; +} static int get_dimm(struct nfit_mem *nfit_mem, unsigned int func) { @@ -1296,6 +1428,14 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc, rc = nd_intel_test_cmd_master_secure_erase(t, buf, buf_len, i); break; + case NVDIMM_INTEL_FW_ACTIVATE_DIMMINFO: + rc = nd_intel_test_cmd_fw_activate_dimminfo( + t, buf, buf_len, i); + break; + case NVDIMM_INTEL_FW_ACTIVATE_ARM: + rc = nd_intel_test_cmd_fw_activate_arm( + t, buf, buf_len, i); + break; case ND_INTEL_ENABLE_LSS_STATUS: rc = nd_intel_test_cmd_set_lss_status(t, buf, buf_len); @@ -1380,9 +1520,9 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc, if (!nd_desc) return -ENOTTY; - if (cmd == ND_CMD_CALL) { + if (cmd == ND_CMD_CALL && call_pkg->nd_family + == NVDIMM_BUS_FAMILY_NFIT) { func = call_pkg->nd_command; - buf_len = call_pkg->nd_size_in + call_pkg->nd_size_out; buf = (void *) call_pkg->nd_payload; @@ -1406,7 +1546,26 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc, default: return -ENOTTY; } - } + } else if (cmd == ND_CMD_CALL && call_pkg->nd_family + == NVDIMM_BUS_FAMILY_INTEL) { + func = call_pkg->nd_command; + buf_len = call_pkg->nd_size_in + call_pkg->nd_size_out; + buf = (void *) call_pkg->nd_payload; + + switch (func) { + case NVDIMM_BUS_INTEL_FW_ACTIVATE_BUSINFO: + rc = nvdimm_bus_intel_fw_activate_businfo(t, + buf, buf_len); + return rc; + case NVDIMM_BUS_INTEL_FW_ACTIVATE: + rc = nvdimm_bus_intel_fw_activate(t, buf, + buf_len); + return rc; + default: + return -ENOTTY; + } + } else if (cmd == ND_CMD_CALL) + return -ENOTTY; if (!nd_desc || !test_bit(cmd, &nd_desc->cmd_mask)) return -ENOTTY; @@ -1832,6 +1991,7 @@ static void nfit_test0_setup(struct nfit_test *t) struct acpi_nfit_flush_address *flush; struct acpi_nfit_capabilities *pcap; unsigned int offset = 0, i; + unsigned long *acpi_mask; /* * spa0 (interleave first half of dimm0 and dimm1, note storage @@ -2558,6 +2718,12 @@ static void nfit_test0_setup(struct nfit_test *t) &acpi_desc->dimm_cmd_force_en); set_bit(NVDIMM_INTEL_MASTER_SECURE_ERASE, &acpi_desc->dimm_cmd_force_en); + set_bit(NVDIMM_INTEL_FW_ACTIVATE_DIMMINFO, &acpi_desc->dimm_cmd_force_en); + set_bit(NVDIMM_INTEL_FW_ACTIVATE_ARM, &acpi_desc->dimm_cmd_force_en); + + acpi_mask = &acpi_desc->family_dsm_mask[NVDIMM_BUS_FAMILY_INTEL]; + set_bit(NVDIMM_BUS_INTEL_FW_ACTIVATE_BUSINFO, acpi_mask); + set_bit(NVDIMM_BUS_INTEL_FW_ACTIVATE, acpi_mask); } static void nfit_test1_setup(struct nfit_test *t) @@ -2733,6 +2899,7 @@ static int nfit_ctl_test(struct device *dev) struct nd_cmd_clear_error clear_err; struct nd_cmd_ars_status ars_stat; struct nd_cmd_ars_cap ars_cap; + struct nd_intel_bus_fw_activate_businfo fwa_info; char buf[sizeof(struct nd_cmd_ars_status) + sizeof(struct nd_ars_record)]; }; @@ -2761,11 +2928,15 @@ static int nfit_ctl_test(struct device *dev) .module = THIS_MODULE, .provider_name = "ACPI.NFIT", .ndctl = acpi_nfit_ctl, + .bus_family_mask = 1UL << NVDIMM_BUS_FAMILY_NFIT + | 1UL << NVDIMM_BUS_FAMILY_INTEL, }, .bus_dsm_mask = 1UL << NFIT_CMD_TRANSLATE_SPA | 1UL << NFIT_CMD_ARS_INJECT_SET | 1UL << NFIT_CMD_ARS_INJECT_CLEAR | 1UL << NFIT_CMD_ARS_INJECT_GET, + .family_dsm_mask[NVDIMM_BUS_FAMILY_INTEL] = + NVDIMM_BUS_INTEL_FW_ACTIVATE_CMDMASK, .dev = &adev->dev, }; @@ -2932,6 +3103,36 @@ static int nfit_ctl_test(struct device *dev) return -EIO; } + /* test firmware activate bus info */ + cmd_size = sizeof(cmd.fwa_info); + cmd = (struct nfit_ctl_test_cmd) { + .pkg = { + .nd_command = NVDIMM_BUS_INTEL_FW_ACTIVATE_BUSINFO, + .nd_family = NVDIMM_BUS_FAMILY_INTEL, + .nd_size_out = cmd_size, + .nd_fw_size = cmd_size, + }, + .fwa_info = { + .state = ND_INTEL_FWA_IDLE, + .capability = ND_INTEL_BUS_FWA_CAP_FWQUIESCE + | ND_INTEL_BUS_FWA_CAP_OSQUIESCE, + .activate_tmo = 1, + .cpu_quiesce_tmo = 1, + .io_quiesce_tmo = 1, + .max_quiesce_tmo = 1, + }, + }; + rc = setup_result(cmd.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_CALL, + &cmd, sizeof(cmd.pkg) + cmd_size, &cmd_rc); + if (rc < 0 || cmd_rc) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + return 0; } From 60d360acddc54344409a710af07c561e025f13f5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:08:07 -0700 Subject: [PATCH 178/291] driver-core: Introduce DEVICE_ATTR_ADMIN_{RO,RW} A common pattern for using plain DEVICE_ATTR() instead of DEVICE_ATTR_RO() and DEVICE_ATTR_RW() is for attributes that want to limit read to only root. I.e. many users of DEVICE_ATTR() are specifying 0400 or 0600 for permissions. Given the expectation that CAP_SYS_ADMIN is needed to access these sensitive attributes add an explicit helper with the _ADMIN_ identifier for DEVICE_ATTR_ADMIN_{RO,RW}. Cc: "Rafael J. Wysocki" Reviewed-by: Greg Kroah-Hartman Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- include/linux/device.h | 4 ++++ include/linux/sysfs.h | 7 +++++++ 2 files changed, 11 insertions(+) diff --git a/include/linux/device.h b/include/linux/device.h index 15460a5ac024..d7c2570368fa 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -128,8 +128,12 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, __ATTR_PREALLOC(_name, _mode, _show, _store) #define DEVICE_ATTR_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW(_name) +#define DEVICE_ATTR_ADMIN_RW(_name) \ + struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600) #define DEVICE_ATTR_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO(_name) +#define DEVICE_ATTR_ADMIN_RO(_name) \ + struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400) #define DEVICE_ATTR_WO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_WO(_name) #define DEVICE_ULONG_ATTR(_name, _mode, _var) \ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 86067dbe7745..34e84122f635 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -123,6 +123,13 @@ struct attribute_group { .show = _name##_show, \ } +#define __ATTR_RW_MODE(_name, _mode) { \ + .attr = { .name = __stringify(_name), \ + .mode = VERIFY_OCTAL_PERMISSIONS(_mode) }, \ + .show = _name##_show, \ + .store = _name##_store, \ +} + #define __ATTR_WO(_name) { \ .attr = { .name = __stringify(_name), .mode = 0200 }, \ .store = _name##_store, \ From e86d1aa8b60f7ea18d36f50296d7d20eb2852e7e Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 24 Jul 2020 12:43:20 +0100 Subject: [PATCH 179/291] iommu/arm-smmu: Move Arm SMMU drivers into their own subdirectory The Arm SMMU drivers are getting fat on vendor value-add, so move them to their own subdirectory out of the way of the other IOMMU drivers. Suggested-by: Joerg Roedel Signed-off-by: Will Deacon --- MAINTAINERS | 4 ++-- drivers/iommu/Makefile | 5 +---- drivers/iommu/arm/Makefile | 2 ++ drivers/iommu/arm/arm-smmu-v3/Makefile | 2 ++ drivers/iommu/{ => arm/arm-smmu-v3}/arm-smmu-v3.c | 0 drivers/iommu/arm/arm-smmu/Makefile | 4 ++++ drivers/iommu/{ => arm/arm-smmu}/arm-smmu-impl.c | 0 drivers/iommu/{ => arm/arm-smmu}/arm-smmu-nvidia.c | 0 drivers/iommu/{ => arm/arm-smmu}/arm-smmu-qcom.c | 0 drivers/iommu/{ => arm/arm-smmu}/arm-smmu.c | 0 drivers/iommu/{ => arm/arm-smmu}/arm-smmu.h | 0 drivers/iommu/{ => arm/arm-smmu}/qcom_iommu.c | 0 12 files changed, 11 insertions(+), 6 deletions(-) create mode 100644 drivers/iommu/arm/Makefile create mode 100644 drivers/iommu/arm/arm-smmu-v3/Makefile rename drivers/iommu/{ => arm/arm-smmu-v3}/arm-smmu-v3.c (100%) create mode 100644 drivers/iommu/arm/arm-smmu/Makefile rename drivers/iommu/{ => arm/arm-smmu}/arm-smmu-impl.c (100%) rename drivers/iommu/{ => arm/arm-smmu}/arm-smmu-nvidia.c (100%) rename drivers/iommu/{ => arm/arm-smmu}/arm-smmu-qcom.c (100%) rename drivers/iommu/{ => arm/arm-smmu}/arm-smmu.c (100%) rename drivers/iommu/{ => arm/arm-smmu}/arm-smmu.h (100%) rename drivers/iommu/{ => arm/arm-smmu}/qcom_iommu.c (100%) diff --git a/MAINTAINERS b/MAINTAINERS index ee2c0ba13a0f..e15470442d3e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1498,7 +1498,7 @@ R: Robin Murphy L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/iommu/arm,smmu* -F: drivers/iommu/arm-smmu* +F: drivers/iommu/arm/ F: drivers/iommu/io-pgtable-arm-v7s.c F: drivers/iommu/io-pgtable-arm.c @@ -16813,7 +16813,7 @@ M: Thierry Reding R: Krishna Reddy L: linux-tegra@vger.kernel.org S: Supported -F: drivers/iommu/arm-smmu-nvidia.c +F: drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c F: drivers/iommu/tegra* TEGRA KBC DRIVER diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 2b8203db73ec..d971cffc810b 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +obj-y += arm/ obj-$(CONFIG_IOMMU_API) += iommu.o obj-$(CONFIG_IOMMU_API) += iommu-traces.o obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o @@ -14,9 +15,6 @@ obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o obj-$(CONFIG_AMD_IOMMU) += amd/iommu.o amd/init.o amd/quirks.o obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd/debugfs.o obj-$(CONFIG_AMD_IOMMU_V2) += amd/iommu_v2.o -obj-$(CONFIG_ARM_SMMU) += arm_smmu.o -arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o arm-smmu-qcom.o -obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o obj-$(CONFIG_DMAR_TABLE) += intel/dmar.o obj-$(CONFIG_INTEL_IOMMU) += intel/iommu.o intel/pasid.o obj-$(CONFIG_INTEL_IOMMU) += intel/trace.o @@ -35,6 +33,5 @@ obj-$(CONFIG_TEGRA_IOMMU_SMMU) += tegra-smmu.o obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o obj-$(CONFIG_S390_IOMMU) += s390-iommu.o -obj-$(CONFIG_QCOM_IOMMU) += qcom_iommu.o obj-$(CONFIG_HYPERV_IOMMU) += hyperv-iommu.o obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o diff --git a/drivers/iommu/arm/Makefile b/drivers/iommu/arm/Makefile new file mode 100644 index 000000000000..0f9efeab709f --- /dev/null +++ b/drivers/iommu/arm/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-y += arm-smmu/ arm-smmu-v3/ diff --git a/drivers/iommu/arm/arm-smmu-v3/Makefile b/drivers/iommu/arm/arm-smmu-v3/Makefile new file mode 100644 index 000000000000..569e24e9f162 --- /dev/null +++ b/drivers/iommu/arm/arm-smmu-v3/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c similarity index 100% rename from drivers/iommu/arm-smmu-v3.c rename to drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c diff --git a/drivers/iommu/arm/arm-smmu/Makefile b/drivers/iommu/arm/arm-smmu/Makefile new file mode 100644 index 000000000000..e240a7bcf310 --- /dev/null +++ b/drivers/iommu/arm/arm-smmu/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_QCOM_IOMMU) += qcom_iommu.o +obj-$(CONFIG_ARM_SMMU) += arm_smmu.o +arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o arm-smmu-qcom.o diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c similarity index 100% rename from drivers/iommu/arm-smmu-impl.c rename to drivers/iommu/arm/arm-smmu/arm-smmu-impl.c diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c similarity index 100% rename from drivers/iommu/arm-smmu-nvidia.c rename to drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c diff --git a/drivers/iommu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c similarity index 100% rename from drivers/iommu/arm-smmu-qcom.c rename to drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c similarity index 100% rename from drivers/iommu/arm-smmu.c rename to drivers/iommu/arm/arm-smmu/arm-smmu.c diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h similarity index 100% rename from drivers/iommu/arm-smmu.h rename to drivers/iommu/arm/arm-smmu/arm-smmu.h diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c similarity index 100% rename from drivers/iommu/qcom_iommu.c rename to drivers/iommu/arm/arm-smmu/qcom_iommu.c From e013f455d95add874f310dc47c608e8c70692ae5 Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Thu, 23 Jul 2020 01:40:45 +0530 Subject: [PATCH 180/291] remoteproc: qcom_q6v5_mss: Validate MBA firmware size before load The following mem abort is observed when the mba firmware size exceeds the allocated mba region. MBA firmware size is restricted to a maximum size of 1M and remaining memory region is used by modem debug policy firmware when available. Hence verify whether the MBA firmware size lies within the allocated memory region and is not greater than 1M before loading. Err Logs: Unable to handle kernel paging request at virtual address Mem abort info: ... Call trace: __memcpy+0x110/0x180 rproc_start+0x40/0x218 rproc_boot+0x5b4/0x608 state_store+0x54/0xf8 dev_attr_store+0x44/0x60 sysfs_kf_write+0x58/0x80 kernfs_fop_write+0x140/0x230 vfs_write+0xc4/0x208 ksys_write+0x74/0xf8 __arm64_sys_write+0x24/0x30 ... Reviewed-by: Bjorn Andersson Fixes: 051fb70fd4ea4 ("remoteproc: qcom: Driver for the self-authenticating Hexagon v5") Cc: stable@vger.kernel.org Signed-off-by: Sibi Sankar Link: https://lore.kernel.org/r/20200722201047.12975-2-sibis@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_q6v5_mss.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index 03d7f3d702b3..7826f229957d 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -411,6 +411,12 @@ static int q6v5_load(struct rproc *rproc, const struct firmware *fw) { struct q6v5 *qproc = rproc->priv; + /* MBA is restricted to a maximum size of 1M */ + if (fw->size > qproc->mba_size || fw->size > SZ_1M) { + dev_err(qproc->dev, "MBA firmware load failed\n"); + return -EINVAL; + } + memcpy(qproc->mba_region, fw->data, fw->size); return 0; From 135b9e8d1cd8ba5ac9ad9bcf24b464b7b052e5b8 Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Thu, 23 Jul 2020 01:40:46 +0530 Subject: [PATCH 181/291] remoteproc: qcom_q6v5_mss: Validate modem blob firmware size before load The following mem abort is observed when one of the modem blob firmware size exceeds the allocated mpss region. Fix this by restricting the copy size to segment size using request_firmware_into_buf before load. Err Logs: Unable to handle kernel paging request at virtual address Mem abort info: ... Call trace: __memcpy+0x110/0x180 rproc_start+0xd0/0x190 rproc_boot+0x404/0x550 state_store+0x54/0xf8 dev_attr_store+0x44/0x60 sysfs_kf_write+0x58/0x80 kernfs_fop_write+0x140/0x230 vfs_write+0xc4/0x208 ksys_write+0x74/0xf8 ... Reviewed-by: Bjorn Andersson Fixes: 051fb70fd4ea4 ("remoteproc: qcom: Driver for the self-authenticating Hexagon v5") Cc: stable@vger.kernel.org Signed-off-by: Sibi Sankar Link: https://lore.kernel.org/r/20200722201047.12975-3-sibis@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_q6v5_mss.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index 7826f229957d..8199d9f59209 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -1173,15 +1173,14 @@ static int q6v5_mpss_load(struct q6v5 *qproc) } else if (phdr->p_filesz) { /* Replace "xxx.xxx" with "xxx.bxx" */ sprintf(fw_name + fw_name_len - 3, "b%02d", i); - ret = request_firmware(&seg_fw, fw_name, qproc->dev); + ret = request_firmware_into_buf(&seg_fw, fw_name, qproc->dev, + ptr, phdr->p_filesz); if (ret) { dev_err(qproc->dev, "failed to load %s\n", fw_name); iounmap(ptr); goto release_firmware; } - memcpy(ptr, seg_fw->data, seg_fw->size); - release_firmware(seg_fw); } From fe6a5dc4b03171653d217e6dc7c1739e90c660bb Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Thu, 23 Jul 2020 01:40:47 +0530 Subject: [PATCH 182/291] remoteproc: qcom_q6v5_mss: Add modem debug policy support Add modem debug policy support which will enable coredumps and live debug support when the msadp firmware is present on secure devices. Reviewed-by: Bjorn Andersson Signed-off-by: Sibi Sankar Link: https://lore.kernel.org/r/20200722201047.12975-4-sibis@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_q6v5_mss.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index 8199d9f59209..a720c0adb3b6 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -190,6 +190,7 @@ struct q6v5 { phys_addr_t mba_phys; void *mba_region; size_t mba_size; + size_t dp_size; phys_addr_t mpss_phys; phys_addr_t mpss_reloc; @@ -407,6 +408,21 @@ static int q6v5_xfer_mem_ownership(struct q6v5 *qproc, int *current_perm, current_perm, next, perms); } +static void q6v5_debug_policy_load(struct q6v5 *qproc) +{ + const struct firmware *dp_fw; + + if (request_firmware_direct(&dp_fw, "msadp", qproc->dev)) + return; + + if (SZ_1M + dp_fw->size <= qproc->mba_size) { + memcpy(qproc->mba_region + SZ_1M, dp_fw->data, dp_fw->size); + qproc->dp_size = dp_fw->size; + } + + release_firmware(dp_fw); +} + static int q6v5_load(struct rproc *rproc, const struct firmware *fw) { struct q6v5 *qproc = rproc->priv; @@ -418,6 +434,7 @@ static int q6v5_load(struct rproc *rproc, const struct firmware *fw) } memcpy(qproc->mba_region, fw->data, fw->size); + q6v5_debug_policy_load(qproc); return 0; } @@ -927,6 +944,10 @@ static int q6v5_mba_load(struct q6v5 *qproc) } writel(qproc->mba_phys, qproc->rmb_base + RMB_MBA_IMAGE_REG); + if (qproc->dp_size) { + writel(qproc->mba_phys + SZ_1M, qproc->rmb_base + RMB_PMI_CODE_START_REG); + writel(qproc->dp_size, qproc->rmb_base + RMB_PMI_CODE_LENGTH_REG); + } ret = q6v5proc_reset(qproc); if (ret) @@ -995,6 +1016,7 @@ static void q6v5_mba_reclaim(struct q6v5 *qproc) u32 val; qproc->dump_mba_loaded = false; + qproc->dp_size = 0; q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_q6); q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_modem); @@ -1289,7 +1311,8 @@ static int q6v5_start(struct rproc *rproc) if (ret) return ret; - dev_info(qproc->dev, "MBA booted, loading mpss\n"); + dev_info(qproc->dev, "MBA booted with%s debug policy, loading mpss\n", + qproc->dp_size ? "" : "out"); ret = q6v5_mpss_load(qproc); if (ret) From 5b7be880074c73540948f8fc597e0407b98fabfa Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Tue, 2 Jun 2020 22:02:56 +0530 Subject: [PATCH 183/291] remoteproc: qcom: q6v5: Update running state before requesting stop Sometimes the stop triggers a watchdog rather than a stop-ack. Update the running state to false on requesting stop to skip the watchdog instead. Error Logs: $ echo stop > /sys/class/remoteproc/remoteproc0/state ipa 1e40000.ipa: received modem stopping event remoteproc-modem: watchdog received: sys_m_smsm_mpss.c:291:APPS force stop qcom-q6v5-mss 4080000.remoteproc-modem: port failed halt ipa 1e40000.ipa: received modem offline event remoteproc0: stopped remote processor 4080000.remoteproc-modem Reviewed-by: Evan Green Fixes: 3b415c8fb263 ("remoteproc: q6v5: Extract common resource handling") Cc: stable@vger.kernel.org Signed-off-by: Sibi Sankar Link: https://lore.kernel.org/r/20200602163257.26978-1-sibis@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_q6v5.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/remoteproc/qcom_q6v5.c b/drivers/remoteproc/qcom_q6v5.c index 111a442c993c..fd6fd36268d9 100644 --- a/drivers/remoteproc/qcom_q6v5.c +++ b/drivers/remoteproc/qcom_q6v5.c @@ -153,6 +153,8 @@ int qcom_q6v5_request_stop(struct qcom_q6v5 *q6v5) { int ret; + q6v5->running = false; + qcom_smem_state_update_bits(q6v5->state, BIT(q6v5->stop_bit), BIT(q6v5->stop_bit)); From 42a51c7504945caa08ee73faff3862e740c094e1 Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Tue, 2 Jun 2020 22:02:57 +0530 Subject: [PATCH 184/291] remoteproc: qcom_q6v5_mss: Remove redundant running state Remove the redundant running state, as an equivalent is maintained in the common q6v5 resource handling helpers. Reviewed-by: Bjorn Andersson Reviewed-by: Evan Green Signed-off-by: Sibi Sankar Link: https://lore.kernel.org/r/20200602163257.26978-2-sibis@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_q6v5_mss.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index a720c0adb3b6..ae3739082fdd 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -181,8 +181,6 @@ struct q6v5 { int active_reg_count; int proxy_reg_count; - bool running; - bool dump_mba_loaded; size_t current_dump_size; size_t total_dump_size; @@ -1333,7 +1331,6 @@ static int q6v5_start(struct rproc *rproc) /* Reset Dump Segment Mask */ qproc->current_dump_size = 0; - qproc->running = true; return 0; @@ -1349,8 +1346,6 @@ static int q6v5_stop(struct rproc *rproc) struct q6v5 *qproc = (struct q6v5 *)rproc->priv; int ret; - qproc->running = false; - ret = qcom_q6v5_request_stop(&qproc->q6v5); if (ret == -ETIMEDOUT) dev_err(qproc->dev, "timed out on wait\n"); From 476af91933ce81d534761d31382459f6e9eb6c6d Mon Sep 17 00:00:00 2001 From: Mike Marshall Date: Thu, 9 Jul 2020 15:02:32 -0400 Subject: [PATCH 185/291] orangefs: posix acl fix... Al Viro pointed out that I broke some acl functionality... * ACLs could not be fully removed * posix_acl_chmod would be called while the old ACL was still cached * new mode propagated to orangefs server before ACL. ... when I tried to make sure that modes that got changed as a result of ACL-sets would be sent back to the orangefs server. Not wanting to try and change the code without having some cases to test it with, I began to hunt for setfacl examples that were expressible in pure mode. Along the way I found examples like the following which confused me: user A had a file (/home/A/asdf) with mode 740 user B was in user A's group user C was not in user A's group setfacl -m u:C:rwx /home/A/asdf The above setfacl caused ls -l /home/A/asdf to show a mode of 770, making it appear that all users in user A's group now had full access to /home/A/asdf, however, user B still only had read acces. Madness. Anywho, I finally found that the above (whacky as it is) appears to be "posixly on purpose" and explained in acl(5): If the ACL has an ACL_MASK entry, the group permissions correspond to the permissions of the ACL_MASK entry. Signed-off-by: Mike Marshall --- fs/orangefs/acl.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c index eced272a3c57..a25e6c890975 100644 --- a/fs/orangefs/acl.c +++ b/fs/orangefs/acl.c @@ -122,6 +122,8 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) struct iattr iattr; int rc; + memset(&iattr, 0, sizeof iattr); + if (type == ACL_TYPE_ACCESS && acl) { /* * posix_acl_update_mode checks to see if the permissions @@ -138,18 +140,17 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return error; } - if (acl) { - rc = __orangefs_set_acl(inode, acl, type); - } else { + if (inode->i_mode != iattr.ia_mode) iattr.ia_valid = ATTR_MODE; - rc = __orangefs_setattr(inode, &iattr); - } - return rc; - - } else { - return -EINVAL; } + + rc = __orangefs_set_acl(inode, acl, type); + + if (!rc && (iattr.ia_valid == ATTR_MODE)) + rc = __orangefs_setattr(inode, &iattr); + + return rc; } int orangefs_init_acl(struct inode *inode, struct inode *dir) From 231609785cbfb341e7d6d24a74d6ab8cc518835f Mon Sep 17 00:00:00 2001 From: Coly Li Date: Sun, 26 Jul 2020 00:24:50 +0800 Subject: [PATCH 186/291] dax: print error message by pr_info() in __generic_fsdax_supported() In struct dax_operations, the callback routine dax_supported() returns a bool type result. For false return value, the caller has no idea whether the device does not support dax at all, or it is just some mis- configuration issue. An example is formatting an Ext4 file system on pmem device on top of a NVDIMM namespace by, # mkfs.ext4 /dev/pmem0 If the fs block size does not match kernel space memory page size (which is possible on non-x86 platform), mount this Ext4 file system will fail, # mount -o dax /dev/pmem0 /mnt mount: /mnt: wrong fs type, bad option, bad superblock on /dev/pmem0, missing codepage or helper program, or other error. And from the dmesg output there is only the following information, [ 307.853148] EXT4-fs (pmem0): DAX unsupported by block device. The above information is quite confusing. Because definitely the pmem0 device supports dax operation, and the super block is consistent as how it was created by mkfs.ext4. Indeed the failure is from __generic_fsdax_supported() by the following code piece, if (blocksize != PAGE_SIZE) { pr_debug("%s: error: unsupported blocksize for dax\n", bdevname(bdev, buf)); return false; } It is because the Ext4 block size is 4KB and kernel page size is 8KB or 16KB. It is not simple to make dax_supported() from struct dax_operations or __generic_fsdax_supported() to return exact failure type right now. So the simplest fix is to use pr_info() to print all the error messages inside __generic_fsdax_supported(). Then users may find informative clue from the kernel message at least. Message printed by pr_debug() is very easy to be ignored by users. This patch prints error message by pr_info() in __generic_fsdax_supported(), when then mount fails, following lines can be found from dmesg output, [ 2705.500885] pmem0: error: unsupported blocksize for dax [ 2705.500888] EXT4-fs (pmem0): DAX unsupported by block device. Now the users may have idea the mount failure is from pmem driver for unsupported block size. Link: https://lore.kernel.org/r/20200725162450.95999-1-colyli@suse.de Cc: Dan Williams Cc: Anthony Iliopoulos Reported-by: Michal Suchanek Suggested-by: Jan Kara Reviewed-by: Jan Kara Reviewed-by: Ira Weiny Reviewed-by: Pankaj Gupta Signed-off-by: Coly Li Signed-off-by: Vishal Verma --- drivers/dax/super.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 8e32345be0f7..de0d02ec0347 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -80,14 +80,14 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev, int err, id; if (blocksize != PAGE_SIZE) { - pr_debug("%s: error: unsupported blocksize for dax\n", + pr_info("%s: error: unsupported blocksize for dax\n", bdevname(bdev, buf)); return false; } err = bdev_dax_pgoff(bdev, start, PAGE_SIZE, &pgoff); if (err) { - pr_debug("%s: error: unaligned partition for dax\n", + pr_info("%s: error: unaligned partition for dax\n", bdevname(bdev, buf)); return false; } @@ -95,7 +95,7 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev, last_page = PFN_DOWN((start + sectors - 1) * 512) * PAGE_SIZE / 512; err = bdev_dax_pgoff(bdev, last_page, PAGE_SIZE, &pgoff_end); if (err) { - pr_debug("%s: error: unaligned partition for dax\n", + pr_info("%s: error: unaligned partition for dax\n", bdevname(bdev, buf)); return false; } @@ -106,7 +106,7 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev, dax_read_unlock(id); if (len < 1 || len2 < 1) { - pr_debug("%s: error: dax access failed (%ld)\n", + pr_info("%s: error: dax access failed (%ld)\n", bdevname(bdev, buf), len < 1 ? len : len2); return false; } @@ -139,7 +139,7 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev, } if (!dax_enabled) { - pr_debug("%s: error: dax support not enabled\n", + pr_info("%s: error: dax support not enabled\n", bdevname(bdev, buf)); return false; } From c7fe193f1877e80e905a39e494ff53bd20c97970 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Fri, 17 Jul 2020 00:20:49 -0700 Subject: [PATCH 187/291] fs/dax: Remove unused size parameter Passing size to copy_user_dax implies it can copy variable sizes of data when in fact it calls copy_user_page() which is exactly a page. We are safe because the only caller uses PAGE_SIZE anyway so just remove the variable for clarity. While we are at it change copy_user_dax() to copy_cow_page_dax() to make it clear it is a singleton helper for this one case not implementing what dax_iomap_actor() does. Link: https://lore.kernel.org/r/20200717072056.73134-11-ira.weiny@intel.com Reviewed-by: Ben Widawsky Reviewed-by: Dan Williams Signed-off-by: Ira Weiny Signed-off-by: Vishal Verma --- fs/dax.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index 11b16729b86f..3e0babeb0365 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -680,21 +680,20 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping, return __dax_invalidate_entry(mapping, index, false); } -static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev, - sector_t sector, size_t size, struct page *to, - unsigned long vaddr) +static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_dev, + sector_t sector, struct page *to, unsigned long vaddr) { void *vto, *kaddr; pgoff_t pgoff; long rc; int id; - rc = bdev_dax_pgoff(bdev, sector, size, &pgoff); + rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff); if (rc) return rc; id = dax_read_lock(); - rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, NULL); + rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(PAGE_SIZE), &kaddr, NULL); if (rc < 0) { dax_read_unlock(id); return rc; @@ -1305,8 +1304,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, clear_user_highpage(vmf->cow_page, vaddr); break; case IOMAP_MAPPED: - error = copy_user_dax(iomap.bdev, iomap.dax_dev, - sector, PAGE_SIZE, vmf->cow_page, vaddr); + error = copy_cow_page_dax(iomap.bdev, iomap.dax_dev, + sector, vmf->cow_page, vaddr); break; default: WARN_ON_ONCE(1); From eedfd73d401b5584ab270b5f9f80079e56c7807e Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Fri, 17 Jul 2020 00:20:50 -0700 Subject: [PATCH 188/291] drivers/dax: Expand lock scope to cover the use of addresses The addition of PKS protection to dax read lock/unlock will require that the address returned by dax_direct_access() be protected by this lock. Correct the locking by ensuring that the use of kaddr and end_kaddr are covered by the dax read lock/unlock. Link: https://lore.kernel.org/r/20200717072056.73134-12-ira.weiny@intel.com Reviewed-by: Dan Williams Signed-off-by: Ira Weiny Signed-off-by: Vishal Verma --- drivers/dax/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index de0d02ec0347..ec62752215e4 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -103,11 +103,11 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev, id = dax_read_lock(); len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn); len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn); - dax_read_unlock(id); if (len < 1 || len2 < 1) { pr_info("%s: error: dax access failed (%ld)\n", bdevname(bdev, buf), len < 1 ? len : len2); + dax_read_unlock(id); return false; } @@ -137,6 +137,7 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev, put_dev_pagemap(end_pgmap); } + dax_read_unlock(id); if (!dax_enabled) { pr_info("%s: error: dax support not enabled\n", From 5cf81ce1893da01fede18c6749eafd4bc1c5ae9b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:08:13 -0700 Subject: [PATCH 189/291] libnvdimm: Convert to DEVICE_ATTR_ADMIN_RO() Move libnvdimm sysfs attributes that currently use an open coded DEVICE_ATTR() to hide sensitive root-only information (physical memory layout) to the new DEVICE_ATTR_ADMIN_RO() helper. Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- drivers/nvdimm/namespace_devs.c | 2 +- drivers/nvdimm/pfn_devs.c | 2 +- drivers/nvdimm/region_devs.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index ae155e860fdc..6da67f4d641a 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -1309,7 +1309,7 @@ static ssize_t resource_show(struct device *dev, return -ENXIO; return sprintf(buf, "%#llx\n", (unsigned long long) res->start); } -static DEVICE_ATTR(resource, 0400, resource_show, NULL); +static DEVICE_ATTR_ADMIN_RO(resource); static const unsigned long blk_lbasize_supported[] = { 512, 520, 528, 4096, 4104, 4160, 4224, 0 }; diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index 34db557dbad1..3e11ef8d3f5b 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -218,7 +218,7 @@ static ssize_t resource_show(struct device *dev, return rc; } -static DEVICE_ATTR(resource, 0400, resource_show, NULL); +static DEVICE_ATTR_ADMIN_RO(resource); static ssize_t size_show(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 4502f9c4708d..20ff30c2ab93 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -605,7 +605,7 @@ static ssize_t resource_show(struct device *dev, return sprintf(buf, "%#llx\n", nd_region->ndr_start); } -static DEVICE_ATTR(resource, 0400, resource_show, NULL); +static DEVICE_ATTR_ADMIN_RO(resource); static ssize_t persistence_domain_show(struct device *dev, struct device_attribute *attr, char *buf) From 44aa656f22d287b33f33bdb28dfb900846e1fc60 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Tue, 21 Jul 2020 17:36:12 -0500 Subject: [PATCH 190/291] dt-bindings: arm: keystone: Add common TI SCI bindings Add a bindings document that defines the common TI SCI properties used by various K3 device management nodes such as clock controllers, interrupt controllers, reset controllers or remoteproc devices. The required properties for each device management node shall be specified in the respective binding document. Reviewed-by: Rob Herring Signed-off-by: Suman Anna Link: https://lore.kernel.org/r/20200721223617.20312-2-s-anna@ti.com Signed-off-by: Bjorn Andersson --- .../arm/keystone/ti,k3-sci-common.yaml | 44 +++++++++++++++++++ MAINTAINERS | 1 + 2 files changed, 45 insertions(+) create mode 100644 Documentation/devicetree/bindings/arm/keystone/ti,k3-sci-common.yaml diff --git a/Documentation/devicetree/bindings/arm/keystone/ti,k3-sci-common.yaml b/Documentation/devicetree/bindings/arm/keystone/ti,k3-sci-common.yaml new file mode 100644 index 000000000000..7597bc93a55f --- /dev/null +++ b/Documentation/devicetree/bindings/arm/keystone/ti,k3-sci-common.yaml @@ -0,0 +1,44 @@ +# SPDX-License-Identifier: (GPL-2.0-only or BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/arm/keystone/ti,k3-sci-common.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Common K3 TI-SCI bindings + +maintainers: + - Nishanth Menon + +description: | + The TI K3 family of SoCs usually have a central System Controller Processor + that is responsible for managing various SoC-level resources like clocks, + resets, interrupts etc. The communication with that processor is performed + through the TI-SCI protocol. + + Each specific device management node like a clock controller node, a reset + controller node or an interrupt-controller node should define a common set + of properties that enables them to implement the corresponding functionality + over the TI-SCI protocol. The following are some of the common properties + needed by such individual nodes. The required properties for each device + management node is defined in the respective binding. + +properties: + ti,sci: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Should be a phandle to the TI-SCI System Controller node + + ti,sci-dev-id: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + Should contain the TI-SCI device id corresponding to the device. Please + refer to the corresponding System Controller documentation for valid + values for the desired device. + + ti,sci-proc-ids: + description: Should contain a single tuple of . + $ref: /schemas/types.yaml#/definitions/uint32-array + items: + - description: TI-SCI processor id for the remote processor device + - description: TI-SCI host id to which processor control ownership + should be transferred to diff --git a/MAINTAINERS b/MAINTAINERS index 68f21d46614c..b0b00447cf2d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16887,6 +16887,7 @@ M: Tero Kristo M: Santosh Shilimkar L: linux-arm-kernel@lists.infradead.org S: Maintained +F: Documentation/devicetree/bindings/arm/keystone/ti,k3-sci-common.yaml F: Documentation/devicetree/bindings/arm/keystone/ti,sci.txt F: Documentation/devicetree/bindings/clock/ti,sci-clk.txt F: Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.txt From a8aa5ee100df45f4988975822f5af7c2b67ee9e6 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Tue, 21 Jul 2020 17:36:13 -0500 Subject: [PATCH 191/291] remoteproc: Introduce rproc_of_parse_firmware() helper Add a new helper function rproc_of_parse_firmware() to the remoteproc core that can be used by various remoteproc drivers to look up the the "firmware-name" property from a rproc device node. This property is already being used by multiple drivers, so this helper can avoid repeating equivalent code in remoteproc drivers. Signed-off-by: Suman Anna Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200721223617.20312-3-s-anna@ti.com Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 23 +++++++++++++++++++++++ drivers/remoteproc/remoteproc_internal.h | 2 ++ 2 files changed, 25 insertions(+) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 7f0d55fceb02..277d3bf7a250 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1046,6 +1046,29 @@ rproc_of_resm_mem_entry_init(struct device *dev, u32 of_resm_idx, size_t len, } EXPORT_SYMBOL(rproc_of_resm_mem_entry_init); +/** + * rproc_of_parse_firmware() - parse and return the firmware-name + * @dev: pointer on device struct representing a rproc + * @index: index to use for the firmware-name retrieval + * @fw_name: pointer to a character string, in which the firmware + * name is returned on success and unmodified otherwise. + * + * This is an OF helper function that parses a device's DT node for + * the "firmware-name" property and returns the firmware name pointer + * in @fw_name on success. + * + * Return: 0 on success, or an appropriate failure. + */ +int rproc_of_parse_firmware(struct device *dev, int index, const char **fw_name) +{ + int ret; + + ret = of_property_read_string_index(dev->of_node, "firmware-name", + index, fw_name); + return ret ? ret : 0; +} +EXPORT_SYMBOL(rproc_of_parse_firmware); + /* * A lookup table for resource handlers. The indices are defined in * enum fw_resource_type. diff --git a/drivers/remoteproc/remoteproc_internal.h b/drivers/remoteproc/remoteproc_internal.h index 26fe012e6803..cd4176b033a3 100644 --- a/drivers/remoteproc/remoteproc_internal.h +++ b/drivers/remoteproc/remoteproc_internal.h @@ -28,6 +28,8 @@ struct rproc_debug_trace { void rproc_release(struct kref *kref); irqreturn_t rproc_vq_interrupt(struct rproc *rproc, int vq_id); void rproc_vdev_release(struct kref *ref); +int rproc_of_parse_firmware(struct device *dev, int index, + const char **fw_name); /* from remoteproc_virtio.c */ int rproc_add_virtio_dev(struct rproc_vdev *rvdev, int id); From cf7acb49083658be69d6ef83d06865fc9cc51426 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Tue, 21 Jul 2020 17:36:14 -0500 Subject: [PATCH 192/291] remoteproc: k3: Add TI-SCI processor control helper functions Texas Instruments' K3 generation SoCs have specific modules/register spaces used for configuring the various aspects of a remote processor. These include power, reset, boot vector and other configuration features specific to each compute processor present on the SoC. These registers are managed by the System Controller such as DMSC on K3 AM65x SoCs. The Texas Instrument's System Control Interface (TI-SCI) Message Protocol is used to communicate to the System Controller from various compute processors to invoke specific services provided by the firmware running on the System Controller. Add a common processor control interface header file that can be used by multiple remoteproc drivers. The helper functions within this header file abstract the various TI SCI protocol ops for the remoteproc drivers, and allow them to request the System Controller to be able to program and manage various remote processors on the SoC. The remoteproc drivers are expected to manage the life-cycle of their ti_sci_proc_dev local structures. Signed-off-by: Suman Anna Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200721223617.20312-4-s-anna@ti.com Signed-off-by: Bjorn Andersson --- drivers/remoteproc/ti_sci_proc.h | 104 +++++++++++++++++++++++++++++++ 1 file changed, 104 insertions(+) create mode 100644 drivers/remoteproc/ti_sci_proc.h diff --git a/drivers/remoteproc/ti_sci_proc.h b/drivers/remoteproc/ti_sci_proc.h new file mode 100644 index 000000000000..778558abcdcc --- /dev/null +++ b/drivers/remoteproc/ti_sci_proc.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Texas Instruments TI-SCI Processor Controller Helper Functions + * + * Copyright (C) 2018-2020 Texas Instruments Incorporated - https://www.ti.com/ + * Suman Anna + */ + +#ifndef REMOTEPROC_TI_SCI_PROC_H +#define REMOTEPROC_TI_SCI_PROC_H + +#include + +/** + * struct ti_sci_proc - structure representing a processor control client + * @sci: cached TI-SCI protocol handle + * @ops: cached TI-SCI proc ops + * @dev: cached client device pointer + * @proc_id: processor id for the consumer remoteproc device + * @host_id: host id to pass the control over for this consumer remoteproc + * device + */ +struct ti_sci_proc { + const struct ti_sci_handle *sci; + const struct ti_sci_proc_ops *ops; + struct device *dev; + u8 proc_id; + u8 host_id; +}; + +static inline int ti_sci_proc_request(struct ti_sci_proc *tsp) +{ + int ret; + + ret = tsp->ops->request(tsp->sci, tsp->proc_id); + if (ret) + dev_err(tsp->dev, "ti-sci processor request failed: %d\n", + ret); + return ret; +} + +static inline int ti_sci_proc_release(struct ti_sci_proc *tsp) +{ + int ret; + + ret = tsp->ops->release(tsp->sci, tsp->proc_id); + if (ret) + dev_err(tsp->dev, "ti-sci processor release failed: %d\n", + ret); + return ret; +} + +static inline int ti_sci_proc_handover(struct ti_sci_proc *tsp) +{ + int ret; + + ret = tsp->ops->handover(tsp->sci, tsp->proc_id, tsp->host_id); + if (ret) + dev_err(tsp->dev, "ti-sci processor handover of %d to %d failed: %d\n", + tsp->proc_id, tsp->host_id, ret); + return ret; +} + +static inline int ti_sci_proc_set_config(struct ti_sci_proc *tsp, + u64 boot_vector, + u32 cfg_set, u32 cfg_clr) +{ + int ret; + + ret = tsp->ops->set_config(tsp->sci, tsp->proc_id, boot_vector, + cfg_set, cfg_clr); + if (ret) + dev_err(tsp->dev, "ti-sci processor set_config failed: %d\n", + ret); + return ret; +} + +static inline int ti_sci_proc_set_control(struct ti_sci_proc *tsp, + u32 ctrl_set, u32 ctrl_clr) +{ + int ret; + + ret = tsp->ops->set_control(tsp->sci, tsp->proc_id, ctrl_set, ctrl_clr); + if (ret) + dev_err(tsp->dev, "ti-sci processor set_control failed: %d\n", + ret); + return ret; +} + +static inline int ti_sci_proc_get_status(struct ti_sci_proc *tsp, + u64 *boot_vector, u32 *cfg_flags, + u32 *ctrl_flags, u32 *status_flags) +{ + int ret; + + ret = tsp->ops->get_status(tsp->sci, tsp->proc_id, boot_vector, + cfg_flags, ctrl_flags, status_flags); + if (ret) + dev_err(tsp->dev, "ti-sci processor get_status failed: %d\n", + ret); + return ret; +} + +#endif /* REMOTEPROC_TI_SCI_PROC_H */ From 2a2180206ab62b42c6a7fd3d77c47c3675cbc893 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Tue, 21 Jul 2020 17:36:15 -0500 Subject: [PATCH 193/291] dt-bindings: remoteproc: Add bindings for C66x DSPs on TI K3 SoCs Some Texas Instruments K3 family of SoCs have one of more Digital Signal Processor (DSP) subsystems that are comprised of either a TMS320C66x CorePac and/or a next-generation TMS320C71x CorePac processor subsystem. Add the device tree bindings document for the C66x DSP devices on these SoCs. The added example illustrates the DT nodes for the first C66x DSP device present on the K3 J721E family of SoCs. Signed-off-by: Suman Anna Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20200721223617.20312-5-s-anna@ti.com Signed-off-by: Bjorn Andersson --- .../bindings/remoteproc/ti,k3-dsp-rproc.yaml | 142 ++++++++++++++++++ 1 file changed, 142 insertions(+) create mode 100644 Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml diff --git a/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml new file mode 100644 index 000000000000..a7834bc1530f --- /dev/null +++ b/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml @@ -0,0 +1,142 @@ +# SPDX-License-Identifier: (GPL-2.0-only or BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/remoteproc/ti,k3-dsp-rproc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: TI K3 DSP devices + +maintainers: + - Suman Anna + +description: | + The TI K3 family of SoCs usually have one or more TI DSP Core sub-systems + that are used to offload some of the processor-intensive tasks or algorithms, + for achieving various system level goals. + + These processor sub-systems usually contain additional sub-modules like + L1 and/or L2 caches/SRAMs, an Interrupt Controller, an external memory + controller, a dedicated local power/sleep controller etc. The DSP processor + cores in the K3 SoCs are usually either a TMS320C66x CorePac processor or a + TMS320C71x CorePac processor. + + Each DSP Core sub-system is represented as a single DT node. Each node has a + number of required or optional properties that enable the OS running on the + host processor (Arm CorePac) to perform the device management of the remote + processor and to communicate with the remote processor. + +allOf: + - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml# + +properties: + compatible: + const: ti,j721e-c66-dsp + description: + Use "ti,j721e-c66-dsp" for C66x DSPs on K3 J721E SoCs + + reg: + items: + - description: Address and Size of the L2 SRAM internal memory region + - description: Address and Size of the L1 PRAM internal memory region + - description: Address and Size of the L1 DRAM internal memory region + + reg-names: + items: + - const: l2sram + - const: l1pram + - const: l1dram + + resets: + description: | + Should contain the phandle to the reset controller node managing the + local resets for this device, and a reset specifier. + maxItems: 1 + + firmware-name: + description: | + Should contain the name of the default firmware image + file located on the firmware search path + + mboxes: + description: | + OMAP Mailbox specifier denoting the sub-mailbox, to be used for + communication with the remote processor. This property should match + with the sub-mailbox node used in the firmware image. + maxItems: 1 + + memory-region: + minItems: 2 + maxItems: 8 + description: | + phandle to the reserved memory nodes to be associated with the remoteproc + device. There should be at least two reserved memory nodes defined. The + reserved memory nodes should be carveout nodes, and should be defined as + per the bindings in + Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt + items: + - description: region used for dynamic DMA allocations like vrings and + vring buffers + - description: region reserved for firmware image sections + additionalItems: true + +# Optional properties: +# -------------------- + + sram: + $ref: /schemas/types.yaml#/definitions/phandle-array + minItems: 1 + maxItems: 4 + description: | + phandles to one or more reserved on-chip SRAM regions. The regions + should be defined as child nodes of the respective SRAM node, and + should be defined as per the generic bindings in, + Documentation/devicetree/bindings/sram/sram.yaml + +required: + - compatible + - reg + - reg-names + - ti,sci + - ti,sci-dev-id + - ti,sci-proc-ids + - resets + - firmware-name + - mboxes + - memory-region + +unevaluatedProperties: false + +examples: + - | + / { + model = "Texas Instruments K3 J721E SoC"; + compatible = "ti,j721e"; + #address-cells = <2>; + #size-cells = <2>; + + bus@100000 { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0x00 0x00100000 0x00 0x00100000 0x00 0x00020000>, /* ctrl mmr */ + <0x4d 0x80800000 0x4d 0x80800000 0x00 0x00800000>, /* C66_0 */ + <0x4d 0x81800000 0x4d 0x81800000 0x00 0x00800000>; /* C66_1 */ + + /* J721E C66_0 DSP node */ + dsp@4d80800000 { + compatible = "ti,j721e-c66-dsp"; + reg = <0x4d 0x80800000 0x00 0x00048000>, + <0x4d 0x80e00000 0x00 0x00008000>, + <0x4d 0x80f00000 0x00 0x00008000>; + reg-names = "l2sram", "l1pram", "l1dram"; + ti,sci = <&dmsc>; + ti,sci-dev-id = <142>; + ti,sci-proc-ids = <0x03 0xFF>; + resets = <&k3_reset 142 1>; + firmware-name = "j7-c66_0-fw"; + memory-region = <&c66_0_dma_memory_region>, + <&c66_0_memory_region>; + mboxes = <&mailbox0_cluster3 &mbox_c66_0>; + }; + }; + }; From 6edbe024ba17777b065e0d0b8aeca9789a4d880b Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Tue, 21 Jul 2020 17:36:16 -0500 Subject: [PATCH 194/291] remoteproc: k3-dsp: Add a remoteproc driver of K3 C66x DSPs The Texas Instrument's K3 J721E SoCs have two C66x DSP Subsystems in MAIN voltage domain that are based on the TI's standard TMS320C66x DSP CorePac module. Each subsystem has a Fixed/Floating-Point DSP CPU, with 32 KB each of L1P & L1D SRAMs that can be configured and partitioned as either RAM and/or Cache, and 288 KB of L2 SRAM with 256 KB of memory configurable as either RAM and/or Cache. The CorePac also includes an Internal DMA (IDMA), External Memory Controller (EMC), Extended Memory Controller (XMC) with a Region Address Translator (RAT) unit for 32-bit to 48-bit address extension/translations, an Interrupt Controller (INTC) and a Powerdown Controller (PDC). A new remoteproc module is added to perform the device management of these DSP devices. The support is limited to images using only external DDR memory at the moment, the loading support to internal memories and any on-chip RAM memories will be added in a subsequent patch. RAT support is also left for a future patch, and as such the reserved memory carveout regions are all expected to be using memory regions within the first 2 GB. Error Recovery and Power Management features are not currently supported. The C66x remote processors do not have an MMU, and so require fixed memory carveout regions matching the firmware image addresses. Support for this is provided by mandating multiple memory regions to be attached to the remoteproc device. The first memory region will be used to serve as the DMA pool for all dynamic allocations like the vrings and vring buffers. The remaining memory regions are mapped into the kernel at device probe time, and are used to provide address translations for firmware image segments without the need for any RSC_CARVEOUT entries. Any firmware image using memory outside of the supplied reserved memory carveout regions will be errored out. The driver uses various TI-SCI interfaces to talk to the System Controller (DMSC) for managing configuration, power and reset management of these cores. IPC between the A72 cores and the DSP cores is supported through the virtio rpmsg stack using shared memory and OMAP Mailboxes. Signed-off-by: Suman Anna Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200721223617.20312-6-s-anna@ti.com Signed-off-by: Bjorn Andersson --- drivers/remoteproc/Kconfig | 13 + drivers/remoteproc/Makefile | 1 + drivers/remoteproc/ti_k3_dsp_remoteproc.c | 699 ++++++++++++++++++++++ 3 files changed, 713 insertions(+) create mode 100644 drivers/remoteproc/ti_k3_dsp_remoteproc.c diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index 3e8d5d1a2b9e..3e70d972a186 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -257,6 +257,19 @@ config STM32_RPROC This can be either built-in or a loadable module. +config TI_K3_DSP_REMOTEPROC + tristate "TI K3 DSP remoteproc support" + depends on ARCH_K3 + select MAILBOX + select OMAP2PLUS_MBOX + help + Say m here to support TI's C66x and C71x DSP remote processor + subsystems on various TI K3 family of SoCs through the remote + processor framework. + + It's safe to say N here if you're not interested in utilizing + the DSP slave processors. + endif # REMOTEPROC endmenu diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile index a4c1397d6367..7ce1b8ef7677 100644 --- a/drivers/remoteproc/Makefile +++ b/drivers/remoteproc/Makefile @@ -32,3 +32,4 @@ qcom_wcnss_pil-y += qcom_wcnss_iris.o obj-$(CONFIG_ST_REMOTEPROC) += st_remoteproc.o obj-$(CONFIG_ST_SLIM_REMOTEPROC) += st_slim_rproc.o obj-$(CONFIG_STM32_RPROC) += stm32_rproc.o +obj-$(CONFIG_TI_K3_DSP_REMOTEPROC) += ti_k3_dsp_remoteproc.o diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c new file mode 100644 index 000000000000..18f714b012df --- /dev/null +++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c @@ -0,0 +1,699 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * TI K3 DSP Remote Processor(s) driver + * + * Copyright (C) 2018-2020 Texas Instruments Incorporated - https://www.ti.com/ + * Suman Anna + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "omap_remoteproc.h" +#include "remoteproc_internal.h" +#include "ti_sci_proc.h" + +#define KEYSTONE_RPROC_LOCAL_ADDRESS_MASK (SZ_16M - 1) + +/** + * struct k3_dsp_mem - internal memory structure + * @cpu_addr: MPU virtual address of the memory region + * @bus_addr: Bus address used to access the memory region + * @dev_addr: Device address of the memory region from DSP view + * @size: Size of the memory region + */ +struct k3_dsp_mem { + void __iomem *cpu_addr; + phys_addr_t bus_addr; + u32 dev_addr; + size_t size; +}; + +/** + * struct k3_dsp_mem_data - memory definitions for a DSP + * @name: name for this memory entry + * @dev_addr: device address for the memory entry + */ +struct k3_dsp_mem_data { + const char *name; + const u32 dev_addr; +}; + +/** + * struct k3_dsp_dev_data - device data structure for a DSP + * @mems: pointer to memory definitions for a DSP + * @num_mems: number of memory regions in @mems + * @boot_align_addr: boot vector address alignment granularity + * @uses_lreset: flag to denote the need for local reset management + */ +struct k3_dsp_dev_data { + const struct k3_dsp_mem_data *mems; + u32 num_mems; + u32 boot_align_addr; + bool uses_lreset; +}; + +/** + * struct k3_dsp_rproc - k3 DSP remote processor driver structure + * @dev: cached device pointer + * @rproc: remoteproc device handle + * @mem: internal memory regions data + * @num_mems: number of internal memory regions + * @rmem: reserved memory regions data + * @num_rmems: number of reserved memory regions + * @reset: reset control handle + * @data: pointer to DSP-specific device data + * @tsp: TI-SCI processor control handle + * @ti_sci: TI-SCI handle + * @ti_sci_id: TI-SCI device identifier + * @mbox: mailbox channel handle + * @client: mailbox client to request the mailbox channel + */ +struct k3_dsp_rproc { + struct device *dev; + struct rproc *rproc; + struct k3_dsp_mem *mem; + int num_mems; + struct k3_dsp_mem *rmem; + int num_rmems; + struct reset_control *reset; + const struct k3_dsp_dev_data *data; + struct ti_sci_proc *tsp; + const struct ti_sci_handle *ti_sci; + u32 ti_sci_id; + struct mbox_chan *mbox; + struct mbox_client client; +}; + +/** + * k3_dsp_rproc_mbox_callback() - inbound mailbox message handler + * @client: mailbox client pointer used for requesting the mailbox channel + * @data: mailbox payload + * + * This handler is invoked by the OMAP mailbox driver whenever a mailbox + * message is received. Usually, the mailbox payload simply contains + * the index of the virtqueue that is kicked by the remote processor, + * and we let remoteproc core handle it. + * + * In addition to virtqueue indices, we also have some out-of-band values + * that indicate different events. Those values are deliberately very + * large so they don't coincide with virtqueue indices. + */ +static void k3_dsp_rproc_mbox_callback(struct mbox_client *client, void *data) +{ + struct k3_dsp_rproc *kproc = container_of(client, struct k3_dsp_rproc, + client); + struct device *dev = kproc->rproc->dev.parent; + const char *name = kproc->rproc->name; + u32 msg = omap_mbox_message(data); + + dev_dbg(dev, "mbox msg: 0x%x\n", msg); + + switch (msg) { + case RP_MBOX_CRASH: + /* + * remoteproc detected an exception, but error recovery is not + * supported. So, just log this for now + */ + dev_err(dev, "K3 DSP rproc %s crashed\n", name); + break; + case RP_MBOX_ECHO_REPLY: + dev_info(dev, "received echo reply from %s\n", name); + break; + default: + /* silently handle all other valid messages */ + if (msg >= RP_MBOX_READY && msg < RP_MBOX_END_MSG) + return; + if (msg > kproc->rproc->max_notifyid) { + dev_dbg(dev, "dropping unknown message 0x%x", msg); + return; + } + /* msg contains the index of the triggered vring */ + if (rproc_vq_interrupt(kproc->rproc, msg) == IRQ_NONE) + dev_dbg(dev, "no message was found in vqid %d\n", msg); + } +} + +/* + * Kick the remote processor to notify about pending unprocessed messages. + * The vqid usage is not used and is inconsequential, as the kick is performed + * through a simulated GPIO (a bit in an IPC interrupt-triggering register), + * the remote processor is expected to process both its Tx and Rx virtqueues. + */ +static void k3_dsp_rproc_kick(struct rproc *rproc, int vqid) +{ + struct k3_dsp_rproc *kproc = rproc->priv; + struct device *dev = rproc->dev.parent; + mbox_msg_t msg = (mbox_msg_t)vqid; + int ret; + + /* send the index of the triggered virtqueue in the mailbox payload */ + ret = mbox_send_message(kproc->mbox, (void *)msg); + if (ret < 0) + dev_err(dev, "failed to send mailbox message, status = %d\n", + ret); +} + +/* Put the DSP processor into reset */ +static int k3_dsp_rproc_reset(struct k3_dsp_rproc *kproc) +{ + struct device *dev = kproc->dev; + int ret; + + ret = reset_control_assert(kproc->reset); + if (ret) { + dev_err(dev, "local-reset assert failed, ret = %d\n", ret); + return ret; + } + + ret = kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci, + kproc->ti_sci_id); + if (ret) { + dev_err(dev, "module-reset assert failed, ret = %d\n", ret); + if (reset_control_deassert(kproc->reset)) + dev_warn(dev, "local-reset deassert back failed\n"); + } + + return ret; +} + +/* Release the DSP processor from reset */ +static int k3_dsp_rproc_release(struct k3_dsp_rproc *kproc) +{ + struct device *dev = kproc->dev; + int ret; + + ret = kproc->ti_sci->ops.dev_ops.get_device(kproc->ti_sci, + kproc->ti_sci_id); + if (ret) { + dev_err(dev, "module-reset deassert failed, ret = %d\n", ret); + return ret; + } + + ret = reset_control_deassert(kproc->reset); + if (ret) { + dev_err(dev, "local-reset deassert failed, ret = %d\n", ret); + if (kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci, + kproc->ti_sci_id)) + dev_warn(dev, "module-reset assert back failed\n"); + } + + return ret; +} + +/* + * Power up the DSP remote processor. + * + * This function will be invoked only after the firmware for this rproc + * was loaded, parsed successfully, and all of its resource requirements + * were met. + */ +static int k3_dsp_rproc_start(struct rproc *rproc) +{ + struct k3_dsp_rproc *kproc = rproc->priv; + struct mbox_client *client = &kproc->client; + struct device *dev = kproc->dev; + u32 boot_addr; + int ret; + + client->dev = dev; + client->tx_done = NULL; + client->rx_callback = k3_dsp_rproc_mbox_callback; + client->tx_block = false; + client->knows_txdone = false; + + kproc->mbox = mbox_request_channel(client, 0); + if (IS_ERR(kproc->mbox)) { + ret = -EBUSY; + dev_err(dev, "mbox_request_channel failed: %ld\n", + PTR_ERR(kproc->mbox)); + return ret; + } + + /* + * Ping the remote processor, this is only for sanity-sake for now; + * there is no functional effect whatsoever. + * + * Note that the reply will _not_ arrive immediately: this message + * will wait in the mailbox fifo until the remote processor is booted. + */ + ret = mbox_send_message(kproc->mbox, (void *)RP_MBOX_ECHO_REQUEST); + if (ret < 0) { + dev_err(dev, "mbox_send_message failed: %d\n", ret); + goto put_mbox; + } + + boot_addr = rproc->bootaddr; + if (boot_addr & (kproc->data->boot_align_addr - 1)) { + dev_err(dev, "invalid boot address 0x%x, must be aligned on a 0x%x boundary\n", + boot_addr, kproc->data->boot_align_addr); + ret = -EINVAL; + goto put_mbox; + } + + dev_err(dev, "booting DSP core using boot addr = 0x%x\n", boot_addr); + ret = ti_sci_proc_set_config(kproc->tsp, boot_addr, 0, 0); + if (ret) + goto put_mbox; + + ret = k3_dsp_rproc_release(kproc); + if (ret) + goto put_mbox; + + return 0; + +put_mbox: + mbox_free_channel(kproc->mbox); + return ret; +} + +/* + * Stop the DSP remote processor. + * + * This function puts the DSP processor into reset, and finishes processing + * of any pending messages. + */ +static int k3_dsp_rproc_stop(struct rproc *rproc) +{ + struct k3_dsp_rproc *kproc = rproc->priv; + + mbox_free_channel(kproc->mbox); + + k3_dsp_rproc_reset(kproc); + + return 0; +} + +/* + * Custom function to translate a DSP device address (internal RAMs only) to a + * kernel virtual address. The DSPs can access their RAMs at either an internal + * address visible only from a DSP, or at the SoC-level bus address. Both these + * addresses need to be looked through for translation. The translated addresses + * can be used either by the remoteproc core for loading (when using kernel + * remoteproc loader), or by any rpmsg bus drivers. + */ +static void *k3_dsp_rproc_da_to_va(struct rproc *rproc, u64 da, size_t len) +{ + struct k3_dsp_rproc *kproc = rproc->priv; + void __iomem *va = NULL; + phys_addr_t bus_addr; + u32 dev_addr, offset; + size_t size; + int i; + + if (len == 0) + return NULL; + + for (i = 0; i < kproc->num_mems; i++) { + bus_addr = kproc->mem[i].bus_addr; + dev_addr = kproc->mem[i].dev_addr; + size = kproc->mem[i].size; + + if (da < KEYSTONE_RPROC_LOCAL_ADDRESS_MASK) { + /* handle DSP-view addresses */ + if (da >= dev_addr && + ((da + len) <= (dev_addr + size))) { + offset = da - dev_addr; + va = kproc->mem[i].cpu_addr + offset; + return (__force void *)va; + } + } else { + /* handle SoC-view addresses */ + if (da >= bus_addr && + (da + len) <= (bus_addr + size)) { + offset = da - bus_addr; + va = kproc->mem[i].cpu_addr + offset; + return (__force void *)va; + } + } + } + + /* handle static DDR reserved memory regions */ + for (i = 0; i < kproc->num_rmems; i++) { + dev_addr = kproc->rmem[i].dev_addr; + size = kproc->rmem[i].size; + + if (da >= dev_addr && ((da + len) <= (dev_addr + size))) { + offset = da - dev_addr; + va = kproc->rmem[i].cpu_addr + offset; + return (__force void *)va; + } + } + + return NULL; +} + +static const struct rproc_ops k3_dsp_rproc_ops = { + .start = k3_dsp_rproc_start, + .stop = k3_dsp_rproc_stop, + .kick = k3_dsp_rproc_kick, + .da_to_va = k3_dsp_rproc_da_to_va, +}; + +static int k3_dsp_rproc_of_get_memories(struct platform_device *pdev, + struct k3_dsp_rproc *kproc) +{ + const struct k3_dsp_dev_data *data = kproc->data; + struct device *dev = &pdev->dev; + struct resource *res; + int num_mems = 0; + int i; + + num_mems = kproc->data->num_mems; + kproc->mem = devm_kcalloc(kproc->dev, num_mems, + sizeof(*kproc->mem), GFP_KERNEL); + if (!kproc->mem) + return -ENOMEM; + + for (i = 0; i < num_mems; i++) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + data->mems[i].name); + if (!res) { + dev_err(dev, "found no memory resource for %s\n", + data->mems[i].name); + return -EINVAL; + } + if (!devm_request_mem_region(dev, res->start, + resource_size(res), + dev_name(dev))) { + dev_err(dev, "could not request %s region for resource\n", + data->mems[i].name); + return -EBUSY; + } + + kproc->mem[i].cpu_addr = devm_ioremap_wc(dev, res->start, + resource_size(res)); + if (IS_ERR(kproc->mem[i].cpu_addr)) { + dev_err(dev, "failed to map %s memory\n", + data->mems[i].name); + return PTR_ERR(kproc->mem[i].cpu_addr); + } + kproc->mem[i].bus_addr = res->start; + kproc->mem[i].dev_addr = data->mems[i].dev_addr; + kproc->mem[i].size = resource_size(res); + + dev_dbg(dev, "memory %8s: bus addr %pa size 0x%zx va %pK da 0x%x\n", + data->mems[i].name, &kproc->mem[i].bus_addr, + kproc->mem[i].size, kproc->mem[i].cpu_addr, + kproc->mem[i].dev_addr); + } + kproc->num_mems = num_mems; + + return 0; +} + +static int k3_dsp_reserved_mem_init(struct k3_dsp_rproc *kproc) +{ + struct device *dev = kproc->dev; + struct device_node *np = dev->of_node; + struct device_node *rmem_np; + struct reserved_mem *rmem; + int num_rmems; + int ret, i; + + num_rmems = of_property_count_elems_of_size(np, "memory-region", + sizeof(phandle)); + if (num_rmems <= 0) { + dev_err(dev, "device does not reserved memory regions, ret = %d\n", + num_rmems); + return -EINVAL; + } + if (num_rmems < 2) { + dev_err(dev, "device needs atleast two memory regions to be defined, num = %d\n", + num_rmems); + return -EINVAL; + } + + /* use reserved memory region 0 for vring DMA allocations */ + ret = of_reserved_mem_device_init_by_idx(dev, np, 0); + if (ret) { + dev_err(dev, "device cannot initialize DMA pool, ret = %d\n", + ret); + return ret; + } + + num_rmems--; + kproc->rmem = kcalloc(num_rmems, sizeof(*kproc->rmem), GFP_KERNEL); + if (!kproc->rmem) { + ret = -ENOMEM; + goto release_rmem; + } + + /* use remaining reserved memory regions for static carveouts */ + for (i = 0; i < num_rmems; i++) { + rmem_np = of_parse_phandle(np, "memory-region", i + 1); + if (!rmem_np) { + ret = -EINVAL; + goto unmap_rmem; + } + + rmem = of_reserved_mem_lookup(rmem_np); + if (!rmem) { + of_node_put(rmem_np); + ret = -EINVAL; + goto unmap_rmem; + } + of_node_put(rmem_np); + + kproc->rmem[i].bus_addr = rmem->base; + /* 64-bit address regions currently not supported */ + kproc->rmem[i].dev_addr = (u32)rmem->base; + kproc->rmem[i].size = rmem->size; + kproc->rmem[i].cpu_addr = ioremap_wc(rmem->base, rmem->size); + if (!kproc->rmem[i].cpu_addr) { + dev_err(dev, "failed to map reserved memory#%d at %pa of size %pa\n", + i + 1, &rmem->base, &rmem->size); + ret = -ENOMEM; + goto unmap_rmem; + } + + dev_dbg(dev, "reserved memory%d: bus addr %pa size 0x%zx va %pK da 0x%x\n", + i + 1, &kproc->rmem[i].bus_addr, + kproc->rmem[i].size, kproc->rmem[i].cpu_addr, + kproc->rmem[i].dev_addr); + } + kproc->num_rmems = num_rmems; + + return 0; + +unmap_rmem: + for (i--; i >= 0; i--) + iounmap(kproc->rmem[i].cpu_addr); + kfree(kproc->rmem); +release_rmem: + of_reserved_mem_device_release(kproc->dev); + return ret; +} + +static void k3_dsp_reserved_mem_exit(struct k3_dsp_rproc *kproc) +{ + int i; + + for (i = 0; i < kproc->num_rmems; i++) + iounmap(kproc->rmem[i].cpu_addr); + kfree(kproc->rmem); + + of_reserved_mem_device_release(kproc->dev); +} + +static +struct ti_sci_proc *k3_dsp_rproc_of_get_tsp(struct device *dev, + const struct ti_sci_handle *sci) +{ + struct ti_sci_proc *tsp; + u32 temp[2]; + int ret; + + ret = of_property_read_u32_array(dev->of_node, "ti,sci-proc-ids", + temp, 2); + if (ret < 0) + return ERR_PTR(ret); + + tsp = kzalloc(sizeof(*tsp), GFP_KERNEL); + if (!tsp) + return ERR_PTR(-ENOMEM); + + tsp->dev = dev; + tsp->sci = sci; + tsp->ops = &sci->ops.proc_ops; + tsp->proc_id = temp[0]; + tsp->host_id = temp[1]; + + return tsp; +} + +static int k3_dsp_rproc_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + const struct k3_dsp_dev_data *data; + struct k3_dsp_rproc *kproc; + struct rproc *rproc; + const char *fw_name; + int ret = 0; + int ret1; + + data = of_device_get_match_data(dev); + if (!data) + return -ENODEV; + + ret = rproc_of_parse_firmware(dev, 0, &fw_name); + if (ret) { + dev_err(dev, "failed to parse firmware-name property, ret = %d\n", + ret); + return ret; + } + + rproc = rproc_alloc(dev, dev_name(dev), &k3_dsp_rproc_ops, fw_name, + sizeof(*kproc)); + if (!rproc) + return -ENOMEM; + + rproc->has_iommu = false; + rproc->recovery_disabled = true; + kproc = rproc->priv; + kproc->rproc = rproc; + kproc->dev = dev; + kproc->data = data; + + kproc->ti_sci = ti_sci_get_by_phandle(np, "ti,sci"); + if (IS_ERR(kproc->ti_sci)) { + ret = PTR_ERR(kproc->ti_sci); + if (ret != -EPROBE_DEFER) { + dev_err(dev, "failed to get ti-sci handle, ret = %d\n", + ret); + } + kproc->ti_sci = NULL; + goto free_rproc; + } + + ret = of_property_read_u32(np, "ti,sci-dev-id", &kproc->ti_sci_id); + if (ret) { + dev_err(dev, "missing 'ti,sci-dev-id' property\n"); + goto put_sci; + } + + kproc->reset = devm_reset_control_get_exclusive(dev, NULL); + if (IS_ERR(kproc->reset)) { + ret = PTR_ERR(kproc->reset); + dev_err(dev, "failed to get reset, status = %d\n", ret); + goto put_sci; + } + + kproc->tsp = k3_dsp_rproc_of_get_tsp(dev, kproc->ti_sci); + if (IS_ERR(kproc->tsp)) { + dev_err(dev, "failed to construct ti-sci proc control, ret = %d\n", + ret); + ret = PTR_ERR(kproc->tsp); + goto put_sci; + } + + ret = ti_sci_proc_request(kproc->tsp); + if (ret < 0) { + dev_err(dev, "ti_sci_proc_request failed, ret = %d\n", ret); + goto free_tsp; + } + + ret = k3_dsp_rproc_of_get_memories(pdev, kproc); + if (ret) + goto release_tsp; + + ret = k3_dsp_reserved_mem_init(kproc); + if (ret) { + dev_err(dev, "reserved memory init failed, ret = %d\n", ret); + goto release_tsp; + } + + ret = rproc_add(rproc); + if (ret) { + dev_err(dev, "failed to add register device with remoteproc core, status = %d\n", + ret); + goto release_mem; + } + + platform_set_drvdata(pdev, kproc); + + return 0; + +release_mem: + k3_dsp_reserved_mem_exit(kproc); +release_tsp: + ret1 = ti_sci_proc_release(kproc->tsp); + if (ret1) + dev_err(dev, "failed to release proc, ret = %d\n", ret1); +free_tsp: + kfree(kproc->tsp); +put_sci: + ret1 = ti_sci_put_handle(kproc->ti_sci); + if (ret1) + dev_err(dev, "failed to put ti_sci handle, ret = %d\n", ret1); +free_rproc: + rproc_free(rproc); + return ret; +} + +static int k3_dsp_rproc_remove(struct platform_device *pdev) +{ + struct k3_dsp_rproc *kproc = platform_get_drvdata(pdev); + struct device *dev = &pdev->dev; + int ret; + + rproc_del(kproc->rproc); + + ret = ti_sci_proc_release(kproc->tsp); + if (ret) + dev_err(dev, "failed to release proc, ret = %d\n", ret); + + kfree(kproc->tsp); + + ret = ti_sci_put_handle(kproc->ti_sci); + if (ret) + dev_err(dev, "failed to put ti_sci handle, ret = %d\n", ret); + + k3_dsp_reserved_mem_exit(kproc); + rproc_free(kproc->rproc); + + return 0; +} + +static const struct k3_dsp_mem_data c66_mems[] = { + { .name = "l2sram", .dev_addr = 0x800000 }, + { .name = "l1pram", .dev_addr = 0xe00000 }, + { .name = "l1dram", .dev_addr = 0xf00000 }, +}; + +static const struct k3_dsp_dev_data c66_data = { + .mems = c66_mems, + .num_mems = ARRAY_SIZE(c66_mems), + .boot_align_addr = SZ_1K, + .uses_lreset = true, +}; + +static const struct of_device_id k3_dsp_of_match[] = { + { .compatible = "ti,j721e-c66-dsp", .data = &c66_data, }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, k3_dsp_of_match); + +static struct platform_driver k3_dsp_rproc_driver = { + .probe = k3_dsp_rproc_probe, + .remove = k3_dsp_rproc_remove, + .driver = { + .name = "k3-dsp-rproc", + .of_match_table = k3_dsp_of_match, + }, +}; + +module_platform_driver(k3_dsp_rproc_driver); + +MODULE_AUTHOR("Suman Anna "); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("TI K3 DSP Remoteproc driver"); From 21a4d7386e7e8b5f6fb97ced6af3b8181f2c9bd5 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Tue, 21 Jul 2020 17:36:17 -0500 Subject: [PATCH 195/291] remoteproc: k3-dsp: Add support for L2RAM loading on C66x DSPs The resets for the DSP processors on K3 SoCs are managed through the Power and Sleep Controller (PSC) module. Each DSP typically has two resets - a global module reset for powering on the device, and a local reset that affects only the CPU while allowing access to the other sub-modules within the DSP processor sub-systems. The C66x DSPs have two levels of internal RAMs that can be used to boot from, and the firmware loading into these RAMs require the local reset to be asserted with the device powered on/enabled using the module reset. Enhance the K3 DSP remoteproc driver to add support for loading into the internal RAMs. The local reset is deasserted on SoC power-on-reset, so logic has to be added in probe in remoteproc mode to balance the remoteproc state-machine. Note that the local resets are a no-op on C71x cores, and the hardware does not supporting loading into its internal RAMs. Signed-off-by: Suman Anna Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200721223617.20312-7-s-anna@ti.com Signed-off-by: Bjorn Andersson --- drivers/remoteproc/ti_k3_dsp_remoteproc.c | 72 +++++++++++++++++++++++ 1 file changed, 72 insertions(+) diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c index 18f714b012df..43566ead7a1d 100644 --- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c +++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c @@ -174,6 +174,9 @@ static int k3_dsp_rproc_reset(struct k3_dsp_rproc *kproc) return ret; } + if (kproc->data->uses_lreset) + return ret; + ret = kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci, kproc->ti_sci_id); if (ret) { @@ -191,6 +194,9 @@ static int k3_dsp_rproc_release(struct k3_dsp_rproc *kproc) struct device *dev = kproc->dev; int ret; + if (kproc->data->uses_lreset) + goto lreset; + ret = kproc->ti_sci->ops.dev_ops.get_device(kproc->ti_sci, kproc->ti_sci_id); if (ret) { @@ -198,6 +204,7 @@ static int k3_dsp_rproc_release(struct k3_dsp_rproc *kproc) return ret; } +lreset: ret = reset_control_deassert(kproc->reset); if (ret) { dev_err(dev, "local-reset deassert failed, ret = %d\n", ret); @@ -209,6 +216,53 @@ static int k3_dsp_rproc_release(struct k3_dsp_rproc *kproc) return ret; } +/* + * The C66x DSP cores have a local reset that affects only the CPU, and a + * generic module reset that powers on the device and allows the DSP internal + * memories to be accessed while the local reset is asserted. This function is + * used to release the global reset on C66x DSPs to allow loading into the DSP + * internal RAMs. The .prepare() ops is invoked by remoteproc core before any + * firmware loading, and is followed by the .start() ops after loading to + * actually let the C66x DSP cores run. + */ +static int k3_dsp_rproc_prepare(struct rproc *rproc) +{ + struct k3_dsp_rproc *kproc = rproc->priv; + struct device *dev = kproc->dev; + int ret; + + ret = kproc->ti_sci->ops.dev_ops.get_device(kproc->ti_sci, + kproc->ti_sci_id); + if (ret) + dev_err(dev, "module-reset deassert failed, cannot enable internal RAM loading, ret = %d\n", + ret); + + return ret; +} + +/* + * This function implements the .unprepare() ops and performs the complimentary + * operations to that of the .prepare() ops. The function is used to assert the + * global reset on applicable C66x cores. This completes the second portion of + * powering down the C66x DSP cores. The cores themselves are only halted in the + * .stop() callback through the local reset, and the .unprepare() ops is invoked + * by the remoteproc core after the remoteproc is stopped to balance the global + * reset. + */ +static int k3_dsp_rproc_unprepare(struct rproc *rproc) +{ + struct k3_dsp_rproc *kproc = rproc->priv; + struct device *dev = kproc->dev; + int ret; + + ret = kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci, + kproc->ti_sci_id); + if (ret) + dev_err(dev, "module-reset assert failed, ret = %d\n", ret); + + return ret; +} + /* * Power up the DSP remote processor. * @@ -352,6 +406,8 @@ static void *k3_dsp_rproc_da_to_va(struct rproc *rproc, u64 da, size_t len) } static const struct rproc_ops k3_dsp_rproc_ops = { + .prepare = k3_dsp_rproc_prepare, + .unprepare = k3_dsp_rproc_unprepare, .start = k3_dsp_rproc_start, .stop = k3_dsp_rproc_stop, .kick = k3_dsp_rproc_kick, @@ -612,6 +668,22 @@ static int k3_dsp_rproc_probe(struct platform_device *pdev) goto release_tsp; } + /* + * ensure the DSP local reset is asserted to ensure the DSP doesn't + * execute bogus code in .prepare() when the module reset is released. + */ + if (data->uses_lreset) { + ret = reset_control_status(kproc->reset); + if (ret < 0) { + dev_err(dev, "failed to get reset status, status = %d\n", + ret); + goto release_mem; + } else if (ret == 0) { + dev_warn(dev, "local reset is deasserted for device\n"); + k3_dsp_rproc_reset(kproc); + } + } + ret = rproc_add(rproc); if (ret) { dev_err(dev, "failed to add register device with remoteproc core, status = %d\n", From c6caf22eaa2347e75ef639ccfafd277ce466e1ca Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Fri, 12 Jun 2020 17:53:56 -0500 Subject: [PATCH 196/291] dt-bindings: remoteproc: k3-dsp: Update bindings for C71x DSPs Some Texas Instruments K3 family of SoCs have one of more newer generation TMS320C71x CorePac processor subsystem in addition to the existing TMS320C66x CorePac processor subsystems. Update the device tree bindings document for the C71x DSP devices. The example is also updated to show the single C71 DSP present on J721E SoCs. Reviewed-by: Rob Herring Signed-off-by: Suman Anna Link: https://lore.kernel.org/r/20200612225357.8251-2-s-anna@ti.com Signed-off-by: Bjorn Andersson --- .../bindings/remoteproc/ti,k3-dsp-rproc.yaml | 68 +++++++++++++++---- 1 file changed, 55 insertions(+), 13 deletions(-) diff --git a/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml index a7834bc1530f..24b0c50fa436 100644 --- a/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml +++ b/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml @@ -30,21 +30,12 @@ allOf: properties: compatible: - const: ti,j721e-c66-dsp + enum: + - ti,j721e-c66-dsp + - ti,j721e-c71-dsp description: Use "ti,j721e-c66-dsp" for C66x DSPs on K3 J721E SoCs - - reg: - items: - - description: Address and Size of the L2 SRAM internal memory region - - description: Address and Size of the L1 PRAM internal memory region - - description: Address and Size of the L1 DRAM internal memory region - - reg-names: - items: - - const: l2sram - - const: l1pram - - const: l1dram + Use "ti,j721e-c71-dsp" for C71x DSPs on K3 J721E SoCs resets: description: | @@ -92,6 +83,40 @@ properties: should be defined as per the generic bindings in, Documentation/devicetree/bindings/sram/sram.yaml +if: + properties: + compatible: + enum: + - ti,j721e-c66-dsp +then: + properties: + reg: + items: + - description: Address and Size of the L2 SRAM internal memory region + - description: Address and Size of the L1 PRAM internal memory region + - description: Address and Size of the L1 DRAM internal memory region + reg-names: + items: + - const: l2sram + - const: l1pram + - const: l1dram +else: + if: + properties: + compatible: + enum: + - ti,j721e-c71-dsp + then: + properties: + reg: + items: + - description: Address and Size of the L2 SRAM internal memory region + - description: Address and Size of the L1 DRAM internal memory region + reg-names: + items: + - const: l2sram + - const: l1dram + required: - compatible - reg @@ -119,6 +144,7 @@ examples: #address-cells = <2>; #size-cells = <2>; ranges = <0x00 0x00100000 0x00 0x00100000 0x00 0x00020000>, /* ctrl mmr */ + <0x00 0x64800000 0x00 0x64800000 0x00 0x00800000>, /* C71_0 */ <0x4d 0x80800000 0x4d 0x80800000 0x00 0x00800000>, /* C66_0 */ <0x4d 0x81800000 0x4d 0x81800000 0x00 0x00800000>; /* C66_1 */ @@ -138,5 +164,21 @@ examples: <&c66_0_memory_region>; mboxes = <&mailbox0_cluster3 &mbox_c66_0>; }; + + /* J721E C71_0 DSP node */ + c71_0: dsp@64800000 { + compatible = "ti,j721e-c71-dsp"; + reg = <0x00 0x64800000 0x00 0x00080000>, + <0x00 0x64e00000 0x00 0x0000c000>; + reg-names = "l2sram", "l1dram"; + ti,sci = <&dmsc>; + ti,sci-dev-id = <15>; + ti,sci-proc-ids = <0x30 0xFF>; + resets = <&k3_reset 15 1>; + firmware-name = "j7-c71_0-fw"; + memory-region = <&c71_0_dma_memory_region>, + <&c71_0_memory_region>; + mboxes = <&mailbox0_cluster4 &mbox_c71_0>; + }; }; }; From 87218f96c21a992817f3841078df873a1b037a58 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Fri, 12 Jun 2020 17:53:57 -0500 Subject: [PATCH 197/291] remoteproc: k3-dsp: Add support for C71x DSPs The Texas Instrument's K3 J721E SoCs have a newer next-generation C71x DSP Subsystem in the MAIN voltage domain in addition to the previous generation C66x DSP subsystems. The C71x DSP subsystem is based on the TMS320C71x DSP CorePac module. The C71x CPU is a true 64-bit machine including 64-bit memory addressing and single-cycle 64-bit base arithmetic operations and supports vector signal processing providing a significant lift in DSP processing power over C66x DSPs. J721E SoCs use a C711 (a one-core 512-bit vector width CPU core) DSP that is cache coherent with the A72 Arm cores. Each subsystem has one or more Fixed/Floating-Point DSP CPUs, with 32 KB of L1P Cache, 48 KB of L1D SRAM that can be configured and partitioned as either RAM and/or Cache, and 512 KB of L2 SRAM configurable as either RAM and/or Cache. The CorePac also includes a Matrix Multiplication Accelerator (MMA), a Stream Engine (SE) and a C71x Memory Management Unit (CMMU), an Interrupt Controller (INTC) and a Powerdown Management Unit (PMU) modules. Update the existing K3 DSP remoteproc driver to add support for this C71x DSP subsystem. The firmware loading support is provided by using the newly added 64-bit ELF loader support, and is limited to images using only external DDR memory at the moment. The L1D and L2 SRAMs are used as scratch memory when using as RAMs, and cannot be used for loadable segments. The CMMU is also not supported to begin with, and the driver is designed to treat the MMU as if it is in bypass mode. Signed-off-by: Suman Anna Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200612225357.8251-3-s-anna@ti.com Signed-off-by: Bjorn Andersson --- drivers/remoteproc/ti_k3_dsp_remoteproc.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c index 43566ead7a1d..9011e477290c 100644 --- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c +++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c @@ -406,8 +406,6 @@ static void *k3_dsp_rproc_da_to_va(struct rproc *rproc, u64 da, size_t len) } static const struct rproc_ops k3_dsp_rproc_ops = { - .prepare = k3_dsp_rproc_prepare, - .unprepare = k3_dsp_rproc_unprepare, .start = k3_dsp_rproc_start, .stop = k3_dsp_rproc_stop, .kick = k3_dsp_rproc_kick, @@ -615,6 +613,10 @@ static int k3_dsp_rproc_probe(struct platform_device *pdev) rproc->has_iommu = false; rproc->recovery_disabled = true; + if (data->uses_lreset) { + rproc->ops->prepare = k3_dsp_rproc_prepare; + rproc->ops->unprepare = k3_dsp_rproc_unprepare; + } kproc = rproc->priv; kproc->rproc = rproc; kproc->dev = dev; @@ -742,6 +744,12 @@ static const struct k3_dsp_mem_data c66_mems[] = { { .name = "l1dram", .dev_addr = 0xf00000 }, }; +/* C71x cores only have a L1P Cache, there are no L1P SRAMs */ +static const struct k3_dsp_mem_data c71_mems[] = { + { .name = "l2sram", .dev_addr = 0x800000 }, + { .name = "l1dram", .dev_addr = 0xe00000 }, +}; + static const struct k3_dsp_dev_data c66_data = { .mems = c66_mems, .num_mems = ARRAY_SIZE(c66_mems), @@ -749,8 +757,16 @@ static const struct k3_dsp_dev_data c66_data = { .uses_lreset = true, }; +static const struct k3_dsp_dev_data c71_data = { + .mems = c71_mems, + .num_mems = ARRAY_SIZE(c71_mems), + .boot_align_addr = SZ_2M, + .uses_lreset = false, +}; + static const struct of_device_id k3_dsp_of_match[] = { { .compatible = "ti,j721e-c66-dsp", .data = &c66_data, }, + { .compatible = "ti,j721e-c71-dsp", .data = &c71_data, }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, k3_dsp_of_match); From 30eb3fbee3da7892b98283f9d68667fc59bc390e Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 24 Jul 2020 13:11:41 -0500 Subject: [PATCH 198/291] net: ipa: new notification infrastructure Use the new SSR notifier infrastructure to request notifications of modem events, rather than the remoteproc IPA notification system. The latter was put in place temporarily with the knowledge that the new mechanism would become available. Acked-by: David S. Miller Reviewed-by: Bjorn Andersson Signed-off-by: Alex Elder Link: https://lore.kernel.org/r/20200724181142.13581-2-elder@linaro.org Signed-off-by: Bjorn Andersson --- drivers/net/ipa/ipa.h | 3 ++ drivers/net/ipa/ipa_modem.c | 56 +++++++++++++++++++++++-------------- 2 files changed, 38 insertions(+), 21 deletions(-) diff --git a/drivers/net/ipa/ipa.h b/drivers/net/ipa/ipa.h index b10a85392952..55115cfb2972 100644 --- a/drivers/net/ipa/ipa.h +++ b/drivers/net/ipa/ipa.h @@ -10,6 +10,7 @@ #include #include #include +#include #include "ipa_version.h" #include "gsi.h" @@ -73,6 +74,8 @@ struct ipa { enum ipa_version version; struct platform_device *pdev; struct rproc *modem_rproc; + struct notifier_block nb; + void *notifier; struct ipa_smp2p *smp2p; struct ipa_clock *clock; atomic_t suspend_ref; diff --git a/drivers/net/ipa/ipa_modem.c b/drivers/net/ipa/ipa_modem.c index ed10818dd99f..e34fe2d77324 100644 --- a/drivers/net/ipa/ipa_modem.c +++ b/drivers/net/ipa/ipa_modem.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include "ipa.h" #include "ipa_data.h" @@ -311,43 +311,40 @@ static void ipa_modem_crashed(struct ipa *ipa) dev_err(dev, "error %d zeroing modem memory regions\n", ret); } -static void ipa_modem_notify(void *data, enum qcom_rproc_event event) +static int ipa_modem_notify(struct notifier_block *nb, unsigned long action, + void *data) { - struct ipa *ipa = data; - struct device *dev; + struct ipa *ipa = container_of(nb, struct ipa, nb); + struct qcom_ssr_notify_data *notify_data = data; + struct device *dev = &ipa->pdev->dev; - dev = &ipa->pdev->dev; - switch (event) { - case MODEM_STARTING: + switch (action) { + case QCOM_SSR_BEFORE_POWERUP: dev_info(dev, "received modem starting event\n"); ipa_smp2p_notify_reset(ipa); break; - case MODEM_RUNNING: + case QCOM_SSR_AFTER_POWERUP: dev_info(dev, "received modem running event\n"); break; - case MODEM_STOPPING: - case MODEM_CRASHED: + case QCOM_SSR_BEFORE_SHUTDOWN: dev_info(dev, "received modem %s event\n", - event == MODEM_STOPPING ? "stopping" - : "crashed"); + notify_data->crashed ? "crashed" : "stopping"); if (ipa->setup_complete) ipa_modem_crashed(ipa); break; - case MODEM_OFFLINE: + case QCOM_SSR_AFTER_SHUTDOWN: dev_info(dev, "received modem offline event\n"); break; - case MODEM_REMOVING: - dev_info(dev, "received modem stopping event\n"); - break; - default: - dev_err(&ipa->pdev->dev, "unrecognized event %u\n", event); + dev_err(dev, "received unrecognized event %lu\n", action); break; } + + return NOTIFY_OK; } int ipa_modem_init(struct ipa *ipa, bool modem_init) @@ -362,13 +359,30 @@ void ipa_modem_exit(struct ipa *ipa) int ipa_modem_config(struct ipa *ipa) { - return qcom_register_ipa_notify(ipa->modem_rproc, ipa_modem_notify, - ipa); + void *notifier; + + ipa->nb.notifier_call = ipa_modem_notify; + + notifier = qcom_register_ssr_notifier("mpss", &ipa->nb); + if (IS_ERR(notifier)) + return PTR_ERR(notifier); + + ipa->notifier = notifier; + + return 0; } void ipa_modem_deconfig(struct ipa *ipa) { - qcom_deregister_ipa_notify(ipa->modem_rproc); + struct device *dev = &ipa->pdev->dev; + int ret; + + ret = qcom_unregister_ssr_notifier(ipa->notifier, &ipa->nb); + if (ret) + dev_err(dev, "error %d unregistering notifier", ret); + + ipa->notifier = NULL; + memset(&ipa->nb, 0, sizeof(ipa->nb)); } int ipa_modem_setup(struct ipa *ipa) From 2f3ee5e481ce850b5b51a306b01a5e9187b206ae Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 24 Jul 2020 13:11:42 -0500 Subject: [PATCH 199/291] remoteproc: kill IPA notify code The IPA code now uses the generic remoteproc SSR notification mechanism. This makes the original IPA notification code unused and unnecessary, so get rid of it. This is effectively a revert of commit d7f5f3c89c1a ("remoteproc: add IPA notification to q6v5 driver"). Reviewed-by: Bjorn Andersson Signed-off-by: Alex Elder Link: https://lore.kernel.org/r/20200724181142.13581-3-elder@linaro.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/Kconfig | 4 - drivers/remoteproc/Makefile | 1 - drivers/remoteproc/qcom_q6v5_ipa_notify.c | 85 ------------------- drivers/remoteproc/qcom_q6v5_mss.c | 38 --------- .../linux/remoteproc/qcom_q6v5_ipa_notify.h | 82 ------------------ 5 files changed, 210 deletions(-) delete mode 100644 drivers/remoteproc/qcom_q6v5_ipa_notify.c delete mode 100644 include/linux/remoteproc/qcom_q6v5_ipa_notify.h diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index 3e70d972a186..48315dc4a30c 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -154,7 +154,6 @@ config QCOM_Q6V5_MSS select QCOM_MDT_LOADER select QCOM_PIL_INFO select QCOM_Q6V5_COMMON - select QCOM_Q6V5_IPA_NOTIFY select QCOM_RPROC_COMMON select QCOM_SCM help @@ -196,9 +195,6 @@ config QCOM_Q6V5_WCSS Say y here to support the Qualcomm Peripheral Image Loader for the Hexagon V5 based WCSS remote processors. -config QCOM_Q6V5_IPA_NOTIFY - tristate - config QCOM_SYSMON tristate "Qualcomm sysmon driver" depends on RPMSG diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile index 7ce1b8ef7677..4d4307dc8fa9 100644 --- a/drivers/remoteproc/Makefile +++ b/drivers/remoteproc/Makefile @@ -24,7 +24,6 @@ obj-$(CONFIG_QCOM_Q6V5_ADSP) += qcom_q6v5_adsp.o obj-$(CONFIG_QCOM_Q6V5_MSS) += qcom_q6v5_mss.o obj-$(CONFIG_QCOM_Q6V5_PAS) += qcom_q6v5_pas.o obj-$(CONFIG_QCOM_Q6V5_WCSS) += qcom_q6v5_wcss.o -obj-$(CONFIG_QCOM_Q6V5_IPA_NOTIFY) += qcom_q6v5_ipa_notify.o obj-$(CONFIG_QCOM_SYSMON) += qcom_sysmon.o obj-$(CONFIG_QCOM_WCNSS_PIL) += qcom_wcnss_pil.o qcom_wcnss_pil-y += qcom_wcnss.o diff --git a/drivers/remoteproc/qcom_q6v5_ipa_notify.c b/drivers/remoteproc/qcom_q6v5_ipa_notify.c deleted file mode 100644 index e1c10a128bfd..000000000000 --- a/drivers/remoteproc/qcom_q6v5_ipa_notify.c +++ /dev/null @@ -1,85 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -/* - * Qualcomm IPA notification subdev support - * - * Copyright (C) 2019 Linaro Ltd. - */ - -#include -#include -#include -#include - -static void -ipa_notify_common(struct rproc_subdev *subdev, enum qcom_rproc_event event) -{ - struct qcom_rproc_ipa_notify *ipa_notify; - qcom_ipa_notify_t notify; - - ipa_notify = container_of(subdev, struct qcom_rproc_ipa_notify, subdev); - notify = ipa_notify->notify; - if (notify) - notify(ipa_notify->data, event); -} - -static int ipa_notify_prepare(struct rproc_subdev *subdev) -{ - ipa_notify_common(subdev, MODEM_STARTING); - - return 0; -} - -static int ipa_notify_start(struct rproc_subdev *subdev) -{ - ipa_notify_common(subdev, MODEM_RUNNING); - - return 0; -} - -static void ipa_notify_stop(struct rproc_subdev *subdev, bool crashed) - -{ - ipa_notify_common(subdev, crashed ? MODEM_CRASHED : MODEM_STOPPING); -} - -static void ipa_notify_unprepare(struct rproc_subdev *subdev) -{ - ipa_notify_common(subdev, MODEM_OFFLINE); -} - -static void ipa_notify_removing(struct rproc_subdev *subdev) -{ - ipa_notify_common(subdev, MODEM_REMOVING); -} - -/* Register the IPA notification subdevice with the Q6V5 MSS remoteproc */ -void qcom_add_ipa_notify_subdev(struct rproc *rproc, - struct qcom_rproc_ipa_notify *ipa_notify) -{ - ipa_notify->notify = NULL; - ipa_notify->data = NULL; - ipa_notify->subdev.prepare = ipa_notify_prepare; - ipa_notify->subdev.start = ipa_notify_start; - ipa_notify->subdev.stop = ipa_notify_stop; - ipa_notify->subdev.unprepare = ipa_notify_unprepare; - - rproc_add_subdev(rproc, &ipa_notify->subdev); -} -EXPORT_SYMBOL_GPL(qcom_add_ipa_notify_subdev); - -/* Remove the IPA notification subdevice */ -void qcom_remove_ipa_notify_subdev(struct rproc *rproc, - struct qcom_rproc_ipa_notify *ipa_notify) -{ - struct rproc_subdev *subdev = &ipa_notify->subdev; - - ipa_notify_removing(subdev); - - rproc_remove_subdev(rproc, subdev); - ipa_notify->notify = NULL; /* Make it obvious */ -} -EXPORT_SYMBOL_GPL(qcom_remove_ipa_notify_subdev); - -MODULE_LICENSE("GPL v2"); -MODULE_DESCRIPTION("Qualcomm IPA notification remoteproc subdev"); diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index ae3739082fdd..68f158931010 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -23,7 +23,6 @@ #include #include #include -#include "linux/remoteproc/qcom_q6v5_ipa_notify.h" #include #include #include @@ -197,7 +196,6 @@ struct q6v5 { struct qcom_rproc_glink glink_subdev; struct qcom_rproc_subdev smd_subdev; struct qcom_rproc_ssr ssr_subdev; - struct qcom_rproc_ipa_notify ipa_notify_subdev; struct qcom_sysmon *sysmon; bool need_mem_protection; bool has_alt_reset; @@ -1607,39 +1605,6 @@ static int q6v5_alloc_memory_region(struct q6v5 *qproc) return 0; } -#if IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) - -/* Register IPA notification function */ -int qcom_register_ipa_notify(struct rproc *rproc, qcom_ipa_notify_t notify, - void *data) -{ - struct qcom_rproc_ipa_notify *ipa_notify; - struct q6v5 *qproc = rproc->priv; - - if (!notify) - return -EINVAL; - - ipa_notify = &qproc->ipa_notify_subdev; - if (ipa_notify->notify) - return -EBUSY; - - ipa_notify->notify = notify; - ipa_notify->data = data; - - return 0; -} -EXPORT_SYMBOL_GPL(qcom_register_ipa_notify); - -/* Deregister IPA notification function */ -void qcom_deregister_ipa_notify(struct rproc *rproc) -{ - struct q6v5 *qproc = rproc->priv; - - qproc->ipa_notify_subdev.notify = NULL; -} -EXPORT_SYMBOL_GPL(qcom_deregister_ipa_notify); -#endif /* !IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) */ - static int q6v5_probe(struct platform_device *pdev) { const struct rproc_hexagon_res *desc; @@ -1766,7 +1731,6 @@ static int q6v5_probe(struct platform_device *pdev) qcom_add_glink_subdev(rproc, &qproc->glink_subdev, "mpss"); qcom_add_smd_subdev(rproc, &qproc->smd_subdev); qcom_add_ssr_subdev(rproc, &qproc->ssr_subdev, "mpss"); - qcom_add_ipa_notify_subdev(rproc, &qproc->ipa_notify_subdev); qproc->sysmon = qcom_add_sysmon_subdev(rproc, "modem", 0x12); if (IS_ERR(qproc->sysmon)) { ret = PTR_ERR(qproc->sysmon); @@ -1782,7 +1746,6 @@ static int q6v5_probe(struct platform_device *pdev) remove_sysmon_subdev: qcom_remove_sysmon_subdev(qproc->sysmon); remove_subdevs: - qcom_remove_ipa_notify_subdev(qproc->rproc, &qproc->ipa_notify_subdev); qcom_remove_ssr_subdev(rproc, &qproc->ssr_subdev); qcom_remove_smd_subdev(rproc, &qproc->smd_subdev); qcom_remove_glink_subdev(rproc, &qproc->glink_subdev); @@ -1804,7 +1767,6 @@ static int q6v5_remove(struct platform_device *pdev) rproc_del(rproc); qcom_remove_sysmon_subdev(qproc->sysmon); - qcom_remove_ipa_notify_subdev(rproc, &qproc->ipa_notify_subdev); qcom_remove_ssr_subdev(rproc, &qproc->ssr_subdev); qcom_remove_smd_subdev(rproc, &qproc->smd_subdev); qcom_remove_glink_subdev(rproc, &qproc->glink_subdev); diff --git a/include/linux/remoteproc/qcom_q6v5_ipa_notify.h b/include/linux/remoteproc/qcom_q6v5_ipa_notify.h deleted file mode 100644 index 0820edc0ab7d..000000000000 --- a/include/linux/remoteproc/qcom_q6v5_ipa_notify.h +++ /dev/null @@ -1,82 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Copyright (C) 2019 Linaro Ltd. */ - -#ifndef __QCOM_Q6V5_IPA_NOTIFY_H__ -#define __QCOM_Q6V5_IPA_NOTIFY_H__ - -#if IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) - -#include - -enum qcom_rproc_event { - MODEM_STARTING = 0, /* Modem is about to be started */ - MODEM_RUNNING = 1, /* Startup complete; modem is operational */ - MODEM_STOPPING = 2, /* Modem is about to shut down */ - MODEM_CRASHED = 3, /* Modem has crashed (implies stopping) */ - MODEM_OFFLINE = 4, /* Modem is now offline */ - MODEM_REMOVING = 5, /* Modem is about to be removed */ -}; - -typedef void (*qcom_ipa_notify_t)(void *data, enum qcom_rproc_event event); - -struct qcom_rproc_ipa_notify { - struct rproc_subdev subdev; - - qcom_ipa_notify_t notify; - void *data; -}; - -/** - * qcom_add_ipa_notify_subdev() - Register IPA notification subdevice - * @rproc: rproc handle - * @ipa_notify: IPA notification subdevice handle - * - * Register the @ipa_notify subdevice with the @rproc so modem events - * can be sent to IPA when they occur. - * - * This is defined in "qcom_q6v5_ipa_notify.c". - */ -void qcom_add_ipa_notify_subdev(struct rproc *rproc, - struct qcom_rproc_ipa_notify *ipa_notify); - -/** - * qcom_remove_ipa_notify_subdev() - Remove IPA SSR subdevice - * @rproc: rproc handle - * @ipa_notify: IPA notification subdevice handle - * - * This is defined in "qcom_q6v5_ipa_notify.c". - */ -void qcom_remove_ipa_notify_subdev(struct rproc *rproc, - struct qcom_rproc_ipa_notify *ipa_notify); - -/** - * qcom_register_ipa_notify() - Register IPA notification function - * @rproc: Remote processor handle - * @notify: Non-null IPA notification callback function pointer - * @data: Data supplied to IPA notification callback function - * - * @Return: 0 if successful, or a negative error code otherwise - * - * This is defined in "qcom_q6v5_mss.c". - */ -int qcom_register_ipa_notify(struct rproc *rproc, qcom_ipa_notify_t notify, - void *data); -/** - * qcom_deregister_ipa_notify() - Deregister IPA notification function - * @rproc: Remote processor handle - * - * This is defined in "qcom_q6v5_mss.c". - */ -void qcom_deregister_ipa_notify(struct rproc *rproc); - -#else /* !IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) */ - -struct qcom_rproc_ipa_notify { /* empty */ }; - -#define qcom_add_ipa_notify_subdev(rproc, ipa_notify) /* no-op */ -#define qcom_remove_ipa_notify_subdev(rproc, ipa_notify) /* no-op */ - -#endif /* !IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) */ - -#endif /* !__QCOM_Q6V5_IPA_NOTIFY_H__ */ From 48001ea50d17f3eb06a552e9ecf21f7fc01b25da Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:08:18 -0700 Subject: [PATCH 200/291] PM, libnvdimm: Add runtime firmware activation support Abstract platform specific mechanics for nvdimm firmware activation behind a handful of generic ops. At the bus level ->activate_state() indicates the unified state (idle, busy, armed) of all DIMMs on the bus, and ->capability() indicates the system state expectations for activate. At the DIMM level ->activate_state() indicates the per-DIMM state, ->activate_result() indicates the outcome of the last activation attempt, and ->arm() attempts to transition the DIMM from 'idle' to 'armed'. A new hibernate_quiet_exec() facility is added to support firmware activation in an OS defined system quiesce state. It leverages the fact that the hibernate-freeze state wants to assert that a memory hibernation snapshot can be taken. This is in contrast to a platform firmware defined quiesce state that may forcefully quiet the memory controller independent of whether an individual device-driver properly supports hibernate-freeze. The libnvdimm sysfs interface is extended to support detection of a firmware activate capability. The mechanism supports enumeration and triggering of firmware activate, optionally in the hibernate_quiet_exec() context. [rafael: hibernate_quiet_exec() proposal] [vishal: fix up sparse warning, grammar in Documentation/] Cc: Pavel Machek Cc: Ira Weiny Cc: Len Brown Cc: Jonathan Corbet Cc: Dave Jiang Cc: Vishal Verma Reported-by: kernel test robot Co-developed-by: "Rafael J. Wysocki" Signed-off-by: "Rafael J. Wysocki" Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- Documentation/ABI/testing/sysfs-bus-nvdimm | 2 + .../driver-api/nvdimm/firmware-activate.rst | 86 ++++++++++ drivers/nvdimm/core.c | 149 ++++++++++++++++++ drivers/nvdimm/dimm_devs.c | 115 ++++++++++++++ drivers/nvdimm/nd-core.h | 1 + include/linux/libnvdimm.h | 44 ++++++ include/linux/suspend.h | 6 + kernel/power/hibernate.c | 97 ++++++++++++ 8 files changed, 500 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-bus-nvdimm create mode 100644 Documentation/driver-api/nvdimm/firmware-activate.rst diff --git a/Documentation/ABI/testing/sysfs-bus-nvdimm b/Documentation/ABI/testing/sysfs-bus-nvdimm new file mode 100644 index 000000000000..d64380262be8 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-nvdimm @@ -0,0 +1,2 @@ +The libnvdimm sub-system implements a common sysfs interface for +platform nvdimm resources. See Documentation/driver-api/nvdimm/. diff --git a/Documentation/driver-api/nvdimm/firmware-activate.rst b/Documentation/driver-api/nvdimm/firmware-activate.rst new file mode 100644 index 000000000000..7ee7decbbdc3 --- /dev/null +++ b/Documentation/driver-api/nvdimm/firmware-activate.rst @@ -0,0 +1,86 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================== +NVDIMM Runtime Firmware Activation +================================== + +Some persistent memory devices run a firmware locally on the device / +"DIMM" to perform tasks like media management, capacity provisioning, +and health monitoring. The process of updating that firmware typically +involves a reboot because it has implications for in-flight memory +transactions. However, reboots are disruptive and at least the Intel +persistent memory platform implementation, described by the Intel ACPI +DSM specification [1], has added support for activating firmware at +runtime. + +A native sysfs interface is implemented in libnvdimm to allow platform +to advertise and control their local runtime firmware activation +capability. + +The libnvdimm bus object, ndbusX, implements an ndbusX/firmware/activate +attribute that shows the state of the firmware activation as one of 'idle', +'armed', 'overflow', and 'busy'. + +- idle: + No devices are set / armed to activate firmware + +- armed: + At least one device is armed + +- busy: + In the busy state armed devices are in the process of transitioning + back to idle and completing an activation cycle. + +- overflow: + If the platform has a concept of incremental work needed to perform + the activation it could be the case that too many DIMMs are armed for + activation. In that scenario the potential for firmware activation to + timeout is indicated by the 'overflow' state. + +The 'ndbusX/firmware/activate' property can be written with a value of +either 'live', or 'quiesce'. A value of 'quiesce' triggers the kernel to +run firmware activation from within the equivalent of the hibernation +'freeze' state where drivers and applications are notified to stop their +modifications of system memory. A value of 'live' attempts +firmware activation without this hibernation cycle. The +'ndbusX/firmware/activate' property will be elided completely if no +firmware activation capability is detected. + +Another property 'ndbusX/firmware/capability' indicates a value of +'live' or 'quiesce', where 'live' indicates that the firmware +does not require or inflict any quiesce period on the system to update +firmware. A capability value of 'quiesce' indicates that firmware does +expect and injects a quiet period for the memory controller, but 'live' +may still be written to 'ndbusX/firmware/activate' as an override to +assume the risk of racing firmware update with in-flight device and +application activity. The 'ndbusX/firmware/capability' property will be +elided completely if no firmware activation capability is detected. + +The libnvdimm memory-device / DIMM object, nmemX, implements +'nmemX/firmware/activate' and 'nmemX/firmware/result' attributes to +communicate the per-device firmware activation state. Similar to the +'ndbusX/firmware/activate' attribute, the 'nmemX/firmware/activate' +attribute indicates 'idle', 'armed', or 'busy'. The state transitions +from 'armed' to 'idle' when the system is prepared to activate firmware, +firmware staged + state set to armed, and 'ndbusX/firmware/activate' is +triggered. After that activation event the nmemX/firmware/result +attribute reflects the state of the last activation as one of: + +- none: + No runtime activation triggered since the last time the device was reset + +- success: + The last runtime activation completed successfully. + +- fail: + The last runtime activation failed for device-specific reasons. + +- not_staged: + The last runtime activation failed due to a sequencing error of the + firmware image not being staged. + +- need_reset: + Runtime firmware activation failed, but the firmware can still be + activated via the legacy method of power-cycling the system. + +[1]: https://docs.pmem.io/persistent-memory/ diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index fe9bd6febdd2..c21ba0602029 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -4,6 +4,7 @@ */ #include #include +#include #include #include #include @@ -389,8 +390,156 @@ static const struct attribute_group nvdimm_bus_attribute_group = { .attrs = nvdimm_bus_attributes, }; +static ssize_t capability_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); + struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; + enum nvdimm_fwa_capability cap; + + if (!nd_desc->fw_ops) + return -EOPNOTSUPP; + + nvdimm_bus_lock(dev); + cap = nd_desc->fw_ops->capability(nd_desc); + nvdimm_bus_unlock(dev); + + switch (cap) { + case NVDIMM_FWA_CAP_QUIESCE: + return sprintf(buf, "quiesce\n"); + case NVDIMM_FWA_CAP_LIVE: + return sprintf(buf, "live\n"); + default: + return -EOPNOTSUPP; + } +} + +static DEVICE_ATTR_RO(capability); + +static ssize_t activate_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); + struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; + enum nvdimm_fwa_capability cap; + enum nvdimm_fwa_state state; + + if (!nd_desc->fw_ops) + return -EOPNOTSUPP; + + nvdimm_bus_lock(dev); + cap = nd_desc->fw_ops->capability(nd_desc); + state = nd_desc->fw_ops->activate_state(nd_desc); + nvdimm_bus_unlock(dev); + + if (cap < NVDIMM_FWA_CAP_QUIESCE) + return -EOPNOTSUPP; + + switch (state) { + case NVDIMM_FWA_IDLE: + return sprintf(buf, "idle\n"); + case NVDIMM_FWA_BUSY: + return sprintf(buf, "busy\n"); + case NVDIMM_FWA_ARMED: + return sprintf(buf, "armed\n"); + case NVDIMM_FWA_ARM_OVERFLOW: + return sprintf(buf, "overflow\n"); + default: + return -ENXIO; + } +} + +static int exec_firmware_activate(void *data) +{ + struct nvdimm_bus_descriptor *nd_desc = data; + + return nd_desc->fw_ops->activate(nd_desc); +} + +static ssize_t activate_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); + struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; + enum nvdimm_fwa_state state; + bool quiesce; + ssize_t rc; + + if (!nd_desc->fw_ops) + return -EOPNOTSUPP; + + if (sysfs_streq(buf, "live")) + quiesce = false; + else if (sysfs_streq(buf, "quiesce")) + quiesce = true; + else + return -EINVAL; + + nvdimm_bus_lock(dev); + state = nd_desc->fw_ops->activate_state(nd_desc); + + switch (state) { + case NVDIMM_FWA_BUSY: + rc = -EBUSY; + break; + case NVDIMM_FWA_ARMED: + case NVDIMM_FWA_ARM_OVERFLOW: + if (quiesce) + rc = hibernate_quiet_exec(exec_firmware_activate, nd_desc); + else + rc = nd_desc->fw_ops->activate(nd_desc); + break; + case NVDIMM_FWA_IDLE: + default: + rc = -ENXIO; + } + nvdimm_bus_unlock(dev); + + if (rc == 0) + rc = len; + return rc; +} + +static DEVICE_ATTR_ADMIN_RW(activate); + +static umode_t nvdimm_bus_firmware_visible(struct kobject *kobj, struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, typeof(*dev), kobj); + struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); + struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; + enum nvdimm_fwa_capability cap; + + /* + * Both 'activate' and 'capability' disappear when no ops + * detected, or a negative capability is indicated. + */ + if (!nd_desc->fw_ops) + return 0; + + nvdimm_bus_lock(dev); + cap = nd_desc->fw_ops->capability(nd_desc); + nvdimm_bus_unlock(dev); + + if (cap < NVDIMM_FWA_CAP_QUIESCE) + return 0; + + return a->mode; +} +static struct attribute *nvdimm_bus_firmware_attributes[] = { + &dev_attr_activate.attr, + &dev_attr_capability.attr, + NULL, +}; + +static const struct attribute_group nvdimm_bus_firmware_attribute_group = { + .name = "firmware", + .attrs = nvdimm_bus_firmware_attributes, + .is_visible = nvdimm_bus_firmware_visible, +}; + const struct attribute_group *nvdimm_bus_attribute_groups[] = { &nvdimm_bus_attribute_group, + &nvdimm_bus_firmware_attribute_group, NULL, }; diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index b7b77e8d9027..85b53a7f44f2 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -446,9 +446,124 @@ static const struct attribute_group nvdimm_attribute_group = { .is_visible = nvdimm_visible, }; +static ssize_t result_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct nvdimm *nvdimm = to_nvdimm(dev); + enum nvdimm_fwa_result result; + + if (!nvdimm->fw_ops) + return -EOPNOTSUPP; + + nvdimm_bus_lock(dev); + result = nvdimm->fw_ops->activate_result(nvdimm); + nvdimm_bus_unlock(dev); + + switch (result) { + case NVDIMM_FWA_RESULT_NONE: + return sprintf(buf, "none\n"); + case NVDIMM_FWA_RESULT_SUCCESS: + return sprintf(buf, "success\n"); + case NVDIMM_FWA_RESULT_FAIL: + return sprintf(buf, "fail\n"); + case NVDIMM_FWA_RESULT_NOTSTAGED: + return sprintf(buf, "not_staged\n"); + case NVDIMM_FWA_RESULT_NEEDRESET: + return sprintf(buf, "need_reset\n"); + default: + return -ENXIO; + } +} +static DEVICE_ATTR_ADMIN_RO(result); + +static ssize_t activate_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct nvdimm *nvdimm = to_nvdimm(dev); + enum nvdimm_fwa_state state; + + if (!nvdimm->fw_ops) + return -EOPNOTSUPP; + + nvdimm_bus_lock(dev); + state = nvdimm->fw_ops->activate_state(nvdimm); + nvdimm_bus_unlock(dev); + + switch (state) { + case NVDIMM_FWA_IDLE: + return sprintf(buf, "idle\n"); + case NVDIMM_FWA_BUSY: + return sprintf(buf, "busy\n"); + case NVDIMM_FWA_ARMED: + return sprintf(buf, "armed\n"); + default: + return -ENXIO; + } +} + +static ssize_t activate_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + struct nvdimm *nvdimm = to_nvdimm(dev); + enum nvdimm_fwa_trigger arg; + int rc; + + if (!nvdimm->fw_ops) + return -EOPNOTSUPP; + + if (sysfs_streq(buf, "arm")) + arg = NVDIMM_FWA_ARM; + else if (sysfs_streq(buf, "disarm")) + arg = NVDIMM_FWA_DISARM; + else + return -EINVAL; + + nvdimm_bus_lock(dev); + rc = nvdimm->fw_ops->arm(nvdimm, arg); + nvdimm_bus_unlock(dev); + + if (rc < 0) + return rc; + return len; +} +static DEVICE_ATTR_ADMIN_RW(activate); + +static struct attribute *nvdimm_firmware_attributes[] = { + &dev_attr_activate.attr, + &dev_attr_result.attr, +}; + +static umode_t nvdimm_firmware_visible(struct kobject *kobj, struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, typeof(*dev), kobj); + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); + struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; + struct nvdimm *nvdimm = to_nvdimm(dev); + enum nvdimm_fwa_capability cap; + + if (!nd_desc->fw_ops) + return 0; + if (!nvdimm->fw_ops) + return 0; + + nvdimm_bus_lock(dev); + cap = nd_desc->fw_ops->capability(nd_desc); + nvdimm_bus_unlock(dev); + + if (cap < NVDIMM_FWA_CAP_QUIESCE) + return 0; + + return a->mode; +} + +static const struct attribute_group nvdimm_firmware_attribute_group = { + .name = "firmware", + .attrs = nvdimm_firmware_attributes, + .is_visible = nvdimm_firmware_visible, +}; + static const struct attribute_group *nvdimm_attribute_groups[] = { &nd_device_attribute_group, &nvdimm_attribute_group, + &nvdimm_firmware_attribute_group, NULL, }; diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index ddb9d97d9129..564faa36a3ca 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -45,6 +45,7 @@ struct nvdimm { struct kernfs_node *overwrite_state; } sec; struct delayed_work dwork; + const struct nvdimm_fw_ops *fw_ops; }; static inline unsigned long nvdimm_security_flags( diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index ad9898ece7d3..15dbcb718316 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -86,6 +86,7 @@ struct nvdimm_bus_descriptor { int (*flush_probe)(struct nvdimm_bus_descriptor *nd_desc); int (*clear_to_send)(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, unsigned int cmd, void *data); + const struct nvdimm_bus_fw_ops *fw_ops; }; struct nd_cmd_desc { @@ -200,6 +201,49 @@ struct nvdimm_security_ops { int (*query_overwrite)(struct nvdimm *nvdimm); }; +enum nvdimm_fwa_state { + NVDIMM_FWA_INVALID, + NVDIMM_FWA_IDLE, + NVDIMM_FWA_ARMED, + NVDIMM_FWA_BUSY, + NVDIMM_FWA_ARM_OVERFLOW, +}; + +enum nvdimm_fwa_trigger { + NVDIMM_FWA_ARM, + NVDIMM_FWA_DISARM, +}; + +enum nvdimm_fwa_capability { + NVDIMM_FWA_CAP_INVALID, + NVDIMM_FWA_CAP_NONE, + NVDIMM_FWA_CAP_QUIESCE, + NVDIMM_FWA_CAP_LIVE, +}; + +enum nvdimm_fwa_result { + NVDIMM_FWA_RESULT_INVALID, + NVDIMM_FWA_RESULT_NONE, + NVDIMM_FWA_RESULT_SUCCESS, + NVDIMM_FWA_RESULT_NOTSTAGED, + NVDIMM_FWA_RESULT_NEEDRESET, + NVDIMM_FWA_RESULT_FAIL, +}; + +struct nvdimm_bus_fw_ops { + enum nvdimm_fwa_state (*activate_state) + (struct nvdimm_bus_descriptor *nd_desc); + enum nvdimm_fwa_capability (*capability) + (struct nvdimm_bus_descriptor *nd_desc); + int (*activate)(struct nvdimm_bus_descriptor *nd_desc); +}; + +struct nvdimm_fw_ops { + enum nvdimm_fwa_state (*activate_state)(struct nvdimm *nvdimm); + enum nvdimm_fwa_result (*activate_result)(struct nvdimm *nvdimm); + int (*arm)(struct nvdimm *nvdimm, enum nvdimm_fwa_trigger arg); +}; + void badrange_init(struct badrange *badrange); int badrange_add(struct badrange *badrange, u64 addr, u64 length); void badrange_forget(struct badrange *badrange, phys_addr_t start, diff --git a/include/linux/suspend.h b/include/linux/suspend.h index b960098acfb0..cb9afad82a90 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -453,6 +453,8 @@ extern bool hibernation_available(void); asmlinkage int swsusp_save(void); extern struct pbe *restore_pblist; int pfn_is_nosave(unsigned long pfn); + +int hibernate_quiet_exec(int (*func)(void *data), void *data); #else /* CONFIG_HIBERNATION */ static inline void register_nosave_region(unsigned long b, unsigned long e) {} static inline void register_nosave_region_late(unsigned long b, unsigned long e) {} @@ -464,6 +466,10 @@ static inline void hibernation_set_ops(const struct platform_hibernation_ops *op static inline int hibernate(void) { return -ENOSYS; } static inline bool system_entering_hibernation(void) { return false; } static inline bool hibernation_available(void) { return false; } + +static inline int hibernate_quiet_exec(int (*func)(void *data), void *data) { + return -ENOTSUPP; +} #endif /* CONFIG_HIBERNATION */ #ifdef CONFIG_HIBERNATION_SNAPSHOT_DEV diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 02ec716a4927..e6fab3f09c98 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -795,6 +795,103 @@ int hibernate(void) return error; } +/** + * hibernate_quiet_exec - Execute a function with all devices frozen. + * @func: Function to execute. + * @data: Data pointer to pass to @func. + * + * Return the @func return value or an error code if it cannot be executed. + */ +int hibernate_quiet_exec(int (*func)(void *data), void *data) +{ + int error, nr_calls = 0; + + lock_system_sleep(); + + if (!hibernate_acquire()) { + error = -EBUSY; + goto unlock; + } + + pm_prepare_console(); + + error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls); + if (error) { + nr_calls--; + goto exit; + } + + error = freeze_processes(); + if (error) + goto exit; + + lock_device_hotplug(); + + pm_suspend_clear_flags(); + + error = platform_begin(true); + if (error) + goto thaw; + + error = freeze_kernel_threads(); + if (error) + goto thaw; + + error = dpm_prepare(PMSG_FREEZE); + if (error) + goto dpm_complete; + + suspend_console(); + + error = dpm_suspend(PMSG_FREEZE); + if (error) + goto dpm_resume; + + error = dpm_suspend_end(PMSG_FREEZE); + if (error) + goto dpm_resume; + + error = platform_pre_snapshot(true); + if (error) + goto skip; + + error = func(data); + +skip: + platform_finish(true); + + dpm_resume_start(PMSG_THAW); + +dpm_resume: + dpm_resume(PMSG_THAW); + + resume_console(); + +dpm_complete: + dpm_complete(PMSG_THAW); + + thaw_kernel_threads(); + +thaw: + platform_end(true); + + unlock_device_hotplug(); + + thaw_processes(); + +exit: + __pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL); + + pm_restore_console(); + + hibernate_release(); + +unlock: + unlock_system_sleep(); + + return error; +} +EXPORT_SYMBOL_GPL(hibernate_quiet_exec); /** * software_resume - Resume from a saved hibernation image. From a1facc1fffc17a65e2c12a8de7434b9325ec0324 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:08:24 -0700 Subject: [PATCH 201/291] ACPI: NFIT: Add runtime firmware activate support Plumb the platform specific backend for the generic libnvdimm firmware activate interface. Register dimm level operations to arm/disarm activation, and register bus level operations to report the dynamic platform-quiesce time relative to the number of dimms armed for firmware activation. A new nfit-specific bus attribute "firmware_activate_noidle" is added to allow the activation to switch between platform enforced, and OS opportunistic device quiesce. In other words, let the hibernate cycle handle in-flight device-dma rather than the platform attempting to increase PCI-E timeouts and the like. Cc: Dave Jiang Cc: Ira Weiny Cc: Vishal Verma Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- Documentation/ABI/testing/sysfs-bus-nfit | 19 ++ drivers/acpi/nfit/core.c | 41 ++- drivers/acpi/nfit/intel.c | 386 +++++++++++++++++++++++ drivers/acpi/nfit/intel.h | 3 + drivers/acpi/nfit/nfit.h | 10 + drivers/nvdimm/dimm_devs.c | 4 +- include/linux/libnvdimm.h | 5 +- 7 files changed, 461 insertions(+), 7 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-bus-nfit b/Documentation/ABI/testing/sysfs-bus-nfit index a1cb44dcb908..e4f76e7eab93 100644 --- a/Documentation/ABI/testing/sysfs-bus-nfit +++ b/Documentation/ABI/testing/sysfs-bus-nfit @@ -202,6 +202,25 @@ Description: functions. See the section named 'NVDIMM Root Device _DSMs' in the ACPI specification. +What: /sys/bus/nd/devices/ndbusX/nfit/firmware_activate_noidle +Date: Apr, 2020 +KernelVersion: v5.8 +Contact: linux-nvdimm@lists.01.org +Description: + (RW) The Intel platform implementation of firmware activate + support exposes an option let the platform force idle devices in + the system over the activation event, or trust that the OS will + do it. The safe default is to let the platform force idle + devices since the kernel is already in a suspend state, and on + the chance that a driver does not properly quiesce bus-mastering + after a suspend callback the platform will handle it. However, + the activation might abort if, for example, platform firmware + determines that the activation time exceeds the max PCI-E + completion timeout. Since the platform does not know whether the + OS is running the activation from a suspend context it aborts, + but if the system owner trusts driver suspend callback to be + sufficient then 'firmware_activation_noidle' can be + enabled to bypass the activation abort. What: /sys/bus/nd/devices/regionX/nfit/range_index Date: Jun, 2015 diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 78cc9e2d2aa3..fb775b967c52 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1392,8 +1392,12 @@ static umode_t nfit_visible(struct kobject *kobj, struct attribute *a, int n) struct device *dev = container_of(kobj, struct device, kobj); struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); - if (a == &dev_attr_scrub.attr && !ars_supported(nvdimm_bus)) - return 0; + if (a == &dev_attr_scrub.attr) + return ars_supported(nvdimm_bus) ? a->mode : 0; + + if (a == &dev_attr_firmware_activate_noidle.attr) + return intel_fwa_supported(nvdimm_bus) ? a->mode : 0; + return a->mode; } @@ -1402,6 +1406,7 @@ static struct attribute *acpi_nfit_attributes[] = { &dev_attr_scrub.attr, &dev_attr_hw_error_scrub.attr, &dev_attr_bus_dsm_mask.attr, + &dev_attr_firmware_activate_noidle.attr, NULL, }; @@ -2019,6 +2024,26 @@ static const struct nvdimm_security_ops *acpi_nfit_get_security_ops(int family) } } +static const struct nvdimm_fw_ops *acpi_nfit_get_fw_ops( + struct nfit_mem *nfit_mem) +{ + unsigned long mask; + struct acpi_nfit_desc *acpi_desc = nfit_mem->acpi_desc; + struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc; + + if (!nd_desc->fw_ops) + return NULL; + + if (nfit_mem->family != NVDIMM_FAMILY_INTEL) + return NULL; + + mask = nfit_mem->dsm_mask & NVDIMM_INTEL_FW_ACTIVATE_CMDMASK; + if (mask != NVDIMM_INTEL_FW_ACTIVATE_CMDMASK) + return NULL; + + return intel_fw_ops; +} + static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) { struct nfit_mem *nfit_mem; @@ -2095,7 +2120,8 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) acpi_nfit_dimm_attribute_groups, flags, cmd_mask, flush ? flush->hint_count : 0, nfit_mem->flush_wpq, &nfit_mem->id[0], - acpi_nfit_get_security_ops(nfit_mem->family)); + acpi_nfit_get_security_ops(nfit_mem->family), + acpi_nfit_get_fw_ops(nfit_mem)); if (!nvdimm) return -ENOMEM; @@ -2170,8 +2196,10 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) if (acpi_desc->bus_cmd_force_en) { nd_desc->cmd_mask = acpi_desc->bus_cmd_force_en; mask = &nd_desc->bus_family_mask; - if (acpi_desc->family_dsm_mask[NVDIMM_BUS_FAMILY_INTEL]) + if (acpi_desc->family_dsm_mask[NVDIMM_BUS_FAMILY_INTEL]) { set_bit(NVDIMM_BUS_FAMILY_INTEL, mask); + nd_desc->fw_ops = intel_bus_fw_ops; + } } adev = to_acpi_dev(acpi_desc); @@ -2202,6 +2230,11 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) for_each_set_bit(i, &dsm_mask, BITS_PER_LONG) if (acpi_check_dsm(adev->handle, guid, 1, 1ULL << i)) set_bit(i, mask); + + if (*mask == dsm_mask) { + set_bit(NVDIMM_BUS_FAMILY_INTEL, &nd_desc->bus_family_mask); + nd_desc->fw_ops = intel_bus_fw_ops; + } } static ssize_t range_index_show(struct device *dev, diff --git a/drivers/acpi/nfit/intel.c b/drivers/acpi/nfit/intel.c index 1113b679cd7b..8dd792a55730 100644 --- a/drivers/acpi/nfit/intel.c +++ b/drivers/acpi/nfit/intel.c @@ -7,6 +7,48 @@ #include "intel.h" #include "nfit.h" +static ssize_t firmware_activate_noidle_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); + struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus); + struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); + + return sprintf(buf, "%s\n", acpi_desc->fwa_noidle ? "Y" : "N"); +} + +static ssize_t firmware_activate_noidle_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t size) +{ + struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); + struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus); + struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); + ssize_t rc; + bool val; + + rc = kstrtobool(buf, &val); + if (rc) + return rc; + if (val != acpi_desc->fwa_noidle) + acpi_desc->fwa_cap = NVDIMM_FWA_CAP_INVALID; + acpi_desc->fwa_noidle = val; + return size; +} +DEVICE_ATTR_RW(firmware_activate_noidle); + +bool intel_fwa_supported(struct nvdimm_bus *nvdimm_bus) +{ + struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus); + struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); + unsigned long *mask; + + if (!test_bit(NVDIMM_BUS_FAMILY_INTEL, &nd_desc->bus_family_mask)) + return false; + + mask = &acpi_desc->family_dsm_mask[NVDIMM_BUS_FAMILY_INTEL]; + return *mask == NVDIMM_BUS_INTEL_FW_ACTIVATE_CMDMASK; +} + static unsigned long intel_security_flags(struct nvdimm *nvdimm, enum nvdimm_passphrase_type ptype) { @@ -389,3 +431,347 @@ static const struct nvdimm_security_ops __intel_security_ops = { }; const struct nvdimm_security_ops *intel_security_ops = &__intel_security_ops; + +static int intel_bus_fwa_businfo(struct nvdimm_bus_descriptor *nd_desc, + struct nd_intel_bus_fw_activate_businfo *info) +{ + struct { + struct nd_cmd_pkg pkg; + struct nd_intel_bus_fw_activate_businfo cmd; + } nd_cmd = { + .pkg = { + .nd_command = NVDIMM_BUS_INTEL_FW_ACTIVATE_BUSINFO, + .nd_family = NVDIMM_BUS_FAMILY_INTEL, + .nd_size_out = + sizeof(struct nd_intel_bus_fw_activate_businfo), + .nd_fw_size = + sizeof(struct nd_intel_bus_fw_activate_businfo), + }, + }; + int rc; + + rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), + NULL); + *info = nd_cmd.cmd; + return rc; +} + +/* The fw_ops expect to be called with the nvdimm_bus_lock() held */ +static enum nvdimm_fwa_state intel_bus_fwa_state( + struct nvdimm_bus_descriptor *nd_desc) +{ + struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); + struct nd_intel_bus_fw_activate_businfo info; + struct device *dev = acpi_desc->dev; + enum nvdimm_fwa_state state; + int rc; + + /* + * It should not be possible for platform firmware to return + * busy because activate is a synchronous operation. Treat it + * similar to invalid, i.e. always refresh / poll the status. + */ + switch (acpi_desc->fwa_state) { + case NVDIMM_FWA_INVALID: + case NVDIMM_FWA_BUSY: + break; + default: + /* check if capability needs to be refreshed */ + if (acpi_desc->fwa_cap == NVDIMM_FWA_CAP_INVALID) + break; + return acpi_desc->fwa_state; + } + + /* Refresh with platform firmware */ + rc = intel_bus_fwa_businfo(nd_desc, &info); + if (rc) + return NVDIMM_FWA_INVALID; + + switch (info.state) { + case ND_INTEL_FWA_IDLE: + state = NVDIMM_FWA_IDLE; + break; + case ND_INTEL_FWA_BUSY: + state = NVDIMM_FWA_BUSY; + break; + case ND_INTEL_FWA_ARMED: + if (info.activate_tmo > info.max_quiesce_tmo) + state = NVDIMM_FWA_ARM_OVERFLOW; + else + state = NVDIMM_FWA_ARMED; + break; + default: + dev_err_once(dev, "invalid firmware activate state %d\n", + info.state); + return NVDIMM_FWA_INVALID; + } + + /* + * Capability data is available in the same payload as state. It + * is expected to be static. + */ + if (acpi_desc->fwa_cap == NVDIMM_FWA_CAP_INVALID) { + if (info.capability & ND_INTEL_BUS_FWA_CAP_FWQUIESCE) + acpi_desc->fwa_cap = NVDIMM_FWA_CAP_QUIESCE; + else if (info.capability & ND_INTEL_BUS_FWA_CAP_OSQUIESCE) { + /* + * Skip hibernate cycle by default if platform + * indicates that it does not need devices to be + * quiesced. + */ + acpi_desc->fwa_cap = NVDIMM_FWA_CAP_LIVE; + } else + acpi_desc->fwa_cap = NVDIMM_FWA_CAP_NONE; + } + + acpi_desc->fwa_state = state; + + return state; +} + +static enum nvdimm_fwa_capability intel_bus_fwa_capability( + struct nvdimm_bus_descriptor *nd_desc) +{ + struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); + + if (acpi_desc->fwa_cap > NVDIMM_FWA_CAP_INVALID) + return acpi_desc->fwa_cap; + + if (intel_bus_fwa_state(nd_desc) > NVDIMM_FWA_INVALID) + return acpi_desc->fwa_cap; + + return NVDIMM_FWA_CAP_INVALID; +} + +static int intel_bus_fwa_activate(struct nvdimm_bus_descriptor *nd_desc) +{ + struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); + struct { + struct nd_cmd_pkg pkg; + struct nd_intel_bus_fw_activate cmd; + } nd_cmd = { + .pkg = { + .nd_command = NVDIMM_BUS_INTEL_FW_ACTIVATE, + .nd_family = NVDIMM_BUS_FAMILY_INTEL, + .nd_size_in = sizeof(nd_cmd.cmd.iodev_state), + .nd_size_out = + sizeof(struct nd_intel_bus_fw_activate), + .nd_fw_size = + sizeof(struct nd_intel_bus_fw_activate), + }, + /* + * Even though activate is run from a suspended context, + * for safety, still ask platform firmware to force + * quiesce devices by default. Let a module + * parameter override that policy. + */ + .cmd = { + .iodev_state = acpi_desc->fwa_noidle + ? ND_INTEL_BUS_FWA_IODEV_OS_IDLE + : ND_INTEL_BUS_FWA_IODEV_FORCE_IDLE, + }, + }; + int rc; + + switch (intel_bus_fwa_state(nd_desc)) { + case NVDIMM_FWA_ARMED: + case NVDIMM_FWA_ARM_OVERFLOW: + break; + default: + return -ENXIO; + } + + rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), + NULL); + + /* + * Whether the command succeeded, or failed, the agent checking + * for the result needs to query the DIMMs individually. + * Increment the activation count to invalidate all the DIMM + * states at once (it's otherwise not possible to take + * acpi_desc->init_mutex in this context) + */ + acpi_desc->fwa_state = NVDIMM_FWA_INVALID; + acpi_desc->fwa_count++; + + dev_dbg(acpi_desc->dev, "result: %d\n", rc); + + return rc; +} + +static const struct nvdimm_bus_fw_ops __intel_bus_fw_ops = { + .activate_state = intel_bus_fwa_state, + .capability = intel_bus_fwa_capability, + .activate = intel_bus_fwa_activate, +}; + +const struct nvdimm_bus_fw_ops *intel_bus_fw_ops = &__intel_bus_fw_ops; + +static int intel_fwa_dimminfo(struct nvdimm *nvdimm, + struct nd_intel_fw_activate_dimminfo *info) +{ + struct { + struct nd_cmd_pkg pkg; + struct nd_intel_fw_activate_dimminfo cmd; + } nd_cmd = { + .pkg = { + .nd_command = NVDIMM_INTEL_FW_ACTIVATE_DIMMINFO, + .nd_family = NVDIMM_FAMILY_INTEL, + .nd_size_out = + sizeof(struct nd_intel_fw_activate_dimminfo), + .nd_fw_size = + sizeof(struct nd_intel_fw_activate_dimminfo), + }, + }; + int rc; + + rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL); + *info = nd_cmd.cmd; + return rc; +} + +static enum nvdimm_fwa_state intel_fwa_state(struct nvdimm *nvdimm) +{ + struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm); + struct acpi_nfit_desc *acpi_desc = nfit_mem->acpi_desc; + struct nd_intel_fw_activate_dimminfo info; + int rc; + + /* + * Similar to the bus state, since activate is synchronous the + * busy state should resolve within the context of 'activate'. + */ + switch (nfit_mem->fwa_state) { + case NVDIMM_FWA_INVALID: + case NVDIMM_FWA_BUSY: + break; + default: + /* If no activations occurred the old state is still valid */ + if (nfit_mem->fwa_count == acpi_desc->fwa_count) + return nfit_mem->fwa_state; + } + + rc = intel_fwa_dimminfo(nvdimm, &info); + if (rc) + return NVDIMM_FWA_INVALID; + + switch (info.state) { + case ND_INTEL_FWA_IDLE: + nfit_mem->fwa_state = NVDIMM_FWA_IDLE; + break; + case ND_INTEL_FWA_BUSY: + nfit_mem->fwa_state = NVDIMM_FWA_BUSY; + break; + case ND_INTEL_FWA_ARMED: + nfit_mem->fwa_state = NVDIMM_FWA_ARMED; + break; + default: + nfit_mem->fwa_state = NVDIMM_FWA_INVALID; + break; + } + + switch (info.result) { + case ND_INTEL_DIMM_FWA_NONE: + nfit_mem->fwa_result = NVDIMM_FWA_RESULT_NONE; + break; + case ND_INTEL_DIMM_FWA_SUCCESS: + nfit_mem->fwa_result = NVDIMM_FWA_RESULT_SUCCESS; + break; + case ND_INTEL_DIMM_FWA_NOTSTAGED: + nfit_mem->fwa_result = NVDIMM_FWA_RESULT_NOTSTAGED; + break; + case ND_INTEL_DIMM_FWA_NEEDRESET: + nfit_mem->fwa_result = NVDIMM_FWA_RESULT_NEEDRESET; + break; + case ND_INTEL_DIMM_FWA_MEDIAFAILED: + case ND_INTEL_DIMM_FWA_ABORT: + case ND_INTEL_DIMM_FWA_NOTSUPP: + case ND_INTEL_DIMM_FWA_ERROR: + default: + nfit_mem->fwa_result = NVDIMM_FWA_RESULT_FAIL; + break; + } + + nfit_mem->fwa_count = acpi_desc->fwa_count; + + return nfit_mem->fwa_state; +} + +static enum nvdimm_fwa_result intel_fwa_result(struct nvdimm *nvdimm) +{ + struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm); + struct acpi_nfit_desc *acpi_desc = nfit_mem->acpi_desc; + + if (nfit_mem->fwa_count == acpi_desc->fwa_count + && nfit_mem->fwa_result > NVDIMM_FWA_RESULT_INVALID) + return nfit_mem->fwa_result; + + if (intel_fwa_state(nvdimm) > NVDIMM_FWA_INVALID) + return nfit_mem->fwa_result; + + return NVDIMM_FWA_RESULT_INVALID; +} + +static int intel_fwa_arm(struct nvdimm *nvdimm, enum nvdimm_fwa_trigger arm) +{ + struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm); + struct acpi_nfit_desc *acpi_desc = nfit_mem->acpi_desc; + struct { + struct nd_cmd_pkg pkg; + struct nd_intel_fw_activate_arm cmd; + } nd_cmd = { + .pkg = { + .nd_command = NVDIMM_INTEL_FW_ACTIVATE_ARM, + .nd_family = NVDIMM_FAMILY_INTEL, + .nd_size_in = sizeof(nd_cmd.cmd.activate_arm), + .nd_size_out = + sizeof(struct nd_intel_fw_activate_arm), + .nd_fw_size = + sizeof(struct nd_intel_fw_activate_arm), + }, + .cmd = { + .activate_arm = arm == NVDIMM_FWA_ARM + ? ND_INTEL_DIMM_FWA_ARM + : ND_INTEL_DIMM_FWA_DISARM, + }, + }; + int rc; + + switch (intel_fwa_state(nvdimm)) { + case NVDIMM_FWA_INVALID: + return -ENXIO; + case NVDIMM_FWA_BUSY: + return -EBUSY; + case NVDIMM_FWA_IDLE: + if (arm == NVDIMM_FWA_DISARM) + return 0; + break; + case NVDIMM_FWA_ARMED: + if (arm == NVDIMM_FWA_ARM) + return 0; + break; + default: + return -ENXIO; + } + + /* + * Invalidate the bus-level state, now that we're committed to + * changing the 'arm' state. + */ + acpi_desc->fwa_state = NVDIMM_FWA_INVALID; + nfit_mem->fwa_state = NVDIMM_FWA_INVALID; + + rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL); + + dev_dbg(acpi_desc->dev, "%s result: %d\n", arm == NVDIMM_FWA_ARM + ? "arm" : "disarm", rc); + return rc; +} + +static const struct nvdimm_fw_ops __intel_fw_ops = { + .activate_state = intel_fwa_state, + .activate_result = intel_fwa_result, + .arm = intel_fwa_arm, +}; + +const struct nvdimm_fw_ops *intel_fw_ops = &__intel_fw_ops; diff --git a/drivers/acpi/nfit/intel.h b/drivers/acpi/nfit/intel.h index 49a598623024..b768234ccebc 100644 --- a/drivers/acpi/nfit/intel.h +++ b/drivers/acpi/nfit/intel.h @@ -169,4 +169,7 @@ struct nd_intel_bus_fw_activate { u8 iodev_state; u32 status; } __packed; + +extern const struct nvdimm_fw_ops *intel_fw_ops; +extern const struct nvdimm_bus_fw_ops *intel_bus_fw_ops; #endif diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 97c122628975..67b7807ed200 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -220,6 +220,9 @@ struct nfit_mem { struct list_head list; struct acpi_device *adev; struct acpi_nfit_desc *acpi_desc; + enum nvdimm_fwa_state fwa_state; + enum nvdimm_fwa_result fwa_result; + int fwa_count; char id[NFIT_DIMM_ID_LEN+1]; struct resource *flush_wpq; unsigned long dsm_mask; @@ -265,6 +268,11 @@ struct acpi_nfit_desc { unsigned int scrub_tmo; int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, void *iobuf, u64 len, int rw); + enum nvdimm_fwa_state fwa_state; + enum nvdimm_fwa_capability fwa_cap; + int fwa_count; + bool fwa_noidle; + bool fwa_nosuspend; }; enum scrub_mode { @@ -367,4 +375,6 @@ void __acpi_nvdimm_notify(struct device *dev, u32 event); int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc); void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev); +bool intel_fwa_supported(struct nvdimm_bus *nvdimm_bus); +extern struct device_attribute dev_attr_firmware_activate_noidle; #endif /* __NFIT_H__ */ diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 85b53a7f44f2..2f0815e15986 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -582,7 +582,8 @@ struct nvdimm *__nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data, const struct attribute_group **groups, unsigned long flags, unsigned long cmd_mask, int num_flush, struct resource *flush_wpq, const char *dimm_id, - const struct nvdimm_security_ops *sec_ops) + const struct nvdimm_security_ops *sec_ops, + const struct nvdimm_fw_ops *fw_ops) { struct nvdimm *nvdimm = kzalloc(sizeof(*nvdimm), GFP_KERNEL); struct device *dev; @@ -612,6 +613,7 @@ struct nvdimm *__nvdimm_create(struct nvdimm_bus *nvdimm_bus, dev->devt = MKDEV(nvdimm_major, nvdimm->id); dev->groups = groups; nvdimm->sec.ops = sec_ops; + nvdimm->fw_ops = fw_ops; nvdimm->sec.overwrite_tmo = 0; INIT_DELAYED_WORK(&nvdimm->dwork, nvdimm_security_overwrite_query); /* diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 15dbcb718316..01f251b6e36c 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -269,14 +269,15 @@ struct nvdimm *__nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data, const struct attribute_group **groups, unsigned long flags, unsigned long cmd_mask, int num_flush, struct resource *flush_wpq, const char *dimm_id, - const struct nvdimm_security_ops *sec_ops); + const struct nvdimm_security_ops *sec_ops, + const struct nvdimm_fw_ops *fw_ops); static inline struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data, const struct attribute_group **groups, unsigned long flags, unsigned long cmd_mask, int num_flush, struct resource *flush_wpq) { return __nvdimm_create(nvdimm_bus, provider_data, groups, flags, - cmd_mask, num_flush, flush_wpq, NULL, NULL); + cmd_mask, num_flush, flush_wpq, NULL, NULL, NULL); } const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd); From ab65ba57e3acb55920999f96a6152228b52a2f49 Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Tue, 30 Jun 2020 13:06:35 -0700 Subject: [PATCH 202/291] iommu/vt-d: Move Kconfig and Makefile bits down into intel directory Move Intel Kconfig and Makefile bits down into intel directory with the rest of the Intel specific files. Signed-off-by: Jerry Snitselaar Reviewed-by: Lu Baolu Cc: Joerg Roedel Cc: Lu Baolu Link: https://lore.kernel.org/r/20200630200636.48600-2-jsnitsel@redhat.com Signed-off-by: Joerg Roedel --- drivers/iommu/Kconfig | 86 +----------------------------------- drivers/iommu/Makefile | 8 +--- drivers/iommu/intel/Kconfig | 86 ++++++++++++++++++++++++++++++++++++ drivers/iommu/intel/Makefile | 7 +++ 4 files changed, 96 insertions(+), 91 deletions(-) create mode 100644 drivers/iommu/intel/Kconfig create mode 100644 drivers/iommu/intel/Makefile diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index af6c081d164f..e9e1238aac21 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -172,91 +172,7 @@ config AMD_IOMMU_DEBUGFS This option is -NOT- intended for production environments, and should not generally be enabled. -# Intel IOMMU support -config DMAR_TABLE - bool - -config INTEL_IOMMU - bool "Support for Intel IOMMU using DMA Remapping Devices" - depends on PCI_MSI && ACPI && (X86 || IA64) - select IOMMU_API - select IOMMU_IOVA - select NEED_DMA_MAP_STATE - select DMAR_TABLE - select SWIOTLB - select IOASID - help - DMA remapping (DMAR) devices support enables independent address - translations for Direct Memory Access (DMA) from devices. - These DMA remapping devices are reported via ACPI tables - and include PCI device scope covered by these DMA - remapping devices. - -config INTEL_IOMMU_DEBUGFS - bool "Export Intel IOMMU internals in Debugfs" - depends on INTEL_IOMMU && IOMMU_DEBUGFS - help - !!!WARNING!!! - - DO NOT ENABLE THIS OPTION UNLESS YOU REALLY KNOW WHAT YOU ARE DOING!!! - - Expose Intel IOMMU internals in Debugfs. - - This option is -NOT- intended for production environments, and should - only be enabled for debugging Intel IOMMU. - -config INTEL_IOMMU_SVM - bool "Support for Shared Virtual Memory with Intel IOMMU" - depends on INTEL_IOMMU && X86_64 - select PCI_PASID - select PCI_PRI - select MMU_NOTIFIER - select IOASID - help - Shared Virtual Memory (SVM) provides a facility for devices - to access DMA resources through process address space by - means of a Process Address Space ID (PASID). - -config INTEL_IOMMU_DEFAULT_ON - def_bool y - prompt "Enable Intel DMA Remapping Devices by default" - depends on INTEL_IOMMU - help - Selecting this option will enable a DMAR device at boot time if - one is found. If this option is not selected, DMAR support can - be enabled by passing intel_iommu=on to the kernel. - -config INTEL_IOMMU_BROKEN_GFX_WA - bool "Workaround broken graphics drivers (going away soon)" - depends on INTEL_IOMMU && BROKEN && X86 - help - Current Graphics drivers tend to use physical address - for DMA and avoid using DMA APIs. Setting this config - option permits the IOMMU driver to set a unity map for - all the OS-visible memory. Hence the driver can continue - to use physical addresses for DMA, at least until this - option is removed in the 2.6.32 kernel. - -config INTEL_IOMMU_FLOPPY_WA - def_bool y - depends on INTEL_IOMMU && X86 - help - Floppy disk drivers are known to bypass DMA API calls - thereby failing to work when IOMMU is enabled. This - workaround will setup a 1:1 mapping for the first - 16MiB to make floppy (an ISA device) work. - -config INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON - bool "Enable Intel IOMMU scalable mode by default" - depends on INTEL_IOMMU - help - Selecting this option will enable by default the scalable mode if - hardware presents the capability. The scalable mode is defined in - VT-d 3.0. The scalable mode capability could be checked by reading - /sys/devices/virtual/iommu/dmar*/intel-iommu/ecap. If this option - is not selected, scalable mode support could also be enabled by - passing intel_iommu=sm_on to the kernel. If not sure, please use - the default value. +source "drivers/iommu/intel/Kconfig" config IRQ_REMAP bool "Support for Interrupt Remapping" diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 342190196dfb..71dd2f382e78 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +obj-y += intel/ obj-$(CONFIG_IOMMU_API) += iommu.o obj-$(CONFIG_IOMMU_API) += iommu-traces.o obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o @@ -17,13 +18,8 @@ obj-$(CONFIG_AMD_IOMMU_V2) += amd/iommu_v2.o obj-$(CONFIG_ARM_SMMU) += arm_smmu.o arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o -obj-$(CONFIG_DMAR_TABLE) += intel/dmar.o -obj-$(CONFIG_INTEL_IOMMU) += intel/iommu.o intel/pasid.o -obj-$(CONFIG_INTEL_IOMMU) += intel/trace.o -obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += intel/debugfs.o -obj-$(CONFIG_INTEL_IOMMU_SVM) += intel/svm.o obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o -obj-$(CONFIG_IRQ_REMAP) += intel/irq_remapping.o irq_remapping.o +obj-$(CONFIG_IRQ_REMAP) += irq_remapping.o obj-$(CONFIG_MTK_IOMMU) += mtk_iommu.o obj-$(CONFIG_MTK_IOMMU_V1) += mtk_iommu_v1.o obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig new file mode 100644 index 000000000000..877beec9d987 --- /dev/null +++ b/drivers/iommu/intel/Kconfig @@ -0,0 +1,86 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Intel IOMMU support +config DMAR_TABLE + bool + +config INTEL_IOMMU + bool "Support for Intel IOMMU using DMA Remapping Devices" + depends on PCI_MSI && ACPI && (X86 || IA64) + select IOMMU_API + select IOMMU_IOVA + select NEED_DMA_MAP_STATE + select DMAR_TABLE + select SWIOTLB + select IOASID + help + DMA remapping (DMAR) devices support enables independent address + translations for Direct Memory Access (DMA) from devices. + These DMA remapping devices are reported via ACPI tables + and include PCI device scope covered by these DMA + remapping devices. + +config INTEL_IOMMU_DEBUGFS + bool "Export Intel IOMMU internals in Debugfs" + depends on INTEL_IOMMU && IOMMU_DEBUGFS + help + !!!WARNING!!! + + DO NOT ENABLE THIS OPTION UNLESS YOU REALLY KNOW WHAT YOU ARE DOING!!! + + Expose Intel IOMMU internals in Debugfs. + + This option is -NOT- intended for production environments, and should + only be enabled for debugging Intel IOMMU. + +config INTEL_IOMMU_SVM + bool "Support for Shared Virtual Memory with Intel IOMMU" + depends on INTEL_IOMMU && X86_64 + select PCI_PASID + select PCI_PRI + select MMU_NOTIFIER + select IOASID + help + Shared Virtual Memory (SVM) provides a facility for devices + to access DMA resources through process address space by + means of a Process Address Space ID (PASID). + +config INTEL_IOMMU_DEFAULT_ON + def_bool y + prompt "Enable Intel DMA Remapping Devices by default" + depends on INTEL_IOMMU + help + Selecting this option will enable a DMAR device at boot time if + one is found. If this option is not selected, DMAR support can + be enabled by passing intel_iommu=on to the kernel. + +config INTEL_IOMMU_BROKEN_GFX_WA + bool "Workaround broken graphics drivers (going away soon)" + depends on INTEL_IOMMU && BROKEN && X86 + help + Current Graphics drivers tend to use physical address + for DMA and avoid using DMA APIs. Setting this config + option permits the IOMMU driver to set a unity map for + all the OS-visible memory. Hence the driver can continue + to use physical addresses for DMA, at least until this + option is removed in the 2.6.32 kernel. + +config INTEL_IOMMU_FLOPPY_WA + def_bool y + depends on INTEL_IOMMU && X86 + help + Floppy disk drivers are known to bypass DMA API calls + thereby failing to work when IOMMU is enabled. This + workaround will setup a 1:1 mapping for the first + 16MiB to make floppy (an ISA device) work. + +config INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON + bool "Enable Intel IOMMU scalable mode by default" + depends on INTEL_IOMMU + help + Selecting this option will enable by default the scalable mode if + hardware presents the capability. The scalable mode is defined in + VT-d 3.0. The scalable mode capability could be checked by reading + /sys/devices/virtual/iommu/dmar*/intel-iommu/ecap. If this option + is not selected, scalable mode support could also be enabled by + passing intel_iommu=sm_on to the kernel. If not sure, please use + the default value. diff --git a/drivers/iommu/intel/Makefile b/drivers/iommu/intel/Makefile new file mode 100644 index 000000000000..fb8e1e8c8029 --- /dev/null +++ b/drivers/iommu/intel/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_DMAR_TABLE) += dmar.o +obj-$(CONFIG_INTEL_IOMMU) += iommu.o pasid.o +obj-$(CONFIG_INTEL_IOMMU) += trace.o +obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += debugfs.o +obj-$(CONFIG_INTEL_IOMMU_SVM) += svm.o +obj-$(CONFIG_IRQ_REMAP) += irq_remapping.o From cbe94c6e1a7d11050050c4d5b89bb278c163e8d6 Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Tue, 30 Jun 2020 13:06:36 -0700 Subject: [PATCH 203/291] iommu/amd: Move Kconfig and Makefile bits down into amd directory Move AMD Kconfig and Makefile bits down into the amd directory with the rest of the AMD specific files. Signed-off-by: Jerry Snitselaar Cc: Joerg Roedel Cc: Suravee Suthikulpanit Link: https://lore.kernel.org/r/20200630200636.48600-3-jsnitsel@redhat.com Signed-off-by: Joerg Roedel --- drivers/iommu/Kconfig | 45 +------------------------------------- drivers/iommu/Makefile | 5 +---- drivers/iommu/amd/Kconfig | 44 +++++++++++++++++++++++++++++++++++++ drivers/iommu/amd/Makefile | 4 ++++ 4 files changed, 50 insertions(+), 48 deletions(-) create mode 100644 drivers/iommu/amd/Kconfig create mode 100644 drivers/iommu/amd/Makefile diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index e9e1238aac21..8ef9860b8d7f 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -128,50 +128,7 @@ config MSM_IOMMU If unsure, say N here. -# AMD IOMMU support -config AMD_IOMMU - bool "AMD IOMMU support" - select SWIOTLB - select PCI_MSI - select PCI_ATS - select PCI_PRI - select PCI_PASID - select IOMMU_API - select IOMMU_IOVA - select IOMMU_DMA - depends on X86_64 && PCI && ACPI - help - With this option you can enable support for AMD IOMMU hardware in - your system. An IOMMU is a hardware component which provides - remapping of DMA memory accesses from devices. With an AMD IOMMU you - can isolate the DMA memory of different devices and protect the - system from misbehaving device drivers or hardware. - - You can find out if your system has an AMD IOMMU if you look into - your BIOS for an option to enable it or if you have an IVRS ACPI - table. - -config AMD_IOMMU_V2 - tristate "AMD IOMMU Version 2 driver" - depends on AMD_IOMMU - select MMU_NOTIFIER - help - This option enables support for the AMD IOMMUv2 features of the IOMMU - hardware. Select this option if you want to use devices that support - the PCI PRI and PASID interface. - -config AMD_IOMMU_DEBUGFS - bool "Enable AMD IOMMU internals in DebugFS" - depends on AMD_IOMMU && IOMMU_DEBUGFS - help - !!!WARNING!!! !!!WARNING!!! !!!WARNING!!! !!!WARNING!!! - - DO NOT ENABLE THIS OPTION UNLESS YOU REALLY, -REALLY- KNOW WHAT YOU ARE DOING!!! - Exposes AMD IOMMU device internals in DebugFS. - - This option is -NOT- intended for production environments, and should - not generally be enabled. - +source "drivers/iommu/amd/Kconfig" source "drivers/iommu/intel/Kconfig" config IRQ_REMAP diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 71dd2f382e78..f356bc12b1c7 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y += intel/ +obj-y += amd/ intel/ obj-$(CONFIG_IOMMU_API) += iommu.o obj-$(CONFIG_IOMMU_API) += iommu-traces.o obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o @@ -12,9 +12,6 @@ obj-$(CONFIG_IOASID) += ioasid.o obj-$(CONFIG_IOMMU_IOVA) += iova.o obj-$(CONFIG_OF_IOMMU) += of_iommu.o obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o -obj-$(CONFIG_AMD_IOMMU) += amd/iommu.o amd/init.o amd/quirks.o -obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd/debugfs.o -obj-$(CONFIG_AMD_IOMMU_V2) += amd/iommu_v2.o obj-$(CONFIG_ARM_SMMU) += arm_smmu.o arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o diff --git a/drivers/iommu/amd/Kconfig b/drivers/iommu/amd/Kconfig new file mode 100644 index 000000000000..1f061d91e0b8 --- /dev/null +++ b/drivers/iommu/amd/Kconfig @@ -0,0 +1,44 @@ +# SPDX-License-Identifier: GPL-2.0-only +# AMD IOMMU support +config AMD_IOMMU + bool "AMD IOMMU support" + select SWIOTLB + select PCI_MSI + select PCI_ATS + select PCI_PRI + select PCI_PASID + select IOMMU_API + select IOMMU_IOVA + select IOMMU_DMA + depends on X86_64 && PCI && ACPI + help + With this option you can enable support for AMD IOMMU hardware in + your system. An IOMMU is a hardware component which provides + remapping of DMA memory accesses from devices. With an AMD IOMMU you + can isolate the DMA memory of different devices and protect the + system from misbehaving device drivers or hardware. + + You can find out if your system has an AMD IOMMU if you look into + your BIOS for an option to enable it or if you have an IVRS ACPI + table. + +config AMD_IOMMU_V2 + tristate "AMD IOMMU Version 2 driver" + depends on AMD_IOMMU + select MMU_NOTIFIER + help + This option enables support for the AMD IOMMUv2 features of the IOMMU + hardware. Select this option if you want to use devices that support + the PCI PRI and PASID interface. + +config AMD_IOMMU_DEBUGFS + bool "Enable AMD IOMMU internals in DebugFS" + depends on AMD_IOMMU && IOMMU_DEBUGFS + help + !!!WARNING!!! !!!WARNING!!! !!!WARNING!!! !!!WARNING!!! + + DO NOT ENABLE THIS OPTION UNLESS YOU REALLY, -REALLY- KNOW WHAT YOU ARE DOING!!! + Exposes AMD IOMMU device internals in DebugFS. + + This option is -NOT- intended for production environments, and should + not generally be enabled. diff --git a/drivers/iommu/amd/Makefile b/drivers/iommu/amd/Makefile new file mode 100644 index 000000000000..dc5a2fa4fd37 --- /dev/null +++ b/drivers/iommu/amd/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_AMD_IOMMU) += iommu.o init.o quirks.o +obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += debugfs.o +obj-$(CONFIG_AMD_IOMMU_V2) += iommu_v2.o From 49688e654e48ae176b5bfda33d2416b68e607ce8 Mon Sep 17 00:00:00 2001 From: Hao Li Date: Wed, 29 Jul 2020 11:44:36 +0800 Subject: [PATCH 204/291] dax: Fix incorrect argument passed to xas_set_err() The argument passed to xas_set_err() to indicate an error should be negative. Otherwise, xas_error() will return 0, and grab_mapping_entry() will return the found entry instead of 'SIGBUS' when the entry is not in fact valid. This would result in problems in subsequent code paths. Link: https://lore.kernel.org/r/20200729034436.24267-1-lihao2018.fnst@cn.fujitsu.com Reviewed-by: Pankaj Gupta Signed-off-by: Hao Li Signed-off-by: Vishal Verma --- fs/dax.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/dax.c b/fs/dax.c index 3e0babeb0365..95341af1a966 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -488,7 +488,7 @@ static void *grab_mapping_entry(struct xa_state *xas, if (dax_is_conflict(entry)) goto fallback; if (!xa_is_value(entry)) { - xas_set_err(xas, EIO); + xas_set_err(xas, -EIO); goto out_unlock; } From 7f4784f1881cbf7d3e6367e1c4341c1ab2ccdb5b Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 28 Jul 2020 02:13:55 -0700 Subject: [PATCH 205/291] platform/chrome: cros_ec_sensorhub: Simplify legacy timestamp spreading On some machines (nami), interrupt latency cause samples to appear to be from the future and are pegged to the current time. We would see samples with this pattern: [t, t + ~5ms, t + ~10ms, t + ~10ms + 100us, t + ~10ms + 200us], (current now) (current now) (t is the last timestamp time) Last 2 samples would be barely spread, causing applications to complain. We now spread the entire sequence. This is not great: in the example the sensor was supposed to send samples every 5ms, it now appears to send one every 2.5ms, but it is slightly closer to reality: sampling time in the example above At sensor level 1 2 3 4 5 +-----5ms-----+-----5ms-----+-----5ms-----+----5ms-----+---> t Before, at host level 1 2 3 4 5 --interrupt delay------+-----5ms-----+-----5ms-----+-+-+---> t Afer, at host level 1 2 3 4 5 --interrupt delay------+-2.5ms-+-2.5ms-+-2.5ms-+-2.5ms-+---> t Signed-off-by: Gwendal Grignou Signed-off-by: Enric Balletbo i Serra --- .../platform/chrome/cros_ec_sensorhub_ring.c | 96 +++++++------------ 1 file changed, 34 insertions(+), 62 deletions(-) diff --git a/drivers/platform/chrome/cros_ec_sensorhub_ring.c b/drivers/platform/chrome/cros_ec_sensorhub_ring.c index b1c641c72f51..8921f24e83ba 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub_ring.c +++ b/drivers/platform/chrome/cros_ec_sensorhub_ring.c @@ -673,29 +673,22 @@ cros_ec_sensor_ring_spread_add(struct cros_ec_sensorhub *sensorhub, * cros_ec_sensor_ring_spread_add_legacy: Calculate proper timestamps then * add to ringbuffer (legacy). * - * Note: This assumes we're running old firmware, where every sample's timestamp - * is after the sample. Run if tight_timestamps == false. - * - * If there is a sample with a proper timestamp + * Note: This assumes we're running old firmware, where timestamp + * is inserted after its sample(s)e. There can be several samples between + * timestamps, so several samples can have the same timestamp. * * timestamp | count * ----------------- - * older_unprocess_out --> TS1 | 1 - * TS1 | 2 - * out --> TS1 | 3 - * next_out --> TS2 | + * 1st sample --> TS1 | 1 + * TS2 | 2 + * TS2 | 3 + * TS3 | 4 + * last_out --> * - * We spread time for the samples [older_unprocess_out .. out] - * between TS1 and TS2: [TS1+1/4, TS1+2/4, TS1+3/4, TS2]. * - * If we reach the end of the samples, we compare with the - * current timestamp: + * We spread time for the samples using perod p = (current - TS1)/4. + * between TS1 and TS2: [TS1+p/4, TS1+2p/4, TS1+3p/4, current_timestamp]. * - * older_unprocess_out --> TS1 | 1 - * TS1 | 2 - * out --> TS1 | 3 - * - * We know have [TS1+1/3, TS1+2/3, current timestamp] */ static void cros_ec_sensor_ring_spread_add_legacy(struct cros_ec_sensorhub *sensorhub, @@ -708,58 +701,37 @@ cros_ec_sensor_ring_spread_add_legacy(struct cros_ec_sensorhub *sensorhub, int i; for_each_set_bit(i, &sensor_mask, sensorhub->sensor_num) { - s64 older_timestamp; s64 timestamp; - struct cros_ec_sensors_ring_sample *older_unprocess_out = - sensorhub->ring; - struct cros_ec_sensors_ring_sample *next_out; - int count = 1; + int count = 0; + s64 time_period; - for (out = sensorhub->ring; out < last_out; out = next_out) { - s64 time_period; - - next_out = out + 1; + for (out = sensorhub->ring; out < last_out; out++) { if (out->sensor_id != i) continue; /* Timestamp to start with */ - older_timestamp = out->timestamp; - - /* Find next sample. */ - while (next_out < last_out && next_out->sensor_id != i) - next_out++; - - if (next_out >= last_out) { - timestamp = current_timestamp; - } else { - timestamp = next_out->timestamp; - if (timestamp == older_timestamp) { - count++; - continue; - } - } - - /* - * The next sample has a new timestamp, spread the - * unprocessed samples. - */ - if (next_out < last_out) - count++; - time_period = div_s64(timestamp - older_timestamp, - count); - - for (; older_unprocess_out <= out; - older_unprocess_out++) { - if (older_unprocess_out->sensor_id != i) - continue; - older_timestamp += time_period; - older_unprocess_out->timestamp = - older_timestamp; - } + timestamp = out->timestamp; + out++; count = 1; - /* The next_out sample has a valid timestamp, skip. */ - next_out++; - older_unprocess_out = next_out; + break; + } + for (; out < last_out; out++) { + /* Find last sample. */ + if (out->sensor_id != i) + continue; + count++; + } + if (count == 0) + continue; + + /* Spread uniformly between the first and last samples. */ + time_period = div_s64(current_timestamp - timestamp, count); + + for (out = sensorhub->ring; out < last_out; out++) { + if (out->sensor_id != i) + continue; + timestamp += time_period; + out->timestamp = timestamp; } } From c214e564acb2ad9463293ab9c109bfdae91fbeaf Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 24 Jul 2020 12:08:40 -0700 Subject: [PATCH 206/291] platform/chrome: cros_ec_proto: ignore unnecessary wakeups on old ECs ECs that don't implement EC_CMD_HOST_EVENT_GET_WAKE_MASK should still have some reasonable default mask -- otherwise, they'll treat a variety of EC signals as spurious wakeups. Battery and AC events can be especially common, for devices that have been sitting at full charge plugged into AC for a long time, as they may cycle their charging off and on, or their battery may start reporting failures as it ages. Treating these as wakeups does not serve a useful purpose, and is instead often counterproductive. And indeed, later ECs (that implement the mask) don't include these events in their wake-mask. Note that this patch doesn't do anything without the subsequent patch ("platform/chrome: cros_ec_proto: check for missing EC_CMD_HOST_EVENT_GET_WAKE_MASK"), because cros_ec_get_host_event_wake_mask() currently does not return an error if EC_CMD_HOST_EVENT_GET_WAKE_MASK is not implemented. Some additional notes: While the EC typically knows not to wake the CPU for these unimportant events once the CPU reaches a sleep state, it doesn't really have a way to know that the CPU is "almost" asleep, unless it has support for EC_CMD_HOST_SLEEP_EVENT. Alas, these older ECs do not support that command either, so this solution is not 100% complete. Signed-off-by: Brian Norris Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_proto.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 11a2db7cd0f7..b6b583b5868a 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -469,14 +469,26 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev) &ver_mask); ec_dev->host_sleep_v1 = (ret >= 0 && (ver_mask & EC_VER_MASK(1))); - /* - * Get host event wake mask, assume all events are wake events - * if unavailable. - */ + /* Get host event wake mask. */ ret = cros_ec_get_host_event_wake_mask(ec_dev, proto_msg, &ec_dev->host_event_wake_mask); - if (ret < 0) - ec_dev->host_event_wake_mask = U32_MAX; + if (ret < 0) { + /* + * If the EC doesn't support EC_CMD_HOST_EVENT_GET_WAKE_MASK, + * use a reasonable default. Note that we ignore various + * battery, AC status, and power-state events, because (a) + * those can be quite common (e.g., when sitting at full + * charge, on AC) and (b) these are not actionable wake events; + * if anything, we'd like to continue suspending (to save + * power), not wake up. + */ + ec_dev->host_event_wake_mask = U32_MAX & + ~(BIT(EC_HOST_EVENT_AC_DISCONNECTED) | + BIT(EC_HOST_EVENT_BATTERY_LOW) | + BIT(EC_HOST_EVENT_BATTERY_CRITICAL) | + BIT(EC_HOST_EVENT_PD_MCU) | + BIT(EC_HOST_EVENT_BATTERY_STATUS)); + } ret = 0; From fc8cacf3fc68664e30a6df2b361ae05b9769585e Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 24 Jul 2020 12:08:41 -0700 Subject: [PATCH 207/291] platform/chrome: cros_ec_proto: check for missing EC_CMD_HOST_EVENT_GET_WAKE_MASK As with cros_ec_cmd_xfer_status(), etc., it's not enough to simply check for the return status of send_command() -- that only covers transport or other similarly-fatal errors. One must also check the ->result field, to see whether the command really succeeded. If not, we can't use the data it returns. The caller of cros_ec_get_host_event_wake_mask() ignores this, and so for example, on EC's where the command is not implemented, we're using junk (or in practice, all zeros) for our wake-mask. We should be using a non-zero default (currently, it's supposed to be all-1's). Fix this by checking the ->result field and returning -EPROTO for errors. I might label this as fixing commit 29d99b966d60 ("cros_ec: Don't signal wake event for non-wake host events"), except that this fix alone actually may make things worse, as it now allows for a lot more spurious wakeups. The patch "platform/chrome: cros_ec_proto: ignore battery/AC wakeups on old ECs" helps to mitigate this. Signed-off-by: Brian Norris Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec_proto.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index b6b583b5868a..8d52b3b4bd4e 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -208,6 +208,12 @@ static int cros_ec_get_host_event_wake_mask(struct cros_ec_device *ec_dev, msg->insize = sizeof(*r); ret = send_command(ec_dev, msg); + if (ret >= 0) { + if (msg->result == EC_RES_INVALID_COMMAND) + return -EOPNOTSUPP; + if (msg->result != EC_RES_SUCCESS) + return -EPROTO; + } if (ret > 0) { r = (struct ec_response_host_event_mask *)msg->data; *mask = r->mask; @@ -488,6 +494,13 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev) BIT(EC_HOST_EVENT_BATTERY_CRITICAL) | BIT(EC_HOST_EVENT_PD_MCU) | BIT(EC_HOST_EVENT_BATTERY_STATUS)); + /* + * Old ECs may not support this command. Complain about all + * other errors. + */ + if (ret != -EOPNOTSUPP) + dev_err(ec_dev->dev, + "failed to retrieve wake mask: %d\n", ret); } ret = 0; From 9f1048d47e8ae4cc21e80facf2ba4b01a6623b67 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 31 Jul 2020 18:38:26 -0700 Subject: [PATCH 208/291] ACPI: NFIT: Fix ARS zero-sized allocation Pending commit in -next "devres: handle zero size in devm_kmalloc()" triggers a boot regression due to the ARS implementation expecting NULL from a zero-sized allocation. Avoid the zero-sized allocation by skipping ARS, otherwise crashes with the following signature when de-referencing ZERO_SIZE_PTR. BUG: kernel NULL pointer dereference, address: 0000000000000018 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page RIP: 0010:__acpi_nfit_scrub+0x28a/0x350 [nfit] [..] Call Trace: ? acpi_nfit_query_poison+0x6a/0x180 [nfit] acpi_nfit_scrub+0x36/0xb0 [nfit] process_one_work+0x23c/0x580 worker_thread+0x50/0x3b0 Otherwise the implementation correctly aborts when NULL is returned from devm_kzalloc() in ars_status_alloc(). Link: https://lore.kernel.org/r/159624590643.3037264.14157533719042907758.stgit@dwillia2-desk3.amr.corp.intel.com Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- drivers/acpi/nfit/core.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index fb775b967c52..26dd208a0d63 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3334,7 +3334,7 @@ static void acpi_nfit_init_ars(struct acpi_nfit_desc *acpi_desc, static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc) { struct nfit_spa *nfit_spa; - int rc; + int rc, do_sched_ars = 0; set_bit(ARS_VALID, &acpi_desc->scrub_flags); list_for_each_entry(nfit_spa, &acpi_desc->spas, list) { @@ -3346,7 +3346,7 @@ static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc) } } - list_for_each_entry(nfit_spa, &acpi_desc->spas, list) + list_for_each_entry(nfit_spa, &acpi_desc->spas, list) { switch (nfit_spa_type(nfit_spa->spa)) { case NFIT_SPA_VOLATILE: case NFIT_SPA_PM: @@ -3354,6 +3354,13 @@ static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc) rc = ars_register(acpi_desc, nfit_spa); if (rc) return rc; + + /* + * Kick off background ARS if at least one + * region successfully registered ARS + */ + if (!test_bit(ARS_FAILED, &nfit_spa->ars_state)) + do_sched_ars++; break; case NFIT_SPA_BDW: /* nothing to register */ @@ -3372,8 +3379,10 @@ static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc) /* don't register unknown regions */ break; } + } - sched_ars(acpi_desc); + if (do_sched_ars) + sched_ars(acpi_desc); return 0; } From 321bd212619a7269308696e4ddc446930ea73fad Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 24 Jun 2020 18:24:33 -0400 Subject: [PATCH 209/291] virtio: VIRTIO_F_IOMMU_PLATFORM -> VIRTIO_F_ACCESS_PLATFORM Rename the bit to match latest virtio spec. Add a compat macro to avoid breaking existing userspace. Signed-off-by: Michael S. Tsirkin Reviewed-by: David Hildenbrand --- arch/um/drivers/virtio_uml.c | 2 +- drivers/vdpa/ifcvf/ifcvf_base.h | 2 +- drivers/vdpa/vdpa_sim/vdpa_sim.c | 4 ++-- drivers/vhost/net.c | 4 ++-- drivers/vhost/vdpa.c | 2 +- drivers/virtio/virtio_balloon.c | 2 +- drivers/virtio/virtio_ring.c | 2 +- include/linux/virtio_config.h | 2 +- include/uapi/linux/virtio_config.h | 10 +++++++--- tools/virtio/linux/virtio_config.h | 2 +- 10 files changed, 18 insertions(+), 14 deletions(-) diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index 351aee52aca6..a6c4bb6c2c01 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -385,7 +385,7 @@ static irqreturn_t vu_req_interrupt(int irq, void *data) } break; case VHOST_USER_SLAVE_IOTLB_MSG: - /* not supported - VIRTIO_F_IOMMU_PLATFORM */ + /* not supported - VIRTIO_F_ACCESS_PLATFORM */ case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG: /* not supported - VHOST_USER_PROTOCOL_F_HOST_NOTIFIER */ default: diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h index f4554412e607..24af422b5a3e 100644 --- a/drivers/vdpa/ifcvf/ifcvf_base.h +++ b/drivers/vdpa/ifcvf/ifcvf_base.h @@ -29,7 +29,7 @@ (1ULL << VIRTIO_F_VERSION_1) | \ (1ULL << VIRTIO_NET_F_STATUS) | \ (1ULL << VIRTIO_F_ORDER_PLATFORM) | \ - (1ULL << VIRTIO_F_IOMMU_PLATFORM) | \ + (1ULL << VIRTIO_F_ACCESS_PLATFORM) | \ (1ULL << VIRTIO_NET_F_MRG_RXBUF)) /* Only one queue pair for now. */ diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index c7334cc65bb2..a9bc5e0fb353 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -55,7 +55,7 @@ struct vdpasim_virtqueue { static u64 vdpasim_features = (1ULL << VIRTIO_F_ANY_LAYOUT) | (1ULL << VIRTIO_F_VERSION_1) | - (1ULL << VIRTIO_F_IOMMU_PLATFORM); + (1ULL << VIRTIO_F_ACCESS_PLATFORM); /* State of each vdpasim device */ struct vdpasim { @@ -450,7 +450,7 @@ static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features) struct vdpasim *vdpasim = vdpa_to_sim(vdpa); /* DMA mapping must be done by driver */ - if (!(features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))) + if (!(features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) return -EINVAL; vdpasim->features = features & vdpasim_features; diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index e992decfec53..8e0921d3805d 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -73,7 +73,7 @@ enum { VHOST_NET_FEATURES = VHOST_FEATURES | (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) | (1ULL << VIRTIO_NET_F_MRG_RXBUF) | - (1ULL << VIRTIO_F_IOMMU_PLATFORM) + (1ULL << VIRTIO_F_ACCESS_PLATFORM) }; enum { @@ -1653,7 +1653,7 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features) !vhost_log_access_ok(&n->dev)) goto out_unlock; - if ((features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))) { + if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) { if (vhost_init_device_iotlb(&n->dev, true)) goto out_unlock; } diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index a54b60d6623f..18869a35d408 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -31,7 +31,7 @@ enum { (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) | (1ULL << VIRTIO_F_ANY_LAYOUT) | (1ULL << VIRTIO_F_VERSION_1) | - (1ULL << VIRTIO_F_IOMMU_PLATFORM) | + (1ULL << VIRTIO_F_ACCESS_PLATFORM) | (1ULL << VIRTIO_F_RING_PACKED) | (1ULL << VIRTIO_F_ORDER_PLATFORM) | (1ULL << VIRTIO_RING_F_INDIRECT_DESC) | diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 8be02f333b7a..54fd989f9353 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -1129,7 +1129,7 @@ static int virtballoon_validate(struct virtio_device *vdev) else if (!virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_REPORTING); - __virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM); + __virtio_clear_bit(vdev, VIRTIO_F_ACCESS_PLATFORM); return 0; } diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 58b96baa8d48..a1a5c2a91426 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2225,7 +2225,7 @@ void vring_transport_features(struct virtio_device *vdev) break; case VIRTIO_F_VERSION_1: break; - case VIRTIO_F_IOMMU_PLATFORM: + case VIRTIO_F_ACCESS_PLATFORM: break; case VIRTIO_F_RING_PACKED: break; diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index bb4cc4910750..f2cc2a0df174 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -171,7 +171,7 @@ static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev) * Note the reverse polarity of the quirk feature (compared to most * other features), this is for compatibility with legacy systems. */ - return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM); + return !virtio_has_feature(vdev, VIRTIO_F_ACCESS_PLATFORM); } static inline diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index ff8e7dc9d4dd..b5eda06f0d57 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -67,13 +67,17 @@ #define VIRTIO_F_VERSION_1 32 /* - * If clear - device has the IOMMU bypass quirk feature. - * If set - use platform tools to detect the IOMMU. + * If clear - device has the platform DMA (e.g. IOMMU) bypass quirk feature. + * If set - use platform DMA tools to access the memory. * * Note the reverse polarity (compared to most other features), * this is for compatibility with legacy systems. */ -#define VIRTIO_F_IOMMU_PLATFORM 33 +#define VIRTIO_F_ACCESS_PLATFORM 33 +#ifndef __KERNEL__ +/* Legacy name for VIRTIO_F_ACCESS_PLATFORM (for compatibility with old userspace) */ +#define VIRTIO_F_IOMMU_PLATFORM VIRTIO_F_ACCESS_PLATFORM +#endif /* __KERNEL__ */ /* This feature indicates support for the packed virtqueue layout. */ #define VIRTIO_F_RING_PACKED 34 diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h index dbf14c1e2188..f99ae42668e0 100644 --- a/tools/virtio/linux/virtio_config.h +++ b/tools/virtio/linux/virtio_config.h @@ -51,7 +51,7 @@ static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev) * Note the reverse polarity of the quirk feature (compared to most * other features), this is for compatibility with legacy systems. */ - return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM); + return !virtio_has_feature(vdev, VIRTIO_F_ACCESS_PLATFORM); } static inline bool virtio_is_little_endian(struct virtio_device *vdev) From 24b6842ade6925199e182988259761504aacfbc0 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 24 Jun 2020 19:17:04 -0400 Subject: [PATCH 210/291] virtio: virtio_has_iommu_quirk -> virtio_has_dma_quirk Now that the corresponding feature bit has been renamed, rename the quirk too - it's about special ways to do DMA, not necessarily about the IOMMU. Signed-off-by: Michael S. Tsirkin --- drivers/gpu/drm/virtio/virtgpu_object.c | 2 +- drivers/gpu/drm/virtio/virtgpu_vq.c | 4 ++-- drivers/virtio/virtio_ring.c | 2 +- include/linux/virtio_config.h | 4 ++-- tools/virtio/linux/virtio_config.h | 4 ++-- 5 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 6ccbd01cd888..e8799ab0c753 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -141,7 +141,7 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, struct virtio_gpu_mem_entry **ents, unsigned int *nents) { - bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev); + bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo); struct scatterlist *sg; int si, ret; diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index 9e663a5d9952..53af60d484a4 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -599,7 +599,7 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]); struct virtio_gpu_transfer_to_host_2d *cmd_p; struct virtio_gpu_vbuffer *vbuf; - bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev); + bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo); if (use_dma_api) @@ -1015,7 +1015,7 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]); struct virtio_gpu_transfer_host_3d *cmd_p; struct virtio_gpu_vbuffer *vbuf; - bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev); + bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo); if (use_dma_api) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index a1a5c2a91426..34253cb69cb8 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -240,7 +240,7 @@ static inline bool virtqueue_use_indirect(struct virtqueue *_vq, static bool vring_use_dma_api(struct virtio_device *vdev) { - if (!virtio_has_iommu_quirk(vdev)) + if (!virtio_has_dma_quirk(vdev)) return true; /* Otherwise, we are left to guess. */ diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index f2cc2a0df174..3b4eae5ac5e3 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -162,10 +162,10 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev, } /** - * virtio_has_iommu_quirk - determine whether this device has the iommu quirk + * virtio_has_dma_quirk - determine whether this device has the DMA quirk * @vdev: the device */ -static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev) +static inline bool virtio_has_dma_quirk(const struct virtio_device *vdev) { /* * Note the reverse polarity of the quirk feature (compared to most diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h index f99ae42668e0..f2640e505c4e 100644 --- a/tools/virtio/linux/virtio_config.h +++ b/tools/virtio/linux/virtio_config.h @@ -42,10 +42,10 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev, (__virtio_test_bit((dev), feature)) /** - * virtio_has_iommu_quirk - determine whether this device has the iommu quirk + * virtio_has_dma_quirk - determine whether this device has the DMA quirk * @vdev: the device */ -static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev) +static inline bool virtio_has_dma_quirk(const struct virtio_device *vdev) { /* * Note the reverse polarity of the quirk feature (compared to most From dad42d17558f316e9e807698cd4207359b636084 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Mon, 3 Aug 2020 16:41:37 -0600 Subject: [PATCH 211/291] libnvdimm/security: fix a typo commit d78c620a2e82 ("libnvdimm/security: Introduce a 'frozen' attribute") introduced a typo, causing a 'nvdimm->sec.flags' update being overwritten by the subsequent update meant for 'nvdimm->sec.ext_flags'. Link: https://lore.kernel.org/r/1596494499-9852-1-git-send-email-jane.chu@oracle.com Fixes: d78c620a2e82 ("libnvdimm/security: Introduce a 'frozen' attribute") Cc: Dan Williams Reviewed-by: Dave Jiang Signed-off-by: Jane Chu Signed-off-by: Vishal Verma --- drivers/nvdimm/security.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvdimm/security.c b/drivers/nvdimm/security.c index 89b85970912d..acfd211c01b9 100644 --- a/drivers/nvdimm/security.c +++ b/drivers/nvdimm/security.c @@ -457,7 +457,7 @@ void __nvdimm_security_overwrite_query(struct nvdimm *nvdimm) clear_bit(NDD_WORK_PENDING, &nvdimm->flags); put_device(&nvdimm->dev); nvdimm->sec.flags = nvdimm_security_flags(nvdimm, NVDIMM_USER); - nvdimm->sec.flags = nvdimm_security_flags(nvdimm, NVDIMM_MASTER); + nvdimm->sec.ext_flags = nvdimm_security_flags(nvdimm, NVDIMM_MASTER); } void nvdimm_security_overwrite_query(struct work_struct *work) From 7c02d53dfe4db08cd7b4d4be8c7f1b801cf8b899 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Mon, 3 Aug 2020 16:41:38 -0600 Subject: [PATCH 212/291] libnvdimm/security: the 'security' attr never show 'overwrite' state 'security' attribute displays the security state of an nvdimm. During normal operation, the nvdimm state maybe one of 'disabled', 'unlocked' or 'locked'. When an admin issues # ndctl sanitize-dimm nmem0 --overwrite the attribute is expected to change to 'overwrite' until the overwrite operation completes. But tests on our systems show that 'overwrite' is never shown during the overwrite operation. i.e. # cat /sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0012:00/ndbus0/nmem0/security unlocked the attribute remain 'unlocked' through out the operation, consequently "ndctl wait-overwrite nmem0" command doesn't wait at all. The driver tracks the state in 'nvdimm->sec.flags': when the operation starts, it adds an overwrite bit to the flags; and when the operation completes, it removes the bit. Hence security_show() should check the 'overwrite' bit first, in order to indicate the actual state when multiple bits are set in the flags. Link: https://lore.kernel.org/r/1596494499-9852-2-git-send-email-jane.chu@oracle.com Reviewed-by: Dave Jiang Signed-off-by: Jane Chu Signed-off-by: Vishal Verma --- drivers/nvdimm/dimm_devs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 2f0815e15986..61374def5155 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -363,14 +363,14 @@ __weak ssize_t security_show(struct device *dev, { struct nvdimm *nvdimm = to_nvdimm(dev); + if (test_bit(NVDIMM_SECURITY_OVERWRITE, &nvdimm->sec.flags)) + return sprintf(buf, "overwrite\n"); if (test_bit(NVDIMM_SECURITY_DISABLED, &nvdimm->sec.flags)) return sprintf(buf, "disabled\n"); if (test_bit(NVDIMM_SECURITY_UNLOCKED, &nvdimm->sec.flags)) return sprintf(buf, "unlocked\n"); if (test_bit(NVDIMM_SECURITY_LOCKED, &nvdimm->sec.flags)) return sprintf(buf, "locked\n"); - if (test_bit(NVDIMM_SECURITY_OVERWRITE, &nvdimm->sec.flags)) - return sprintf(buf, "overwrite\n"); return -ENOTTY; } From 7f674025d9f7321dea11b802cc0ab3f09cbe51c5 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Mon, 3 Aug 2020 16:41:39 -0600 Subject: [PATCH 213/291] libnvdimm/security: ensure sysfs poll thread woke up and fetch updated attr commit 7d988097c546 ("acpi/nfit, libnvdimm/security: Add security DSM overwrite support") adds a sysfs_notify_dirent() to wake up userspace poll thread when the "overwrite" operation has completed. But the notification is issued before the internal dimm security state and flags have been updated, so the userspace poll thread wakes up and fetches the not-yet-updated attr and falls back to sleep, forever. But if user from another terminal issue "ndctl wait-overwrite nmemX" again, the command returns instantly. Link: https://lore.kernel.org/r/1596494499-9852-3-git-send-email-jane.chu@oracle.com Fixes: 7d988097c546 ("acpi/nfit, libnvdimm/security: Add security DSM overwrite support") Cc: Dave Jiang Cc: Dan Williams Reviewed-by: Dave Jiang Signed-off-by: Jane Chu Signed-off-by: Vishal Verma --- drivers/nvdimm/security.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/nvdimm/security.c b/drivers/nvdimm/security.c index acfd211c01b9..35d265014e1e 100644 --- a/drivers/nvdimm/security.c +++ b/drivers/nvdimm/security.c @@ -450,14 +450,19 @@ void __nvdimm_security_overwrite_query(struct nvdimm *nvdimm) else dev_dbg(&nvdimm->dev, "overwrite completed\n"); - if (nvdimm->sec.overwrite_state) - sysfs_notify_dirent(nvdimm->sec.overwrite_state); + /* + * Mark the overwrite work done and update dimm security flags, + * then send a sysfs event notification to wake up userspace + * poll threads to picked up the changed state. + */ nvdimm->sec.overwrite_tmo = 0; clear_bit(NDD_SECURITY_OVERWRITE, &nvdimm->flags); clear_bit(NDD_WORK_PENDING, &nvdimm->flags); - put_device(&nvdimm->dev); nvdimm->sec.flags = nvdimm_security_flags(nvdimm, NVDIMM_USER); nvdimm->sec.ext_flags = nvdimm_security_flags(nvdimm, NVDIMM_MASTER); + if (nvdimm->sec.overwrite_state) + sysfs_notify_dirent(nvdimm->sec.overwrite_state); + put_device(&nvdimm->dev); } void nvdimm_security_overwrite_query(struct work_struct *work) From e848643b524be9c10826c2cf36eebb74eef643d2 Mon Sep 17 00:00:00 2001 From: Jing Xiangfeng Date: Fri, 17 Jul 2020 17:52:59 +0800 Subject: [PATCH 214/291] orangefs: remove unnecessary assignment to variable ret The variable ret is guaranteed to be 0 in this if (). So we can remove this assignement. Signed-off-by: Jing Xiangfeng Signed-off-by: Mike Marshall --- fs/orangefs/orangefs-mod.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c index 289b648ae196..74a3d6337ef4 100644 --- a/fs/orangefs/orangefs-mod.c +++ b/fs/orangefs/orangefs-mod.c @@ -149,7 +149,6 @@ static int __init orangefs_init(void) pr_info("%s: module version %s loaded\n", __func__, ORANGEFS_VERSION); - ret = 0; goto out; } From 4476770881d7ac647e3bcae0943f37e00b9c3f3c Mon Sep 17 00:00:00 2001 From: Siddharth Gupta Date: Wed, 29 Jul 2020 10:40:00 -0700 Subject: [PATCH 215/291] remoteproc: Add remoteproc character device interface Add the character device interface into remoteproc framework. This interface can be used in order to boot/shutdown remote subsystems and provides a basic ioctl based interface to implement supplementary functionality. An ioctl call is implemented to enable the shutdown on release feature which will allow remote processors to be shutdown when the controlling userspace application crashes or hangs. Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Signed-off-by: Rishabh Bhatnagar Signed-off-by: Siddharth Gupta Link: https://lore.kernel.org/r/1596044401-22083-2-git-send-email-sidgup@codeaurora.org [bjorn: s/int32_t/s32/ per checkpatch] Signed-off-by: Bjorn Andersson --- .../userspace-api/ioctl/ioctl-number.rst | 1 + drivers/remoteproc/Kconfig | 9 ++ drivers/remoteproc/Makefile | 1 + drivers/remoteproc/remoteproc_cdev.c | 124 ++++++++++++++++++ drivers/remoteproc/remoteproc_internal.h | 28 ++++ include/linux/remoteproc.h | 5 + include/uapi/linux/remoteproc_cdev.h | 37 ++++++ 7 files changed, 205 insertions(+) create mode 100644 drivers/remoteproc/remoteproc_cdev.c create mode 100644 include/uapi/linux/remoteproc_cdev.h diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 59472cd6a11d..2a198838fca9 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -339,6 +339,7 @@ Code Seq# Include File Comments 0xB4 00-0F linux/gpio.h 0xB5 00-0F uapi/linux/rpmsg.h 0xB6 all linux/fpga-dfl.h +0xB7 all uapi/linux/remoteproc_cdev.h 0xC0 00-0F linux/usb/iowarrior.h 0xCA 00-0F uapi/misc/cxl.h 0xCA 10-2F uapi/misc/ocxl.h diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index 48315dc4a30c..c6659dfea7c7 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -14,6 +14,15 @@ config REMOTEPROC if REMOTEPROC +config REMOTEPROC_CDEV + bool "Remoteproc character device interface" + help + Say y here to have a character device interface for the remoteproc + framework. Userspace can boot/shutdown remote processors through + this interface. + + It's safe to say N if you don't want to use this interface. + config IMX_REMOTEPROC tristate "IMX6/7 remoteproc support" depends on ARCH_MXC diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile index 4d4307dc8fa9..3dfa28e6c701 100644 --- a/drivers/remoteproc/Makefile +++ b/drivers/remoteproc/Makefile @@ -10,6 +10,7 @@ remoteproc-y += remoteproc_debugfs.o remoteproc-y += remoteproc_sysfs.o remoteproc-y += remoteproc_virtio.o remoteproc-y += remoteproc_elf_loader.o +obj-$(CONFIG_REMOTEPROC_CDEV) += remoteproc_cdev.o obj-$(CONFIG_IMX_REMOTEPROC) += imx_rproc.o obj-$(CONFIG_INGENIC_VPU_RPROC) += ingenic_rproc.o obj-$(CONFIG_MTK_SCP) += mtk_scp.o mtk_scp_ipi.o diff --git a/drivers/remoteproc/remoteproc_cdev.c b/drivers/remoteproc/remoteproc_cdev.c new file mode 100644 index 000000000000..b19ea3057bde --- /dev/null +++ b/drivers/remoteproc/remoteproc_cdev.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Character device interface driver for Remoteproc framework. + * + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "remoteproc_internal.h" + +#define NUM_RPROC_DEVICES 64 +static dev_t rproc_major; + +static ssize_t rproc_cdev_write(struct file *filp, const char __user *buf, size_t len, loff_t *pos) +{ + struct rproc *rproc = container_of(filp->f_inode->i_cdev, struct rproc, cdev); + int ret = 0; + char cmd[10]; + + if (!len || len > sizeof(cmd)) + return -EINVAL; + + ret = copy_from_user(cmd, buf, len); + if (ret) + return -EFAULT; + + if (!strncmp(cmd, "start", len)) { + if (rproc->state == RPROC_RUNNING) + return -EBUSY; + + ret = rproc_boot(rproc); + } else if (!strncmp(cmd, "stop", len)) { + if (rproc->state != RPROC_RUNNING) + return -EINVAL; + + rproc_shutdown(rproc); + } else { + dev_err(&rproc->dev, "Unrecognized option\n"); + ret = -EINVAL; + } + + return ret ? ret : len; +} + +static long rproc_device_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) +{ + struct rproc *rproc = container_of(filp->f_inode->i_cdev, struct rproc, cdev); + void __user *argp = (void __user *)arg; + s32 param; + + switch (ioctl) { + case RPROC_SET_SHUTDOWN_ON_RELEASE: + if (copy_from_user(¶m, argp, sizeof(s32))) + return -EFAULT; + + rproc->cdev_put_on_release = !!param; + break; + case RPROC_GET_SHUTDOWN_ON_RELEASE: + param = (s32)rproc->cdev_put_on_release; + if (copy_to_user(argp, ¶m, sizeof(s32))) + return -EFAULT; + + break; + default: + dev_err(&rproc->dev, "Unsupported ioctl\n"); + return -EINVAL; + } + + return 0; +} + +static int rproc_cdev_release(struct inode *inode, struct file *filp) +{ + struct rproc *rproc = container_of(inode->i_cdev, struct rproc, cdev); + + if (rproc->cdev_put_on_release && rproc->state == RPROC_RUNNING) + rproc_shutdown(rproc); + + return 0; +} + +static const struct file_operations rproc_fops = { + .write = rproc_cdev_write, + .unlocked_ioctl = rproc_device_ioctl, + .compat_ioctl = compat_ptr_ioctl, + .release = rproc_cdev_release, +}; + +int rproc_char_device_add(struct rproc *rproc) +{ + int ret; + + cdev_init(&rproc->cdev, &rproc_fops); + rproc->cdev.owner = THIS_MODULE; + + rproc->dev.devt = MKDEV(MAJOR(rproc_major), rproc->index); + cdev_set_parent(&rproc->cdev, &rproc->dev.kobj); + ret = cdev_add(&rproc->cdev, rproc->dev.devt, 1); + if (ret < 0) + dev_err(&rproc->dev, "Failed to add char dev for %s\n", rproc->name); + + return ret; +} + +void rproc_char_device_remove(struct rproc *rproc) +{ + __unregister_chrdev(MAJOR(rproc->dev.devt), rproc->index, 1, "remoteproc"); +} + +void __init rproc_init_cdev(void) +{ + int ret; + + ret = alloc_chrdev_region(&rproc_major, 0, NUM_RPROC_DEVICES, "remoteproc"); + if (ret < 0) + pr_err("Failed to alloc rproc_cdev region, err %d\n", ret); +} diff --git a/drivers/remoteproc/remoteproc_internal.h b/drivers/remoteproc/remoteproc_internal.h index cd4176b033a3..c34002888d2c 100644 --- a/drivers/remoteproc/remoteproc_internal.h +++ b/drivers/remoteproc/remoteproc_internal.h @@ -53,6 +53,34 @@ void rproc_exit_sysfs(void); void rproc_coredump_cleanup(struct rproc *rproc); void rproc_coredump(struct rproc *rproc); +#ifdef CONFIG_REMOTEPROC_CDEV +void rproc_init_cdev(void); +void rproc_exit_cdev(void); +int rproc_char_device_add(struct rproc *rproc); +void rproc_char_device_remove(struct rproc *rproc); +#else +static inline void rproc_init_cdev(void) +{ +} + +static inline void rproc_exit_cdev(void) +{ +} + +/* + * The character device interface is an optional feature, if it is not enabled + * the function should not return an error. + */ +static inline int rproc_char_device_add(struct rproc *rproc) +{ + return 0; +} + +static inline void rproc_char_device_remove(struct rproc *rproc) +{ +} +#endif + void rproc_free_vring(struct rproc_vring *rvring); int rproc_alloc_vring(struct rproc_vdev *rvdev, int i); diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 0e8d2ff575b4..2fa68bf5aa4f 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -38,6 +38,7 @@ #include #include #include +#include #include #include #include @@ -509,6 +510,8 @@ struct rproc_dump_segment { * @autonomous: true if an external entity has booted the remote processor * @dump_segments: list of segments in the firmware * @nb_vdev: number of vdev currently handled by rproc + * @char_dev: character device of the rproc + * @cdev_put_on_release: flag to indicate if remoteproc should be shutdown on @char_dev release */ struct rproc { struct list_head node; @@ -546,6 +549,8 @@ struct rproc { int nb_vdev; u8 elf_class; u16 elf_machine; + struct cdev cdev; + bool cdev_put_on_release; }; /** diff --git a/include/uapi/linux/remoteproc_cdev.h b/include/uapi/linux/remoteproc_cdev.h new file mode 100644 index 000000000000..c43768e4b0dc --- /dev/null +++ b/include/uapi/linux/remoteproc_cdev.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * IOCTLs for Remoteproc's character device interface. + * + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _UAPI_REMOTEPROC_CDEV_H_ +#define _UAPI_REMOTEPROC_CDEV_H_ + +#include +#include + +#define RPROC_MAGIC 0xB7 + +/* + * The RPROC_SET_SHUTDOWN_ON_RELEASE ioctl allows to enable/disable the shutdown of a remote + * processor automatically when the controlling userpsace closes the char device interface. + * + * input parameter: integer + * 0 : disable automatic shutdown + * other : enable automatic shutdown + */ +#define RPROC_SET_SHUTDOWN_ON_RELEASE _IOW(RPROC_MAGIC, 1, __s32) + +/* + * The RPROC_GET_SHUTDOWN_ON_RELEASE ioctl gets information about whether the automatic shutdown of + * a remote processor is enabled or disabled when the controlling userspace closes the char device + * interface. + * + * output parameter: integer + * 0 : automatic shutdown disable + * other : automatic shutdown enable + */ +#define RPROC_GET_SHUTDOWN_ON_RELEASE _IOR(RPROC_MAGIC, 2, __s32) + +#endif From 62b8f9e99329c92286534d05dac9dc0a6e0ba0cf Mon Sep 17 00:00:00 2001 From: Siddharth Gupta Date: Wed, 29 Jul 2020 10:40:01 -0700 Subject: [PATCH 216/291] remoteproc: core: Register the character device interface Add the character device during rproc_add. This would create a character device node at /dev/remoteproc. Userspace applications can interact with the remote processor using this interface. Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Signed-off-by: Rishabh Bhatnagar Signed-off-by: Siddharth Gupta Link: https://lore.kernel.org/r/1596044401-22083-3-git-send-email-sidgup@codeaurora.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 277d3bf7a250..7f90eeea67e2 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1986,6 +1986,11 @@ int rproc_add(struct rproc *rproc) /* create debugfs entries */ rproc_create_debug_dir(rproc); + /* add char device for this remoteproc */ + ret = rproc_char_device_add(rproc); + if (ret < 0) + return ret; + /* * Remind ourselves the remote processor has been attached to rather * than booted by the remoteproc core. This is important because the @@ -2262,6 +2267,7 @@ int rproc_del(struct rproc *rproc) mutex_unlock(&rproc->lock); rproc_delete_debug_dir(rproc); + rproc_char_device_remove(rproc); /* the rproc is downref'ed as soon as it's removed from the klist */ mutex_lock(&rproc_list_mutex); @@ -2430,6 +2436,7 @@ static int __init remoteproc_init(void) { rproc_init_sysfs(); rproc_init_debugfs(); + rproc_init_cdev(); rproc_init_panic(); return 0; From 35efb0e1d5c60e334ea719586ff2509fde2e613b Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 28 Jul 2020 17:47:57 -0700 Subject: [PATCH 217/291] dt-bindings: hwlock: qcom: Remove invalid binding The Qualcomm hwlock is described in DeviceTree either directly on the mmio bus or split between a syscon and a mutex node, but as noted in [1] the latter is not valid DT, so remove any traces of this from the binding. [1] https://lore.kernel.org/r/CAL_JsqLa9GBtbgN6aL7AQ=A6V-YRtPgYqh6XgM2kpx532+r4Gg@mail.gmail.com/ Reviewed-by: Rob Herring Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200729004757.1901107-1-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- .../bindings/hwlock/qcom-hwspinlock.yaml | 25 +------------------ 1 file changed, 1 insertion(+), 24 deletions(-) diff --git a/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml index 88f975837588..1c7149f7d171 100644 --- a/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml +++ b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml @@ -25,37 +25,14 @@ properties: '#hwlock-cells': const: 1 - syscon: - $ref: "/schemas/types.yaml#/definitions/phandle-array" - description: - Should be a triple of phandle referencing the TCSR mutex syscon, offset - of first mutex within the syscon and stride between each mutex. - required: - compatible + - reg - '#hwlock-cells' -oneOf: - - required: - - reg - - required: - - syscon - additionalProperties: false examples: - - | - tcsr_mutex_block: syscon@fd484000 { - compatible = "syscon"; - reg = <0xfd484000 0x2000>; - }; - - hwlock { - compatible = "qcom,tcsr-mutex"; - syscon = <&tcsr_mutex_block 0 0x80>; - - #hwlock-cells = <1>; - }; - | tcsr_mutex: hwlock@1f40000 { compatible = "qcom,tcsr-mutex"; From 8875bbba97087bf4a677071723d04fc00730f1e7 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 06:34:49 -0400 Subject: [PATCH 218/291] virtio_balloon: fix sparse warning balloon uses virtio32_to_cpu instead of cpu_to_virtio32 to convert a native endian number to virtio. No practical difference but makes sparse warn. Fix it up. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck Acked-by: David Hildenbrand Reviewed-by: Cornelia Huck --- drivers/virtio/virtio_balloon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 54fd989f9353..8bc1704ffdf3 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -600,7 +600,7 @@ static int send_cmd_id_start(struct virtio_balloon *vb) while (virtqueue_get_buf(vq, &unused)) ; - vb->cmd_id_active = virtio32_to_cpu(vb->vdev, + vb->cmd_id_active = cpu_to_virtio32(vb->vdev, virtio_balloon_cmd_id_received(vb)); sg_init_one(&sg, &vb->cmd_id_active, sizeof(vb->cmd_id_active)); err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_active, GFP_KERNEL); From 5487196878bc926a1ee15069c13aa48b9a894fab Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 06:46:04 -0400 Subject: [PATCH 219/291] virtio_ring: sparse warning fixup virtio_store_mb was built with split ring in mind so it accepts __virtio16 arguments. Packed ring uses __le16 values, so sparse complains. It's just a store with some barriers so let's convert it to a macro, we don't loose too much type safety by doing that. Signed-off-by: Michael S. Tsirkin Acked-by: Cornelia Huck --- include/linux/virtio_ring.h | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 3dc70adfe5f5..b485b13fa50b 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -46,16 +46,15 @@ static inline void virtio_wmb(bool weak_barriers) dma_wmb(); } -static inline void virtio_store_mb(bool weak_barriers, - __virtio16 *p, __virtio16 v) -{ - if (weak_barriers) { - virt_store_mb(*p, v); - } else { - WRITE_ONCE(*p, v); - mb(); - } -} +#define virtio_store_mb(weak_barriers, p, v) \ +do { \ + if (weak_barriers) { \ + virt_store_mb(*p, v); \ + } else { \ + WRITE_ONCE(*p, v); \ + mb(); \ + } \ +} while (0) \ struct virtio_device; struct virtqueue; From a4235ec06acf05c58081700cda02dcd480d9e9cb Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 03:20:21 -0400 Subject: [PATCH 220/291] virtio: allow __virtioXX, __leXX in config space Currently all config space fields are of the type __uXX. This confuses people and some drivers (notably vdpa) access them using CPU endian-ness - which only works well for legacy or LE platforms. Update virtio_cread/virtio_cwrite macros to allow __virtioXX and __leXX field types. Follow-up patches will convert config space to use these types. Signed-off-by: Michael S. Tsirkin Acked-by: Cornelia Huck --- include/linux/virtio_config.h | 50 +++++++++++++++++++++++++++++++++-- 1 file changed, 48 insertions(+), 2 deletions(-) diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 3b4eae5ac5e3..64da491936f7 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -6,6 +6,7 @@ #include #include #include +#include #include struct irq_affinity; @@ -287,12 +288,57 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) return __cpu_to_virtio64(virtio_is_little_endian(vdev), val); } +/* + * Only the checker differentiates between __virtioXX and __uXX types. But we + * try to share as much code as we can with the regular GCC build. + */ +#if !defined(CONFIG_CC_IS_GCC) && !defined(__CHECKER__) + +/* Not a checker - we can keep things simple */ +#define __virtio_native_typeof(x) typeof(x) + +#else + +/* + * We build this out of a couple of helper macros in a vain attempt to + * help you keep your lunch down while reading it. + */ +#define __virtio_pick_value(x, type, then, otherwise) \ + __builtin_choose_expr(__same_type(x, type), then, otherwise) + +#define __virtio_pick_type(x, type, then, otherwise) \ + __virtio_pick_value(x, type, (then)0, otherwise) + +#define __virtio_pick_endian(x, x16, x32, x64, otherwise) \ + __virtio_pick_type(x, x16, __u16, \ + __virtio_pick_type(x, x32, __u32, \ + __virtio_pick_type(x, x64, __u64, \ + otherwise))) + +#define __virtio_native_typeof(x) typeof( \ + __virtio_pick_type(x, __u8, __u8, \ + __virtio_pick_endian(x, __virtio16, __virtio32, __virtio64, \ + __virtio_pick_endian(x, __le16, __le32, __le64, \ + __virtio_pick_endian(x, __u16, __u32, __u64, \ + /* No other type allowed */ \ + (void)0))))) + +#endif + +#define __virtio_native_type(structname, member) \ + __virtio_native_typeof(((structname*)0)->member) + +#define __virtio_typecheck(structname, member, val) \ + /* Must match the member's type, and be integer */ \ + typecheck(__virtio_native_type(structname, member), (val)) + + /* Config space accessors. */ #define virtio_cread(vdev, structname, member, ptr) \ do { \ might_sleep(); \ /* Must match the member's type, and be integer */ \ - if (!typecheck(typeof((((structname*)0)->member)), *(ptr))) \ + if (!__virtio_typecheck(structname, member, *(ptr))) \ (*ptr) = 1; \ \ switch (sizeof(*ptr)) { \ @@ -322,7 +368,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) do { \ might_sleep(); \ /* Must match the member's type, and be integer */ \ - if (!typecheck(typeof((((structname*)0)->member)), *(ptr))) \ + if (!__virtio_typecheck(structname, member, *(ptr))) \ BUG_ON((*ptr) == 1); \ \ switch (sizeof(*ptr)) { \ From cae19a6386c86dec8ec2810a96d7497a2eec8d38 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 221/291] virtio_9p: correct tags for config space fields Tag config space fields as having virtio endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_9p.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/virtio_9p.h b/include/uapi/linux/virtio_9p.h index 277c4ad44e84..441047432258 100644 --- a/include/uapi/linux/virtio_9p.h +++ b/include/uapi/linux/virtio_9p.h @@ -25,7 +25,7 @@ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ -#include +#include #include #include @@ -36,7 +36,7 @@ struct virtio_9p_config { /* length of the tag name */ - __u16 tag_len; + __virtio16 tag_len; /* non-NULL terminated tag name */ __u8 tag[0]; } __attribute__((packed)); From c73cb10cc4421baa669c1edd8211086280273216 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 222/291] virtio_balloon: correct tags for config space fields Tag config space fields as having little endian-ness. Note that balloon is special: LE even when using the legacy interface. Signed-off-by: Michael S. Tsirkin Acked-by: David Hildenbrand Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_balloon.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h index dc3e656470dd..ddaa45e723c4 100644 --- a/include/uapi/linux/virtio_balloon.h +++ b/include/uapi/linux/virtio_balloon.h @@ -45,20 +45,20 @@ #define VIRTIO_BALLOON_CMD_ID_DONE 1 struct virtio_balloon_config { /* Number of pages host wants Guest to give up. */ - __u32 num_pages; + __le32 num_pages; /* Number of pages we've actually got in balloon. */ - __u32 actual; + __le32 actual; /* * Free page hint command id, readonly by guest. * Was previously named free_page_report_cmd_id so we * need to carry that name for legacy support. */ union { - __u32 free_page_hint_cmd_id; - __u32 free_page_report_cmd_id; /* deprecated */ + __le32 free_page_hint_cmd_id; + __le32 free_page_report_cmd_id; /* deprecated */ }; /* Stores PAGE_POISON if page poisoning is in use */ - __u32 poison_val; + __le32 poison_val; }; #define VIRTIO_BALLOON_S_SWAP_IN 0 /* Amount of memory swapped in */ From 40e04c488bd6ab1859778d40bf9bb3ca294ab97b Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 223/291] virtio_blk: correct tags for config space fields Tag config space fields as having virtio endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck Reviewed-by: Stefano Garzarella Reviewed-by: Stefano Garzarella --- include/uapi/linux/virtio_blk.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h index 0f99d7b49ede..d888f013d9ff 100644 --- a/include/uapi/linux/virtio_blk.h +++ b/include/uapi/linux/virtio_blk.h @@ -57,20 +57,20 @@ struct virtio_blk_config { /* The capacity (in 512-byte sectors). */ - __u64 capacity; + __virtio64 capacity; /* The maximum segment size (if VIRTIO_BLK_F_SIZE_MAX) */ - __u32 size_max; + __virtio32 size_max; /* The maximum number of segments (if VIRTIO_BLK_F_SEG_MAX) */ - __u32 seg_max; + __virtio32 seg_max; /* geometry of the device (if VIRTIO_BLK_F_GEOMETRY) */ struct virtio_blk_geometry { - __u16 cylinders; + __virtio16 cylinders; __u8 heads; __u8 sectors; } geometry; /* block size of device (if VIRTIO_BLK_F_BLK_SIZE) */ - __u32 blk_size; + __virtio32 blk_size; /* the next 4 entries are guarded by VIRTIO_BLK_F_TOPOLOGY */ /* exponent for physical block per logical block. */ @@ -78,42 +78,42 @@ struct virtio_blk_config { /* alignment offset in logical blocks. */ __u8 alignment_offset; /* minimum I/O size without performance penalty in logical blocks. */ - __u16 min_io_size; + __virtio16 min_io_size; /* optimal sustained I/O size in logical blocks. */ - __u32 opt_io_size; + __virtio32 opt_io_size; /* writeback mode (if VIRTIO_BLK_F_CONFIG_WCE) */ __u8 wce; __u8 unused; /* number of vqs, only available when VIRTIO_BLK_F_MQ is set */ - __u16 num_queues; + __virtio16 num_queues; /* the next 3 entries are guarded by VIRTIO_BLK_F_DISCARD */ /* * The maximum discard sectors (in 512-byte sectors) for * one segment. */ - __u32 max_discard_sectors; + __virtio32 max_discard_sectors; /* * The maximum number of discard segments in a * discard command. */ - __u32 max_discard_seg; + __virtio32 max_discard_seg; /* Discard commands must be aligned to this number of sectors. */ - __u32 discard_sector_alignment; + __virtio32 discard_sector_alignment; /* the next 3 entries are guarded by VIRTIO_BLK_F_WRITE_ZEROES */ /* * The maximum number of write zeroes sectors (in 512-byte sectors) in * one segment. */ - __u32 max_write_zeroes_sectors; + __virtio32 max_write_zeroes_sectors; /* * The maximum number of segments in a write zeroes * command. */ - __u32 max_write_zeroes_seg; + __virtio32 max_write_zeroes_seg; /* * Set if a VIRTIO_BLK_T_WRITE_ZEROES request may result in the * deallocation of one or more of the sectors. From dbe2dc8c5838ef415620a4fe691570b062ab046f Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 224/291] virtio_console: correct tags for config space fields Tag config space fields as having virtio endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_console.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/uapi/linux/virtio_console.h b/include/uapi/linux/virtio_console.h index b7fb108c9310..7e6ec2ff0560 100644 --- a/include/uapi/linux/virtio_console.h +++ b/include/uapi/linux/virtio_console.h @@ -45,13 +45,13 @@ struct virtio_console_config { /* colums of the screens */ - __u16 cols; + __virtio16 cols; /* rows of the screens */ - __u16 rows; + __virtio16 rows; /* max. number of ports this device can hold */ - __u32 max_nr_ports; + __virtio32 max_nr_ports; /* emergency write register */ - __u32 emerg_wr; + __virtio32 emerg_wr; } __attribute__((packed)); /* From 24bcf35b695ef5228f3035eb979cc2de571d560b Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 225/291] virtio_crypto: correct tags for config space fields Since crypto is a modern-only device, tag config space fields as having little endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_crypto.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/include/uapi/linux/virtio_crypto.h b/include/uapi/linux/virtio_crypto.h index 50cdc8aebfcf..a03932f10565 100644 --- a/include/uapi/linux/virtio_crypto.h +++ b/include/uapi/linux/virtio_crypto.h @@ -414,33 +414,33 @@ struct virtio_crypto_op_data_req { struct virtio_crypto_config { /* See VIRTIO_CRYPTO_OP_* above */ - __u32 status; + __le32 status; /* * Maximum number of data queue */ - __u32 max_dataqueues; + __le32 max_dataqueues; /* * Specifies the services mask which the device support, * see VIRTIO_CRYPTO_SERVICE_* above */ - __u32 crypto_services; + __le32 crypto_services; /* Detailed algorithms mask */ - __u32 cipher_algo_l; - __u32 cipher_algo_h; - __u32 hash_algo; - __u32 mac_algo_l; - __u32 mac_algo_h; - __u32 aead_algo; + __le32 cipher_algo_l; + __le32 cipher_algo_h; + __le32 hash_algo; + __le32 mac_algo_l; + __le32 mac_algo_h; + __le32 aead_algo; /* Maximum length of cipher key */ - __u32 max_cipher_key_len; + __le32 max_cipher_key_len; /* Maximum length of authenticated key */ - __u32 max_auth_key_len; - __u32 reserve; + __le32 max_auth_key_len; + __le32 reserve; /* Maximum size of each crypto request's content */ - __u64 max_size; + __le64 max_size; }; struct virtio_crypto_inhdr { From fc4a1accbb4ef372bb55b7ab161cf88e3b631935 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 226/291] virtio_fs: correct tags for config space fields Since fs is a modern-only device, tag config space fields as having little endian-ness. Signed-off-by: Michael S. Tsirkin Acked-by: Vivek Goyal Acked-by: Vivek Goyal Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/virtio_fs.h b/include/uapi/linux/virtio_fs.h index b02eb2ac3d99..3056b6e9f8ce 100644 --- a/include/uapi/linux/virtio_fs.h +++ b/include/uapi/linux/virtio_fs.h @@ -13,7 +13,7 @@ struct virtio_fs_config { __u8 tag[36]; /* Number of request queues */ - __u32 num_request_queues; + __le32 num_request_queues; } __attribute__((packed)); #endif /* _UAPI_LINUX_VIRTIO_FS_H */ From f378444b7c97e39358de5d50d01fb0e92f259073 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 227/291] virtio_gpu: correct tags for config space fields Since gpu is a modern-only device, tag config space fields as having little endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_gpu.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index 0c85914d9369..ccbd174ef321 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -320,10 +320,10 @@ struct virtio_gpu_resp_edid { #define VIRTIO_GPU_EVENT_DISPLAY (1 << 0) struct virtio_gpu_config { - __u32 events_read; - __u32 events_clear; - __u32 num_scanouts; - __u32 num_capsets; + __le32 events_read; + __le32 events_clear; + __le32 num_scanouts; + __le32 num_capsets; }; /* simple formats for fbcon/X use */ From 924b59a6dfa85dc9eac4c7f2fe1857bba2cb2510 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 228/291] virtio_input: correct tags for config space fields Since this is a modern-only device, tag config space fields as having little endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Gerd Hoffmann Reviewed-by: Gerd Hoffmann Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_input.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/include/uapi/linux/virtio_input.h b/include/uapi/linux/virtio_input.h index a7fe5c8fb135..52084b1fb965 100644 --- a/include/uapi/linux/virtio_input.h +++ b/include/uapi/linux/virtio_input.h @@ -40,18 +40,18 @@ enum virtio_input_config_select { }; struct virtio_input_absinfo { - __u32 min; - __u32 max; - __u32 fuzz; - __u32 flat; - __u32 res; + __le32 min; + __le32 max; + __le32 fuzz; + __le32 flat; + __le32 res; }; struct virtio_input_devids { - __u16 bustype; - __u16 vendor; - __u16 product; - __u16 version; + __le16 bustype; + __le16 vendor; + __le16 product; + __le16 version; }; struct virtio_input_config { From 0ebcffcc2731682777bab19b51a512d8f31e1bdd Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 229/291] virtio_iommu: correct tags for config space fields Since this is a modern-only device, tag config space fields as having little endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Jean-Philippe Brucker Reviewed-by: Jean-Philippe Brucker Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_iommu.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/include/uapi/linux/virtio_iommu.h b/include/uapi/linux/virtio_iommu.h index 48e3c29223b5..237e36a280cb 100644 --- a/include/uapi/linux/virtio_iommu.h +++ b/include/uapi/linux/virtio_iommu.h @@ -18,24 +18,24 @@ #define VIRTIO_IOMMU_F_MMIO 5 struct virtio_iommu_range_64 { - __u64 start; - __u64 end; + __le64 start; + __le64 end; }; struct virtio_iommu_range_32 { - __u32 start; - __u32 end; + __le32 start; + __le32 end; }; struct virtio_iommu_config { /* Supported page sizes */ - __u64 page_size_mask; + __le64 page_size_mask; /* Supported IOVA range */ struct virtio_iommu_range_64 input_range; /* Max domain ID size */ struct virtio_iommu_range_32 domain_range; /* Probe buffer size */ - __u32 probe_size; + __le32 probe_size; }; /* Request types */ From 79268954424771185fb4ca304786dd561a272246 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 230/291] virtio_mem: correct tags for config space fields Since this is a modern-only device, tag config space fields as having little endian-ness. TODO: check other uses of __virtioXX types in this header, should probably be __leXX. Signed-off-by: Michael S. Tsirkin Acked-by: David Hildenbrand Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_mem.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h index a9ffe041843c..70e01c687d5e 100644 --- a/include/uapi/linux/virtio_mem.h +++ b/include/uapi/linux/virtio_mem.h @@ -185,27 +185,27 @@ struct virtio_mem_resp { struct virtio_mem_config { /* Block size and alignment. Cannot change. */ - __u64 block_size; + __le64 block_size; /* Valid with VIRTIO_MEM_F_ACPI_PXM. Cannot change. */ - __u16 node_id; + __le16 node_id; __u8 padding[6]; /* Start address of the memory region. Cannot change. */ - __u64 addr; + __le64 addr; /* Region size (maximum). Cannot change. */ - __u64 region_size; + __le64 region_size; /* * Currently usable region size. Can grow up to region_size. Can * shrink due to VIRTIO_MEM_REQ_UNPLUG_ALL (in which case no config * update will be sent). */ - __u64 usable_region_size; + __le64 usable_region_size; /* * Currently used size. Changes due to plug/unplug requests, but no * config updates will be sent. */ - __u64 plugged_size; + __le64 plugged_size; /* Requested size. New plug requests cannot exceed it. Can change. */ - __u64 requested_size; + __le64 requested_size; }; #endif /* _LINUX_VIRTIO_MEM_H */ From 577e677a785357542311a645eeb1756cd83988be Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 231/291] virtio_net: correct tags for config space fields Tag config space fields as having virtio endian-ness. Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_net.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 19d23e5baa4e..27d996f29dd1 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -87,19 +87,19 @@ struct virtio_net_config { /* The config defining mac address (if VIRTIO_NET_F_MAC) */ __u8 mac[ETH_ALEN]; /* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */ - __u16 status; + __virtio16 status; /* Maximum number of each of transmit and receive queues; * see VIRTIO_NET_F_MQ and VIRTIO_NET_CTRL_MQ. * Legal values are between 1 and 0x8000 */ - __u16 max_virtqueue_pairs; + __virtio16 max_virtqueue_pairs; /* Default maximum transmit unit advice */ - __u16 mtu; + __virtio16 mtu; /* * speed, in units of 1Mb. All values 0 to INT_MAX are legal. * Any other value stands for unknown. */ - __u32 speed; + __virtio32 speed; /* * 0x00 - half duplex * 0x01 - full duplex From a28feb855cc0ad452acd3dfe2b8f2841927da5f1 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 232/291] virtio_pmem: correct tags for config space fields Since this is a modern-only device, tag config space fields as having little endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_pmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h index b022787ffb94..d676b3620383 100644 --- a/include/uapi/linux/virtio_pmem.h +++ b/include/uapi/linux/virtio_pmem.h @@ -15,8 +15,8 @@ #include struct virtio_pmem_config { - __u64 start; - __u64 size; + __le64 start; + __le64 size; }; #define VIRTIO_PMEM_REQ_TYPE_FLUSH 0 From 965b5350514b597dc6347b733127e180844aeb43 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: [PATCH 233/291] virtio_scsi: correct tags for config space fields Tag config space fields as having virtio endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- drivers/scsi/virtio_scsi.c | 4 ++-- include/uapi/linux/virtio_scsi.h | 20 ++++++++++---------- 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 0e0910c5b942..c36aeb9a1330 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -746,14 +746,14 @@ static struct scsi_host_template virtscsi_host_template = { #define virtscsi_config_get(vdev, fld) \ ({ \ - typeof(((struct virtio_scsi_config *)0)->fld) __val; \ + __virtio_native_type(struct virtio_scsi_config, fld) __val; \ virtio_cread(vdev, struct virtio_scsi_config, fld, &__val); \ __val; \ }) #define virtscsi_config_set(vdev, fld, val) \ do { \ - typeof(((struct virtio_scsi_config *)0)->fld) __val = (val); \ + __virtio_native_type(struct virtio_scsi_config, fld) __val = (val); \ virtio_cwrite(vdev, struct virtio_scsi_config, fld, &__val); \ } while(0) diff --git a/include/uapi/linux/virtio_scsi.h b/include/uapi/linux/virtio_scsi.h index cc18ef8825c0..0abaae4027c0 100644 --- a/include/uapi/linux/virtio_scsi.h +++ b/include/uapi/linux/virtio_scsi.h @@ -103,16 +103,16 @@ struct virtio_scsi_event { } __attribute__((packed)); struct virtio_scsi_config { - __u32 num_queues; - __u32 seg_max; - __u32 max_sectors; - __u32 cmd_per_lun; - __u32 event_info_size; - __u32 sense_size; - __u32 cdb_size; - __u16 max_channel; - __u16 max_target; - __u32 max_lun; + __virtio32 num_queues; + __virtio32 seg_max; + __virtio32 max_sectors; + __virtio32 cmd_per_lun; + __virtio32 event_info_size; + __virtio32 sense_size; + __virtio32 cdb_size; + __virtio16 max_channel; + __virtio16 max_target; + __virtio32 max_lun; } __attribute__((packed)); /* Feature Bits */ From 4a04cfb0eb5e00432f9ff978f2b81bd1736e85db Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:55:52 -0400 Subject: [PATCH 234/291] virtio_config: disallow native type fields Transitional devices should all use __virtioXX types (and __leXX for fields not present in legacy devices). Modern ones should use __leXX. _uXX type would be a bug. Let's prevent that. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 64da491936f7..c68f58f3bf34 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -319,9 +319,8 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) __virtio_pick_type(x, __u8, __u8, \ __virtio_pick_endian(x, __virtio16, __virtio32, __virtio64, \ __virtio_pick_endian(x, __le16, __le32, __le64, \ - __virtio_pick_endian(x, __u16, __u32, __u64, \ - /* No other type allowed */ \ - (void)0))))) + /* No other type allowed */ \ + (void)0)))) #endif From 03bea764bf61c9f9918324bda7362616024386e8 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Sun, 12 Jul 2020 10:56:34 -0400 Subject: [PATCH 235/291] mlxbf-tmfifo: sparse tags for config access mlxbf-tmfifo accesses config space using native types - which works for it since the legacy virtio native types. This will break if it ever needs to support modern virtio, so with new tags previously introduced for virtio net config, sparse now warns for this in drivers. Since this is a legacy only device, fix it up using virtio_legacy_is_little_endian for now. No functional changes. Signed-off-by: Michael S. Tsirkin Acked-by: Cornelia Huck Acked-by: Andy Shevchenko Acked-by: Andy Shevchenko --- drivers/platform/mellanox/mlxbf-tmfifo.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c index 5739a9669b29..bbc4e71a16ff 100644 --- a/drivers/platform/mellanox/mlxbf-tmfifo.c +++ b/drivers/platform/mellanox/mlxbf-tmfifo.c @@ -625,7 +625,10 @@ static void mlxbf_tmfifo_rxtx_header(struct mlxbf_tmfifo_vring *vring, vdev_id = VIRTIO_ID_NET; hdr_len = sizeof(struct virtio_net_hdr); config = &fifo->vdev[vdev_id]->config.net; - if (ntohs(hdr.len) > config->mtu + + /* A legacy-only interface for now. */ + if (ntohs(hdr.len) > + __virtio16_to_cpu(virtio_legacy_is_little_endian(), + config->mtu) + MLXBF_TMFIFO_NET_L2_OVERHEAD) return; } else { @@ -1231,8 +1234,12 @@ static int mlxbf_tmfifo_probe(struct platform_device *pdev) /* Create the network vdev. */ memset(&net_config, 0, sizeof(net_config)); - net_config.mtu = ETH_DATA_LEN; - net_config.status = VIRTIO_NET_S_LINK_UP; + + /* A legacy-only interface for now. */ + net_config.mtu = __cpu_to_virtio16(virtio_legacy_is_little_endian(), + ETH_DATA_LEN); + net_config.status = __cpu_to_virtio16(virtio_legacy_is_little_endian(), + VIRTIO_NET_S_LINK_UP); mlxbf_tmfifo_get_cfg_mac(net_config.mac); rc = mlxbf_tmfifo_create_vdev(dev, fifo, VIRTIO_ID_NET, MLXBF_TMFIFO_NET_FEATURES, &net_config, From 452639a64ad880792652b6d20cc5c8dd4ecf27d9 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 27 Jul 2020 10:51:55 -0400 Subject: [PATCH 236/291] vdpa: make sure set_features is invoked for legacy Some legacy guests just assume features are 0 after reset. We detect that config space is accessed before features are set and set features to 0 automatically. Note: some legacy guests might not even access config space, if this is reported in the field we might need to catch a kick to handle these. Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 1 + include/linux/vdpa.h | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+) diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index de211ef3738c..7105265e4793 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -96,6 +96,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->dev.release = vdpa_release_dev; vdev->index = err; vdev->config = config; + vdev->features_valid = false; err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index); if (err) diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 239db794357c..29b8296f1414 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -33,12 +33,14 @@ struct vdpa_notification_area { * @dma_dev: the actual device that is performing DMA * @config: the configuration ops for this device. * @index: device index + * @features_valid: were features initialized? for legacy guests */ struct vdpa_device { struct device dev; struct device *dma_dev; const struct vdpa_config_ops *config; unsigned int index; + bool features_valid; }; /** @@ -266,4 +268,36 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev) { return vdev->dma_dev; } + +static inline void vdpa_reset(struct vdpa_device *vdev) +{ + const struct vdpa_config_ops *ops = vdev->config; + + vdev->features_valid = false; + ops->set_status(vdev, 0); +} + +static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) +{ + const struct vdpa_config_ops *ops = vdev->config; + + vdev->features_valid = true; + return ops->set_features(vdev, features); +} + + +static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset, + void *buf, unsigned int len) +{ + const struct vdpa_config_ops *ops = vdev->config; + + /* + * Config accesses aren't supposed to trigger before features are set. + * If it does happen we assume a legacy guest. + */ + if (!vdev->features_valid) + vdpa_set_features(vdev, 0); + ops->get_config(vdev, offset, buf, len); +} + #endif /* _LINUX_VDPA_H */ From 0d234007a5f8914ba94388b2ed93e0fd9b12e68c Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 27 Jul 2020 10:58:18 -0400 Subject: [PATCH 237/291] vhost/vdpa: switch to new helpers For new helpers handling legacy features to be effective, vhost needs to invoke them. Tie them in. Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vdpa.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 18869a35d408..3674404688f5 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -118,9 +118,8 @@ static irqreturn_t vhost_vdpa_config_cb(void *private) static void vhost_vdpa_reset(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; - const struct vdpa_config_ops *ops = vdpa->config; - ops->set_status(vdpa, 0); + vdpa_reset(vdpa); } static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp) @@ -196,7 +195,6 @@ static long vhost_vdpa_get_config(struct vhost_vdpa *v, struct vhost_vdpa_config __user *c) { struct vdpa_device *vdpa = v->vdpa; - const struct vdpa_config_ops *ops = vdpa->config; struct vhost_vdpa_config config; unsigned long size = offsetof(struct vhost_vdpa_config, buf); u8 *buf; @@ -209,7 +207,7 @@ static long vhost_vdpa_get_config(struct vhost_vdpa *v, if (!buf) return -ENOMEM; - ops->get_config(vdpa, config.off, buf, config.len); + vdpa_get_config(vdpa, config.off, buf, config.len); if (copy_to_user(c->buf, buf, config.len)) { kvfree(buf); @@ -282,7 +280,7 @@ static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep) if (features & ~vhost_vdpa_features[v->virtio_id]) return -EINVAL; - if (ops->set_features(vdpa, features)) + if (vdpa_set_features(vdpa, features)) return -EINVAL; return 0; From 639916734754b20fc34d956515a67b6a05776534 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 27 Jul 2020 10:59:02 -0400 Subject: [PATCH 238/291] virtio_vdpa: legacy features handling We normally expect vdpa to use the modern interface. However for consistency, let's use same APIs as vhost for legacy guests. Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_vdpa.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index c30eb55030be..4a9ddb44b2a7 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -57,9 +57,8 @@ static void virtio_vdpa_get(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len) { struct vdpa_device *vdpa = vd_get_vdpa(vdev); - const struct vdpa_config_ops *ops = vdpa->config; - ops->get_config(vdpa, offset, buf, len); + vdpa_get_config(vdpa, offset, buf, len); } static void virtio_vdpa_set(struct virtio_device *vdev, unsigned offset, @@ -101,9 +100,8 @@ static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status) static void virtio_vdpa_reset(struct virtio_device *vdev) { struct vdpa_device *vdpa = vd_get_vdpa(vdev); - const struct vdpa_config_ops *ops = vdpa->config; - return ops->set_status(vdpa, 0); + vdpa_reset(vdpa); } static bool virtio_vdpa_notify(struct virtqueue *vq) @@ -294,12 +292,11 @@ static u64 virtio_vdpa_get_features(struct virtio_device *vdev) static int virtio_vdpa_finalize_features(struct virtio_device *vdev) { struct vdpa_device *vdpa = vd_get_vdpa(vdev); - const struct vdpa_config_ops *ops = vdpa->config; /* Give virtio_ring a chance to accept features. */ vring_transport_features(vdev); - return ops->set_features(vdpa, vdev->features); + return vdpa_set_features(vdpa, vdev->features); } static const char *virtio_vdpa_bus_name(struct virtio_device *vdev) From 5d7d0f387ae1b933ff9771dc921f5e2f65271df9 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Sun, 12 Jul 2020 10:57:02 -0400 Subject: [PATCH 239/291] vdpa_sim: fix endian-ness of config space VDPA sim accesses config space as native endian - this is wrong since it's a modern device and actually uses LE. It only supports modern guests so we could punt and just force LE, but let's use the full virtio APIs since people tend to copy/paste code, and this is not data path anyway. Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 33 +++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index a9bc5e0fb353..b7d5727fde4c 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -72,6 +73,23 @@ struct vdpasim { u64 features; }; +/* TODO: cross-endian support */ +static inline bool vdpasim_is_little_endian(struct vdpasim *vdpasim) +{ + return virtio_legacy_is_little_endian() || + (vdpasim->features & (1ULL << VIRTIO_F_VERSION_1)); +} + +static inline u16 vdpasim16_to_cpu(struct vdpasim *vdpasim, __virtio16 val) +{ + return __virtio16_to_cpu(vdpasim_is_little_endian(vdpasim), val); +} + +static inline __virtio16 cpu_to_vdpasim16(struct vdpasim *vdpasim, u16 val) +{ + return __cpu_to_virtio16(vdpasim_is_little_endian(vdpasim), val); +} + static struct vdpasim *vdpasim_dev; static struct vdpasim *vdpa_to_sim(struct vdpa_device *vdpa) @@ -306,7 +324,6 @@ static const struct vdpa_config_ops vdpasim_net_config_ops; static struct vdpasim *vdpasim_create(void) { - struct virtio_net_config *config; struct vdpasim *vdpasim; struct device *dev; int ret = -ENOMEM; @@ -331,10 +348,7 @@ static struct vdpasim *vdpasim_create(void) if (!vdpasim->buffer) goto err_iommu; - config = &vdpasim->config; - config->mtu = 1500; - config->status = VIRTIO_NET_S_LINK_UP; - eth_random_addr(config->mac); + eth_random_addr(vdpasim->config.mac); vringh_set_iotlb(&vdpasim->vqs[0].vring, vdpasim->iommu); vringh_set_iotlb(&vdpasim->vqs[1].vring, vdpasim->iommu); @@ -448,6 +462,7 @@ static u64 vdpasim_get_features(struct vdpa_device *vdpa) static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct virtio_net_config *config = &vdpasim->config; /* DMA mapping must be done by driver */ if (!(features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) @@ -455,6 +470,14 @@ static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features) vdpasim->features = features & vdpasim_features; + /* We generally only know whether guest is using the legacy interface + * here, so generally that's the earliest we can set config fields. + * Note: We actually require VIRTIO_F_ACCESS_PLATFORM above which + * implies VIRTIO_F_VERSION_1, but let's not try to be clever here. + */ + + config->mtu = cpu_to_vdpasim16(vdpasim, 1500); + config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP); return 0; } From cacaf775c699e9e8473491197587535f1c10ac8f Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 30 Jul 2020 16:12:40 -0400 Subject: [PATCH 240/291] virtio_config: cread/write cleanup Use vars of the correct type instead of casting. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-) diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index c68f58f3bf34..5c3b02245ecd 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -444,53 +444,60 @@ static inline void virtio_cwrite8(struct virtio_device *vdev, static inline u16 virtio_cread16(struct virtio_device *vdev, unsigned int offset) { - u16 ret; + __virtio16 ret; might_sleep(); vdev->config->get(vdev, offset, &ret, sizeof(ret)); - return virtio16_to_cpu(vdev, (__force __virtio16)ret); + return virtio16_to_cpu(vdev, ret); } static inline void virtio_cwrite16(struct virtio_device *vdev, unsigned int offset, u16 val) { + __virtio16 v; + might_sleep(); - val = (__force u16)cpu_to_virtio16(vdev, val); - vdev->config->set(vdev, offset, &val, sizeof(val)); + v = cpu_to_virtio16(vdev, val); + vdev->config->set(vdev, offset, &v, sizeof(v)); } static inline u32 virtio_cread32(struct virtio_device *vdev, unsigned int offset) { - u32 ret; + __virtio32 ret; might_sleep(); vdev->config->get(vdev, offset, &ret, sizeof(ret)); - return virtio32_to_cpu(vdev, (__force __virtio32)ret); + return virtio32_to_cpu(vdev, ret); } static inline void virtio_cwrite32(struct virtio_device *vdev, unsigned int offset, u32 val) { + __virtio32 v; + might_sleep(); - val = (__force u32)cpu_to_virtio32(vdev, val); - vdev->config->set(vdev, offset, &val, sizeof(val)); + v = cpu_to_virtio32(vdev, val); + vdev->config->set(vdev, offset, &v, sizeof(v)); } static inline u64 virtio_cread64(struct virtio_device *vdev, unsigned int offset) { - u64 ret; + __virtio64 ret; + __virtio_cread_many(vdev, offset, &ret, 1, sizeof(ret)); - return virtio64_to_cpu(vdev, (__force __virtio64)ret); + return virtio64_to_cpu(vdev, ret); } static inline void virtio_cwrite64(struct virtio_device *vdev, unsigned int offset, u64 val) { + __virtio64 v; + might_sleep(); - val = (__force u64)cpu_to_virtio64(vdev, val); - vdev->config->set(vdev, offset, &val, sizeof(val)); + v = cpu_to_virtio64(vdev, val); + vdev->config->set(vdev, offset, &v, sizeof(v)); } /* Conditional config space accessors. */ From a5b90f2db8e0ef6504695cbd36a65fd8296338ee Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 3 Aug 2020 16:08:11 -0400 Subject: [PATCH 241/291] virtio_config: rewrite using _Generic Min compiler version has been raised, so that's ok now. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 163 ++++++++++++++++------------------ 1 file changed, 77 insertions(+), 86 deletions(-) diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 5c3b02245ecd..7fa000f02721 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -288,112 +288,103 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) return __cpu_to_virtio64(virtio_is_little_endian(vdev), val); } -/* - * Only the checker differentiates between __virtioXX and __uXX types. But we - * try to share as much code as we can with the regular GCC build. - */ -#if !defined(CONFIG_CC_IS_GCC) && !defined(__CHECKER__) +#define virtio_to_cpu(vdev, x) \ + _Generic((x), \ + __u8: (x), \ + __virtio16: virtio16_to_cpu((vdev), (x)), \ + __virtio32: virtio32_to_cpu((vdev), (x)), \ + __virtio64: virtio64_to_cpu((vdev), (x)), \ + /* + * Why define a default? checker can distinguish between + * e.g. __u16, __le16 and __virtio16, but GCC can't so + * attempts to define variants for both look like a duplicate + * variant to it. + */ \ + default: _Generic((x), \ + __u8: (x), \ + __le16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \ + __le32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \ + __le64: virtio64_to_cpu((vdev), (__force __virtio64)(x)), \ + default: _Generic((x), \ + __u8: (x), \ + __u16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \ + __u32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \ + __u64: virtio64_to_cpu((vdev), (__force __virtio64)(x)) \ + ) \ + ) \ + ) -/* Not a checker - we can keep things simple */ -#define __virtio_native_typeof(x) typeof(x) - -#else - -/* - * We build this out of a couple of helper macros in a vain attempt to - * help you keep your lunch down while reading it. - */ -#define __virtio_pick_value(x, type, then, otherwise) \ - __builtin_choose_expr(__same_type(x, type), then, otherwise) - -#define __virtio_pick_type(x, type, then, otherwise) \ - __virtio_pick_value(x, type, (then)0, otherwise) - -#define __virtio_pick_endian(x, x16, x32, x64, otherwise) \ - __virtio_pick_type(x, x16, __u16, \ - __virtio_pick_type(x, x32, __u32, \ - __virtio_pick_type(x, x64, __u64, \ - otherwise))) - -#define __virtio_native_typeof(x) typeof( \ - __virtio_pick_type(x, __u8, __u8, \ - __virtio_pick_endian(x, __virtio16, __virtio32, __virtio64, \ - __virtio_pick_endian(x, __le16, __le32, __le64, \ - /* No other type allowed */ \ - (void)0)))) - -#endif +#define cpu_to_virtio(vdev, x, m) \ + _Generic((m), \ + __u8: (x), \ + __virtio16: cpu_to_virtio16((vdev), (x)), \ + __virtio32: cpu_to_virtio32((vdev), (x)), \ + __virtio64: cpu_to_virtio64((vdev), (x)), \ + /* + * Why define a default? checker can distinguish between + * e.g. __u16, __le16 and __virtio16, but GCC can't so + * attempts to define variants for both look like a duplicate + * variant to it. + */ \ + default: _Generic((m), \ + __u8: (x), \ + __le16: (__force __le16)cpu_to_virtio16((vdev), (x)), \ + __le32: (__force __le32)cpu_to_virtio32((vdev), (x)), \ + __le64: (__force __le64)cpu_to_virtio64((vdev), (x)), \ + default: _Generic((m), \ + __u8: (x), \ + __u16: (__force __u16)cpu_to_virtio16((vdev), (x)), \ + __u32: (__force __u32)cpu_to_virtio32((vdev), (x)), \ + __u64: (__force __u64)cpu_to_virtio64((vdev), (x)) \ + ) \ + ) \ + ) #define __virtio_native_type(structname, member) \ - __virtio_native_typeof(((structname*)0)->member) - -#define __virtio_typecheck(structname, member, val) \ - /* Must match the member's type, and be integer */ \ - typecheck(__virtio_native_type(structname, member), (val)) - + typeof(virtio_to_cpu(NULL, ((structname*)0)->member)) /* Config space accessors. */ #define virtio_cread(vdev, structname, member, ptr) \ do { \ - might_sleep(); \ - /* Must match the member's type, and be integer */ \ - if (!__virtio_typecheck(structname, member, *(ptr))) \ - (*ptr) = 1; \ + typeof(((structname*)0)->member) virtio_cread_v; \ \ - switch (sizeof(*ptr)) { \ + might_sleep(); \ + /* Sanity check: must match the member's type */ \ + typecheck(typeof(virtio_to_cpu((vdev), virtio_cread_v)), *(ptr)); \ + \ + switch (sizeof(virtio_cread_v)) { \ case 1: \ - *(ptr) = virtio_cread8(vdev, \ - offsetof(structname, member)); \ - break; \ case 2: \ - *(ptr) = virtio_cread16(vdev, \ - offsetof(structname, member)); \ - break; \ case 4: \ - *(ptr) = virtio_cread32(vdev, \ - offsetof(structname, member)); \ - break; \ - case 8: \ - *(ptr) = virtio_cread64(vdev, \ - offsetof(structname, member)); \ + vdev->config->get((vdev), \ + offsetof(structname, member), \ + &virtio_cread_v, \ + sizeof(virtio_cread_v)); \ break; \ default: \ - BUG(); \ + __virtio_cread_many((vdev), \ + offsetof(structname, member), \ + &virtio_cread_v, \ + 1, \ + sizeof(virtio_cread_v)); \ + break; \ } \ + *(ptr) = virtio_to_cpu(vdev, virtio_cread_v); \ } while(0) /* Config space accessors. */ #define virtio_cwrite(vdev, structname, member, ptr) \ do { \ - might_sleep(); \ - /* Must match the member's type, and be integer */ \ - if (!__virtio_typecheck(structname, member, *(ptr))) \ - BUG_ON((*ptr) == 1); \ + typeof(((structname*)0)->member) virtio_cwrite_v = \ + cpu_to_virtio(vdev, *(ptr), ((structname*)0)->member); \ \ - switch (sizeof(*ptr)) { \ - case 1: \ - virtio_cwrite8(vdev, \ - offsetof(structname, member), \ - *(ptr)); \ - break; \ - case 2: \ - virtio_cwrite16(vdev, \ - offsetof(structname, member), \ - *(ptr)); \ - break; \ - case 4: \ - virtio_cwrite32(vdev, \ - offsetof(structname, member), \ - *(ptr)); \ - break; \ - case 8: \ - virtio_cwrite64(vdev, \ - offsetof(structname, member), \ - *(ptr)); \ - break; \ - default: \ - BUG(); \ - } \ + might_sleep(); \ + /* Sanity check: must match the member's type */ \ + typecheck(typeof(virtio_to_cpu((vdev), virtio_cwrite_v)), *(ptr)); \ + \ + vdev->config->set((vdev), offsetof(structname, member), \ + &virtio_cwrite_v, \ + sizeof(virtio_cwrite_v)); \ } while(0) /* Read @count fields, @bytes each. */ From 14191c15ab9d87e60d2ebbfbf6df83d546152af1 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:55:52 -0400 Subject: [PATCH 242/291] virtio_config: disallow native type fields (again) _Generic version allowed __uXX types but that is no longer necessary: Transitional devices should all use __virtioXX types (and __leXX for fields not present in the legacy devices). Modern ones should use __leXX. _uXX type would be a bug. Let's prevent that. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 7fa000f02721..441fd6dd42ab 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -304,13 +304,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) __u8: (x), \ __le16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \ __le32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \ - __le64: virtio64_to_cpu((vdev), (__force __virtio64)(x)), \ - default: _Generic((x), \ - __u8: (x), \ - __u16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \ - __u32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \ - __u64: virtio64_to_cpu((vdev), (__force __virtio64)(x)) \ - ) \ + __le64: virtio64_to_cpu((vdev), (__force __virtio64)(x)) \ ) \ ) @@ -330,13 +324,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) __u8: (x), \ __le16: (__force __le16)cpu_to_virtio16((vdev), (x)), \ __le32: (__force __le32)cpu_to_virtio32((vdev), (x)), \ - __le64: (__force __le64)cpu_to_virtio64((vdev), (x)), \ - default: _Generic((m), \ - __u8: (x), \ - __u16: (__force __u16)cpu_to_virtio16((vdev), (x)), \ - __u32: (__force __u32)cpu_to_virtio32((vdev), (x)), \ - __u64: (__force __u64)cpu_to_virtio64((vdev), (x)) \ - ) \ + __le64: (__force __le64)cpu_to_virtio64((vdev), (x)) \ ) \ ) From e598960ff5e511b76a0eb8dff25207d35c2442c8 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 4 Aug 2020 17:33:08 -0400 Subject: [PATCH 243/291] virtio_config: LE config space accessors To be used by modern code, as well as to handle LE only fields such as balloon. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 65 +++++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 441fd6dd42ab..5b5196fec899 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -375,6 +375,71 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) sizeof(virtio_cwrite_v)); \ } while(0) +/* + * Nothing virtio-specific about these, but let's worry about generalizing + * these later. + */ +#define virtio_le_to_cpu(x) \ + _Generic((x), \ + __u8: (x), \ + __le16: le16_to_cpu(x), \ + __le32: le32_to_cpu(x), \ + __le64: le64_to_cpu(x) \ + ) + +#define virtio_cpu_to_le(x, m) \ + _Generic((m), \ + __u8: (x), \ + __le16: cpu_to_le16(x), \ + __le32: cpu_to_le32(x), \ + __le64: cpu_to_le64(x) \ + ) + +/* LE (e.g. modern) Config space accessors. */ +#define virtio_cread_le(vdev, structname, member, ptr) \ + do { \ + typeof(((structname*)0)->member) virtio_cread_v; \ + \ + might_sleep(); \ + /* Sanity check: must match the member's type */ \ + typecheck(typeof(virtio_le_to_cpu(virtio_cread_v)), *(ptr)); \ + \ + switch (sizeof(virtio_cread_v)) { \ + case 1: \ + case 2: \ + case 4: \ + vdev->config->get((vdev), \ + offsetof(structname, member), \ + &virtio_cread_v, \ + sizeof(virtio_cread_v)); \ + break; \ + default: \ + __virtio_cread_many((vdev), \ + offsetof(structname, member), \ + &virtio_cread_v, \ + 1, \ + sizeof(virtio_cread_v)); \ + break; \ + } \ + *(ptr) = virtio_le_to_cpu(virtio_cread_v); \ + } while(0) + +/* Config space accessors. */ +#define virtio_cwrite_le(vdev, structname, member, ptr) \ + do { \ + typeof(((structname*)0)->member) virtio_cwrite_v = \ + virtio_cpu_to_le(*(ptr), ((structname*)0)->member); \ + \ + might_sleep(); \ + /* Sanity check: must match the member's type */ \ + typecheck(typeof(virtio_le_to_cpu(virtio_cwrite_v)), *(ptr)); \ + \ + vdev->config->set((vdev), offsetof(structname, member), \ + &virtio_cwrite_v, \ + sizeof(virtio_cwrite_v)); \ + } while(0) + + /* Read @count fields, @bytes each. */ static inline void __virtio_cread_many(struct virtio_device *vdev, unsigned int offset, From e3e7994d53082e48d2a6a248376683d3be3dff9d Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 4 Aug 2020 18:02:39 -0400 Subject: [PATCH 244/291] virtio_caif: correct tags for config space fields Tag config space fields as having virtio endian-ness. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_caif.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/virtio_caif.h b/include/linux/virtio_caif.h index 5d2d3124ca3d..ea722479510c 100644 --- a/include/linux/virtio_caif.h +++ b/include/linux/virtio_caif.h @@ -11,9 +11,9 @@ #include struct virtio_caif_transf_config { - u16 headroom; - u16 tailroom; - u32 mtu; + __virtio16 headroom; + __virtio16 tailroom; + __virtio32 mtu; u8 reserved[4]; }; From 035ce4210be1257dd417785ff7818b5c0f2205fb Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 09:17:38 -0400 Subject: [PATCH 245/291] virtio_config: add virtio_cread_le_feature Mirrors virtio_cread_feature but for LE fields. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 5b5196fec899..cc7a2b1fd7b2 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -555,4 +555,14 @@ static inline void virtio_cwrite64(struct virtio_device *vdev, _r; \ }) +/* Conditional config space accessors. */ +#define virtio_cread_le_feature(vdev, fbit, structname, member, ptr) \ + ({ \ + int _r = 0; \ + if (!virtio_has_feature(vdev, fbit)) \ + _r = -ENOENT; \ + else \ + virtio_cread_le((vdev), structname, member, ptr); \ + _r; \ + }) #endif /* _LINUX_VIRTIO_CONFIG_H */ From 805769d7c0ddc4dd07a35f81c8b7a0a20f90dd05 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 4 Aug 2020 17:51:35 -0400 Subject: [PATCH 246/291] virtio_balloon: use LE config space accesses Balloon is LE, it's cleaner to access it as such directly. Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_balloon.c | 26 +++++++++----------------- 1 file changed, 9 insertions(+), 17 deletions(-) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 8bc1704ffdf3..31cc97f2f515 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -398,12 +398,9 @@ static inline s64 towards_target(struct virtio_balloon *vb) s64 target; u32 num_pages; - virtio_cread(vb->vdev, struct virtio_balloon_config, num_pages, - &num_pages); - /* Legacy balloon config space is LE, unlike all other devices. */ - if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1)) - num_pages = le32_to_cpu((__force __le32)num_pages); + virtio_cread_le(vb->vdev, struct virtio_balloon_config, num_pages, + &num_pages); target = num_pages; return target - vb->num_pages; @@ -462,11 +459,8 @@ static void update_balloon_size(struct virtio_balloon *vb) u32 actual = vb->num_pages; /* Legacy balloon config space is LE, unlike all other devices. */ - if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1)) - actual = (__force u32)cpu_to_le32(actual); - - virtio_cwrite(vb->vdev, struct virtio_balloon_config, actual, - &actual); + virtio_cwrite_le(vb->vdev, struct virtio_balloon_config, actual, + &actual); } static void update_balloon_stats_func(struct work_struct *work) @@ -579,12 +573,10 @@ static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb) { if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID, &vb->config_read_bitmap)) { - virtio_cread(vb->vdev, struct virtio_balloon_config, - free_page_hint_cmd_id, - &vb->cmd_id_received_cache); /* Legacy balloon config space is LE, unlike all other devices. */ - if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1)) - vb->cmd_id_received_cache = le32_to_cpu((__force __le32)vb->cmd_id_received_cache); + virtio_cread_le(vb->vdev, struct virtio_balloon_config, + free_page_hint_cmd_id, + &vb->cmd_id_received_cache); } return vb->cmd_id_received_cache; @@ -987,8 +979,8 @@ static int virtballoon_probe(struct virtio_device *vdev) if (!want_init_on_free()) memset(&poison_val, PAGE_POISON, sizeof(poison_val)); - virtio_cwrite(vb->vdev, struct virtio_balloon_config, - poison_val, &poison_val); + virtio_cwrite_le(vb->vdev, struct virtio_balloon_config, + poison_val, &poison_val); } vb->pr_dev_info.report = virtballoon_free_page_report; From b025584098e621d88894d28e80af686958e273af Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 05:39:36 -0400 Subject: [PATCH 247/291] virtio_input: convert to LE accessors Virtio input is modern-only. Use LE accessors for config space. Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_input.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c index efaf65b0f42d..877b2ea3ed05 100644 --- a/drivers/virtio/virtio_input.c +++ b/drivers/virtio/virtio_input.c @@ -113,9 +113,9 @@ static u8 virtinput_cfg_select(struct virtio_input *vi, { u8 size; - virtio_cwrite(vi->vdev, struct virtio_input_config, select, &select); - virtio_cwrite(vi->vdev, struct virtio_input_config, subsel, &subsel); - virtio_cread(vi->vdev, struct virtio_input_config, size, &size); + virtio_cwrite_le(vi->vdev, struct virtio_input_config, select, &select); + virtio_cwrite_le(vi->vdev, struct virtio_input_config, subsel, &subsel); + virtio_cread_le(vi->vdev, struct virtio_input_config, size, &size); return size; } @@ -158,11 +158,11 @@ static void virtinput_cfg_abs(struct virtio_input *vi, int abs) u32 mi, ma, re, fu, fl; virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ABS_INFO, abs); - virtio_cread(vi->vdev, struct virtio_input_config, u.abs.min, &mi); - virtio_cread(vi->vdev, struct virtio_input_config, u.abs.max, &ma); - virtio_cread(vi->vdev, struct virtio_input_config, u.abs.res, &re); - virtio_cread(vi->vdev, struct virtio_input_config, u.abs.fuzz, &fu); - virtio_cread(vi->vdev, struct virtio_input_config, u.abs.flat, &fl); + virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.min, &mi); + virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.max, &ma); + virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.res, &re); + virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.fuzz, &fu); + virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.flat, &fl); input_set_abs_params(vi->idev, abs, mi, ma, fu, fl); input_abs_set_res(vi->idev, abs, re); } @@ -244,14 +244,14 @@ static int virtinput_probe(struct virtio_device *vdev) size = virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ID_DEVIDS, 0); if (size >= sizeof(struct virtio_input_devids)) { - virtio_cread(vi->vdev, struct virtio_input_config, - u.ids.bustype, &vi->idev->id.bustype); - virtio_cread(vi->vdev, struct virtio_input_config, - u.ids.vendor, &vi->idev->id.vendor); - virtio_cread(vi->vdev, struct virtio_input_config, - u.ids.product, &vi->idev->id.product); - virtio_cread(vi->vdev, struct virtio_input_config, - u.ids.version, &vi->idev->id.version); + virtio_cread_le(vi->vdev, struct virtio_input_config, + u.ids.bustype, &vi->idev->id.bustype); + virtio_cread_le(vi->vdev, struct virtio_input_config, + u.ids.vendor, &vi->idev->id.vendor); + virtio_cread_le(vi->vdev, struct virtio_input_config, + u.ids.product, &vi->idev->id.product); + virtio_cread_le(vi->vdev, struct virtio_input_config, + u.ids.version, &vi->idev->id.version); } else { vi->idev->id.bustype = BUS_VIRTUAL; } From 2c0349ec1a8ee6f20eb164a3a691bf661043fd24 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 05:39:36 -0400 Subject: [PATCH 248/291] virtio_fs: convert to LE accessors Virtio fs is modern-only. Use LE accessors for config space. Signed-off-by: Michael S. Tsirkin --- fs/fuse/virtio_fs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 4c4ef5d69298..104f35de5270 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -606,8 +606,8 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev, unsigned int i; int ret = 0; - virtio_cread(vdev, struct virtio_fs_config, num_request_queues, - &fs->num_request_queues); + virtio_cread_le(vdev, struct virtio_fs_config, num_request_queues, + &fs->num_request_queues); if (fs->num_request_queues == 0) return -EINVAL; From b13a54070cea06d122b3bdc56e5ce024fff4d2d2 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 05:39:36 -0400 Subject: [PATCH 249/291] virtio_crypto: convert to LE accessors Virtio crypto is modern-only. Use LE accessors for config space. Signed-off-by: Michael S. Tsirkin --- drivers/crypto/virtio/virtio_crypto_core.c | 46 +++++++++++----------- 1 file changed, 23 insertions(+), 23 deletions(-) diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c index c8a962c62663..aeecce27fe8f 100644 --- a/drivers/crypto/virtio/virtio_crypto_core.c +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -204,8 +204,8 @@ static int virtcrypto_update_status(struct virtio_crypto *vcrypto) u32 status; int err; - virtio_cread(vcrypto->vdev, - struct virtio_crypto_config, status, &status); + virtio_cread_le(vcrypto->vdev, + struct virtio_crypto_config, status, &status); /* * Unknown status bits would be a host error and the driver @@ -323,31 +323,31 @@ static int virtcrypto_probe(struct virtio_device *vdev) if (!vcrypto) return -ENOMEM; - virtio_cread(vdev, struct virtio_crypto_config, + virtio_cread_le(vdev, struct virtio_crypto_config, max_dataqueues, &max_data_queues); if (max_data_queues < 1) max_data_queues = 1; - virtio_cread(vdev, struct virtio_crypto_config, - max_cipher_key_len, &max_cipher_key_len); - virtio_cread(vdev, struct virtio_crypto_config, - max_auth_key_len, &max_auth_key_len); - virtio_cread(vdev, struct virtio_crypto_config, - max_size, &max_size); - virtio_cread(vdev, struct virtio_crypto_config, - crypto_services, &crypto_services); - virtio_cread(vdev, struct virtio_crypto_config, - cipher_algo_l, &cipher_algo_l); - virtio_cread(vdev, struct virtio_crypto_config, - cipher_algo_h, &cipher_algo_h); - virtio_cread(vdev, struct virtio_crypto_config, - hash_algo, &hash_algo); - virtio_cread(vdev, struct virtio_crypto_config, - mac_algo_l, &mac_algo_l); - virtio_cread(vdev, struct virtio_crypto_config, - mac_algo_h, &mac_algo_h); - virtio_cread(vdev, struct virtio_crypto_config, - aead_algo, &aead_algo); + virtio_cread_le(vdev, struct virtio_crypto_config, + max_cipher_key_len, &max_cipher_key_len); + virtio_cread_le(vdev, struct virtio_crypto_config, + max_auth_key_len, &max_auth_key_len); + virtio_cread_le(vdev, struct virtio_crypto_config, + max_size, &max_size); + virtio_cread_le(vdev, struct virtio_crypto_config, + crypto_services, &crypto_services); + virtio_cread_le(vdev, struct virtio_crypto_config, + cipher_algo_l, &cipher_algo_l); + virtio_cread_le(vdev, struct virtio_crypto_config, + cipher_algo_h, &cipher_algo_h); + virtio_cread_le(vdev, struct virtio_crypto_config, + hash_algo, &hash_algo); + virtio_cread_le(vdev, struct virtio_crypto_config, + mac_algo_l, &mac_algo_l); + virtio_cread_le(vdev, struct virtio_crypto_config, + mac_algo_h, &mac_algo_h); + virtio_cread_le(vdev, struct virtio_crypto_config, + aead_algo, &aead_algo); /* Add virtio crypto device to global table */ err = virtcrypto_devmgr_add_dev(vcrypto); From 02e715b7fadb5674e94b71de6424a07f6d4d493f Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 05:39:36 -0400 Subject: [PATCH 250/291] virtio_pmem: convert to LE accessors Virtio pmem is modern-only. Use LE accessors for config space. Signed-off-by: Michael S. Tsirkin --- drivers/nvdimm/virtio_pmem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c index 5e3d07b47e0c..726c7354d465 100644 --- a/drivers/nvdimm/virtio_pmem.c +++ b/drivers/nvdimm/virtio_pmem.c @@ -58,9 +58,9 @@ static int virtio_pmem_probe(struct virtio_device *vdev) goto out_err; } - virtio_cread(vpmem->vdev, struct virtio_pmem_config, + virtio_cread_le(vpmem->vdev, struct virtio_pmem_config, start, &vpmem->start); - virtio_cread(vpmem->vdev, struct virtio_pmem_config, + virtio_cread_le(vpmem->vdev, struct virtio_pmem_config, size, &vpmem->size); res.start = vpmem->start; From 115a71d8045d8571fb05df45088837621510ba57 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 05:39:36 -0400 Subject: [PATCH 251/291] drm/virtio: convert to LE accessors Virtgpu is modern-only. Use LE accessors for config space. Signed-off-by: Michael S. Tsirkin --- drivers/gpu/drm/virtio/virtgpu_kms.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index 0a5c8cf409fb..4d944a0dff3e 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -39,8 +39,8 @@ static void virtio_gpu_config_changed_work_func(struct work_struct *work) u32 events_read, events_clear = 0; /* read the config space */ - virtio_cread(vgdev->vdev, struct virtio_gpu_config, - events_read, &events_read); + virtio_cread_le(vgdev->vdev, struct virtio_gpu_config, + events_read, &events_read); if (events_read & VIRTIO_GPU_EVENT_DISPLAY) { if (vgdev->has_edid) virtio_gpu_cmd_get_edids(vgdev); @@ -49,8 +49,8 @@ static void virtio_gpu_config_changed_work_func(struct work_struct *work) drm_helper_hpd_irq_event(vgdev->ddev); events_clear |= VIRTIO_GPU_EVENT_DISPLAY; } - virtio_cwrite(vgdev->vdev, struct virtio_gpu_config, - events_clear, &events_clear); + virtio_cwrite_le(vgdev->vdev, struct virtio_gpu_config, + events_clear, &events_clear); } static void virtio_gpu_init_vq(struct virtio_gpu_queue *vgvq, @@ -165,8 +165,8 @@ int virtio_gpu_init(struct drm_device *dev) } /* get display info */ - virtio_cread(vgdev->vdev, struct virtio_gpu_config, - num_scanouts, &num_scanouts); + virtio_cread_le(vgdev->vdev, struct virtio_gpu_config, + num_scanouts, &num_scanouts); vgdev->num_scanouts = min_t(uint32_t, num_scanouts, VIRTIO_GPU_MAX_SCANOUTS); if (!vgdev->num_scanouts) { @@ -176,8 +176,8 @@ int virtio_gpu_init(struct drm_device *dev) } DRM_INFO("number of scanouts: %d\n", num_scanouts); - virtio_cread(vgdev->vdev, struct virtio_gpu_config, - num_capsets, &num_capsets); + virtio_cread_le(vgdev->vdev, struct virtio_gpu_config, + num_capsets, &num_capsets); DRM_INFO("number of cap sets: %d\n", num_capsets); virtio_gpu_modeset_init(vgdev); From 99e0d0488ba6a03c493fef5492696cdee07457ec Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 05:39:36 -0400 Subject: [PATCH 252/291] virtio_mem: convert to LE accessors Virtio mem is modern-only. Use LE accessors for config space. Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_mem.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index f26f5f64ae82..c08512fcea90 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -1530,21 +1530,21 @@ static void virtio_mem_refresh_config(struct virtio_mem *vm) uint64_t new_plugged_size, usable_region_size, end_addr; /* the plugged_size is just a reflection of what _we_ did previously */ - virtio_cread(vm->vdev, struct virtio_mem_config, plugged_size, - &new_plugged_size); + virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size, + &new_plugged_size); if (WARN_ON_ONCE(new_plugged_size != vm->plugged_size)) vm->plugged_size = new_plugged_size; /* calculate the last usable memory block id */ - virtio_cread(vm->vdev, struct virtio_mem_config, - usable_region_size, &usable_region_size); + virtio_cread_le(vm->vdev, struct virtio_mem_config, + usable_region_size, &usable_region_size); end_addr = vm->addr + usable_region_size; end_addr = min(end_addr, phys_limit); vm->last_usable_mb_id = virtio_mem_phys_to_mb_id(end_addr) - 1; /* see if there is a request to change the size */ - virtio_cread(vm->vdev, struct virtio_mem_config, requested_size, - &vm->requested_size); + virtio_cread_le(vm->vdev, struct virtio_mem_config, requested_size, + &vm->requested_size); dev_info(&vm->vdev->dev, "plugged size: 0x%llx", vm->plugged_size); dev_info(&vm->vdev->dev, "requested size: 0x%llx", vm->requested_size); @@ -1677,16 +1677,16 @@ static int virtio_mem_init(struct virtio_mem *vm) } /* Fetch all properties that can't change. */ - virtio_cread(vm->vdev, struct virtio_mem_config, plugged_size, - &vm->plugged_size); - virtio_cread(vm->vdev, struct virtio_mem_config, block_size, - &vm->device_block_size); - virtio_cread(vm->vdev, struct virtio_mem_config, node_id, - &node_id); + virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size, + &vm->plugged_size); + virtio_cread_le(vm->vdev, struct virtio_mem_config, block_size, + &vm->device_block_size); + virtio_cread_le(vm->vdev, struct virtio_mem_config, node_id, + &node_id); vm->nid = virtio_mem_translate_node_id(vm, node_id); - virtio_cread(vm->vdev, struct virtio_mem_config, addr, &vm->addr); - virtio_cread(vm->vdev, struct virtio_mem_config, region_size, - &vm->region_size); + virtio_cread_le(vm->vdev, struct virtio_mem_config, addr, &vm->addr); + virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size, + &vm->region_size); /* * We always hotplug memory in memory block granularity. This way, From d83c67c4a669a4b396239c338bef802cae72e648 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 05:39:36 -0400 Subject: [PATCH 253/291] virtio-iommu: convert to LE accessors Virtio iommu is modern-only. Use LE accessors for config space. Signed-off-by: Michael S. Tsirkin --- drivers/iommu/virtio-iommu.c | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index f6f07489a9aa..b4da396cce60 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -1010,8 +1010,8 @@ static int viommu_probe(struct virtio_device *vdev) if (ret) return ret; - virtio_cread(vdev, struct virtio_iommu_config, page_size_mask, - &viommu->pgsize_bitmap); + virtio_cread_le(vdev, struct virtio_iommu_config, page_size_mask, + &viommu->pgsize_bitmap); if (!viommu->pgsize_bitmap) { ret = -EINVAL; @@ -1022,25 +1022,25 @@ static int viommu_probe(struct virtio_device *vdev) viommu->last_domain = ~0U; /* Optional features */ - virtio_cread_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE, - struct virtio_iommu_config, input_range.start, - &input_start); + virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE, + struct virtio_iommu_config, input_range.start, + &input_start); - virtio_cread_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE, - struct virtio_iommu_config, input_range.end, - &input_end); + virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE, + struct virtio_iommu_config, input_range.end, + &input_end); - virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE, - struct virtio_iommu_config, domain_range.start, - &viommu->first_domain); + virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE, + struct virtio_iommu_config, domain_range.start, + &viommu->first_domain); - virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE, - struct virtio_iommu_config, domain_range.end, - &viommu->last_domain); + virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE, + struct virtio_iommu_config, domain_range.end, + &viommu->last_domain); - virtio_cread_feature(vdev, VIRTIO_IOMMU_F_PROBE, - struct virtio_iommu_config, probe_size, - &viommu->probe_size); + virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_PROBE, + struct virtio_iommu_config, probe_size, + &viommu->probe_size); viommu->geometry = (struct iommu_domain_geometry) { .aperture_start = input_start, From 83eb9db95eb453f1db651909ad4598c3d44ef1e1 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 07:29:12 -0400 Subject: [PATCH 254/291] virtio_config: drop LE option from config space All drivers now use virtio_cread/write_le for LE config space fields. Drop LE option from virtio_cread/write, only leaving the option to access transitional fields. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 28 ++-------------------------- 1 file changed, 2 insertions(+), 26 deletions(-) diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index cc7a2b1fd7b2..ecb166c824bb 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -293,19 +293,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) __u8: (x), \ __virtio16: virtio16_to_cpu((vdev), (x)), \ __virtio32: virtio32_to_cpu((vdev), (x)), \ - __virtio64: virtio64_to_cpu((vdev), (x)), \ - /* - * Why define a default? checker can distinguish between - * e.g. __u16, __le16 and __virtio16, but GCC can't so - * attempts to define variants for both look like a duplicate - * variant to it. - */ \ - default: _Generic((x), \ - __u8: (x), \ - __le16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \ - __le32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \ - __le64: virtio64_to_cpu((vdev), (__force __virtio64)(x)) \ - ) \ + __virtio64: virtio64_to_cpu((vdev), (x)) \ ) #define cpu_to_virtio(vdev, x, m) \ @@ -313,19 +301,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) __u8: (x), \ __virtio16: cpu_to_virtio16((vdev), (x)), \ __virtio32: cpu_to_virtio32((vdev), (x)), \ - __virtio64: cpu_to_virtio64((vdev), (x)), \ - /* - * Why define a default? checker can distinguish between - * e.g. __u16, __le16 and __virtio16, but GCC can't so - * attempts to define variants for both look like a duplicate - * variant to it. - */ \ - default: _Generic((m), \ - __u8: (x), \ - __le16: (__force __le16)cpu_to_virtio16((vdev), (x)), \ - __le32: (__force __le32)cpu_to_virtio32((vdev), (x)), \ - __le64: (__force __le64)cpu_to_virtio64((vdev), (x)) \ - ) \ + __virtio64: cpu_to_virtio64((vdev), (x)) \ ) #define __virtio_native_type(structname, member) \ From 64ffa39dc860fb9772225c694353f73eca5801c6 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 05:39:36 -0400 Subject: [PATCH 255/291] virtio_net: use LE accessors for speed/duplex Speed and duplex config fields depend on VIRTIO_NET_F_SPEED_DUPLEX which being 63>31 depends on VIRTIO_F_VERSION_1. Accordingly, use LE accessors for these fields. Reported-by: Cornelia Huck Signed-off-by: Michael S. Tsirkin --- drivers/net/virtio_net.c | 9 +++++---- include/uapi/linux/virtio_net.h | 2 +- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index ba38765dc490..0934b1ec5320 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2264,12 +2264,13 @@ static void virtnet_update_settings(struct virtnet_info *vi) if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX)) return; - speed = virtio_cread32(vi->vdev, offsetof(struct virtio_net_config, - speed)); + virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed); + if (ethtool_validate_speed(speed)) vi->speed = speed; - duplex = virtio_cread8(vi->vdev, offsetof(struct virtio_net_config, - duplex)); + + virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex); + if (ethtool_validate_duplex(duplex)) vi->duplex = duplex; } diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 27d996f29dd1..3f55a4215f11 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -99,7 +99,7 @@ struct virtio_net_config { * speed, in units of 1Mb. All values 0 to INT_MAX are legal. * Any other value stands for unknown. */ - __virtio32 speed; + __le32 speed; /* * 0x00 - half duplex * 0x01 - full duplex From 481a0d7422db26fb63e2d64f0652667a5c6d0f3e Mon Sep 17 00:00:00 2001 From: Mao Wenan Date: Sun, 2 Aug 2020 15:44:09 +0800 Subject: [PATCH 256/291] virtio_ring: Avoid loop when vq is broken in virtqueue_poll The loop may exist if vq->broken is true, virtqueue_get_buf_ctx_packed or virtqueue_get_buf_ctx_split will return NULL, so virtnet_poll will reschedule napi to receive packet, it will lead cpu usage(si) to 100%. call trace as below: virtnet_poll virtnet_receive virtqueue_get_buf_ctx virtqueue_get_buf_ctx_packed virtqueue_get_buf_ctx_split virtqueue_napi_complete virtqueue_poll //return true virtqueue_napi_schedule //it will reschedule napi to fix this, return false if vq is broken in virtqueue_poll. Signed-off-by: Mao Wenan Acked-by: Michael S. Tsirkin Link: https://lore.kernel.org/r/1596354249-96204-1-git-send-email-wenan.mao@linux.alibaba.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/virtio/virtio_ring.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 34253cb69cb8..7d4bc9eb7fc5 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -1960,6 +1960,9 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx) { struct vring_virtqueue *vq = to_vvq(_vq); + if (unlikely(vq->broken)) + return false; + virtio_mb(vq->weak_barriers); return vq->packed_ring ? virtqueue_poll_packed(_vq, last_used_idx) : virtqueue_poll_split(_vq, last_used_idx); From 6234f80574d7569444d8718355fa2838e92b158b Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Mon, 20 Jul 2020 16:50:43 +0800 Subject: [PATCH 257/291] vhost: vdpa: remove per device feature whitelist We used to have a per device feature whitelist to filter out the unsupported virtio features. But this seems unnecessary since: - the main idea behind feature whitelist is to block control vq feature until we finalize the control virtqueue API. But the current vhost-vDPA uAPI is sufficient to support control virtqueue. For device that has hardware control virtqueue, the vDPA device driver can just setup the hardware virtqueue and let userspace to use hardware virtqueue directly. For device that doesn't have a control virtqueue, the vDPA device driver need to use e.g vringh to emulate a software control virtqueue. - we don't do it in virtio-vDPA driver So remove this limitation. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20200720085043.16485-1-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vdpa.c | 37 ------------------------------------- 1 file changed, 37 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 3674404688f5..210f213a028b 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -26,35 +26,6 @@ #include "vhost.h" -enum { - VHOST_VDPA_FEATURES = - (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) | - (1ULL << VIRTIO_F_ANY_LAYOUT) | - (1ULL << VIRTIO_F_VERSION_1) | - (1ULL << VIRTIO_F_ACCESS_PLATFORM) | - (1ULL << VIRTIO_F_RING_PACKED) | - (1ULL << VIRTIO_F_ORDER_PLATFORM) | - (1ULL << VIRTIO_RING_F_INDIRECT_DESC) | - (1ULL << VIRTIO_RING_F_EVENT_IDX), - - VHOST_VDPA_NET_FEATURES = VHOST_VDPA_FEATURES | - (1ULL << VIRTIO_NET_F_CSUM) | - (1ULL << VIRTIO_NET_F_GUEST_CSUM) | - (1ULL << VIRTIO_NET_F_MTU) | - (1ULL << VIRTIO_NET_F_MAC) | - (1ULL << VIRTIO_NET_F_GUEST_TSO4) | - (1ULL << VIRTIO_NET_F_GUEST_TSO6) | - (1ULL << VIRTIO_NET_F_GUEST_ECN) | - (1ULL << VIRTIO_NET_F_GUEST_UFO) | - (1ULL << VIRTIO_NET_F_HOST_TSO4) | - (1ULL << VIRTIO_NET_F_HOST_TSO6) | - (1ULL << VIRTIO_NET_F_HOST_ECN) | - (1ULL << VIRTIO_NET_F_HOST_UFO) | - (1ULL << VIRTIO_NET_F_MRG_RXBUF) | - (1ULL << VIRTIO_NET_F_STATUS) | - (1ULL << VIRTIO_NET_F_SPEED_DUPLEX), -}; - /* Currently, only network backend w/o multiqueue is supported. */ #define VHOST_VDPA_VQ_MAX 2 @@ -79,10 +50,6 @@ static DEFINE_IDA(vhost_vdpa_ida); static dev_t vhost_vdpa_major; -static const u64 vhost_vdpa_features[] = { - [VIRTIO_ID_NET] = VHOST_VDPA_NET_FEATURES, -}; - static void handle_vq_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, @@ -253,7 +220,6 @@ static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep) u64 features; features = ops->get_features(vdpa); - features &= vhost_vdpa_features[v->virtio_id]; if (copy_to_user(featurep, &features, sizeof(features))) return -EFAULT; @@ -277,9 +243,6 @@ static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep) if (copy_from_user(&features, featurep, sizeof(features))) return -EFAULT; - if (features & ~vhost_vdpa_features[v->virtio_id]) - return -EINVAL; - if (vdpa_set_features(vdpa, features)) return -EINVAL; From 0ea9ee430e74b16c6b17e70757d1c26d8d140e1f Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Fri, 31 Jul 2020 15:38:22 +0800 Subject: [PATCH 258/291] vdpasim: protect concurrent access to iommu iotlb Iommu iotlb can be accessed by different cores for performing IO using multiple virt queues. Add a spinlock to synchronize iotlb accesses. This could be easily reproduced when using more than 1 pktgen threads to inject traffic to vdpa simulator. Fixes: 2c53d0f64c06f("vdpasim: vDPA device simulator") Cc: stable@vger.kernel.org Signed-off-by: Max Gurtovoy Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20200731073822.13326-1-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 31 +++++++++++++++++++++++++++---- 1 file changed, 27 insertions(+), 4 deletions(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index b7d5727fde4c..2a55b463e64c 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -71,6 +71,8 @@ struct vdpasim { u32 status; u32 generation; u64 features; + /* spinlock to synchronize iommu table */ + spinlock_t iommu_lock; }; /* TODO: cross-endian support */ @@ -136,7 +138,9 @@ static void vdpasim_reset(struct vdpasim *vdpasim) for (i = 0; i < VDPASIM_VQ_NUM; i++) vdpasim_vq_reset(&vdpasim->vqs[i]); + spin_lock(&vdpasim->iommu_lock); vhost_iotlb_reset(vdpasim->iommu); + spin_unlock(&vdpasim->iommu_lock); vdpasim->features = 0; vdpasim->status = 0; @@ -254,8 +258,10 @@ static dma_addr_t vdpasim_map_page(struct device *dev, struct page *page, /* For simplicity, use identical mapping to avoid e.g iova * allocator. */ + spin_lock(&vdpasim->iommu_lock); ret = vhost_iotlb_add_range(iommu, pa, pa + size - 1, pa, dir_to_perm(dir)); + spin_unlock(&vdpasim->iommu_lock); if (ret) return DMA_MAPPING_ERROR; @@ -269,8 +275,10 @@ static void vdpasim_unmap_page(struct device *dev, dma_addr_t dma_addr, struct vdpasim *vdpasim = dev_to_sim(dev); struct vhost_iotlb *iommu = vdpasim->iommu; + spin_lock(&vdpasim->iommu_lock); vhost_iotlb_del_range(iommu, (u64)dma_addr, (u64)dma_addr + size - 1); + spin_unlock(&vdpasim->iommu_lock); } static void *vdpasim_alloc_coherent(struct device *dev, size_t size, @@ -282,9 +290,10 @@ static void *vdpasim_alloc_coherent(struct device *dev, size_t size, void *addr = kmalloc(size, flag); int ret; - if (!addr) + spin_lock(&vdpasim->iommu_lock); + if (!addr) { *dma_addr = DMA_MAPPING_ERROR; - else { + } else { u64 pa = virt_to_phys(addr); ret = vhost_iotlb_add_range(iommu, (u64)pa, @@ -297,6 +306,7 @@ static void *vdpasim_alloc_coherent(struct device *dev, size_t size, } else *dma_addr = (dma_addr_t)pa; } + spin_unlock(&vdpasim->iommu_lock); return addr; } @@ -308,8 +318,11 @@ static void vdpasim_free_coherent(struct device *dev, size_t size, struct vdpasim *vdpasim = dev_to_sim(dev); struct vhost_iotlb *iommu = vdpasim->iommu; + spin_lock(&vdpasim->iommu_lock); vhost_iotlb_del_range(iommu, (u64)dma_addr, (u64)dma_addr + size - 1); + spin_unlock(&vdpasim->iommu_lock); + kfree(phys_to_virt((uintptr_t)dma_addr)); } @@ -555,6 +568,7 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, u64 start = 0ULL, last = 0ULL - 1; int ret; + spin_lock(&vdpasim->iommu_lock); vhost_iotlb_reset(vdpasim->iommu); for (map = vhost_iotlb_itree_first(iotlb, start, last); map; @@ -564,10 +578,12 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, if (ret) goto err; } + spin_unlock(&vdpasim->iommu_lock); return 0; err: vhost_iotlb_reset(vdpasim->iommu); + spin_unlock(&vdpasim->iommu_lock); return ret; } @@ -575,16 +591,23 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size, u64 pa, u32 perm) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + int ret; - return vhost_iotlb_add_range(vdpasim->iommu, iova, - iova + size - 1, pa, perm); + spin_lock(&vdpasim->iommu_lock); + ret = vhost_iotlb_add_range(vdpasim->iommu, iova, iova + size - 1, pa, + perm); + spin_unlock(&vdpasim->iommu_lock); + + return ret; } static int vdpasim_dma_unmap(struct vdpa_device *vdpa, u64 iova, u64 size) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + spin_lock(&vdpasim->iommu_lock); vhost_iotlb_del_range(vdpasim->iommu, iova, iova + size - 1); + spin_unlock(&vdpasim->iommu_lock); return 0; } From bf11d71a0a919c32158dd89891d95f6f91a323b2 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 31 Jul 2020 08:09:56 -0500 Subject: [PATCH 259/291] vhost: Use flex_array_size() helper in copy_from_user() Make use of the flex_array_size() helper to calculate the size of a flexible array member within an enclosing structure. This helper offers defense-in-depth against potential integer overflows, while at the same time makes it explicitly clear that we are dealing with a flexible array member. Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200731130956.GA30525@embeddedor Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vhost.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index d7b8df3edffc..39183ed738a1 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1405,7 +1405,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) memcpy(newmem, &mem, size); if (copy_from_user(newmem->regions, m->regions, - mem.nregions * sizeof *m->regions)) { + flex_array_size(newmem, regions, mem.nregions))) { kvfree(newmem); return -EFAULT; } From 265a0ad8731dc04fccb76cd1abf5a85a9359e62e Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Fri, 31 Jul 2020 14:55:28 +0800 Subject: [PATCH 260/291] vhost: introduce vhost_vring_call This commit introduces struct vhost_vring_call which replaced raw struct eventfd_ctx *call_ctx in struct vhost_virtqueue. Besides eventfd_ctx, it contains a spin lock and an irq_bypass_producer in its structure. Signed-off-by: Zhu Lingshan Suggested-by: Jason Wang Link: https://lore.kernel.org/r/20200731065533.4144-2-lingshan.zhu@intel.com Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vdpa.c | 4 ++-- drivers/vhost/vhost.c | 22 ++++++++++++++++------ drivers/vhost/vhost.h | 9 ++++++++- 3 files changed, 26 insertions(+), 9 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 210f213a028b..1789e5ffb18f 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -63,7 +63,7 @@ static void handle_vq_kick(struct vhost_work *work) static irqreturn_t vhost_vdpa_virtqueue_cb(void *private) { struct vhost_virtqueue *vq = private; - struct eventfd_ctx *call_ctx = vq->call_ctx; + struct eventfd_ctx *call_ctx = vq->call_ctx.ctx; if (call_ctx) eventfd_signal(call_ctx, 1); @@ -343,7 +343,7 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, break; case VHOST_SET_VRING_CALL: - if (vq->call_ctx) { + if (vq->call_ctx.ctx) { cb.callback = vhost_vdpa_virtqueue_cb; cb.private = vq; } else { diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 39183ed738a1..8f622064b3e8 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -298,6 +298,13 @@ static void vhost_vq_meta_reset(struct vhost_dev *d) __vhost_vq_meta_reset(d->vqs[i]); } +static void vhost_vring_call_reset(struct vhost_vring_call *call_ctx) +{ + call_ctx->ctx = NULL; + memset(&call_ctx->producer, 0x0, sizeof(struct irq_bypass_producer)); + spin_lock_init(&call_ctx->ctx_lock); +} + static void vhost_vq_reset(struct vhost_dev *dev, struct vhost_virtqueue *vq) { @@ -319,13 +326,13 @@ static void vhost_vq_reset(struct vhost_dev *dev, vq->log_base = NULL; vq->error_ctx = NULL; vq->kick = NULL; - vq->call_ctx = NULL; vq->log_ctx = NULL; vhost_reset_is_le(vq); vhost_disable_cross_endian(vq); vq->busyloop_timeout = 0; vq->umem = NULL; vq->iotlb = NULL; + vhost_vring_call_reset(&vq->call_ctx); __vhost_vq_meta_reset(vq); } @@ -685,8 +692,8 @@ void vhost_dev_cleanup(struct vhost_dev *dev) eventfd_ctx_put(dev->vqs[i]->error_ctx); if (dev->vqs[i]->kick) fput(dev->vqs[i]->kick); - if (dev->vqs[i]->call_ctx) - eventfd_ctx_put(dev->vqs[i]->call_ctx); + if (dev->vqs[i]->call_ctx.ctx) + eventfd_ctx_put(dev->vqs[i]->call_ctx.ctx); vhost_vq_reset(dev, dev->vqs[i]); } vhost_dev_free_iovecs(dev); @@ -1629,7 +1636,10 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg r = PTR_ERR(ctx); break; } - swap(ctx, vq->call_ctx); + + spin_lock(&vq->call_ctx.ctx_lock); + swap(ctx, vq->call_ctx.ctx); + spin_unlock(&vq->call_ctx.ctx_lock); break; case VHOST_SET_VRING_ERR: if (copy_from_user(&f, argp, sizeof f)) { @@ -2440,8 +2450,8 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq) { /* Signal the Guest tell them we used something up. */ - if (vq->call_ctx && vhost_notify(dev, vq)) - eventfd_signal(vq->call_ctx, 1); + if (vq->call_ctx.ctx && vhost_notify(dev, vq)) + eventfd_signal(vq->call_ctx.ctx, 1); } EXPORT_SYMBOL_GPL(vhost_signal); diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index c8e96a095d3b..38eb1aa3b68d 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -13,6 +13,7 @@ #include #include #include +#include struct vhost_work; typedef void (*vhost_work_fn_t)(struct vhost_work *work); @@ -60,6 +61,12 @@ enum vhost_uaddr_type { VHOST_NUM_ADDRS = 3, }; +struct vhost_vring_call { + struct eventfd_ctx *ctx; + struct irq_bypass_producer producer; + spinlock_t ctx_lock; +}; + /* The virtqueue structure describes a queue attached to a device. */ struct vhost_virtqueue { struct vhost_dev *dev; @@ -72,7 +79,7 @@ struct vhost_virtqueue { vring_used_t __user *used; const struct vhost_iotlb_map *meta_iotlb[VHOST_NUM_ADDRS]; struct file *kick; - struct eventfd_ctx *call_ctx; + struct vhost_vring_call call_ctx; struct eventfd_ctx *error_ctx; struct eventfd_ctx *log_ctx; From 2edd9cb79fb31b0907c6e0cdce2824780cf9b153 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Fri, 31 Jul 2020 14:55:29 +0800 Subject: [PATCH 261/291] kvm: detect assigned device via irqbypass manager vDPA devices has dedicated backed hardware like passthrough-ed devices. Then it is possible to setup irq offloading to vCPU for vDPA devices. Thus this patch tries to manipulated assigned device counters by kvm_arch_start/end_assignment() in irqbypass manager, so that assigned devices could be detected in update_pi_irte() We will increase/decrease the assigned device counter in kvm/x86. Both vDPA and VFIO would go through this code path. Only X86 uses these counters and kvm_arch_start/end_assignment(), so this code path only affect x86 for now. Signed-off-by: Zhu Lingshan Suggested-by: Jason Wang Link: https://lore.kernel.org/r/20200731065533.4144-3-lingshan.zhu@intel.com Signed-off-by: Michael S. Tsirkin --- arch/x86/kvm/x86.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 88c593f83b28..76a2e7fd18c7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10630,11 +10630,17 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); + int ret; irqfd->producer = prod; + kvm_arch_start_assignment(irqfd->kvm); + ret = kvm_x86_ops.update_pi_irte(irqfd->kvm, + prod->irq, irqfd->gsi, 1); - return kvm_x86_ops.update_pi_irte(irqfd->kvm, - prod->irq, irqfd->gsi, 1); + if (ret) + kvm_arch_end_assignment(irqfd->kvm); + + return ret; } void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, @@ -10657,6 +10663,8 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, if (ret) printk(KERN_INFO "irq bypass consumer (token %p) unregistration" " fails: %d\n", irqfd->consumer.token, ret); + + kvm_arch_end_assignment(irqfd->kvm); } int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, From 7164675ab5caf46867d6a5448f4ff3af92d80a30 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Fri, 31 Jul 2020 14:55:30 +0800 Subject: [PATCH 262/291] vDPA: add get_vq_irq() in vdpa_config_ops This commit adds a new function get_vq_irq() in struct vdpa_config_ops, which will return the irq number of a virtqueue. Signed-off-by: Zhu Lingshan Suggested-by: Jason Wang Link: https://lore.kernel.org/r/20200731065533.4144-4-lingshan.zhu@intel.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 29b8296f1414..5c530a64aa06 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -89,6 +89,12 @@ struct vdpa_device { * @vdev: vdpa device * @idx: virtqueue index * Returns the notifcation area + * @get_vq_irq: Get the irq number of a virtqueue (optional, + * but must implemented if require vq irq offloading) + * @vdev: vdpa device + * @idx: virtqueue index + * Returns int: irq number of a virtqueue, + * negative number if no irq assigned. * @get_vq_align: Get the virtqueue align requirement * for the device * @vdev: vdpa device @@ -180,6 +186,7 @@ struct vdpa_config_ops { u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx); struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); + int (*get_vq_irq)(struct vdpa_device *vdv, u16 idx); /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); From 2cf1ba9a4d15cb78b96ea97f727b93382c3f9a60 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Fri, 31 Jul 2020 14:55:31 +0800 Subject: [PATCH 263/291] vhost_vdpa: implement IRQ offloading in vhost_vdpa This patch introduce a set of functions for setup/unsetup and update irq offloading respectively by register/unregister and re-register the irq_bypass_producer. With these functions, this commit can setup/unsetup irq offloading through setting DRIVER_OK/!DRIVER_OK, and update irq offloading through SET_VRING_CALL. Signed-off-by: Zhu Lingshan Suggested-by: Jason Wang Link: https://lore.kernel.org/r/20200731065533.4144-5-lingshan.zhu@intel.com Signed-off-by: Michael S. Tsirkin --- drivers/vhost/Kconfig | 1 + drivers/vhost/vdpa.c | 63 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 63 insertions(+), 1 deletion(-) diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig index d3688c6afb87..587fbae06182 100644 --- a/drivers/vhost/Kconfig +++ b/drivers/vhost/Kconfig @@ -65,6 +65,7 @@ config VHOST_VDPA tristate "Vhost driver for vDPA-based backend" depends on EVENTFD select VHOST + select IRQ_BYPASS_MANAGER depends on VDPA help This kernel module can be loaded in host kernel to accelerate diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 1789e5ffb18f..7441b9803eae 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -82,6 +82,39 @@ static irqreturn_t vhost_vdpa_config_cb(void *private) return IRQ_HANDLED; } +static void vhost_vdpa_setup_vq_irq(struct vhost_vdpa *v, u16 qid) +{ + struct vhost_virtqueue *vq = &v->vqs[qid]; + const struct vdpa_config_ops *ops = v->vdpa->config; + struct vdpa_device *vdpa = v->vdpa; + int ret, irq; + + if (!ops->get_vq_irq) + return; + + irq = ops->get_vq_irq(vdpa, qid); + spin_lock(&vq->call_ctx.ctx_lock); + irq_bypass_unregister_producer(&vq->call_ctx.producer); + if (!vq->call_ctx.ctx || irq < 0) { + spin_unlock(&vq->call_ctx.ctx_lock); + return; + } + + vq->call_ctx.producer.token = vq->call_ctx.ctx; + vq->call_ctx.producer.irq = irq; + ret = irq_bypass_register_producer(&vq->call_ctx.producer); + spin_unlock(&vq->call_ctx.ctx_lock); +} + +static void vhost_vdpa_unsetup_vq_irq(struct vhost_vdpa *v, u16 qid) +{ + struct vhost_virtqueue *vq = &v->vqs[qid]; + + spin_lock(&vq->call_ctx.ctx_lock); + irq_bypass_unregister_producer(&vq->call_ctx.producer); + spin_unlock(&vq->call_ctx.ctx_lock); +} + static void vhost_vdpa_reset(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; @@ -121,11 +154,15 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) { struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; - u8 status; + u8 status, status_old; + int nvqs = v->nvqs; + u16 i; if (copy_from_user(&status, statusp, sizeof(status))) return -EFAULT; + status_old = ops->get_status(vdpa); + /* * Userspace shouldn't remove status bits unless reset the * status to 0. @@ -135,6 +172,15 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) ops->set_status(vdpa, status); + /* vq irq is not expected to be changed once DRIVER_OK is set */ + if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK)) + for (i = 0; i < nvqs; i++) + vhost_vdpa_setup_vq_irq(v, i); + + if ((status_old & VIRTIO_CONFIG_S_DRIVER_OK) && !(status & VIRTIO_CONFIG_S_DRIVER_OK)) + for (i = 0; i < nvqs; i++) + vhost_vdpa_unsetup_vq_irq(v, i); + return 0; } @@ -293,6 +339,7 @@ static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp) return 0; } + static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, void __user *argp) { @@ -351,6 +398,7 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, cb.private = NULL; } ops->set_vq_cb(vdpa, idx, &cb); + vhost_vdpa_setup_vq_irq(v, idx); break; case VHOST_SET_VRING_NUM: @@ -726,6 +774,18 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep) return r; } +static void vhost_vdpa_clean_irq(struct vhost_vdpa *v) +{ + struct vhost_virtqueue *vq; + int i; + + for (i = 0; i < v->nvqs; i++) { + vq = &v->vqs[i]; + if (vq->call_ctx.producer.irq) + irq_bypass_unregister_producer(&vq->call_ctx.producer); + } +} + static int vhost_vdpa_release(struct inode *inode, struct file *filep) { struct vhost_vdpa *v = filep->private_data; @@ -738,6 +798,7 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) vhost_vdpa_iotlb_free(v); vhost_vdpa_free_domain(v); vhost_vdpa_config_put(v); + vhost_vdpa_clean_irq(v); vhost_dev_cleanup(&v->vdev); kfree(v->vdev.vqs); mutex_unlock(&d->mutex); From 3597a2fba672cfd4112bbdbe6220127f280c8dba Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Fri, 31 Jul 2020 14:55:32 +0800 Subject: [PATCH 264/291] ifcvf: implement vdpa_config_ops.get_vq_irq() This commit implemented vdpa_config_ops.get_vq_irq() in ifcvf, and initialized vq irq to -EINVAL. So that ifcvf can report irq number of a vq, or -EINVAL if the vq is not assigned an irq number. Signed-off-by: Zhu Lingshan Suggested-by: Jason Wang Link: https://lore.kernel.org/r/20200731065533.4144-6-lingshan.zhu@intel.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/ifcvf/ifcvf_main.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index f5a60c14b979..a902b29b0d29 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -50,8 +50,10 @@ static void ifcvf_free_irq(struct ifcvf_adapter *adapter, int queues) int i; - for (i = 0; i < queues; i++) + for (i = 0; i < queues; i++) { devm_free_irq(&pdev->dev, vf->vring[i].irq, &vf->vring[i]); + vf->vring[i].irq = -EINVAL; + } ifcvf_free_irq_vectors(pdev); } @@ -352,6 +354,14 @@ static void ifcvf_vdpa_set_config_cb(struct vdpa_device *vdpa_dev, vf->config_cb.private = cb->private; } +static int ifcvf_vdpa_get_vq_irq(struct vdpa_device *vdpa_dev, + u16 qid) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + return vf->vring[qid].irq; +} + /* * IFCVF currently does't have on-chip IOMMU, so not * implemented set_map()/dma_map()/dma_unmap() @@ -369,6 +379,7 @@ static const struct vdpa_config_ops ifc_vdpa_ops = { .get_vq_ready = ifcvf_vdpa_get_vq_ready, .set_vq_num = ifcvf_vdpa_set_vq_num, .set_vq_address = ifcvf_vdpa_set_vq_address, + .get_vq_irq = ifcvf_vdpa_get_vq_irq, .kick_vq = ifcvf_vdpa_kick_vq, .get_generation = ifcvf_vdpa_get_generation, .get_device_id = ifcvf_vdpa_get_device_id, @@ -384,7 +395,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct device *dev = &pdev->dev; struct ifcvf_adapter *adapter; struct ifcvf_hw *vf; - int ret; + int ret, i; ret = pcim_enable_device(pdev); if (ret) { @@ -441,6 +452,9 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err; } + for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) + vf->vring[i].irq = -EINVAL; + ret = vdpa_register_device(&adapter->vdpa); if (ret) { IFCVF_ERR(pdev, "Failed to register ifcvf to vdpa bus"); From a979a6aa009f3c99689432e0cdb5402a4463fb88 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Fri, 31 Jul 2020 14:55:33 +0800 Subject: [PATCH 265/291] irqbypass: do not start cons/prod when failed connect If failed to connect, there is no need to start consumer nor producer. Signed-off-by: Zhu Lingshan Suggested-by: Jason Wang Link: https://lore.kernel.org/r/20200731065533.4144-7-lingshan.zhu@intel.com Signed-off-by: Michael S. Tsirkin --- virt/lib/irqbypass.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c index 28fda42e471b..c9bb3957f58a 100644 --- a/virt/lib/irqbypass.c +++ b/virt/lib/irqbypass.c @@ -40,17 +40,21 @@ static int __connect(struct irq_bypass_producer *prod, if (prod->add_consumer) ret = prod->add_consumer(prod, cons); - if (!ret) { - ret = cons->add_producer(cons, prod); - if (ret && prod->del_consumer) - prod->del_consumer(prod, cons); - } + if (ret) + goto err_add_consumer; + + ret = cons->add_producer(cons, prod); + if (ret) + goto err_add_producer; if (cons->start) cons->start(cons); if (prod->start) prod->start(prod); - +err_add_producer: + if (prod->del_consumer) + prod->del_consumer(prod, cons); +err_add_consumer: return ret; } From 46af9adefd2fd44afa9e8a5020c520812151f849 Mon Sep 17 00:00:00 2001 From: Liao Pingfang Date: Mon, 3 Aug 2020 19:52:24 +0800 Subject: [PATCH 266/291] virtio_pci_modern: Fix the comment of virtio_pci_find_capability() Fix the comment of virtio_pci_find_capability() by adding missing comment for the last parameter: bars. Fixes: 59a5b0f7bf74 ("virtio-pci: alloc only resources actually used.") Signed-off-by: Liao Pingfang Signed-off-by: Yi Wang Link: https://lore.kernel.org/r/1596455545-43556-1-git-send-email-wang.yi59@zte.com.cn Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/virtio/virtio_pci_modern.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index db93cedd262f..9bdc6f68221f 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -481,6 +481,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = { * @dev: the pci device * @cfg_type: the VIRTIO_PCI_CAP_* value we seek * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO. + * @bars: the bitmask of BARs * * Returns offset of the capability, or 0. */ From 4c05433bc6fb4ae172270f0279be8ba89a3da64f Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Tue, 4 Aug 2020 18:21:23 +0800 Subject: [PATCH 267/291] vDPA: dont change vq irq after DRIVER_OK IRQ of a vq is not expected to be changed in a DRIVER_OK ~ !DRIVER_OK period for irq offloading purposes. Place this comment at the side of bus ops get_vq_irq than in set_status in vhost_vdpa. Signed-off-by: Zhu Lingshan Link: https://lore.kernel.org/r/20200804102123.69978-1-lingshan.zhu@intel.com Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vdpa.c | 1 - include/linux/vdpa.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 7441b9803eae..f8f8c9cf05b0 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -172,7 +172,6 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) ops->set_status(vdpa, status); - /* vq irq is not expected to be changed once DRIVER_OK is set */ if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK)) for (i = 0; i < nvqs; i++) vhost_vdpa_setup_vq_irq(v, i); diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 5c530a64aa06..565298cb45d2 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -186,6 +186,7 @@ struct vdpa_config_ops { u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx); struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); + /* vq irq is not expected to be changed once DRIVER_OK is set */ int (*get_vq_irq)(struct vdpa_device *vdv, u16 idx); /* Device ops */ From b0bd82bf729dbd05757e599f20df38dff5b97091 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 4 Aug 2020 19:20:37 +0300 Subject: [PATCH 268/291] vhost-vdpa: refine ioctl pre-processing Switch to use 'switch' to make the codes more easier to be extended. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20200804162048.22587-2-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vdpa.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index f8f8c9cf05b0..01475bec6e0d 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -360,15 +360,16 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, idx = array_index_nospec(idx, v->nvqs); vq = &v->vqs[idx]; - if (cmd == VHOST_VDPA_SET_VRING_ENABLE) { + switch (cmd) { + case VHOST_VDPA_SET_VRING_ENABLE: if (copy_from_user(&s, argp, sizeof(s))) return -EFAULT; ops->set_vq_ready(vdpa, idx, s.num); return 0; - } - - if (cmd == VHOST_GET_VRING_BASE) + case VHOST_GET_VRING_BASE: vq->last_avail_idx = ops->get_vq_state(v->vdpa, idx); + break; + } r = vhost_vring_ioctl(&v->vdev, cmd, argp); if (r) From 460f7ce19f50e612a80b8cd0d2e38f2e14e765f6 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 4 Aug 2020 19:20:38 +0300 Subject: [PATCH 269/291] vhost: generialize backend features setting/getting Move the backend features setting/getting from net.c to vhost.c to be reused by vhost-vdpa. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20200804162048.22587-3-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- drivers/vhost/net.c | 18 ++---------------- drivers/vhost/vhost.c | 15 +++++++++++++++ drivers/vhost/vhost.h | 2 ++ 3 files changed, 19 insertions(+), 16 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 8e0921d3805d..bfbbe5c876f9 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1615,21 +1615,6 @@ static long vhost_net_reset_owner(struct vhost_net *n) return err; } -static int vhost_net_set_backend_features(struct vhost_net *n, u64 features) -{ - int i; - - mutex_lock(&n->dev.mutex); - for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { - mutex_lock(&n->vqs[i].vq.mutex); - n->vqs[i].vq.acked_backend_features = features; - mutex_unlock(&n->vqs[i].vq.mutex); - } - mutex_unlock(&n->dev.mutex); - - return 0; -} - static int vhost_net_set_features(struct vhost_net *n, u64 features) { size_t vhost_hlen, sock_hlen, hdr_len; @@ -1730,7 +1715,8 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl, return -EFAULT; if (features & ~VHOST_NET_BACKEND_FEATURES) return -EOPNOTSUPP; - return vhost_net_set_backend_features(n, features); + vhost_set_backend_features(&n->dev, features); + return 0; case VHOST_RESET_OWNER: return vhost_net_reset_owner(n); case VHOST_SET_OWNER: diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 8f622064b3e8..5e5cc3dd983e 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2591,6 +2591,21 @@ struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev, } EXPORT_SYMBOL_GPL(vhost_dequeue_msg); +void vhost_set_backend_features(struct vhost_dev *dev, u64 features) +{ + struct vhost_virtqueue *vq; + int i; + + mutex_lock(&dev->mutex); + for (i = 0; i < dev->nvqs; ++i) { + vq = dev->vqs[i]; + mutex_lock(&vq->mutex); + vq->acked_backend_features = features; + mutex_unlock(&vq->mutex); + } + mutex_unlock(&dev->mutex); +} +EXPORT_SYMBOL_GPL(vhost_set_backend_features); static int __init vhost_init(void) { diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 38eb1aa3b68d..9032d3c2a9f4 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -214,6 +214,8 @@ void vhost_enqueue_msg(struct vhost_dev *dev, struct vhost_msg_node *node); struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev, struct list_head *head); +void vhost_set_backend_features(struct vhost_dev *dev, u64 features); + __poll_t vhost_chr_poll(struct file *file, struct vhost_dev *dev, poll_table *wait); ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to, From 653055b9acd45d602435f2f70b7a85cb3130f018 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 4 Aug 2020 19:20:39 +0300 Subject: [PATCH 270/291] vhost-vdpa: support get/set backend features This patch makes userspace can get and set backend features to vhost-vdpa. Signed-off-by: Cindy Lu Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20200804162048.22587-4-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vdpa.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 01475bec6e0d..61c17d34cb39 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -26,6 +26,10 @@ #include "vhost.h" +enum { + VHOST_VDPA_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) +}; + /* Currently, only network backend w/o multiqueue is supported. */ #define VHOST_VDPA_VQ_MAX 2 @@ -347,6 +351,8 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, struct vdpa_callback cb; struct vhost_virtqueue *vq; struct vhost_vring_state s; + u64 __user *featurep = argp; + u64 features; u32 idx; long r; @@ -369,6 +375,18 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, case VHOST_GET_VRING_BASE: vq->last_avail_idx = ops->get_vq_state(v->vdpa, idx); break; + case VHOST_GET_BACKEND_FEATURES: + features = VHOST_VDPA_BACKEND_FEATURES; + if (copy_to_user(featurep, &features, sizeof(features))) + return -EFAULT; + return 0; + case VHOST_SET_BACKEND_FEATURES: + if (copy_from_user(&features, featurep, sizeof(features))) + return -EFAULT; + if (features & ~VHOST_VDPA_BACKEND_FEATURES) + return -EOPNOTSUPP; + vhost_set_backend_features(&v->vdev, features); + return 0; } r = vhost_vring_ioctl(&v->vdev, cmd, argp); From 25abc060d282132ea5c945392f900dca0a7e9bbb Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 4 Aug 2020 19:20:40 +0300 Subject: [PATCH 271/291] vhost-vdpa: support IOTLB batching hints This patches extend the vhost IOTLB API to accept batch updating hints form userspace. When userspace wants update the device IOTLB in a batch, it may do: 1) Write vhost_iotlb_msg with VHOST_IOTLB_BATCH_BEGIN flag 2) Perform a batch of IOTLB updating via VHOST_IOTLB_UPDATE/INVALIDATE 3) Write vhost_iotlb_msg with VHOST_IOTLB_BATCH_END flag Vhost-vdpa may decide to batch the IOMMU/IOTLB updating in step 3 when vDPA device support set_map() ops. This is useful for the vDPA device that want to know all the mappings to tweak their own DMA translation logic. For vDPA device that doesn't require set_map(), no behavior changes. This capability is advertised via VHOST_BACKEND_F_IOTLB_BATCH capability. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20200804162048.22587-5-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vdpa.c | 36 ++++++++++++++++++++++++-------- include/uapi/linux/vhost.h | 2 ++ include/uapi/linux/vhost_types.h | 11 ++++++++++ 3 files changed, 40 insertions(+), 9 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 61c17d34cb39..e80db051845d 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -27,7 +27,9 @@ #include "vhost.h" enum { - VHOST_VDPA_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) + VHOST_VDPA_BACKEND_FEATURES = + (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) | + (1ULL << VHOST_BACKEND_F_IOTLB_BATCH), }; /* Currently, only network backend w/o multiqueue is supported. */ @@ -48,6 +50,7 @@ struct vhost_vdpa { int virtio_id; int minor; struct eventfd_ctx *config_ctx; + int in_batch; }; static DEFINE_IDA(vhost_vdpa_ida); @@ -124,6 +127,7 @@ static void vhost_vdpa_reset(struct vhost_vdpa *v) struct vdpa_device *vdpa = v->vdpa; vdpa_reset(vdpa); + v->in_batch = 0; } static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp) @@ -546,13 +550,15 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, if (r) return r; - if (ops->dma_map) + if (ops->dma_map) { r = ops->dma_map(vdpa, iova, size, pa, perm); - else if (ops->set_map) - r = ops->set_map(vdpa, dev->iotlb); - else + } else if (ops->set_map) { + if (!v->in_batch) + r = ops->set_map(vdpa, dev->iotlb); + } else { r = iommu_map(v->domain, iova, pa, size, perm_to_iommu_flags(perm)); + } return r; } @@ -565,12 +571,14 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size) vhost_vdpa_iotlb_unmap(v, iova, iova + size - 1); - if (ops->dma_map) + if (ops->dma_map) { ops->dma_unmap(vdpa, iova, size); - else if (ops->set_map) - ops->set_map(vdpa, dev->iotlb); - else + } else if (ops->set_map) { + if (!v->in_batch) + ops->set_map(vdpa, dev->iotlb); + } else { iommu_unmap(v->domain, iova, size); + } } static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, @@ -663,6 +671,8 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, struct vhost_iotlb_msg *msg) { struct vhost_vdpa *v = container_of(dev, struct vhost_vdpa, vdev); + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; int r = 0; r = vhost_dev_check_owner(dev); @@ -676,6 +686,14 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, case VHOST_IOTLB_INVALIDATE: vhost_vdpa_unmap(v, msg->iova, msg->size); break; + case VHOST_IOTLB_BATCH_BEGIN: + v->in_batch = true; + break; + case VHOST_IOTLB_BATCH_END: + if (v->in_batch && ops->set_map) + ops->set_map(vdpa, dev->iotlb); + v->in_batch = false; + break; default: r = -EINVAL; break; diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 0c2349612e77..75232185324a 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -91,6 +91,8 @@ /* Use message type V2 */ #define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 +/* IOTLB can accept batching hints */ +#define VHOST_BACKEND_F_IOTLB_BATCH 0x2 #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) #define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index 669457ce5c48..9a269a88a6ff 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -60,6 +60,17 @@ struct vhost_iotlb_msg { #define VHOST_IOTLB_UPDATE 2 #define VHOST_IOTLB_INVALIDATE 3 #define VHOST_IOTLB_ACCESS_FAIL 4 +/* + * VHOST_IOTLB_BATCH_BEGIN and VHOST_IOTLB_BATCH_END allow modifying + * multiple mappings in one go: beginning with + * VHOST_IOTLB_BATCH_BEGIN, followed by any number of + * VHOST_IOTLB_UPDATE messages, and ending with VHOST_IOTLB_BATCH_END. + * When one of these two values is used as the message type, the rest + * of the fields in the message are ignored. There's no guarantee that + * these changes take place automatically in the device. + */ +#define VHOST_IOTLB_BATCH_BEGIN 5 +#define VHOST_IOTLB_BATCH_END 6 __u8 type; }; From de91a4d0e725db34db64502fad84e8fb1026146b Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 4 Aug 2020 19:20:41 +0300 Subject: [PATCH 272/291] vdpasim: support batch updating The vDPA simulator support both set_map() and dma_map()/dma_unmap() operations. But vhost-vdpa can only use one of them. So this patch introduce a module parameter (batch_mapping) that let vpda_sim to support only one of those dma operations. The batched mapping via set_map() is enabled by default. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20200804162048.22587-6-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 40 +++++++++++++++++++++++++++++--- 1 file changed, 37 insertions(+), 3 deletions(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 2a55b463e64c..7b34d663778f 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -34,6 +34,10 @@ #define DRV_DESC "vDPA Device Simulator" #define DRV_LICENSE "GPL v2" +static int batch_mapping = 1; +module_param(batch_mapping, int, 0444); +MODULE_PARM_DESC(batch_mapping, "Batched mapping 1 -Enable; 0 - Disable"); + struct vdpasim_virtqueue { struct vringh vring; struct vringh_kiov iov; @@ -334,15 +338,21 @@ static const struct dma_map_ops vdpasim_dma_ops = { }; static const struct vdpa_config_ops vdpasim_net_config_ops; +static const struct vdpa_config_ops vdpasim_net_batch_config_ops; static struct vdpasim *vdpasim_create(void) { + const struct vdpa_config_ops *ops; struct vdpasim *vdpasim; struct device *dev; int ret = -ENOMEM; - vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, - &vdpasim_net_config_ops); + if (batch_mapping) + ops = &vdpasim_net_batch_config_ops; + else + ops = &vdpasim_net_config_ops; + + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops); if (!vdpasim) goto err_alloc; @@ -643,12 +653,36 @@ static const struct vdpa_config_ops vdpasim_net_config_ops = { .get_config = vdpasim_get_config, .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, - .set_map = vdpasim_set_map, .dma_map = vdpasim_dma_map, .dma_unmap = vdpasim_dma_unmap, .free = vdpasim_free, }; +static const struct vdpa_config_ops vdpasim_net_batch_config_ops = { + .set_vq_address = vdpasim_set_vq_address, + .set_vq_num = vdpasim_set_vq_num, + .kick_vq = vdpasim_kick_vq, + .set_vq_cb = vdpasim_set_vq_cb, + .set_vq_ready = vdpasim_set_vq_ready, + .get_vq_ready = vdpasim_get_vq_ready, + .set_vq_state = vdpasim_set_vq_state, + .get_vq_state = vdpasim_get_vq_state, + .get_vq_align = vdpasim_get_vq_align, + .get_features = vdpasim_get_features, + .set_features = vdpasim_set_features, + .set_config_cb = vdpasim_set_config_cb, + .get_vq_num_max = vdpasim_get_vq_num_max, + .get_device_id = vdpasim_get_device_id, + .get_vendor_id = vdpasim_get_vendor_id, + .get_status = vdpasim_get_status, + .set_status = vdpasim_set_status, + .get_config = vdpasim_get_config, + .set_config = vdpasim_set_config, + .get_generation = vdpasim_get_generation, + .set_map = vdpasim_set_map, + .free = vdpasim_free, +}; + static int __init vdpasim_dev_init(void) { vdpasim_dev = vdpasim_create(); From a9974489b61c09c702c85c6cba3d1a3fd1be7a15 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Tue, 4 Aug 2020 19:20:42 +0300 Subject: [PATCH 273/291] vdpa: remove hard coded virtq num This will enable vdpa providers to add support for multi queue feature and publish it to upper layers (vhost and virtio). Signed-off-by: Max Gurtovoy Reviewed-by: Jason Wang Link: https://lore.kernel.org/r/20200804162048.22587-7-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/ifcvf/ifcvf_main.c | 3 ++- drivers/vdpa/vdpa.c | 3 +++ drivers/vdpa/vdpa_sim/vdpa_sim.c | 4 ++-- drivers/vhost/vdpa.c | 9 +++------ include/linux/vdpa.h | 6 ++++-- 5 files changed, 14 insertions(+), 11 deletions(-) diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index a902b29b0d29..7c93225367db 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -431,7 +431,8 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) } adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, - dev, &ifc_vdpa_ops); + dev, &ifc_vdpa_ops, + IFCVF_MAX_QUEUE_PAIRS * 2); if (adapter == NULL) { IFCVF_ERR(pdev, "Failed to allocate vDPA structure"); return -ENOMEM; diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 7105265e4793..a69ffc991e13 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -61,6 +61,7 @@ static void vdpa_release_dev(struct device *d) * initialized but before registered. * @parent: the parent device * @config: the bus operations that is supported by this device + * @nvqs: number of virtqueues supported by this device * @size: size of the parent structure that contains private data * * Driver should use vdpa_alloc_device() wrapper macro instead of @@ -71,6 +72,7 @@ static void vdpa_release_dev(struct device *d) */ struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, + int nvqs, size_t size) { struct vdpa_device *vdev; @@ -97,6 +99,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->index = err; vdev->config = config; vdev->features_valid = false; + vdev->nvqs = nvqs; err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index); if (err) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 7b34d663778f..58baff89cc29 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -65,7 +65,7 @@ static u64 vdpasim_features = (1ULL << VIRTIO_F_ANY_LAYOUT) | /* State of each vdpasim device */ struct vdpasim { struct vdpa_device vdpa; - struct vdpasim_virtqueue vqs[2]; + struct vdpasim_virtqueue vqs[VDPASIM_VQ_NUM]; struct work_struct work; /* spinlock to synchronize virtqueue state */ spinlock_t lock; @@ -352,7 +352,7 @@ static struct vdpasim *vdpasim_create(void) else ops = &vdpasim_net_config_ops; - vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops); + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, VDPASIM_VQ_NUM); if (!vdpasim) goto err_alloc; diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index e80db051845d..2d8c950ad3a8 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -32,9 +32,6 @@ enum { (1ULL << VHOST_BACKEND_F_IOTLB_BATCH), }; -/* Currently, only network backend w/o multiqueue is supported. */ -#define VHOST_VDPA_VQ_MAX 2 - #define VHOST_VDPA_DEV_MAX (1U << MINORBITS) struct vhost_vdpa { @@ -930,7 +927,7 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa) { const struct vdpa_config_ops *ops = vdpa->config; struct vhost_vdpa *v; - int minor, nvqs = VHOST_VDPA_VQ_MAX; + int minor; int r; /* Currently, we only accept the network devices. */ @@ -951,14 +948,14 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa) atomic_set(&v->opened, 0); v->minor = minor; v->vdpa = vdpa; - v->nvqs = nvqs; + v->nvqs = vdpa->nvqs; v->virtio_id = ops->get_device_id(vdpa); device_initialize(&v->dev); v->dev.release = vhost_vdpa_release_dev; v->dev.parent = &vdpa->dev; v->dev.devt = MKDEV(MAJOR(vhost_vdpa_major), minor); - v->vqs = kmalloc_array(nvqs, sizeof(struct vhost_virtqueue), + v->vqs = kmalloc_array(v->nvqs, sizeof(struct vhost_virtqueue), GFP_KERNEL); if (!v->vqs) { r = -ENOMEM; diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 565298cb45d2..b5901cde73e0 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -41,6 +41,7 @@ struct vdpa_device { const struct vdpa_config_ops *config; unsigned int index; bool features_valid; + int nvqs; }; /** @@ -218,11 +219,12 @@ struct vdpa_config_ops { struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, + int nvqs, size_t size); -#define vdpa_alloc_device(dev_struct, member, parent, config) \ +#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs) \ container_of(__vdpa_alloc_device( \ - parent, config, \ + parent, config, nvqs, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ dev_struct, member))), \ From aac50c0bd434794b9950181349099e709ca4edad Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 4 Aug 2020 19:20:43 +0300 Subject: [PATCH 274/291] net/vdpa: Use struct for set/get vq state For now VQ state involves 16 bit available index value encoded in u64 variable. In the future it will be extended to contain more fields. Use struct to contain the state, now containing only a single u16 for the available index. In the future we can add fields to this struct. Reviewed-by: Parav Pandit Acked-by: Jason Wang Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20200804162048.22587-8-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/ifcvf/ifcvf_base.c | 4 ++-- drivers/vdpa/ifcvf/ifcvf_base.h | 4 ++-- drivers/vdpa/ifcvf/ifcvf_main.c | 9 +++++---- drivers/vdpa/vdpa_sim/vdpa_sim.c | 10 ++++++---- drivers/vhost/vdpa.c | 7 +++++-- include/linux/vdpa.h | 18 ++++++++++++++---- 6 files changed, 34 insertions(+), 18 deletions(-) diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c index 94bf0328b68d..f2a128e56de5 100644 --- a/drivers/vdpa/ifcvf/ifcvf_base.c +++ b/drivers/vdpa/ifcvf/ifcvf_base.c @@ -272,7 +272,7 @@ static int ifcvf_config_features(struct ifcvf_hw *hw) return 0; } -u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid) +u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid) { struct ifcvf_lm_cfg __iomem *ifcvf_lm; void __iomem *avail_idx_addr; @@ -287,7 +287,7 @@ u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid) return last_avail_idx; } -int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num) +int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num) { struct ifcvf_lm_cfg __iomem *ifcvf_lm; void __iomem *avail_idx_addr; diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h index 24af422b5a3e..08f267a2aafe 100644 --- a/drivers/vdpa/ifcvf/ifcvf_base.h +++ b/drivers/vdpa/ifcvf/ifcvf_base.h @@ -116,7 +116,7 @@ void ifcvf_set_status(struct ifcvf_hw *hw, u8 status); void io_write64_twopart(u64 val, u32 *lo, u32 *hi); void ifcvf_reset(struct ifcvf_hw *hw); u64 ifcvf_get_features(struct ifcvf_hw *hw); -u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid); -int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num); +u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid); +int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num); struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw); #endif /* _IFCVF_H_ */ diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index 7c93225367db..dc311e972b9e 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -237,19 +237,20 @@ static u16 ifcvf_vdpa_get_vq_num_max(struct vdpa_device *vdpa_dev) return IFCVF_QUEUE_MAX; } -static u64 ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid) +static void ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid, + struct vdpa_vq_state *state) { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); - return ifcvf_get_vq_state(vf, qid); + state->avail_index = ifcvf_get_vq_state(vf, qid); } static int ifcvf_vdpa_set_vq_state(struct vdpa_device *vdpa_dev, u16 qid, - u64 num) + const struct vdpa_vq_state *state) { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); - return ifcvf_set_vq_state(vf, qid, num); + return ifcvf_set_vq_state(vf, qid, state->avail_index); } static void ifcvf_vdpa_set_vq_cb(struct vdpa_device *vdpa_dev, u16 qid, diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 58baff89cc29..c93126ad09d1 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -450,26 +450,28 @@ static bool vdpasim_get_vq_ready(struct vdpa_device *vdpa, u16 idx) return vq->ready; } -static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx, u64 state) +static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx, + const struct vdpa_vq_state *state) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; struct vringh *vrh = &vq->vring; spin_lock(&vdpasim->lock); - vrh->last_avail_idx = state; + vrh->last_avail_idx = state->avail_index; spin_unlock(&vdpasim->lock); return 0; } -static u64 vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx) +static void vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx, + struct vdpa_vq_state *state) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; struct vringh *vrh = &vq->vring; - return vrh->last_avail_idx; + state->avail_index = vrh->last_avail_idx; } static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 2d8c950ad3a8..066b165c17b1 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -349,6 +349,7 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, { struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; + struct vdpa_vq_state vq_state; struct vdpa_callback cb; struct vhost_virtqueue *vq; struct vhost_vring_state s; @@ -374,7 +375,8 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, ops->set_vq_ready(vdpa, idx, s.num); return 0; case VHOST_GET_VRING_BASE: - vq->last_avail_idx = ops->get_vq_state(v->vdpa, idx); + ops->get_vq_state(v->vdpa, idx, &vq_state); + vq->last_avail_idx = vq_state.avail_index; break; case VHOST_GET_BACKEND_FEATURES: features = VHOST_VDPA_BACKEND_FEATURES; @@ -404,7 +406,8 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, break; case VHOST_SET_VRING_BASE: - if (ops->set_vq_state(vdpa, idx, vq->last_avail_idx)) + vq_state.avail_index = vq->last_avail_idx; + if (ops->set_vq_state(vdpa, idx, &vq_state)) r = -EINVAL; break; diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index b5901cde73e0..d7399c983734 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -27,6 +27,14 @@ struct vdpa_notification_area { resource_size_t size; }; +/** + * vDPA vq_state definition + * @avail_index: available index + */ +struct vdpa_vq_state { + u16 avail_index; +}; + /** * vDPA device - representation of a vDPA device * @dev: underlying device @@ -80,12 +88,12 @@ struct vdpa_device { * @set_vq_state: Set the state for a virtqueue * @vdev: vdpa device * @idx: virtqueue index - * @state: virtqueue state (last_avail_idx) + * @state: pointer to set virtqueue state (last_avail_idx) * Returns integer: success (0) or error (< 0) * @get_vq_state: Get the state for a virtqueue * @vdev: vdpa device * @idx: virtqueue index - * Returns virtqueue state (last_avail_idx) + * @state: pointer to returned state (last_avail_idx) * @get_vq_notification: Get the notification area for a virtqueue * @vdev: vdpa device * @idx: virtqueue index @@ -183,8 +191,10 @@ struct vdpa_config_ops { struct vdpa_callback *cb); void (*set_vq_ready)(struct vdpa_device *vdev, u16 idx, bool ready); bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx); - int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, u64 state); - u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx); + int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, + const struct vdpa_vq_state *state); + void (*get_vq_state)(struct vdpa_device *vdev, u16 idx, + struct vdpa_vq_state *state); struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* vq irq is not expected to be changed once DRIVER_OK is set */ From 23750e39d57433d0e3d89658f0bc448f9c42ff49 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 4 Aug 2020 19:20:44 +0300 Subject: [PATCH 275/291] vdpa: Modify get_vq_state() to return error code Modify get_vq_state() so it returns an error code. In case of hardware acceleration, the available index may be retrieved from the device, an operation that can possibly fail. Reviewed-by: Parav Pandit Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20200804162048.22587-9-eli@mellanox.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/ifcvf/ifcvf_main.c | 5 +++-- drivers/vdpa/vdpa_sim/vdpa_sim.c | 5 +++-- drivers/vhost/vdpa.c | 5 ++++- include/linux/vdpa.h | 4 ++-- 4 files changed, 12 insertions(+), 7 deletions(-) diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index dc311e972b9e..076d7ac5e723 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -237,12 +237,13 @@ static u16 ifcvf_vdpa_get_vq_num_max(struct vdpa_device *vdpa_dev) return IFCVF_QUEUE_MAX; } -static void ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid, - struct vdpa_vq_state *state) +static int ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid, + struct vdpa_vq_state *state) { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); state->avail_index = ifcvf_get_vq_state(vf, qid); + return 0; } static int ifcvf_vdpa_set_vq_state(struct vdpa_device *vdpa_dev, u16 qid, diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index c93126ad09d1..df3224b138ee 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -464,14 +464,15 @@ static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx, return 0; } -static void vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx, - struct vdpa_vq_state *state) +static int vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx, + struct vdpa_vq_state *state) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; struct vringh *vrh = &vq->vring; state->avail_index = vrh->last_avail_idx; + return 0; } static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 066b165c17b1..3fab94f88894 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -375,7 +375,10 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, ops->set_vq_ready(vdpa, idx, s.num); return 0; case VHOST_GET_VRING_BASE: - ops->get_vq_state(v->vdpa, idx, &vq_state); + r = ops->get_vq_state(v->vdpa, idx, &vq_state); + if (r) + return r; + vq->last_avail_idx = vq_state.avail_index; break; case VHOST_GET_BACKEND_FEATURES: diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index d7399c983734..eae0bfd87d91 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -193,8 +193,8 @@ struct vdpa_config_ops { bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx); int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, const struct vdpa_vq_state *state); - void (*get_vq_state)(struct vdpa_device *vdev, u16 idx, - struct vdpa_vq_state *state); + int (*get_vq_state)(struct vdpa_device *vdev, u16 idx, + struct vdpa_vq_state *state); struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* vq irq is not expected to be changed once DRIVER_OK is set */ From 89349be659d63767cf79e23767da84408a33cd73 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 4 Aug 2020 19:20:45 +0300 Subject: [PATCH 276/291] vdpa/mlx5: Add hardware descriptive header file Keep all vdpa related hardware definitions in this file. Reviewed-by: Parav Pandit Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20200804162048.22587-10-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h | 168 +++++++++++++++++++++++++ 1 file changed, 168 insertions(+) create mode 100644 drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h b/drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h new file mode 100644 index 000000000000..f6f57a29b38e --- /dev/null +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h @@ -0,0 +1,168 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies Ltd. */ + +#ifndef __MLX5_VDPA_IFC_H_ +#define __MLX5_VDPA_IFC_H_ + +#include + +enum { + MLX5_VIRTIO_Q_EVENT_MODE_NO_MSIX_MODE = 0x0, + MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE = 0x1, + MLX5_VIRTIO_Q_EVENT_MODE_MSIX_MODE = 0x2, +}; + +enum { + MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT = 0x1, // do I check this caps? + MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED = 0x2, +}; + +enum { + MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT = 0, + MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED = 1, +}; + +struct mlx5_ifc_virtio_q_bits { + u8 virtio_q_type[0x8]; + u8 reserved_at_8[0x5]; + u8 event_mode[0x3]; + u8 queue_index[0x10]; + + u8 full_emulation[0x1]; + u8 virtio_version_1_0[0x1]; + u8 reserved_at_22[0x2]; + u8 offload_type[0x4]; + u8 event_qpn_or_msix[0x18]; + + u8 doorbell_stride_index[0x10]; + u8 queue_size[0x10]; + + u8 device_emulation_id[0x20]; + + u8 desc_addr[0x40]; + + u8 used_addr[0x40]; + + u8 available_addr[0x40]; + + u8 virtio_q_mkey[0x20]; + + u8 max_tunnel_desc[0x10]; + u8 reserved_at_170[0x8]; + u8 error_type[0x8]; + + u8 umem_1_id[0x20]; + + u8 umem_1_size[0x20]; + + u8 umem_1_offset[0x40]; + + u8 umem_2_id[0x20]; + + u8 umem_2_size[0x20]; + + u8 umem_2_offset[0x40]; + + u8 umem_3_id[0x20]; + + u8 umem_3_size[0x20]; + + u8 umem_3_offset[0x40]; + + u8 counter_set_id[0x20]; + + u8 reserved_at_320[0x8]; + u8 pd[0x18]; + + u8 reserved_at_340[0xc0]; +}; + +struct mlx5_ifc_virtio_net_q_object_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x20]; + + u8 vhca_id[0x10]; + u8 reserved_at_70[0x10]; + + u8 queue_feature_bit_mask_12_3[0xa]; + u8 dirty_bitmap_dump_enable[0x1]; + u8 vhost_log_page[0x5]; + u8 reserved_at_90[0xc]; + u8 state[0x4]; + + u8 reserved_at_a0[0x5]; + u8 queue_feature_bit_mask_2_0[0x3]; + u8 tisn_or_qpn[0x18]; + + u8 dirty_bitmap_mkey[0x20]; + + u8 dirty_bitmap_size[0x20]; + + u8 dirty_bitmap_addr[0x40]; + + u8 hw_available_index[0x10]; + u8 hw_used_index[0x10]; + + u8 reserved_at_160[0xa0]; + + struct mlx5_ifc_virtio_q_bits virtio_q_context; +}; + +struct mlx5_ifc_create_virtio_net_q_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + + struct mlx5_ifc_virtio_net_q_object_bits obj_context; +}; + +struct mlx5_ifc_create_virtio_net_q_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; +}; + +struct mlx5_ifc_destroy_virtio_net_q_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_out_cmd_hdr; +}; + +struct mlx5_ifc_destroy_virtio_net_q_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; +}; + +struct mlx5_ifc_query_virtio_net_q_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; +}; + +struct mlx5_ifc_query_virtio_net_q_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; + + struct mlx5_ifc_virtio_net_q_object_bits obj_context; +}; + +enum { + MLX5_VIRTQ_MODIFY_MASK_STATE = (u64)1 << 0, + MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS = (u64)1 << 3, + MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4, +}; + +enum { + MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT = 0x0, + MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY = 0x1, + MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND = 0x2, + MLX5_VIRTIO_NET_Q_OBJECT_STATE_ERR = 0x3, +}; + +enum { + MLX5_RQTC_LIST_Q_TYPE_RQ = 0x0, + MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q = 0x1, +}; + +struct mlx5_ifc_modify_virtio_net_q_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + + struct mlx5_ifc_virtio_net_q_object_bits obj_context; +}; + +struct mlx5_ifc_modify_virtio_net_q_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; +}; + +#endif /* __MLX5_VDPA_IFC_H_ */ From 29064bfdabd5ef49eac6909d3a36a075e3b52255 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 4 Aug 2020 19:20:46 +0300 Subject: [PATCH 277/291] vdpa/mlx5: Add support library for mlx5 VDPA implementation Following patches introduce VDPA network driver for Mellanox Connectx6 devices. This patch provides functionality that will be used by those patches. Reviewed-by: Parav Pandit Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20200804162048.22587-11-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/Kconfig | 9 + drivers/vdpa/Makefile | 1 + drivers/vdpa/mlx5/Makefile | 1 + drivers/vdpa/mlx5/core/Makefile | 1 + drivers/vdpa/mlx5/core/mlx5_vdpa.h | 57 ++++++ drivers/vdpa/mlx5/core/resources.c | 281 +++++++++++++++++++++++++++++ 6 files changed, 350 insertions(+) create mode 100644 drivers/vdpa/mlx5/Makefile create mode 100644 drivers/vdpa/mlx5/core/Makefile create mode 100644 drivers/vdpa/mlx5/core/mlx5_vdpa.h create mode 100644 drivers/vdpa/mlx5/core/resources.c diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index 3e1ceb8e9f2b..7cb84f82feba 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -28,4 +28,13 @@ config IFCVF To compile this driver as a module, choose M here: the module will be called ifcvf. +config MLX5_VDPA + bool "MLX5 VDPA support library for ConnectX devices" + depends on MLX5_CORE + default n + help + Support library for Mellanox VDPA drivers. Provides code that is + common for all types of VDPA drivers. The following drivers are planned: + net, block. + endif # VDPA diff --git a/drivers/vdpa/Makefile b/drivers/vdpa/Makefile index 8bbb686ca7a2..d160e9b63a66 100644 --- a/drivers/vdpa/Makefile +++ b/drivers/vdpa/Makefile @@ -2,3 +2,4 @@ obj-$(CONFIG_VDPA) += vdpa.o obj-$(CONFIG_VDPA_SIM) += vdpa_sim/ obj-$(CONFIG_IFCVF) += ifcvf/ +obj-$(CONFIG_MLX5_VDPA) += mlx5/ diff --git a/drivers/vdpa/mlx5/Makefile b/drivers/vdpa/mlx5/Makefile new file mode 100644 index 000000000000..d552abb1d126 --- /dev/null +++ b/drivers/vdpa/mlx5/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_MLX5_VDPA) += core/resources.o diff --git a/drivers/vdpa/mlx5/core/Makefile b/drivers/vdpa/mlx5/core/Makefile new file mode 100644 index 000000000000..7070f8c8680d --- /dev/null +++ b/drivers/vdpa/mlx5/core/Makefile @@ -0,0 +1 @@ +obj-y += resources.o diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h new file mode 100644 index 000000000000..f3571c8b257e --- /dev/null +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies Ltd. */ + +#ifndef __MLX5_VDPA_H__ +#define __MLX5_VDPA_H__ + +#include +#include + +struct mlx5_vdpa_resources { + u32 pdn; + struct mlx5_uars_page *uar; + void __iomem *kick_addr; + u16 uid; + u32 null_mkey; + bool valid; +}; + +struct mlx5_vdpa_dev { + struct vdpa_device vdev; + struct mlx5_core_dev *mdev; + struct mlx5_vdpa_resources res; + + u64 mlx_features; + u64 actual_features; + u8 status; + u32 max_vqs; + u32 generation; +}; + +int mlx5_vdpa_alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid); +int mlx5_vdpa_dealloc_pd(struct mlx5_vdpa_dev *dev, u32 pdn, u16 uid); +int mlx5_vdpa_get_null_mkey(struct mlx5_vdpa_dev *dev, u32 *null_mkey); +int mlx5_vdpa_create_tis(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tisn); +void mlx5_vdpa_destroy_tis(struct mlx5_vdpa_dev *mvdev, u32 tisn); +int mlx5_vdpa_create_rqt(struct mlx5_vdpa_dev *mvdev, void *in, int inlen, u32 *rqtn); +void mlx5_vdpa_destroy_rqt(struct mlx5_vdpa_dev *mvdev, u32 rqtn); +int mlx5_vdpa_create_tir(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tirn); +void mlx5_vdpa_destroy_tir(struct mlx5_vdpa_dev *mvdev, u32 tirn); +int mlx5_vdpa_alloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 *tdn); +void mlx5_vdpa_dealloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 tdn); +int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev); +void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev); + +#define mlx5_vdpa_warn(__dev, format, ...) \ + dev_warn((__dev)->mdev->device, "%s:%d:(pid %d) warning: " format, __func__, __LINE__, \ + current->pid, ##__VA_ARGS__) + +#define mlx5_vdpa_info(__dev, format, ...) \ + dev_info((__dev)->mdev->device, "%s:%d:(pid %d): " format, __func__, __LINE__, \ + current->pid, ##__VA_ARGS__) + +#define mlx5_vdpa_dbg(__dev, format, ...) \ + dev_debug((__dev)->mdev->device, "%s:%d:(pid %d): " format, __func__, __LINE__, \ + current->pid, ##__VA_ARGS__) + +#endif /* __MLX5_VDPA_H__ */ diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c new file mode 100644 index 000000000000..6c6552b7e9b5 --- /dev/null +++ b/drivers/vdpa/mlx5/core/resources.c @@ -0,0 +1,281 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Ltd. */ + +#include +#include "mlx5_vdpa.h" + +static int alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid) +{ + struct mlx5_core_dev *mdev = dev->mdev; + + u32 out[MLX5_ST_SZ_DW(alloc_pd_out)] = {}; + u32 in[MLX5_ST_SZ_DW(alloc_pd_in)] = {}; + int err; + + MLX5_SET(alloc_pd_in, in, opcode, MLX5_CMD_OP_ALLOC_PD); + MLX5_SET(alloc_pd_in, in, uid, uid); + + err = mlx5_cmd_exec_inout(mdev, alloc_pd, in, out); + if (!err) + *pdn = MLX5_GET(alloc_pd_out, out, pd); + + return err; +} + +static int dealloc_pd(struct mlx5_vdpa_dev *dev, u32 pdn, u16 uid) +{ + u32 in[MLX5_ST_SZ_DW(dealloc_pd_in)] = {}; + struct mlx5_core_dev *mdev = dev->mdev; + + MLX5_SET(dealloc_pd_in, in, opcode, MLX5_CMD_OP_DEALLOC_PD); + MLX5_SET(dealloc_pd_in, in, pd, pdn); + MLX5_SET(dealloc_pd_in, in, uid, uid); + return mlx5_cmd_exec_in(mdev, dealloc_pd, in); +} + +static int get_null_mkey(struct mlx5_vdpa_dev *dev, u32 *null_mkey) +{ + u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {}; + struct mlx5_core_dev *mdev = dev->mdev; + int err; + + MLX5_SET(query_special_contexts_in, in, opcode, MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS); + err = mlx5_cmd_exec_inout(mdev, query_special_contexts, in, out); + if (!err) + *null_mkey = MLX5_GET(query_special_contexts_out, out, null_mkey); + return err; +} + +static int create_uctx(struct mlx5_vdpa_dev *mvdev, u16 *uid) +{ + u32 out[MLX5_ST_SZ_DW(create_uctx_out)] = {}; + int inlen; + void *in; + int err; + + /* 0 means not supported */ + if (!MLX5_CAP_GEN(mvdev->mdev, log_max_uctx)) + return -EOPNOTSUPP; + + inlen = MLX5_ST_SZ_BYTES(create_uctx_in); + in = kzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(create_uctx_in, in, opcode, MLX5_CMD_OP_CREATE_UCTX); + MLX5_SET(create_uctx_in, in, uctx.cap, MLX5_UCTX_CAP_RAW_TX); + + err = mlx5_cmd_exec(mvdev->mdev, in, inlen, out, sizeof(out)); + kfree(in); + if (!err) + *uid = MLX5_GET(create_uctx_out, out, uid); + + return err; +} + +static void destroy_uctx(struct mlx5_vdpa_dev *mvdev, u32 uid) +{ + u32 out[MLX5_ST_SZ_DW(destroy_uctx_out)] = {}; + u32 in[MLX5_ST_SZ_DW(destroy_uctx_in)] = {}; + + MLX5_SET(destroy_uctx_in, in, opcode, MLX5_CMD_OP_DESTROY_UCTX); + MLX5_SET(destroy_uctx_in, in, uid, uid); + + mlx5_cmd_exec(mvdev->mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5_vdpa_create_tis(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tisn) +{ + u32 out[MLX5_ST_SZ_DW(create_tis_out)] = {}; + int err; + + MLX5_SET(create_tis_in, in, opcode, MLX5_CMD_OP_CREATE_TIS); + MLX5_SET(create_tis_in, in, uid, mvdev->res.uid); + err = mlx5_cmd_exec_inout(mvdev->mdev, create_tis, in, out); + if (!err) + *tisn = MLX5_GET(create_tis_out, out, tisn); + + return err; +} + +void mlx5_vdpa_destroy_tis(struct mlx5_vdpa_dev *mvdev, u32 tisn) +{ + u32 in[MLX5_ST_SZ_DW(destroy_tis_in)] = {}; + + MLX5_SET(destroy_tis_in, in, opcode, MLX5_CMD_OP_DESTROY_TIS); + MLX5_SET(destroy_tis_in, in, uid, mvdev->res.uid); + MLX5_SET(destroy_tis_in, in, tisn, tisn); + mlx5_cmd_exec_in(mvdev->mdev, destroy_tis, in); +} + +int mlx5_vdpa_create_rqt(struct mlx5_vdpa_dev *mvdev, void *in, int inlen, u32 *rqtn) +{ + u32 out[MLX5_ST_SZ_DW(create_rqt_out)] = {}; + int err; + + MLX5_SET(create_rqt_in, in, opcode, MLX5_CMD_OP_CREATE_RQT); + err = mlx5_cmd_exec(mvdev->mdev, in, inlen, out, sizeof(out)); + if (!err) + *rqtn = MLX5_GET(create_rqt_out, out, rqtn); + + return err; +} + +void mlx5_vdpa_destroy_rqt(struct mlx5_vdpa_dev *mvdev, u32 rqtn) +{ + u32 in[MLX5_ST_SZ_DW(destroy_rqt_in)] = {}; + + MLX5_SET(destroy_rqt_in, in, opcode, MLX5_CMD_OP_DESTROY_RQT); + MLX5_SET(destroy_rqt_in, in, uid, mvdev->res.uid); + MLX5_SET(destroy_rqt_in, in, rqtn, rqtn); + mlx5_cmd_exec_in(mvdev->mdev, destroy_rqt, in); +} + +int mlx5_vdpa_create_tir(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tirn) +{ + u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {}; + int err; + + MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR); + err = mlx5_cmd_exec_inout(mvdev->mdev, create_tir, in, out); + if (!err) + *tirn = MLX5_GET(create_tir_out, out, tirn); + + return err; +} + +void mlx5_vdpa_destroy_tir(struct mlx5_vdpa_dev *mvdev, u32 tirn) +{ + u32 in[MLX5_ST_SZ_DW(destroy_tir_in)] = {}; + + MLX5_SET(destroy_tir_in, in, opcode, MLX5_CMD_OP_DESTROY_TIR); + MLX5_SET(destroy_tir_in, in, uid, mvdev->res.uid); + MLX5_SET(destroy_tir_in, in, tirn, tirn); + mlx5_cmd_exec_in(mvdev->mdev, destroy_tir, in); +} + +int mlx5_vdpa_alloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 *tdn) +{ + u32 out[MLX5_ST_SZ_DW(alloc_transport_domain_out)] = {}; + u32 in[MLX5_ST_SZ_DW(alloc_transport_domain_in)] = {}; + int err; + + MLX5_SET(alloc_transport_domain_in, in, opcode, MLX5_CMD_OP_ALLOC_TRANSPORT_DOMAIN); + MLX5_SET(alloc_transport_domain_in, in, uid, mvdev->res.uid); + + err = mlx5_cmd_exec_inout(mvdev->mdev, alloc_transport_domain, in, out); + if (!err) + *tdn = MLX5_GET(alloc_transport_domain_out, out, transport_domain); + + return err; +} + +void mlx5_vdpa_dealloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 tdn) +{ + u32 in[MLX5_ST_SZ_DW(dealloc_transport_domain_in)] = {}; + + MLX5_SET(dealloc_transport_domain_in, in, opcode, MLX5_CMD_OP_DEALLOC_TRANSPORT_DOMAIN); + MLX5_SET(dealloc_transport_domain_in, in, uid, mvdev->res.uid); + MLX5_SET(dealloc_transport_domain_in, in, transport_domain, tdn); + mlx5_cmd_exec_in(mvdev->mdev, dealloc_transport_domain, in); +} + +int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey, u32 *in, + int inlen) +{ + u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {}; + u32 mkey_index; + void *mkc; + int err; + + MLX5_SET(create_mkey_in, in, opcode, MLX5_CMD_OP_CREATE_MKEY); + MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid); + + err = mlx5_cmd_exec(mvdev->mdev, in, inlen, lout, sizeof(lout)); + if (err) + return err; + + mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); + mkey->iova = MLX5_GET64(mkc, mkc, start_addr); + mkey->size = MLX5_GET64(mkc, mkc, len); + mkey->key |= mlx5_idx_to_mkey(mkey_index); + mkey->pd = MLX5_GET(mkc, mkc, pd); + return 0; +} + +int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey) +{ + u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)] = {}; + + MLX5_SET(destroy_mkey_in, in, uid, mvdev->res.uid); + MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY); + MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key)); + return mlx5_cmd_exec_in(mvdev->mdev, destroy_mkey, in); +} + +int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev) +{ + u64 offset = MLX5_CAP64_DEV_VDPA_EMULATION(mvdev->mdev, doorbell_bar_offset); + struct mlx5_vdpa_resources *res = &mvdev->res; + struct mlx5_core_dev *mdev = mvdev->mdev; + u64 kick_addr; + int err; + + if (res->valid) { + mlx5_vdpa_warn(mvdev, "resources already allocated\n"); + return -EINVAL; + } + res->uar = mlx5_get_uars_page(mdev); + if (IS_ERR(res->uar)) { + err = PTR_ERR(res->uar); + goto err_uars; + } + + err = create_uctx(mvdev, &res->uid); + if (err) + goto err_uctx; + + err = alloc_pd(mvdev, &res->pdn, res->uid); + if (err) + goto err_pd; + + err = get_null_mkey(mvdev, &res->null_mkey); + if (err) + goto err_key; + + kick_addr = pci_resource_start(mdev->pdev, 0) + offset; + res->kick_addr = ioremap(kick_addr, PAGE_SIZE); + if (!res->kick_addr) { + err = -ENOMEM; + goto err_key; + } + res->valid = true; + + return 0; + +err_key: + dealloc_pd(mvdev, res->pdn, res->uid); +err_pd: + destroy_uctx(mvdev, res->uid); +err_uctx: + mlx5_put_uars_page(mdev, res->uar); +err_uars: + return err; +} + +void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev) +{ + struct mlx5_vdpa_resources *res = &mvdev->res; + + if (!res->valid) + return; + + iounmap(res->kick_addr); + res->kick_addr = NULL; + dealloc_pd(mvdev, res->pdn, res->uid); + destroy_uctx(mvdev, res->uid); + mlx5_put_uars_page(mvdev->mdev, res->uar); + res->valid = false; +} From 94abbccdf2916cb03f9626f2d36c6e9971490c12 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 4 Aug 2020 19:20:47 +0300 Subject: [PATCH 278/291] vdpa/mlx5: Add shared memory registration code Add code to support registering address space region for the device. The virtio driver can run as either: 1. Guest virtio driver 2. Userspace virtio driver on the host 3. Kernel virtio driver on the host In any case a memory key object is required to provide access to memory for the device. This code will be shared by network or block driver implementations. Reviewed-by: Parav Pandit Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20200804162048.22587-12-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/mlx5/Makefile | 2 +- drivers/vdpa/mlx5/core/Makefile | 1 - drivers/vdpa/mlx5/core/mlx5_vdpa.h | 34 ++ drivers/vdpa/mlx5/core/mr.c | 484 +++++++++++++++++++++++++++++ drivers/vdpa/mlx5/core/resources.c | 3 + 5 files changed, 522 insertions(+), 2 deletions(-) delete mode 100644 drivers/vdpa/mlx5/core/Makefile create mode 100644 drivers/vdpa/mlx5/core/mr.c diff --git a/drivers/vdpa/mlx5/Makefile b/drivers/vdpa/mlx5/Makefile index d552abb1d126..b347c62032ea 100644 --- a/drivers/vdpa/mlx5/Makefile +++ b/drivers/vdpa/mlx5/Makefile @@ -1 +1 @@ -obj-$(CONFIG_MLX5_VDPA) += core/resources.o +obj-$(CONFIG_MLX5_VDPA) += core/resources.o core/mr.o diff --git a/drivers/vdpa/mlx5/core/Makefile b/drivers/vdpa/mlx5/core/Makefile deleted file mode 100644 index 7070f8c8680d..000000000000 --- a/drivers/vdpa/mlx5/core/Makefile +++ /dev/null @@ -1 +0,0 @@ -obj-y += resources.o diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index f3571c8b257e..5c92a576edae 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -7,6 +7,31 @@ #include #include +struct mlx5_vdpa_direct_mr { + u64 start; + u64 end; + u32 perm; + struct mlx5_core_mkey mr; + struct sg_table sg_head; + int log_size; + int nsg; + struct list_head list; + u64 offset; +}; + +struct mlx5_vdpa_mr { + struct mlx5_core_mkey mkey; + + /* list of direct MRs descendants of this indirect mr */ + struct list_head head; + unsigned long num_directs; + unsigned long num_klms; + bool initialized; + + /* serialize mkey creation and destruction */ + struct mutex mkey_mtx; +}; + struct mlx5_vdpa_resources { u32 pdn; struct mlx5_uars_page *uar; @@ -26,6 +51,8 @@ struct mlx5_vdpa_dev { u8 status; u32 max_vqs; u32 generation; + + struct mlx5_vdpa_mr mr; }; int mlx5_vdpa_alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid); @@ -41,6 +68,13 @@ int mlx5_vdpa_alloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 *tdn); void mlx5_vdpa_dealloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 tdn); int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev); void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev); +int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey, u32 *in, + int inlen); +int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey); +int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, + bool *change_map); +int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb); +void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev); #define mlx5_vdpa_warn(__dev, format, ...) \ dev_warn((__dev)->mdev->device, "%s:%d:(pid %d) warning: " format, __func__, __LINE__, \ diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c new file mode 100644 index 000000000000..084698975c47 --- /dev/null +++ b/drivers/vdpa/mlx5/core/mr.c @@ -0,0 +1,484 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Ltd. */ + +#include +#include +#include +#include +#include "mlx5_vdpa.h" + +/* DIV_ROUND_UP where the divider is a power of 2 give by its log base 2 value */ +#define MLX5_DIV_ROUND_UP_POW2(_n, _s) \ +({ \ + u64 __s = _s; \ + u64 _res; \ + _res = (((_n) + (1 << (__s)) - 1) >> (__s)); \ + _res; \ +}) + +static int get_octo_len(u64 len, int page_shift) +{ + u64 page_size = 1ULL << page_shift; + int npages; + + npages = ALIGN(len, page_size) >> page_shift; + return (npages + 1) / 2; +} + +static void fill_sg(struct mlx5_vdpa_direct_mr *mr, void *in) +{ + struct scatterlist *sg; + __be64 *pas; + int i; + + pas = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); + for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) + (*pas) = cpu_to_be64(sg_dma_address(sg)); +} + +static void mlx5_set_access_mode(void *mkc, int mode) +{ + MLX5_SET(mkc, mkc, access_mode_1_0, mode & 0x3); + MLX5_SET(mkc, mkc, access_mode_4_2, mode >> 2); +} + +static void populate_mtts(struct mlx5_vdpa_direct_mr *mr, __be64 *mtt) +{ + struct scatterlist *sg; + int i; + + for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) + mtt[i] = cpu_to_be64(sg_dma_address(sg)); +} + +static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr) +{ + int inlen; + void *mkc; + void *in; + int err; + + inlen = MLX5_ST_SZ_BYTES(create_mkey_in) + roundup(MLX5_ST_SZ_BYTES(mtt) * mr->nsg, 16); + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid); + fill_sg(mr, in); + mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + MLX5_SET(mkc, mkc, lw, !!(mr->perm & VHOST_MAP_WO)); + MLX5_SET(mkc, mkc, lr, !!(mr->perm & VHOST_MAP_RO)); + mlx5_set_access_mode(mkc, MLX5_MKC_ACCESS_MODE_MTT); + MLX5_SET(mkc, mkc, qpn, 0xffffff); + MLX5_SET(mkc, mkc, pd, mvdev->res.pdn); + MLX5_SET64(mkc, mkc, start_addr, mr->offset); + MLX5_SET64(mkc, mkc, len, mr->end - mr->start); + MLX5_SET(mkc, mkc, log_page_size, mr->log_size); + MLX5_SET(mkc, mkc, translations_octword_size, + get_octo_len(mr->end - mr->start, mr->log_size)); + MLX5_SET(create_mkey_in, in, translations_octword_actual_size, + get_octo_len(mr->end - mr->start, mr->log_size)); + populate_mtts(mr, MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt)); + err = mlx5_vdpa_create_mkey(mvdev, &mr->mr, in, inlen); + kvfree(in); + if (err) { + mlx5_vdpa_warn(mvdev, "Failed to create direct MR\n"); + return err; + } + + return 0; +} + +static void destroy_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr) +{ + mlx5_vdpa_destroy_mkey(mvdev, &mr->mr); +} + +static u64 map_start(struct vhost_iotlb_map *map, struct mlx5_vdpa_direct_mr *mr) +{ + return max_t(u64, map->start, mr->start); +} + +static u64 map_end(struct vhost_iotlb_map *map, struct mlx5_vdpa_direct_mr *mr) +{ + return min_t(u64, map->last + 1, mr->end); +} + +static u64 maplen(struct vhost_iotlb_map *map, struct mlx5_vdpa_direct_mr *mr) +{ + return map_end(map, mr) - map_start(map, mr); +} + +#define MLX5_VDPA_INVALID_START_ADDR ((u64)-1) +#define MLX5_VDPA_INVALID_LEN ((u64)-1) + +static u64 indir_start_addr(struct mlx5_vdpa_mr *mkey) +{ + struct mlx5_vdpa_direct_mr *s; + + s = list_first_entry_or_null(&mkey->head, struct mlx5_vdpa_direct_mr, list); + if (!s) + return MLX5_VDPA_INVALID_START_ADDR; + + return s->start; +} + +static u64 indir_len(struct mlx5_vdpa_mr *mkey) +{ + struct mlx5_vdpa_direct_mr *s; + struct mlx5_vdpa_direct_mr *e; + + s = list_first_entry_or_null(&mkey->head, struct mlx5_vdpa_direct_mr, list); + if (!s) + return MLX5_VDPA_INVALID_LEN; + + e = list_last_entry(&mkey->head, struct mlx5_vdpa_direct_mr, list); + + return e->end - s->start; +} + +#define LOG_MAX_KLM_SIZE 30 +#define MAX_KLM_SIZE BIT(LOG_MAX_KLM_SIZE) + +static u32 klm_bcount(u64 size) +{ + return (u32)size; +} + +static void fill_indir(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mkey, void *in) +{ + struct mlx5_vdpa_direct_mr *dmr; + struct mlx5_klm *klmarr; + struct mlx5_klm *klm; + bool first = true; + u64 preve; + int i; + + klmarr = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); + i = 0; + list_for_each_entry(dmr, &mkey->head, list) { +again: + klm = &klmarr[i++]; + if (first) { + preve = dmr->start; + first = false; + } + + if (preve == dmr->start) { + klm->key = cpu_to_be32(dmr->mr.key); + klm->bcount = cpu_to_be32(klm_bcount(dmr->end - dmr->start)); + preve = dmr->end; + } else { + klm->key = cpu_to_be32(mvdev->res.null_mkey); + klm->bcount = cpu_to_be32(klm_bcount(dmr->start - preve)); + preve = dmr->start; + goto again; + } + } +} + +static int klm_byte_size(int nklms) +{ + return 16 * ALIGN(nklms, 4); +} + +static int create_indirect_key(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr) +{ + int inlen; + void *mkc; + void *in; + int err; + u64 start; + u64 len; + + start = indir_start_addr(mr); + len = indir_len(mr); + if (start == MLX5_VDPA_INVALID_START_ADDR || len == MLX5_VDPA_INVALID_LEN) + return -EINVAL; + + inlen = MLX5_ST_SZ_BYTES(create_mkey_in) + klm_byte_size(mr->num_klms); + in = kzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid); + mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + MLX5_SET(mkc, mkc, lw, 1); + MLX5_SET(mkc, mkc, lr, 1); + mlx5_set_access_mode(mkc, MLX5_MKC_ACCESS_MODE_KLMS); + MLX5_SET(mkc, mkc, qpn, 0xffffff); + MLX5_SET(mkc, mkc, pd, mvdev->res.pdn); + MLX5_SET64(mkc, mkc, start_addr, start); + MLX5_SET64(mkc, mkc, len, len); + MLX5_SET(mkc, mkc, translations_octword_size, klm_byte_size(mr->num_klms) / 16); + MLX5_SET(create_mkey_in, in, translations_octword_actual_size, mr->num_klms); + fill_indir(mvdev, mr, in); + err = mlx5_vdpa_create_mkey(mvdev, &mr->mkey, in, inlen); + kfree(in); + return err; +} + +static void destroy_indirect_key(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mkey) +{ + mlx5_vdpa_destroy_mkey(mvdev, &mkey->mkey); +} + +static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr, + struct vhost_iotlb *iotlb) +{ + struct vhost_iotlb_map *map; + unsigned long lgcd = 0; + int log_entity_size; + unsigned long size; + u64 start = 0; + int err; + struct page *pg; + unsigned int nsg; + int sglen; + u64 pa; + u64 paend; + struct scatterlist *sg; + struct device *dma = mvdev->mdev->device; + int ret; + + for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1); + map; map = vhost_iotlb_itree_next(map, start, mr->end - 1)) { + size = maplen(map, mr); + lgcd = gcd(lgcd, size); + start += size; + } + log_entity_size = ilog2(lgcd); + + sglen = 1 << log_entity_size; + nsg = MLX5_DIV_ROUND_UP_POW2(mr->end - mr->start, log_entity_size); + + err = sg_alloc_table(&mr->sg_head, nsg, GFP_KERNEL); + if (err) + return err; + + sg = mr->sg_head.sgl; + for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1); + map; map = vhost_iotlb_itree_next(map, mr->start, mr->end - 1)) { + paend = map->addr + maplen(map, mr); + for (pa = map->addr; pa < paend; pa += sglen) { + pg = pfn_to_page(__phys_to_pfn(pa)); + if (!sg) { + mlx5_vdpa_warn(mvdev, "sg null. start 0x%llx, end 0x%llx\n", + map->start, map->last + 1); + err = -ENOMEM; + goto err_map; + } + sg_set_page(sg, pg, sglen, 0); + sg = sg_next(sg); + if (!sg) + goto done; + } + } +done: + mr->log_size = log_entity_size; + mr->nsg = nsg; + ret = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); + if (!ret) + goto err_map; + + err = create_direct_mr(mvdev, mr); + if (err) + goto err_direct; + + return 0; + +err_direct: + dma_unmap_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); +err_map: + sg_free_table(&mr->sg_head); + return err; +} + +static void unmap_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr) +{ + struct device *dma = mvdev->mdev->device; + + destroy_direct_mr(mvdev, mr); + dma_unmap_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); + sg_free_table(&mr->sg_head); +} + +static int add_direct_chain(struct mlx5_vdpa_dev *mvdev, u64 start, u64 size, u8 perm, + struct vhost_iotlb *iotlb) +{ + struct mlx5_vdpa_mr *mr = &mvdev->mr; + struct mlx5_vdpa_direct_mr *dmr; + struct mlx5_vdpa_direct_mr *n; + LIST_HEAD(tmp); + u64 st; + u64 sz; + int err; + int i = 0; + + st = start; + while (size) { + sz = (u32)min_t(u64, MAX_KLM_SIZE, size); + dmr = kzalloc(sizeof(*dmr), GFP_KERNEL); + if (!dmr) + goto err_alloc; + + dmr->start = st; + dmr->end = st + sz; + dmr->perm = perm; + err = map_direct_mr(mvdev, dmr, iotlb); + if (err) { + kfree(dmr); + goto err_alloc; + } + + list_add_tail(&dmr->list, &tmp); + size -= sz; + mr->num_directs++; + mr->num_klms++; + st += sz; + i++; + } + list_splice_tail(&tmp, &mr->head); + return 0; + +err_alloc: + list_for_each_entry_safe(dmr, n, &mr->head, list) { + list_del_init(&dmr->list); + unmap_direct_mr(mvdev, dmr); + kfree(dmr); + } + return err; +} + +/* The iotlb pointer contains a list of maps. Go over the maps, possibly + * merging mergeable maps, and create direct memory keys that provide the + * device access to memory. The direct mkeys are then referred to by the + * indirect memory key that provides access to the enitre address space given + * by iotlb. + */ +static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) +{ + struct mlx5_vdpa_mr *mr = &mvdev->mr; + struct mlx5_vdpa_direct_mr *dmr; + struct mlx5_vdpa_direct_mr *n; + struct vhost_iotlb_map *map; + u32 pperm = U16_MAX; + u64 last = U64_MAX; + u64 ps = U64_MAX; + u64 pe = U64_MAX; + u64 start = 0; + int err = 0; + int nnuls; + + if (mr->initialized) + return 0; + + INIT_LIST_HEAD(&mr->head); + for (map = vhost_iotlb_itree_first(iotlb, start, last); map; + map = vhost_iotlb_itree_next(map, start, last)) { + start = map->start; + if (pe == map->start && pperm == map->perm) { + pe = map->last + 1; + } else { + if (ps != U64_MAX) { + if (pe < map->start) { + /* We have a hole in the map. Check how + * many null keys are required to fill it. + */ + nnuls = MLX5_DIV_ROUND_UP_POW2(map->start - pe, + LOG_MAX_KLM_SIZE); + mr->num_klms += nnuls; + } + err = add_direct_chain(mvdev, ps, pe - ps, pperm, iotlb); + if (err) + goto err_chain; + } + ps = map->start; + pe = map->last + 1; + pperm = map->perm; + } + } + err = add_direct_chain(mvdev, ps, pe - ps, pperm, iotlb); + if (err) + goto err_chain; + + /* Create the memory key that defines the guests's address space. This + * memory key refers to the direct keys that contain the MTT + * translations + */ + err = create_indirect_key(mvdev, mr); + if (err) + goto err_chain; + + mr->initialized = true; + return 0; + +err_chain: + list_for_each_entry_safe_reverse(dmr, n, &mr->head, list) { + list_del_init(&dmr->list); + unmap_direct_mr(mvdev, dmr); + kfree(dmr); + } + return err; +} + +int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) +{ + struct mlx5_vdpa_mr *mr = &mvdev->mr; + int err; + + mutex_lock(&mr->mkey_mtx); + err = _mlx5_vdpa_create_mr(mvdev, iotlb); + mutex_unlock(&mr->mkey_mtx); + return err; +} + +void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev) +{ + struct mlx5_vdpa_mr *mr = &mvdev->mr; + struct mlx5_vdpa_direct_mr *dmr; + struct mlx5_vdpa_direct_mr *n; + + mutex_lock(&mr->mkey_mtx); + if (!mr->initialized) + goto out; + + destroy_indirect_key(mvdev, mr); + list_for_each_entry_safe_reverse(dmr, n, &mr->head, list) { + list_del_init(&dmr->list); + unmap_direct_mr(mvdev, dmr); + kfree(dmr); + } + memset(mr, 0, sizeof(*mr)); + mr->initialized = false; +out: + mutex_unlock(&mr->mkey_mtx); +} + +static bool map_empty(struct vhost_iotlb *iotlb) +{ + return !vhost_iotlb_itree_first(iotlb, 0, U64_MAX); +} + +int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, + bool *change_map) +{ + struct mlx5_vdpa_mr *mr = &mvdev->mr; + int err; + + *change_map = false; + if (map_empty(iotlb)) { + mlx5_vdpa_destroy_mr(mvdev); + return 0; + } + mutex_lock(&mr->mkey_mtx); + if (mr->initialized) { + mlx5_vdpa_info(mvdev, "memory map update\n"); + *change_map = true; + } + if (!*change_map) + err = _mlx5_vdpa_create_mr(mvdev, iotlb); + mutex_unlock(&mr->mkey_mtx); + + return err; +} diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c index 6c6552b7e9b5..96e6421c5d1c 100644 --- a/drivers/vdpa/mlx5/core/resources.c +++ b/drivers/vdpa/mlx5/core/resources.c @@ -227,6 +227,7 @@ int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev) mlx5_vdpa_warn(mvdev, "resources already allocated\n"); return -EINVAL; } + mutex_init(&mvdev->mr.mkey_mtx); res->uar = mlx5_get_uars_page(mdev); if (IS_ERR(res->uar)) { err = PTR_ERR(res->uar); @@ -262,6 +263,7 @@ int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev) err_uctx: mlx5_put_uars_page(mdev, res->uar); err_uars: + mutex_destroy(&mvdev->mr.mkey_mtx); return err; } @@ -277,5 +279,6 @@ void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev) dealloc_pd(mvdev, res->pdn, res->uid); destroy_uctx(mvdev, res->uid); mlx5_put_uars_page(mvdev->mdev, res->uar); + mutex_destroy(&mvdev->mr.mkey_mtx); res->valid = false; } From 1a86b377aa2147a7c866b03142e848c18e5f3cb8 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 4 Aug 2020 19:20:48 +0300 Subject: [PATCH 279/291] vdpa/mlx5: Add VDPA driver for supported mlx5 devices Add a front end VDPA driver that registers in the VDPA bus and provides networking to a guest. The VDPA driver creates the necessary resources on the VF it is driving such that data path will be offloaded. Notifications are being communicated through the driver. Currently, only VFs are supported. In subsequent patches we will have devlink support to control which VF is used for VDPA and which function is used for regular networking. Reviewed-by: Parav Pandit Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20200804162048.22587-13-eli@mellanox.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/Kconfig | 10 + drivers/vdpa/mlx5/Makefile | 5 +- drivers/vdpa/mlx5/core/mr.c | 2 +- drivers/vdpa/mlx5/net/main.c | 76 ++ drivers/vdpa/mlx5/net/mlx5_vnet.c | 1965 +++++++++++++++++++++++++++++ drivers/vdpa/mlx5/net/mlx5_vnet.h | 24 + 6 files changed, 2080 insertions(+), 2 deletions(-) create mode 100644 drivers/vdpa/mlx5/net/main.c create mode 100644 drivers/vdpa/mlx5/net/mlx5_vnet.c create mode 100644 drivers/vdpa/mlx5/net/mlx5_vnet.h diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index 7cb84f82feba..a8c7607fdc90 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -37,4 +37,14 @@ config MLX5_VDPA common for all types of VDPA drivers. The following drivers are planned: net, block. +config MLX5_VDPA_NET + tristate "vDPA driver for ConnectX devices" + depends on MLX5_VDPA + default n + help + VDPA network driver for ConnectX6 and newer. Provides offloading + of virtio net datapath such that descriptors put on the ring will + be executed by the hardware. It also supports a variety of stateless + offloads depending on the actual device used and firmware version. + endif # VDPA diff --git a/drivers/vdpa/mlx5/Makefile b/drivers/vdpa/mlx5/Makefile index b347c62032ea..89a5bededc9f 100644 --- a/drivers/vdpa/mlx5/Makefile +++ b/drivers/vdpa/mlx5/Makefile @@ -1 +1,4 @@ -obj-$(CONFIG_MLX5_VDPA) += core/resources.o core/mr.o +subdir-ccflags-y += -I$(srctree)/drivers/vdpa/mlx5/core + +obj-$(CONFIG_MLX5_VDPA_NET) += mlx5_vdpa.o +mlx5_vdpa-$(CONFIG_MLX5_VDPA_NET) += net/main.o net/mlx5_vnet.o core/resources.o core/mr.o diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index 084698975c47..f5dec0274133 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -464,7 +464,7 @@ int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *io bool *change_map) { struct mlx5_vdpa_mr *mr = &mvdev->mr; - int err; + int err = 0; *change_map = false; if (map_empty(iotlb)) { diff --git a/drivers/vdpa/mlx5/net/main.c b/drivers/vdpa/mlx5/net/main.c new file mode 100644 index 000000000000..838cd98386ff --- /dev/null +++ b/drivers/vdpa/mlx5/net/main.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Ltd. */ + +#include +#include +#include +#include "mlx5_vdpa_ifc.h" +#include "mlx5_vnet.h" + +MODULE_AUTHOR("Eli Cohen "); +MODULE_DESCRIPTION("Mellanox VDPA driver"); +MODULE_LICENSE("Dual BSD/GPL"); + +static bool required_caps_supported(struct mlx5_core_dev *mdev) +{ + u8 event_mode; + u64 got; + + got = MLX5_CAP_GEN_64(mdev, general_obj_types); + + if (!(got & MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q)) + return false; + + event_mode = MLX5_CAP_DEV_VDPA_EMULATION(mdev, event_mode); + if (!(event_mode & MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE)) + return false; + + if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, eth_frame_offload_type)) + return false; + + return true; +} + +static void *mlx5_vdpa_add(struct mlx5_core_dev *mdev) +{ + struct mlx5_vdpa_dev *vdev; + + if (mlx5_core_is_pf(mdev)) + return NULL; + + if (!required_caps_supported(mdev)) { + dev_info(mdev->device, "virtio net emulation not supported\n"); + return NULL; + } + vdev = mlx5_vdpa_add_dev(mdev); + if (IS_ERR(vdev)) + return NULL; + + return vdev; +} + +static void mlx5_vdpa_remove(struct mlx5_core_dev *mdev, void *context) +{ + struct mlx5_vdpa_dev *vdev = context; + + mlx5_vdpa_remove_dev(vdev); +} + +static struct mlx5_interface mlx5_vdpa_interface = { + .add = mlx5_vdpa_add, + .remove = mlx5_vdpa_remove, + .protocol = MLX5_INTERFACE_PROTOCOL_VDPA, +}; + +static int __init mlx5_vdpa_init(void) +{ + return mlx5_register_interface(&mlx5_vdpa_interface); +} + +static void __exit mlx5_vdpa_exit(void) +{ + mlx5_unregister_interface(&mlx5_vdpa_interface); +} + +module_init(mlx5_vdpa_init); +module_exit(mlx5_vdpa_exit); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c new file mode 100644 index 000000000000..3ec44a4f0e45 --- /dev/null +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -0,0 +1,1965 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Ltd. */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "mlx5_vnet.h" +#include "mlx5_vdpa_ifc.h" +#include "mlx5_vdpa.h" + +#define to_mvdev(__vdev) container_of((__vdev), struct mlx5_vdpa_dev, vdev) + +#define VALID_FEATURES_MASK \ + (BIT(VIRTIO_NET_F_CSUM) | BIT(VIRTIO_NET_F_GUEST_CSUM) | \ + BIT(VIRTIO_NET_F_CTRL_GUEST_OFFLOADS) | BIT(VIRTIO_NET_F_MTU) | BIT(VIRTIO_NET_F_MAC) | \ + BIT(VIRTIO_NET_F_GUEST_TSO4) | BIT(VIRTIO_NET_F_GUEST_TSO6) | \ + BIT(VIRTIO_NET_F_GUEST_ECN) | BIT(VIRTIO_NET_F_GUEST_UFO) | BIT(VIRTIO_NET_F_HOST_TSO4) | \ + BIT(VIRTIO_NET_F_HOST_TSO6) | BIT(VIRTIO_NET_F_HOST_ECN) | BIT(VIRTIO_NET_F_HOST_UFO) | \ + BIT(VIRTIO_NET_F_MRG_RXBUF) | BIT(VIRTIO_NET_F_STATUS) | BIT(VIRTIO_NET_F_CTRL_VQ) | \ + BIT(VIRTIO_NET_F_CTRL_RX) | BIT(VIRTIO_NET_F_CTRL_VLAN) | \ + BIT(VIRTIO_NET_F_CTRL_RX_EXTRA) | BIT(VIRTIO_NET_F_GUEST_ANNOUNCE) | \ + BIT(VIRTIO_NET_F_MQ) | BIT(VIRTIO_NET_F_CTRL_MAC_ADDR) | BIT(VIRTIO_NET_F_HASH_REPORT) | \ + BIT(VIRTIO_NET_F_RSS) | BIT(VIRTIO_NET_F_RSC_EXT) | BIT(VIRTIO_NET_F_STANDBY) | \ + BIT(VIRTIO_NET_F_SPEED_DUPLEX) | BIT(VIRTIO_F_NOTIFY_ON_EMPTY) | \ + BIT(VIRTIO_F_ANY_LAYOUT) | BIT(VIRTIO_F_VERSION_1) | BIT(VIRTIO_F_ACCESS_PLATFORM) | \ + BIT(VIRTIO_F_RING_PACKED) | BIT(VIRTIO_F_ORDER_PLATFORM) | BIT(VIRTIO_F_SR_IOV)) + +#define VALID_STATUS_MASK \ + (VIRTIO_CONFIG_S_ACKNOWLEDGE | VIRTIO_CONFIG_S_DRIVER | VIRTIO_CONFIG_S_DRIVER_OK | \ + VIRTIO_CONFIG_S_FEATURES_OK | VIRTIO_CONFIG_S_NEEDS_RESET | VIRTIO_CONFIG_S_FAILED) + +struct mlx5_vdpa_net_resources { + u32 tisn; + u32 tdn; + u32 tirn; + u32 rqtn; + bool valid; +}; + +struct mlx5_vdpa_cq_buf { + struct mlx5_frag_buf_ctrl fbc; + struct mlx5_frag_buf frag_buf; + int cqe_size; + int nent; +}; + +struct mlx5_vdpa_cq { + struct mlx5_core_cq mcq; + struct mlx5_vdpa_cq_buf buf; + struct mlx5_db db; + int cqe; +}; + +struct mlx5_vdpa_umem { + struct mlx5_frag_buf_ctrl fbc; + struct mlx5_frag_buf frag_buf; + int size; + u32 id; +}; + +struct mlx5_vdpa_qp { + struct mlx5_core_qp mqp; + struct mlx5_frag_buf frag_buf; + struct mlx5_db db; + u16 head; + bool fw; +}; + +struct mlx5_vq_restore_info { + u32 num_ent; + u64 desc_addr; + u64 device_addr; + u64 driver_addr; + u16 avail_index; + bool ready; + struct vdpa_callback cb; + bool restore; +}; + +struct mlx5_vdpa_virtqueue { + bool ready; + u64 desc_addr; + u64 device_addr; + u64 driver_addr; + u32 num_ent; + struct vdpa_callback event_cb; + + /* Resources for implementing the notification channel from the device + * to the driver. fwqp is the firmware end of an RC connection; the + * other end is vqqp used by the driver. cq is is where completions are + * reported. + */ + struct mlx5_vdpa_cq cq; + struct mlx5_vdpa_qp fwqp; + struct mlx5_vdpa_qp vqqp; + + /* umem resources are required for the virtqueue operation. They're use + * is internal and they must be provided by the driver. + */ + struct mlx5_vdpa_umem umem1; + struct mlx5_vdpa_umem umem2; + struct mlx5_vdpa_umem umem3; + + bool initialized; + int index; + u32 virtq_id; + struct mlx5_vdpa_net *ndev; + u16 avail_idx; + int fw_state; + + /* keep last in the struct */ + struct mlx5_vq_restore_info ri; +}; + +/* We will remove this limitation once mlx5_vdpa_alloc_resources() + * provides for driver space allocation + */ +#define MLX5_MAX_SUPPORTED_VQS 16 + +struct mlx5_vdpa_net { + struct mlx5_vdpa_dev mvdev; + struct mlx5_vdpa_net_resources res; + struct virtio_net_config config; + struct mlx5_vdpa_virtqueue vqs[MLX5_MAX_SUPPORTED_VQS]; + + /* Serialize vq resources creation and destruction. This is required + * since memory map might change and we need to destroy and create + * resources while driver in operational. + */ + struct mutex reslock; + struct mlx5_flow_table *rxft; + struct mlx5_fc *rx_counter; + struct mlx5_flow_handle *rx_rule; + bool setup; +}; + +static void free_resources(struct mlx5_vdpa_net *ndev); +static void init_mvqs(struct mlx5_vdpa_net *ndev); +static int setup_driver(struct mlx5_vdpa_net *ndev); +static void teardown_driver(struct mlx5_vdpa_net *ndev); + +static bool mlx5_vdpa_debug; + +#define MLX5_LOG_VIO_FLAG(_feature) \ + do { \ + if (features & BIT(_feature)) \ + mlx5_vdpa_info(mvdev, "%s\n", #_feature); \ + } while (0) + +#define MLX5_LOG_VIO_STAT(_status) \ + do { \ + if (status & (_status)) \ + mlx5_vdpa_info(mvdev, "%s\n", #_status); \ + } while (0) + +static void print_status(struct mlx5_vdpa_dev *mvdev, u8 status, bool set) +{ + if (status & ~VALID_STATUS_MASK) + mlx5_vdpa_warn(mvdev, "Warning: there are invalid status bits 0x%x\n", + status & ~VALID_STATUS_MASK); + + if (!mlx5_vdpa_debug) + return; + + mlx5_vdpa_info(mvdev, "driver status %s", set ? "set" : "get"); + if (set && !status) { + mlx5_vdpa_info(mvdev, "driver resets the device\n"); + return; + } + + MLX5_LOG_VIO_STAT(VIRTIO_CONFIG_S_ACKNOWLEDGE); + MLX5_LOG_VIO_STAT(VIRTIO_CONFIG_S_DRIVER); + MLX5_LOG_VIO_STAT(VIRTIO_CONFIG_S_DRIVER_OK); + MLX5_LOG_VIO_STAT(VIRTIO_CONFIG_S_FEATURES_OK); + MLX5_LOG_VIO_STAT(VIRTIO_CONFIG_S_NEEDS_RESET); + MLX5_LOG_VIO_STAT(VIRTIO_CONFIG_S_FAILED); +} + +static void print_features(struct mlx5_vdpa_dev *mvdev, u64 features, bool set) +{ + if (features & ~VALID_FEATURES_MASK) + mlx5_vdpa_warn(mvdev, "There are invalid feature bits 0x%llx\n", + features & ~VALID_FEATURES_MASK); + + if (!mlx5_vdpa_debug) + return; + + mlx5_vdpa_info(mvdev, "driver %s feature bits:\n", set ? "sets" : "reads"); + if (!features) + mlx5_vdpa_info(mvdev, "all feature bits are cleared\n"); + + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CSUM); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_GUEST_CSUM); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CTRL_GUEST_OFFLOADS); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_MTU); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_MAC); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_GUEST_TSO4); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_GUEST_TSO6); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_GUEST_ECN); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_GUEST_UFO); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_HOST_TSO4); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_HOST_TSO6); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_HOST_ECN); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_HOST_UFO); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_MRG_RXBUF); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_STATUS); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CTRL_VQ); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CTRL_RX); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CTRL_VLAN); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CTRL_RX_EXTRA); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_GUEST_ANNOUNCE); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_MQ); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CTRL_MAC_ADDR); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_HASH_REPORT); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_RSS); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_RSC_EXT); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_STANDBY); + MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_SPEED_DUPLEX); + MLX5_LOG_VIO_FLAG(VIRTIO_F_NOTIFY_ON_EMPTY); + MLX5_LOG_VIO_FLAG(VIRTIO_F_ANY_LAYOUT); + MLX5_LOG_VIO_FLAG(VIRTIO_F_VERSION_1); + MLX5_LOG_VIO_FLAG(VIRTIO_F_ACCESS_PLATFORM); + MLX5_LOG_VIO_FLAG(VIRTIO_F_RING_PACKED); + MLX5_LOG_VIO_FLAG(VIRTIO_F_ORDER_PLATFORM); + MLX5_LOG_VIO_FLAG(VIRTIO_F_SR_IOV); +} + +static int create_tis(struct mlx5_vdpa_net *ndev) +{ + struct mlx5_vdpa_dev *mvdev = &ndev->mvdev; + u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {}; + void *tisc; + int err; + + tisc = MLX5_ADDR_OF(create_tis_in, in, ctx); + MLX5_SET(tisc, tisc, transport_domain, ndev->res.tdn); + err = mlx5_vdpa_create_tis(mvdev, in, &ndev->res.tisn); + if (err) + mlx5_vdpa_warn(mvdev, "create TIS (%d)\n", err); + + return err; +} + +static void destroy_tis(struct mlx5_vdpa_net *ndev) +{ + mlx5_vdpa_destroy_tis(&ndev->mvdev, ndev->res.tisn); +} + +#define MLX5_VDPA_CQE_SIZE 64 +#define MLX5_VDPA_LOG_CQE_SIZE ilog2(MLX5_VDPA_CQE_SIZE) + +static int cq_frag_buf_alloc(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_cq_buf *buf, int nent) +{ + struct mlx5_frag_buf *frag_buf = &buf->frag_buf; + u8 log_wq_stride = MLX5_VDPA_LOG_CQE_SIZE; + u8 log_wq_sz = MLX5_VDPA_LOG_CQE_SIZE; + int err; + + err = mlx5_frag_buf_alloc_node(ndev->mvdev.mdev, nent * MLX5_VDPA_CQE_SIZE, frag_buf, + ndev->mvdev.mdev->priv.numa_node); + if (err) + return err; + + mlx5_init_fbc(frag_buf->frags, log_wq_stride, log_wq_sz, &buf->fbc); + + buf->cqe_size = MLX5_VDPA_CQE_SIZE; + buf->nent = nent; + + return 0; +} + +static int umem_frag_buf_alloc(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_umem *umem, int size) +{ + struct mlx5_frag_buf *frag_buf = &umem->frag_buf; + + return mlx5_frag_buf_alloc_node(ndev->mvdev.mdev, size, frag_buf, + ndev->mvdev.mdev->priv.numa_node); +} + +static void cq_frag_buf_free(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_cq_buf *buf) +{ + mlx5_frag_buf_free(ndev->mvdev.mdev, &buf->frag_buf); +} + +static void *get_cqe(struct mlx5_vdpa_cq *vcq, int n) +{ + return mlx5_frag_buf_get_wqe(&vcq->buf.fbc, n); +} + +static void cq_frag_buf_init(struct mlx5_vdpa_cq *vcq, struct mlx5_vdpa_cq_buf *buf) +{ + struct mlx5_cqe64 *cqe64; + void *cqe; + int i; + + for (i = 0; i < buf->nent; i++) { + cqe = get_cqe(vcq, i); + cqe64 = cqe; + cqe64->op_own = MLX5_CQE_INVALID << 4; + } +} + +static void *get_sw_cqe(struct mlx5_vdpa_cq *cq, int n) +{ + struct mlx5_cqe64 *cqe64 = get_cqe(cq, n & (cq->cqe - 1)); + + if (likely(get_cqe_opcode(cqe64) != MLX5_CQE_INVALID) && + !((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^ !!(n & cq->cqe))) + return cqe64; + + return NULL; +} + +static void rx_post(struct mlx5_vdpa_qp *vqp, int n) +{ + vqp->head += n; + vqp->db.db[0] = cpu_to_be32(vqp->head); +} + +static void qp_prepare(struct mlx5_vdpa_net *ndev, bool fw, void *in, + struct mlx5_vdpa_virtqueue *mvq, u32 num_ent) +{ + struct mlx5_vdpa_qp *vqp; + __be64 *pas; + void *qpc; + + vqp = fw ? &mvq->fwqp : &mvq->vqqp; + MLX5_SET(create_qp_in, in, uid, ndev->mvdev.res.uid); + qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); + if (vqp->fw) { + /* Firmware QP is allocated by the driver for the firmware's + * use so we can skip part of the params as they will be chosen by firmware + */ + qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); + MLX5_SET(qpc, qpc, rq_type, MLX5_ZERO_LEN_RQ); + MLX5_SET(qpc, qpc, no_sq, 1); + return; + } + + MLX5_SET(qpc, qpc, st, MLX5_QP_ST_RC); + MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED); + MLX5_SET(qpc, qpc, pd, ndev->mvdev.res.pdn); + MLX5_SET(qpc, qpc, mtu, MLX5_QPC_MTU_256_BYTES); + MLX5_SET(qpc, qpc, uar_page, ndev->mvdev.res.uar->index); + MLX5_SET(qpc, qpc, log_page_size, vqp->frag_buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); + MLX5_SET(qpc, qpc, no_sq, 1); + MLX5_SET(qpc, qpc, cqn_rcv, mvq->cq.mcq.cqn); + MLX5_SET(qpc, qpc, log_rq_size, ilog2(num_ent)); + MLX5_SET(qpc, qpc, rq_type, MLX5_NON_ZERO_RQ); + pas = (__be64 *)MLX5_ADDR_OF(create_qp_in, in, pas); + mlx5_fill_page_frag_array(&vqp->frag_buf, pas); +} + +static int rq_buf_alloc(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_qp *vqp, u32 num_ent) +{ + return mlx5_frag_buf_alloc_node(ndev->mvdev.mdev, + num_ent * sizeof(struct mlx5_wqe_data_seg), &vqp->frag_buf, + ndev->mvdev.mdev->priv.numa_node); +} + +static void rq_buf_free(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_qp *vqp) +{ + mlx5_frag_buf_free(ndev->mvdev.mdev, &vqp->frag_buf); +} + +static int qp_create(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, + struct mlx5_vdpa_qp *vqp) +{ + struct mlx5_core_dev *mdev = ndev->mvdev.mdev; + int inlen = MLX5_ST_SZ_BYTES(create_qp_in); + u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {}; + void *qpc; + void *in; + int err; + + if (!vqp->fw) { + vqp = &mvq->vqqp; + err = rq_buf_alloc(ndev, vqp, mvq->num_ent); + if (err) + return err; + + err = mlx5_db_alloc(ndev->mvdev.mdev, &vqp->db); + if (err) + goto err_db; + inlen += vqp->frag_buf.npages * sizeof(__be64); + } + + in = kzalloc(inlen, GFP_KERNEL); + if (!in) { + err = -ENOMEM; + goto err_kzalloc; + } + + qp_prepare(ndev, vqp->fw, in, mvq, mvq->num_ent); + qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); + MLX5_SET(qpc, qpc, st, MLX5_QP_ST_RC); + MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED); + MLX5_SET(qpc, qpc, pd, ndev->mvdev.res.pdn); + MLX5_SET(qpc, qpc, mtu, MLX5_QPC_MTU_256_BYTES); + if (!vqp->fw) + MLX5_SET64(qpc, qpc, dbr_addr, vqp->db.dma); + MLX5_SET(create_qp_in, in, opcode, MLX5_CMD_OP_CREATE_QP); + err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); + kfree(in); + if (err) + goto err_kzalloc; + + vqp->mqp.uid = ndev->mvdev.res.uid; + vqp->mqp.qpn = MLX5_GET(create_qp_out, out, qpn); + + if (!vqp->fw) + rx_post(vqp, mvq->num_ent); + + return 0; + +err_kzalloc: + if (!vqp->fw) + mlx5_db_free(ndev->mvdev.mdev, &vqp->db); +err_db: + if (!vqp->fw) + rq_buf_free(ndev, vqp); + + return err; +} + +static void qp_destroy(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_qp *vqp) +{ + u32 in[MLX5_ST_SZ_DW(destroy_qp_in)] = {}; + + MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP); + MLX5_SET(destroy_qp_in, in, qpn, vqp->mqp.qpn); + MLX5_SET(destroy_qp_in, in, uid, ndev->mvdev.res.uid); + if (mlx5_cmd_exec_in(ndev->mvdev.mdev, destroy_qp, in)) + mlx5_vdpa_warn(&ndev->mvdev, "destroy qp 0x%x\n", vqp->mqp.qpn); + if (!vqp->fw) { + mlx5_db_free(ndev->mvdev.mdev, &vqp->db); + rq_buf_free(ndev, vqp); + } +} + +static void *next_cqe_sw(struct mlx5_vdpa_cq *cq) +{ + return get_sw_cqe(cq, cq->mcq.cons_index); +} + +static int mlx5_vdpa_poll_one(struct mlx5_vdpa_cq *vcq) +{ + struct mlx5_cqe64 *cqe64; + + cqe64 = next_cqe_sw(vcq); + if (!cqe64) + return -EAGAIN; + + vcq->mcq.cons_index++; + return 0; +} + +static void mlx5_vdpa_handle_completions(struct mlx5_vdpa_virtqueue *mvq, int num) +{ + mlx5_cq_set_ci(&mvq->cq.mcq); + rx_post(&mvq->vqqp, num); + if (mvq->event_cb.callback) + mvq->event_cb.callback(mvq->event_cb.private); +} + +static void mlx5_vdpa_cq_comp(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe) +{ + struct mlx5_vdpa_virtqueue *mvq = container_of(mcq, struct mlx5_vdpa_virtqueue, cq.mcq); + struct mlx5_vdpa_net *ndev = mvq->ndev; + void __iomem *uar_page = ndev->mvdev.res.uar->map; + int num = 0; + + while (!mlx5_vdpa_poll_one(&mvq->cq)) { + num++; + if (num > mvq->num_ent / 2) { + /* If completions keep coming while we poll, we want to + * let the hardware know that we consumed them by + * updating the doorbell record. We also let vdpa core + * know about this so it passes it on the virtio driver + * on the guest. + */ + mlx5_vdpa_handle_completions(mvq, num); + num = 0; + } + } + + if (num) + mlx5_vdpa_handle_completions(mvq, num); + + mlx5_cq_arm(&mvq->cq.mcq, MLX5_CQ_DB_REQ_NOT, uar_page, mvq->cq.mcq.cons_index); +} + +static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent) +{ + struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx]; + struct mlx5_core_dev *mdev = ndev->mvdev.mdev; + void __iomem *uar_page = ndev->mvdev.res.uar->map; + u32 out[MLX5_ST_SZ_DW(create_cq_out)]; + struct mlx5_vdpa_cq *vcq = &mvq->cq; + unsigned int irqn; + __be64 *pas; + int inlen; + void *cqc; + void *in; + int err; + int eqn; + + err = mlx5_db_alloc(mdev, &vcq->db); + if (err) + return err; + + vcq->mcq.set_ci_db = vcq->db.db; + vcq->mcq.arm_db = vcq->db.db + 1; + vcq->mcq.cqe_sz = 64; + + err = cq_frag_buf_alloc(ndev, &vcq->buf, num_ent); + if (err) + goto err_db; + + cq_frag_buf_init(vcq, &vcq->buf); + + inlen = MLX5_ST_SZ_BYTES(create_cq_in) + + MLX5_FLD_SZ_BYTES(create_cq_in, pas[0]) * vcq->buf.frag_buf.npages; + in = kzalloc(inlen, GFP_KERNEL); + if (!in) { + err = -ENOMEM; + goto err_vzalloc; + } + + MLX5_SET(create_cq_in, in, uid, ndev->mvdev.res.uid); + pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas); + mlx5_fill_page_frag_array(&vcq->buf.frag_buf, pas); + + cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context); + MLX5_SET(cqc, cqc, log_page_size, vcq->buf.frag_buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); + + /* Use vector 0 by default. Consider adding code to choose least used + * vector. + */ + err = mlx5_vector2eqn(mdev, 0, &eqn, &irqn); + if (err) + goto err_vec; + + cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context); + MLX5_SET(cqc, cqc, log_cq_size, ilog2(num_ent)); + MLX5_SET(cqc, cqc, uar_page, ndev->mvdev.res.uar->index); + MLX5_SET(cqc, cqc, c_eqn, eqn); + MLX5_SET64(cqc, cqc, dbr_addr, vcq->db.dma); + + err = mlx5_core_create_cq(mdev, &vcq->mcq, in, inlen, out, sizeof(out)); + if (err) + goto err_vec; + + vcq->mcq.comp = mlx5_vdpa_cq_comp; + vcq->cqe = num_ent; + vcq->mcq.set_ci_db = vcq->db.db; + vcq->mcq.arm_db = vcq->db.db + 1; + mlx5_cq_arm(&mvq->cq.mcq, MLX5_CQ_DB_REQ_NOT, uar_page, mvq->cq.mcq.cons_index); + kfree(in); + return 0; + +err_vec: + kfree(in); +err_vzalloc: + cq_frag_buf_free(ndev, &vcq->buf); +err_db: + mlx5_db_free(ndev->mvdev.mdev, &vcq->db); + return err; +} + +static void cq_destroy(struct mlx5_vdpa_net *ndev, u16 idx) +{ + struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx]; + struct mlx5_core_dev *mdev = ndev->mvdev.mdev; + struct mlx5_vdpa_cq *vcq = &mvq->cq; + + if (mlx5_core_destroy_cq(mdev, &vcq->mcq)) { + mlx5_vdpa_warn(&ndev->mvdev, "destroy CQ 0x%x\n", vcq->mcq.cqn); + return; + } + cq_frag_buf_free(ndev, &vcq->buf); + mlx5_db_free(ndev->mvdev.mdev, &vcq->db); +} + +static int umem_size(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, int num, + struct mlx5_vdpa_umem **umemp) +{ + struct mlx5_core_dev *mdev = ndev->mvdev.mdev; + int p_a; + int p_b; + + switch (num) { + case 1: + p_a = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_1_buffer_param_a); + p_b = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_1_buffer_param_b); + *umemp = &mvq->umem1; + break; + case 2: + p_a = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_2_buffer_param_a); + p_b = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_2_buffer_param_b); + *umemp = &mvq->umem2; + break; + case 3: + p_a = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_3_buffer_param_a); + p_b = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_3_buffer_param_b); + *umemp = &mvq->umem3; + break; + } + return p_a * mvq->num_ent + p_b; +} + +static void umem_frag_buf_free(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_umem *umem) +{ + mlx5_frag_buf_free(ndev->mvdev.mdev, &umem->frag_buf); +} + +static int create_umem(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, int num) +{ + int inlen; + u32 out[MLX5_ST_SZ_DW(create_umem_out)] = {}; + void *um; + void *in; + int err; + __be64 *pas; + int size; + struct mlx5_vdpa_umem *umem; + + size = umem_size(ndev, mvq, num, &umem); + if (size < 0) + return size; + + umem->size = size; + err = umem_frag_buf_alloc(ndev, umem, size); + if (err) + return err; + + inlen = MLX5_ST_SZ_BYTES(create_umem_in) + MLX5_ST_SZ_BYTES(mtt) * umem->frag_buf.npages; + + in = kzalloc(inlen, GFP_KERNEL); + if (!in) { + err = -ENOMEM; + goto err_in; + } + + MLX5_SET(create_umem_in, in, opcode, MLX5_CMD_OP_CREATE_UMEM); + MLX5_SET(create_umem_in, in, uid, ndev->mvdev.res.uid); + um = MLX5_ADDR_OF(create_umem_in, in, umem); + MLX5_SET(umem, um, log_page_size, umem->frag_buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); + MLX5_SET64(umem, um, num_of_mtt, umem->frag_buf.npages); + + pas = (__be64 *)MLX5_ADDR_OF(umem, um, mtt[0]); + mlx5_fill_page_frag_array_perm(&umem->frag_buf, pas, MLX5_MTT_PERM_RW); + + err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out)); + if (err) { + mlx5_vdpa_warn(&ndev->mvdev, "create umem(%d)\n", err); + goto err_cmd; + } + + kfree(in); + umem->id = MLX5_GET(create_umem_out, out, umem_id); + + return 0; + +err_cmd: + kfree(in); +err_in: + umem_frag_buf_free(ndev, umem); + return err; +} + +static void umem_destroy(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, int num) +{ + u32 in[MLX5_ST_SZ_DW(destroy_umem_in)] = {}; + u32 out[MLX5_ST_SZ_DW(destroy_umem_out)] = {}; + struct mlx5_vdpa_umem *umem; + + switch (num) { + case 1: + umem = &mvq->umem1; + break; + case 2: + umem = &mvq->umem2; + break; + case 3: + umem = &mvq->umem3; + break; + } + + MLX5_SET(destroy_umem_in, in, opcode, MLX5_CMD_OP_DESTROY_UMEM); + MLX5_SET(destroy_umem_in, in, umem_id, umem->id); + if (mlx5_cmd_exec(ndev->mvdev.mdev, in, sizeof(in), out, sizeof(out))) + return; + + umem_frag_buf_free(ndev, umem); +} + +static int umems_create(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) +{ + int num; + int err; + + for (num = 1; num <= 3; num++) { + err = create_umem(ndev, mvq, num); + if (err) + goto err_umem; + } + return 0; + +err_umem: + for (num--; num > 0; num--) + umem_destroy(ndev, mvq, num); + + return err; +} + +static void umems_destroy(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) +{ + int num; + + for (num = 3; num > 0; num--) + umem_destroy(ndev, mvq, num); +} + +static int get_queue_type(struct mlx5_vdpa_net *ndev) +{ + u32 type_mask; + + type_mask = MLX5_CAP_DEV_VDPA_EMULATION(ndev->mvdev.mdev, virtio_queue_type); + + /* prefer split queue */ + if (type_mask & MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED) + return MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED; + + WARN_ON(!(type_mask & MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT)); + + return MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT; +} + +static bool vq_is_tx(u16 idx) +{ + return idx % 2; +} + +static u16 get_features_12_3(u64 features) +{ + return (!!(features & BIT(VIRTIO_NET_F_HOST_TSO4)) << 9) | + (!!(features & BIT(VIRTIO_NET_F_HOST_TSO6)) << 8) | + (!!(features & BIT(VIRTIO_NET_F_CSUM)) << 7) | + (!!(features & BIT(VIRTIO_NET_F_GUEST_CSUM)) << 6); +} + +static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) +{ + int inlen = MLX5_ST_SZ_BYTES(create_virtio_net_q_in); + u32 out[MLX5_ST_SZ_DW(create_virtio_net_q_out)] = {}; + void *obj_context; + void *cmd_hdr; + void *vq_ctx; + void *in; + int err; + + err = umems_create(ndev, mvq); + if (err) + return err; + + in = kzalloc(inlen, GFP_KERNEL); + if (!in) { + err = -ENOMEM; + goto err_alloc; + } + + cmd_hdr = MLX5_ADDR_OF(create_virtio_net_q_in, in, general_obj_in_cmd_hdr); + + MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_type, MLX5_OBJ_TYPE_VIRTIO_NET_Q); + MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid); + + obj_context = MLX5_ADDR_OF(create_virtio_net_q_in, in, obj_context); + MLX5_SET(virtio_net_q_object, obj_context, hw_available_index, mvq->avail_idx); + MLX5_SET(virtio_net_q_object, obj_context, queue_feature_bit_mask_12_3, + get_features_12_3(ndev->mvdev.actual_features)); + vq_ctx = MLX5_ADDR_OF(virtio_net_q_object, obj_context, virtio_q_context); + MLX5_SET(virtio_q, vq_ctx, virtio_q_type, get_queue_type(ndev)); + + if (vq_is_tx(mvq->index)) + MLX5_SET(virtio_net_q_object, obj_context, tisn_or_qpn, ndev->res.tisn); + + MLX5_SET(virtio_q, vq_ctx, event_mode, MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE); + MLX5_SET(virtio_q, vq_ctx, queue_index, mvq->index); + MLX5_SET(virtio_q, vq_ctx, event_qpn_or_msix, mvq->fwqp.mqp.qpn); + MLX5_SET(virtio_q, vq_ctx, queue_size, mvq->num_ent); + MLX5_SET(virtio_q, vq_ctx, virtio_version_1_0, + !!(ndev->mvdev.actual_features & VIRTIO_F_VERSION_1)); + MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr); + MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr); + MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr); + MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, ndev->mvdev.mr.mkey.key); + MLX5_SET(virtio_q, vq_ctx, umem_1_id, mvq->umem1.id); + MLX5_SET(virtio_q, vq_ctx, umem_1_size, mvq->umem1.size); + MLX5_SET(virtio_q, vq_ctx, umem_2_id, mvq->umem2.id); + MLX5_SET(virtio_q, vq_ctx, umem_2_size, mvq->umem1.size); + MLX5_SET(virtio_q, vq_ctx, umem_3_id, mvq->umem3.id); + MLX5_SET(virtio_q, vq_ctx, umem_3_size, mvq->umem1.size); + MLX5_SET(virtio_q, vq_ctx, pd, ndev->mvdev.res.pdn); + if (MLX5_CAP_DEV_VDPA_EMULATION(ndev->mvdev.mdev, eth_frame_offload_type)) + MLX5_SET(virtio_q, vq_ctx, virtio_version_1_0, 1); + + err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out)); + if (err) + goto err_cmd; + + kfree(in); + mvq->virtq_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); + + return 0; + +err_cmd: + kfree(in); +err_alloc: + umems_destroy(ndev, mvq); + return err; +} + +static void destroy_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) +{ + u32 in[MLX5_ST_SZ_DW(destroy_virtio_net_q_in)] = {}; + u32 out[MLX5_ST_SZ_DW(destroy_virtio_net_q_out)] = {}; + + MLX5_SET(destroy_virtio_net_q_in, in, general_obj_out_cmd_hdr.opcode, + MLX5_CMD_OP_DESTROY_GENERAL_OBJECT); + MLX5_SET(destroy_virtio_net_q_in, in, general_obj_out_cmd_hdr.obj_id, mvq->virtq_id); + MLX5_SET(destroy_virtio_net_q_in, in, general_obj_out_cmd_hdr.uid, ndev->mvdev.res.uid); + MLX5_SET(destroy_virtio_net_q_in, in, general_obj_out_cmd_hdr.obj_type, + MLX5_OBJ_TYPE_VIRTIO_NET_Q); + if (mlx5_cmd_exec(ndev->mvdev.mdev, in, sizeof(in), out, sizeof(out))) { + mlx5_vdpa_warn(&ndev->mvdev, "destroy virtqueue 0x%x\n", mvq->virtq_id); + return; + } + umems_destroy(ndev, mvq); +} + +static u32 get_rqpn(struct mlx5_vdpa_virtqueue *mvq, bool fw) +{ + return fw ? mvq->vqqp.mqp.qpn : mvq->fwqp.mqp.qpn; +} + +static u32 get_qpn(struct mlx5_vdpa_virtqueue *mvq, bool fw) +{ + return fw ? mvq->fwqp.mqp.qpn : mvq->vqqp.mqp.qpn; +} + +static void alloc_inout(struct mlx5_vdpa_net *ndev, int cmd, void **in, int *inlen, void **out, + int *outlen, u32 qpn, u32 rqpn) +{ + void *qpc; + void *pp; + + switch (cmd) { + case MLX5_CMD_OP_2RST_QP: + *inlen = MLX5_ST_SZ_BYTES(qp_2rst_in); + *outlen = MLX5_ST_SZ_BYTES(qp_2rst_out); + *in = kzalloc(*inlen, GFP_KERNEL); + *out = kzalloc(*outlen, GFP_KERNEL); + if (!in || !out) + goto outerr; + + MLX5_SET(qp_2rst_in, *in, opcode, cmd); + MLX5_SET(qp_2rst_in, *in, uid, ndev->mvdev.res.uid); + MLX5_SET(qp_2rst_in, *in, qpn, qpn); + break; + case MLX5_CMD_OP_RST2INIT_QP: + *inlen = MLX5_ST_SZ_BYTES(rst2init_qp_in); + *outlen = MLX5_ST_SZ_BYTES(rst2init_qp_out); + *in = kzalloc(*inlen, GFP_KERNEL); + *out = kzalloc(MLX5_ST_SZ_BYTES(rst2init_qp_out), GFP_KERNEL); + if (!in || !out) + goto outerr; + + MLX5_SET(rst2init_qp_in, *in, opcode, cmd); + MLX5_SET(rst2init_qp_in, *in, uid, ndev->mvdev.res.uid); + MLX5_SET(rst2init_qp_in, *in, qpn, qpn); + qpc = MLX5_ADDR_OF(rst2init_qp_in, *in, qpc); + MLX5_SET(qpc, qpc, remote_qpn, rqpn); + MLX5_SET(qpc, qpc, rwe, 1); + pp = MLX5_ADDR_OF(qpc, qpc, primary_address_path); + MLX5_SET(ads, pp, vhca_port_num, 1); + break; + case MLX5_CMD_OP_INIT2RTR_QP: + *inlen = MLX5_ST_SZ_BYTES(init2rtr_qp_in); + *outlen = MLX5_ST_SZ_BYTES(init2rtr_qp_out); + *in = kzalloc(*inlen, GFP_KERNEL); + *out = kzalloc(MLX5_ST_SZ_BYTES(init2rtr_qp_out), GFP_KERNEL); + if (!in || !out) + goto outerr; + + MLX5_SET(init2rtr_qp_in, *in, opcode, cmd); + MLX5_SET(init2rtr_qp_in, *in, uid, ndev->mvdev.res.uid); + MLX5_SET(init2rtr_qp_in, *in, qpn, qpn); + qpc = MLX5_ADDR_OF(rst2init_qp_in, *in, qpc); + MLX5_SET(qpc, qpc, mtu, MLX5_QPC_MTU_256_BYTES); + MLX5_SET(qpc, qpc, log_msg_max, 30); + MLX5_SET(qpc, qpc, remote_qpn, rqpn); + pp = MLX5_ADDR_OF(qpc, qpc, primary_address_path); + MLX5_SET(ads, pp, fl, 1); + break; + case MLX5_CMD_OP_RTR2RTS_QP: + *inlen = MLX5_ST_SZ_BYTES(rtr2rts_qp_in); + *outlen = MLX5_ST_SZ_BYTES(rtr2rts_qp_out); + *in = kzalloc(*inlen, GFP_KERNEL); + *out = kzalloc(MLX5_ST_SZ_BYTES(rtr2rts_qp_out), GFP_KERNEL); + if (!in || !out) + goto outerr; + + MLX5_SET(rtr2rts_qp_in, *in, opcode, cmd); + MLX5_SET(rtr2rts_qp_in, *in, uid, ndev->mvdev.res.uid); + MLX5_SET(rtr2rts_qp_in, *in, qpn, qpn); + qpc = MLX5_ADDR_OF(rst2init_qp_in, *in, qpc); + pp = MLX5_ADDR_OF(qpc, qpc, primary_address_path); + MLX5_SET(ads, pp, ack_timeout, 14); + MLX5_SET(qpc, qpc, retry_count, 7); + MLX5_SET(qpc, qpc, rnr_retry, 7); + break; + default: + goto outerr; + } + if (!*in || !*out) + goto outerr; + + return; + +outerr: + kfree(*in); + kfree(*out); + *in = NULL; + *out = NULL; +} + +static void free_inout(void *in, void *out) +{ + kfree(in); + kfree(out); +} + +/* Two QPs are used by each virtqueue. One is used by the driver and one by + * firmware. The fw argument indicates whether the subjected QP is the one used + * by firmware. + */ +static int modify_qp(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, bool fw, int cmd) +{ + int outlen; + int inlen; + void *out; + void *in; + int err; + + alloc_inout(ndev, cmd, &in, &inlen, &out, &outlen, get_qpn(mvq, fw), get_rqpn(mvq, fw)); + if (!in || !out) + return -ENOMEM; + + err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, outlen); + free_inout(in, out); + return err; +} + +static int connect_qps(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) +{ + int err; + + err = modify_qp(ndev, mvq, true, MLX5_CMD_OP_2RST_QP); + if (err) + return err; + + err = modify_qp(ndev, mvq, false, MLX5_CMD_OP_2RST_QP); + if (err) + return err; + + err = modify_qp(ndev, mvq, true, MLX5_CMD_OP_RST2INIT_QP); + if (err) + return err; + + err = modify_qp(ndev, mvq, false, MLX5_CMD_OP_RST2INIT_QP); + if (err) + return err; + + err = modify_qp(ndev, mvq, true, MLX5_CMD_OP_INIT2RTR_QP); + if (err) + return err; + + err = modify_qp(ndev, mvq, false, MLX5_CMD_OP_INIT2RTR_QP); + if (err) + return err; + + return modify_qp(ndev, mvq, true, MLX5_CMD_OP_RTR2RTS_QP); +} + +struct mlx5_virtq_attr { + u8 state; + u16 available_index; +}; + +static int query_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, + struct mlx5_virtq_attr *attr) +{ + int outlen = MLX5_ST_SZ_BYTES(query_virtio_net_q_out); + u32 in[MLX5_ST_SZ_DW(query_virtio_net_q_in)] = {}; + void *out; + void *obj_context; + void *cmd_hdr; + int err; + + out = kzalloc(outlen, GFP_KERNEL); + if (!out) + return -ENOMEM; + + cmd_hdr = MLX5_ADDR_OF(query_virtio_net_q_in, in, general_obj_in_cmd_hdr); + + MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, opcode, MLX5_CMD_OP_QUERY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_type, MLX5_OBJ_TYPE_VIRTIO_NET_Q); + MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_id, mvq->virtq_id); + MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid); + err = mlx5_cmd_exec(ndev->mvdev.mdev, in, sizeof(in), out, outlen); + if (err) + goto err_cmd; + + obj_context = MLX5_ADDR_OF(query_virtio_net_q_out, out, obj_context); + memset(attr, 0, sizeof(*attr)); + attr->state = MLX5_GET(virtio_net_q_object, obj_context, state); + attr->available_index = MLX5_GET(virtio_net_q_object, obj_context, hw_available_index); + kfree(out); + return 0; + +err_cmd: + kfree(out); + return err; +} + +static int modify_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, int state) +{ + int inlen = MLX5_ST_SZ_BYTES(modify_virtio_net_q_in); + u32 out[MLX5_ST_SZ_DW(modify_virtio_net_q_out)] = {}; + void *obj_context; + void *cmd_hdr; + void *in; + int err; + + in = kzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + cmd_hdr = MLX5_ADDR_OF(modify_virtio_net_q_in, in, general_obj_in_cmd_hdr); + + MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, opcode, MLX5_CMD_OP_MODIFY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_type, MLX5_OBJ_TYPE_VIRTIO_NET_Q); + MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_id, mvq->virtq_id); + MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid); + + obj_context = MLX5_ADDR_OF(modify_virtio_net_q_in, in, obj_context); + MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, + MLX5_VIRTQ_MODIFY_MASK_STATE); + MLX5_SET(virtio_net_q_object, obj_context, state, state); + err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out)); + kfree(in); + if (!err) + mvq->fw_state = state; + + return err; +} + +static int setup_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) +{ + u16 idx = mvq->index; + int err; + + if (!mvq->num_ent) + return 0; + + if (mvq->initialized) { + mlx5_vdpa_warn(&ndev->mvdev, "attempt re init\n"); + return -EINVAL; + } + + err = cq_create(ndev, idx, mvq->num_ent); + if (err) + return err; + + err = qp_create(ndev, mvq, &mvq->fwqp); + if (err) + goto err_fwqp; + + err = qp_create(ndev, mvq, &mvq->vqqp); + if (err) + goto err_vqqp; + + err = connect_qps(ndev, mvq); + if (err) + goto err_connect; + + err = create_virtqueue(ndev, mvq); + if (err) + goto err_connect; + + if (mvq->ready) { + err = modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY); + if (err) { + mlx5_vdpa_warn(&ndev->mvdev, "failed to modify to ready vq idx %d(%d)\n", + idx, err); + goto err_connect; + } + } + + mvq->initialized = true; + return 0; + +err_connect: + qp_destroy(ndev, &mvq->vqqp); +err_vqqp: + qp_destroy(ndev, &mvq->fwqp); +err_fwqp: + cq_destroy(ndev, idx); + return err; +} + +static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) +{ + struct mlx5_virtq_attr attr; + + if (!mvq->initialized) + return; + + if (query_virtqueue(ndev, mvq, &attr)) { + mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n"); + return; + } + if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY) + return; + + if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND)) + mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n"); +} + +static void suspend_vqs(struct mlx5_vdpa_net *ndev) +{ + int i; + + for (i = 0; i < MLX5_MAX_SUPPORTED_VQS; i++) + suspend_vq(ndev, &ndev->vqs[i]); +} + +static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) +{ + if (!mvq->initialized) + return; + + suspend_vq(ndev, mvq); + destroy_virtqueue(ndev, mvq); + qp_destroy(ndev, &mvq->vqqp); + qp_destroy(ndev, &mvq->fwqp); + cq_destroy(ndev, mvq->index); + mvq->initialized = false; +} + +static int create_rqt(struct mlx5_vdpa_net *ndev) +{ + int log_max_rqt; + __be32 *list; + void *rqtc; + int inlen; + void *in; + int i, j; + int err; + + log_max_rqt = min_t(int, 1, MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size)); + if (log_max_rqt < 1) + return -EOPNOTSUPP; + + inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + (1 << log_max_rqt) * MLX5_ST_SZ_BYTES(rq_num); + in = kzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(create_rqt_in, in, uid, ndev->mvdev.res.uid); + rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); + + MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q); + MLX5_SET(rqtc, rqtc, rqt_max_size, 1 << log_max_rqt); + MLX5_SET(rqtc, rqtc, rqt_actual_size, 1); + list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]); + for (i = 0, j = 0; j < ndev->mvdev.max_vqs; j++) { + if (!ndev->vqs[j].initialized) + continue; + + if (!vq_is_tx(ndev->vqs[j].index)) { + list[i] = cpu_to_be32(ndev->vqs[j].virtq_id); + i++; + } + } + + err = mlx5_vdpa_create_rqt(&ndev->mvdev, in, inlen, &ndev->res.rqtn); + kfree(in); + if (err) + return err; + + return 0; +} + +static void destroy_rqt(struct mlx5_vdpa_net *ndev) +{ + mlx5_vdpa_destroy_rqt(&ndev->mvdev, ndev->res.rqtn); +} + +static int create_tir(struct mlx5_vdpa_net *ndev) +{ +#define HASH_IP_L4PORTS \ + (MLX5_HASH_FIELD_SEL_SRC_IP | MLX5_HASH_FIELD_SEL_DST_IP | MLX5_HASH_FIELD_SEL_L4_SPORT | \ + MLX5_HASH_FIELD_SEL_L4_DPORT) + static const u8 rx_hash_toeplitz_key[] = { 0x2c, 0xc6, 0x81, 0xd1, 0x5b, 0xdb, 0xf4, 0xf7, + 0xfc, 0xa2, 0x83, 0x19, 0xdb, 0x1a, 0x3e, 0x94, + 0x6b, 0x9e, 0x38, 0xd9, 0x2c, 0x9c, 0x03, 0xd1, + 0xad, 0x99, 0x44, 0xa7, 0xd9, 0x56, 0x3d, 0x59, + 0x06, 0x3c, 0x25, 0xf3, 0xfc, 0x1f, 0xdc, 0x2a }; + void *rss_key; + void *outer; + void *tirc; + void *in; + int err; + + in = kzalloc(MLX5_ST_SZ_BYTES(create_tir_in), GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(create_tir_in, in, uid, ndev->mvdev.res.uid); + tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); + MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT); + + MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); + MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_TOEPLITZ); + rss_key = MLX5_ADDR_OF(tirc, tirc, rx_hash_toeplitz_key); + memcpy(rss_key, rx_hash_toeplitz_key, sizeof(rx_hash_toeplitz_key)); + + outer = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer); + MLX5_SET(rx_hash_field_select, outer, l3_prot_type, MLX5_L3_PROT_TYPE_IPV4); + MLX5_SET(rx_hash_field_select, outer, l4_prot_type, MLX5_L4_PROT_TYPE_TCP); + MLX5_SET(rx_hash_field_select, outer, selected_fields, HASH_IP_L4PORTS); + + MLX5_SET(tirc, tirc, indirect_table, ndev->res.rqtn); + MLX5_SET(tirc, tirc, transport_domain, ndev->res.tdn); + + err = mlx5_vdpa_create_tir(&ndev->mvdev, in, &ndev->res.tirn); + kfree(in); + return err; +} + +static void destroy_tir(struct mlx5_vdpa_net *ndev) +{ + mlx5_vdpa_destroy_tir(&ndev->mvdev, ndev->res.tirn); +} + +static int add_fwd_to_tir(struct mlx5_vdpa_net *ndev) +{ + struct mlx5_flow_destination dest[2] = {}; + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_namespace *ns; + int err; + + /* for now, one entry, match all, forward to tir */ + ft_attr.max_fte = 1; + ft_attr.autogroup.max_num_groups = 1; + + ns = mlx5_get_flow_namespace(ndev->mvdev.mdev, MLX5_FLOW_NAMESPACE_BYPASS); + if (!ns) { + mlx5_vdpa_warn(&ndev->mvdev, "get flow namespace\n"); + return -EOPNOTSUPP; + } + + ndev->rxft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr); + if (IS_ERR(ndev->rxft)) + return PTR_ERR(ndev->rxft); + + ndev->rx_counter = mlx5_fc_create(ndev->mvdev.mdev, false); + if (IS_ERR(ndev->rx_counter)) { + err = PTR_ERR(ndev->rx_counter); + goto err_fc; + } + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest[0].type = MLX5_FLOW_DESTINATION_TYPE_TIR; + dest[0].tir_num = ndev->res.tirn; + dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest[1].counter_id = mlx5_fc_id(ndev->rx_counter); + ndev->rx_rule = mlx5_add_flow_rules(ndev->rxft, NULL, &flow_act, dest, 2); + if (IS_ERR(ndev->rx_rule)) { + err = PTR_ERR(ndev->rx_rule); + ndev->rx_rule = NULL; + goto err_rule; + } + + return 0; + +err_rule: + mlx5_fc_destroy(ndev->mvdev.mdev, ndev->rx_counter); +err_fc: + mlx5_destroy_flow_table(ndev->rxft); + return err; +} + +static void remove_fwd_to_tir(struct mlx5_vdpa_net *ndev) +{ + if (!ndev->rx_rule) + return; + + mlx5_del_flow_rules(ndev->rx_rule); + mlx5_fc_destroy(ndev->mvdev.mdev, ndev->rx_counter); + mlx5_destroy_flow_table(ndev->rxft); + + ndev->rx_rule = NULL; +} + +static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx]; + + if (unlikely(!mvq->ready)) + return; + + iowrite16(idx, ndev->mvdev.res.kick_addr); +} + +static int mlx5_vdpa_set_vq_address(struct vdpa_device *vdev, u16 idx, u64 desc_area, + u64 driver_area, u64 device_area) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx]; + + mvq->desc_addr = desc_area; + mvq->device_addr = device_area; + mvq->driver_addr = driver_area; + return 0; +} + +static void mlx5_vdpa_set_vq_num(struct vdpa_device *vdev, u16 idx, u32 num) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + struct mlx5_vdpa_virtqueue *mvq; + + mvq = &ndev->vqs[idx]; + mvq->num_ent = num; +} + +static void mlx5_vdpa_set_vq_cb(struct vdpa_device *vdev, u16 idx, struct vdpa_callback *cb) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + struct mlx5_vdpa_virtqueue *vq = &ndev->vqs[idx]; + + vq->event_cb = *cb; +} + +static void mlx5_vdpa_set_vq_ready(struct vdpa_device *vdev, u16 idx, bool ready) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx]; + + if (!ready) + suspend_vq(ndev, mvq); + + mvq->ready = ready; +} + +static bool mlx5_vdpa_get_vq_ready(struct vdpa_device *vdev, u16 idx) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx]; + + return mvq->ready; +} + +static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx, + const struct vdpa_vq_state *state) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx]; + + if (mvq->fw_state == MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY) { + mlx5_vdpa_warn(mvdev, "can't modify available index\n"); + return -EINVAL; + } + + mvq->avail_idx = state->avail_index; + return 0; +} + +static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa_vq_state *state) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx]; + struct mlx5_virtq_attr attr; + int err; + + if (!mvq->initialized) + return -EAGAIN; + + err = query_virtqueue(ndev, mvq, &attr); + if (err) { + mlx5_vdpa_warn(mvdev, "failed to query virtqueue\n"); + return err; + } + state->avail_index = attr.available_index; + return 0; +} + +static u32 mlx5_vdpa_get_vq_align(struct vdpa_device *vdev) +{ + return PAGE_SIZE; +} + +enum { MLX5_VIRTIO_NET_F_GUEST_CSUM = 1 << 9, + MLX5_VIRTIO_NET_F_CSUM = 1 << 10, + MLX5_VIRTIO_NET_F_HOST_TSO6 = 1 << 11, + MLX5_VIRTIO_NET_F_HOST_TSO4 = 1 << 12, +}; + +static u64 mlx_to_vritio_features(u16 dev_features) +{ + u64 result = 0; + + if (dev_features & MLX5_VIRTIO_NET_F_GUEST_CSUM) + result |= BIT(VIRTIO_NET_F_GUEST_CSUM); + if (dev_features & MLX5_VIRTIO_NET_F_CSUM) + result |= BIT(VIRTIO_NET_F_CSUM); + if (dev_features & MLX5_VIRTIO_NET_F_HOST_TSO6) + result |= BIT(VIRTIO_NET_F_HOST_TSO6); + if (dev_features & MLX5_VIRTIO_NET_F_HOST_TSO4) + result |= BIT(VIRTIO_NET_F_HOST_TSO4); + + return result; +} + +static u64 mlx5_vdpa_get_features(struct vdpa_device *vdev) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + u16 dev_features; + + dev_features = MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, device_features_bits_mask); + ndev->mvdev.mlx_features = mlx_to_vritio_features(dev_features); + if (MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, virtio_version_1_0)) + ndev->mvdev.mlx_features |= BIT(VIRTIO_F_VERSION_1); + ndev->mvdev.mlx_features |= BIT(VIRTIO_F_ACCESS_PLATFORM); + print_features(mvdev, ndev->mvdev.mlx_features, false); + return ndev->mvdev.mlx_features; +} + +static int verify_min_features(struct mlx5_vdpa_dev *mvdev, u64 features) +{ + if (!(features & BIT(VIRTIO_F_ACCESS_PLATFORM))) + return -EOPNOTSUPP; + + return 0; +} + +static int setup_virtqueues(struct mlx5_vdpa_net *ndev) +{ + int err; + int i; + + for (i = 0; i < 2 * mlx5_vdpa_max_qps(ndev->mvdev.max_vqs); i++) { + err = setup_vq(ndev, &ndev->vqs[i]); + if (err) + goto err_vq; + } + + return 0; + +err_vq: + for (--i; i >= 0; i--) + teardown_vq(ndev, &ndev->vqs[i]); + + return err; +} + +static void teardown_virtqueues(struct mlx5_vdpa_net *ndev) +{ + struct mlx5_vdpa_virtqueue *mvq; + int i; + + for (i = ndev->mvdev.max_vqs - 1; i >= 0; i--) { + mvq = &ndev->vqs[i]; + if (!mvq->initialized) + continue; + + teardown_vq(ndev, mvq); + } +} + +static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + int err; + + print_features(mvdev, features, true); + + err = verify_min_features(mvdev, features); + if (err) + return err; + + ndev->mvdev.actual_features = features & ndev->mvdev.mlx_features; + return err; +} + +static void mlx5_vdpa_set_config_cb(struct vdpa_device *vdev, struct vdpa_callback *cb) +{ + /* not implemented */ + mlx5_vdpa_warn(to_mvdev(vdev), "set config callback not supported\n"); +} + +#define MLX5_VDPA_MAX_VQ_ENTRIES 256 +static u16 mlx5_vdpa_get_vq_num_max(struct vdpa_device *vdev) +{ + return MLX5_VDPA_MAX_VQ_ENTRIES; +} + +static u32 mlx5_vdpa_get_device_id(struct vdpa_device *vdev) +{ + return VIRTIO_ID_NET; +} + +static u32 mlx5_vdpa_get_vendor_id(struct vdpa_device *vdev) +{ + return PCI_VENDOR_ID_MELLANOX; +} + +static u8 mlx5_vdpa_get_status(struct vdpa_device *vdev) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + + print_status(mvdev, ndev->mvdev.status, false); + return ndev->mvdev.status; +} + +static int save_channel_info(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq) +{ + struct mlx5_vq_restore_info *ri = &mvq->ri; + struct mlx5_virtq_attr attr; + int err; + + if (!mvq->initialized) + return 0; + + err = query_virtqueue(ndev, mvq, &attr); + if (err) + return err; + + ri->avail_index = attr.available_index; + ri->ready = mvq->ready; + ri->num_ent = mvq->num_ent; + ri->desc_addr = mvq->desc_addr; + ri->device_addr = mvq->device_addr; + ri->driver_addr = mvq->driver_addr; + ri->cb = mvq->event_cb; + ri->restore = true; + return 0; +} + +static int save_channels_info(struct mlx5_vdpa_net *ndev) +{ + int i; + + for (i = 0; i < ndev->mvdev.max_vqs; i++) { + memset(&ndev->vqs[i].ri, 0, sizeof(ndev->vqs[i].ri)); + save_channel_info(ndev, &ndev->vqs[i]); + } + return 0; +} + +static void mlx5_clear_vqs(struct mlx5_vdpa_net *ndev) +{ + int i; + + for (i = 0; i < ndev->mvdev.max_vqs; i++) + memset(&ndev->vqs[i], 0, offsetof(struct mlx5_vdpa_virtqueue, ri)); +} + +static void restore_channels_info(struct mlx5_vdpa_net *ndev) +{ + struct mlx5_vdpa_virtqueue *mvq; + struct mlx5_vq_restore_info *ri; + int i; + + mlx5_clear_vqs(ndev); + init_mvqs(ndev); + for (i = 0; i < ndev->mvdev.max_vqs; i++) { + mvq = &ndev->vqs[i]; + ri = &mvq->ri; + if (!ri->restore) + continue; + + mvq->avail_idx = ri->avail_index; + mvq->ready = ri->ready; + mvq->num_ent = ri->num_ent; + mvq->desc_addr = ri->desc_addr; + mvq->device_addr = ri->device_addr; + mvq->driver_addr = ri->driver_addr; + mvq->event_cb = ri->cb; + } +} + +static int mlx5_vdpa_change_map(struct mlx5_vdpa_net *ndev, struct vhost_iotlb *iotlb) +{ + int err; + + suspend_vqs(ndev); + err = save_channels_info(ndev); + if (err) + goto err_mr; + + teardown_driver(ndev); + mlx5_vdpa_destroy_mr(&ndev->mvdev); + err = mlx5_vdpa_create_mr(&ndev->mvdev, iotlb); + if (err) + goto err_mr; + + restore_channels_info(ndev); + err = setup_driver(ndev); + if (err) + goto err_setup; + + return 0; + +err_setup: + mlx5_vdpa_destroy_mr(&ndev->mvdev); +err_mr: + return err; +} + +static int setup_driver(struct mlx5_vdpa_net *ndev) +{ + int err; + + mutex_lock(&ndev->reslock); + if (ndev->setup) { + mlx5_vdpa_warn(&ndev->mvdev, "setup driver called for already setup driver\n"); + err = 0; + goto out; + } + err = setup_virtqueues(ndev); + if (err) { + mlx5_vdpa_warn(&ndev->mvdev, "setup_virtqueues\n"); + goto out; + } + + err = create_rqt(ndev); + if (err) { + mlx5_vdpa_warn(&ndev->mvdev, "create_rqt\n"); + goto err_rqt; + } + + err = create_tir(ndev); + if (err) { + mlx5_vdpa_warn(&ndev->mvdev, "create_tir\n"); + goto err_tir; + } + + err = add_fwd_to_tir(ndev); + if (err) { + mlx5_vdpa_warn(&ndev->mvdev, "add_fwd_to_tir\n"); + goto err_fwd; + } + ndev->setup = true; + mutex_unlock(&ndev->reslock); + + return 0; + +err_fwd: + destroy_tir(ndev); +err_tir: + destroy_rqt(ndev); +err_rqt: + teardown_virtqueues(ndev); +out: + mutex_unlock(&ndev->reslock); + return err; +} + +static void teardown_driver(struct mlx5_vdpa_net *ndev) +{ + mutex_lock(&ndev->reslock); + if (!ndev->setup) + goto out; + + remove_fwd_to_tir(ndev); + destroy_tir(ndev); + destroy_rqt(ndev); + teardown_virtqueues(ndev); + ndev->setup = false; +out: + mutex_unlock(&ndev->reslock); +} + +static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + int err; + + print_status(mvdev, status, true); + if (!status) { + mlx5_vdpa_info(mvdev, "performing device reset\n"); + teardown_driver(ndev); + mlx5_vdpa_destroy_mr(&ndev->mvdev); + ndev->mvdev.status = 0; + ndev->mvdev.mlx_features = 0; + ++mvdev->generation; + return; + } + + if ((status ^ ndev->mvdev.status) & VIRTIO_CONFIG_S_DRIVER_OK) { + if (status & VIRTIO_CONFIG_S_DRIVER_OK) { + err = setup_driver(ndev); + if (err) { + mlx5_vdpa_warn(mvdev, "failed to setup driver\n"); + goto err_setup; + } + } else { + mlx5_vdpa_warn(mvdev, "did not expect DRIVER_OK to be cleared\n"); + return; + } + } + + ndev->mvdev.status = status; + return; + +err_setup: + mlx5_vdpa_destroy_mr(&ndev->mvdev); + ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED; +} + +static void mlx5_vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, void *buf, + unsigned int len) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + + if (offset + len < sizeof(struct virtio_net_config)) + memcpy(buf, &ndev->config + offset, len); +} + +static void mlx5_vdpa_set_config(struct vdpa_device *vdev, unsigned int offset, const void *buf, + unsigned int len) +{ + /* not supported */ +} + +static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + + return mvdev->generation; +} + +static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + bool change_map; + int err; + + err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map); + if (err) { + mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err); + return err; + } + + if (change_map) + return mlx5_vdpa_change_map(ndev, iotlb); + + return 0; +} + +static void mlx5_vdpa_free(struct vdpa_device *vdev) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev; + + ndev = to_mlx5_vdpa_ndev(mvdev); + + free_resources(ndev); + mlx5_vdpa_free_resources(&ndev->mvdev); + mutex_destroy(&ndev->reslock); +} + +static struct vdpa_notification_area mlx5_get_vq_notification(struct vdpa_device *vdev, u16 idx) +{ + struct vdpa_notification_area ret = {}; + + return ret; +} + +static int mlx5_get_vq_irq(struct vdpa_device *vdv, u16 idx) +{ + return -EOPNOTSUPP; +} + +static const struct vdpa_config_ops mlx5_vdpa_ops = { + .set_vq_address = mlx5_vdpa_set_vq_address, + .set_vq_num = mlx5_vdpa_set_vq_num, + .kick_vq = mlx5_vdpa_kick_vq, + .set_vq_cb = mlx5_vdpa_set_vq_cb, + .set_vq_ready = mlx5_vdpa_set_vq_ready, + .get_vq_ready = mlx5_vdpa_get_vq_ready, + .set_vq_state = mlx5_vdpa_set_vq_state, + .get_vq_state = mlx5_vdpa_get_vq_state, + .get_vq_notification = mlx5_get_vq_notification, + .get_vq_irq = mlx5_get_vq_irq, + .get_vq_align = mlx5_vdpa_get_vq_align, + .get_features = mlx5_vdpa_get_features, + .set_features = mlx5_vdpa_set_features, + .set_config_cb = mlx5_vdpa_set_config_cb, + .get_vq_num_max = mlx5_vdpa_get_vq_num_max, + .get_device_id = mlx5_vdpa_get_device_id, + .get_vendor_id = mlx5_vdpa_get_vendor_id, + .get_status = mlx5_vdpa_get_status, + .set_status = mlx5_vdpa_set_status, + .get_config = mlx5_vdpa_get_config, + .set_config = mlx5_vdpa_set_config, + .get_generation = mlx5_vdpa_get_generation, + .set_map = mlx5_vdpa_set_map, + .free = mlx5_vdpa_free, +}; + +static int alloc_resources(struct mlx5_vdpa_net *ndev) +{ + struct mlx5_vdpa_net_resources *res = &ndev->res; + int err; + + if (res->valid) { + mlx5_vdpa_warn(&ndev->mvdev, "resources already allocated\n"); + return -EEXIST; + } + + err = mlx5_vdpa_alloc_transport_domain(&ndev->mvdev, &res->tdn); + if (err) + return err; + + err = create_tis(ndev); + if (err) + goto err_tis; + + res->valid = true; + + return 0; + +err_tis: + mlx5_vdpa_dealloc_transport_domain(&ndev->mvdev, res->tdn); + return err; +} + +static void free_resources(struct mlx5_vdpa_net *ndev) +{ + struct mlx5_vdpa_net_resources *res = &ndev->res; + + if (!res->valid) + return; + + destroy_tis(ndev); + mlx5_vdpa_dealloc_transport_domain(&ndev->mvdev, res->tdn); + res->valid = false; +} + +static void init_mvqs(struct mlx5_vdpa_net *ndev) +{ + struct mlx5_vdpa_virtqueue *mvq; + int i; + + for (i = 0; i < 2 * mlx5_vdpa_max_qps(ndev->mvdev.max_vqs); ++i) { + mvq = &ndev->vqs[i]; + memset(mvq, 0, offsetof(struct mlx5_vdpa_virtqueue, ri)); + mvq->index = i; + mvq->ndev = ndev; + mvq->fwqp.fw = true; + } + for (; i < ndev->mvdev.max_vqs; i++) { + mvq = &ndev->vqs[i]; + memset(mvq, 0, offsetof(struct mlx5_vdpa_virtqueue, ri)); + mvq->index = i; + mvq->ndev = ndev; + } +} + +void *mlx5_vdpa_add_dev(struct mlx5_core_dev *mdev) +{ + struct virtio_net_config *config; + struct mlx5_vdpa_dev *mvdev; + struct mlx5_vdpa_net *ndev; + u32 max_vqs; + int err; + + /* we save one virtqueue for control virtqueue should we require it */ + max_vqs = MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues); + max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS); + + ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, + 2 * mlx5_vdpa_max_qps(max_vqs)); + if (IS_ERR(ndev)) + return ndev; + + ndev->mvdev.max_vqs = max_vqs; + mvdev = &ndev->mvdev; + mvdev->mdev = mdev; + init_mvqs(ndev); + mutex_init(&ndev->reslock); + config = &ndev->config; + err = mlx5_query_nic_vport_mtu(mdev, &config->mtu); + if (err) + goto err_mtu; + + err = mlx5_query_nic_vport_mac_address(mdev, 0, 0, config->mac); + if (err) + goto err_mtu; + + mvdev->vdev.dma_dev = mdev->device; + err = mlx5_vdpa_alloc_resources(&ndev->mvdev); + if (err) + goto err_mtu; + + err = alloc_resources(ndev); + if (err) + goto err_res; + + err = vdpa_register_device(&mvdev->vdev); + if (err) + goto err_reg; + + return ndev; + +err_reg: + free_resources(ndev); +err_res: + mlx5_vdpa_free_resources(&ndev->mvdev); +err_mtu: + mutex_destroy(&ndev->reslock); + put_device(&mvdev->vdev.dev); + return ERR_PTR(err); +} + +void mlx5_vdpa_remove_dev(struct mlx5_vdpa_dev *mvdev) +{ + vdpa_unregister_device(&mvdev->vdev); +} diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.h b/drivers/vdpa/mlx5/net/mlx5_vnet.h new file mode 100644 index 000000000000..f2d6d68b020e --- /dev/null +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies Ltd. */ + +#ifndef __MLX5_VNET_H_ +#define __MLX5_VNET_H_ + +#include +#include +#include +#include +#include +#include +#include "mlx5_vdpa.h" + +static inline u32 mlx5_vdpa_max_qps(int max_vqs) +{ + return max_vqs / 2; +} + +#define to_mlx5_vdpa_ndev(__mvdev) container_of(__mvdev, struct mlx5_vdpa_net, mvdev) +void *mlx5_vdpa_add_dev(struct mlx5_core_dev *mdev); +void mlx5_vdpa_remove_dev(struct mlx5_vdpa_dev *mvdev); + +#endif /* __MLX5_VNET_H_ */ From c84f91e2622235bb742f9f20b8675cf095157026 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 19:55:50 -0400 Subject: [PATCH 280/291] virtio_config: fix up warnings on parisc Apparently, on parisc le16_to_cpu returns an int. virtio_cread_le is very strict about type sizes so it causes a warning. Fix it up by casting to the correct type. Reported-by: kernel test robot Signed-off-by: Michael S. Tsirkin Link: https://lore.kernel.org/r/20200805235550.1451637-1-mst@redhat.com --- include/linux/virtio_config.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index ecb166c824bb..8fe857e27ef3 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -357,10 +357,10 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) */ #define virtio_le_to_cpu(x) \ _Generic((x), \ - __u8: (x), \ - __le16: le16_to_cpu(x), \ - __le32: le32_to_cpu(x), \ - __le64: le64_to_cpu(x) \ + __u8: (u8)(x), \ + __le16: (u16)le16_to_cpu(x), \ + __le32: (u32)le32_to_cpu(x), \ + __le64: (u64)le64_to_cpu(x) \ ) #define virtio_cpu_to_le(x, m) \ @@ -400,7 +400,6 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) *(ptr) = virtio_le_to_cpu(virtio_cread_v); \ } while(0) -/* Config space accessors. */ #define virtio_cwrite_le(vdev, structname, member, ptr) \ do { \ typeof(((structname*)0)->member) virtio_cwrite_v = \ From c9fecf505a3421752a598227f8ef895e97966c4b Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Sun, 5 Jul 2020 23:45:12 +0200 Subject: [PATCH 281/291] Replace HTTP links with HTTPS ones: security 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 Acked-by: John Johansen Signed-off-by: James Morris --- security/Kconfig | 2 +- security/apparmor/Kconfig | 2 +- security/integrity/ima/Kconfig | 2 +- security/integrity/ima/ima_template.c | 2 +- security/integrity/ima/ima_template_lib.c | 2 +- security/integrity/ima/ima_template_lib.h | 2 +- security/keys/encrypted-keys/ecryptfs_format.c | 2 +- security/keys/encrypted-keys/ecryptfs_format.h | 2 +- security/keys/encrypted-keys/encrypted.c | 2 +- security/keys/encrypted-keys/masterkey_trusted.c | 2 +- 10 files changed, 10 insertions(+), 10 deletions(-) diff --git a/security/Kconfig b/security/Kconfig index cd3cc7da3a55..7561f6f99f1d 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -118,7 +118,7 @@ config INTEL_TXT it was configured with, especially since they may be responsible for providing such assurances to VMs and services running on it. - See for more information + See for more information about Intel(R) TXT. See for more information about tboot. See Documentation/x86/intel_txt.rst for a description of how to enable diff --git a/security/apparmor/Kconfig b/security/apparmor/Kconfig index 0fe336860773..7e1dfdbd4c41 100644 --- a/security/apparmor/Kconfig +++ b/security/apparmor/Kconfig @@ -76,7 +76,7 @@ config SECURITY_APPARMOR_KUNIT_TEST This builds the AppArmor KUnit tests. 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 KUnit test harness and are not for inclusion into a production build. diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index edde88dbe576..6a5e4a77601b 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -26,7 +26,7 @@ config IMA an aggregate integrity value over this list inside the TPM hardware, so that the TPM can prove to a third party whether or not critical system files have been modified. - Read + Read to learn more about IMA. If unsure, say N. diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c index 062d9ad49afb..da8cf2d3fd64 100644 --- a/security/integrity/ima/ima_template.c +++ b/security/integrity/ima/ima_template.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2013 Politecnico di Torino, Italy - * TORSEC group -- http://security.polito.it + * TORSEC group -- https://security.polito.it * * Author: Roberto Sassu * diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c index 9cd1e50f3ccc..7320b76b1c62 100644 --- a/security/integrity/ima/ima_template_lib.c +++ b/security/integrity/ima/ima_template_lib.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2013 Politecnico di Torino, Italy - * TORSEC group -- http://security.polito.it + * TORSEC group -- https://security.polito.it * * Author: Roberto Sassu * diff --git a/security/integrity/ima/ima_template_lib.h b/security/integrity/ima/ima_template_lib.h index 9a88c79a7a61..6b3b880637a0 100644 --- a/security/integrity/ima/ima_template_lib.h +++ b/security/integrity/ima/ima_template_lib.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2013 Politecnico di Torino, Italy - * TORSEC group -- http://security.polito.it + * TORSEC group -- https://security.polito.it * * Author: Roberto Sassu * diff --git a/security/keys/encrypted-keys/ecryptfs_format.c b/security/keys/encrypted-keys/ecryptfs_format.c index a7339d4de811..8fdd76105ce3 100644 --- a/security/keys/encrypted-keys/ecryptfs_format.c +++ b/security/keys/encrypted-keys/ecryptfs_format.c @@ -4,7 +4,7 @@ * * Copyright (C) 2006 International Business Machines Corp. * Copyright (C) 2010 Politecnico di Torino, Italy - * TORSEC group -- http://security.polito.it + * TORSEC group -- https://security.polito.it * * Authors: * Michael A. Halcrow diff --git a/security/keys/encrypted-keys/ecryptfs_format.h b/security/keys/encrypted-keys/ecryptfs_format.h index 939621d870e4..ed8466578616 100644 --- a/security/keys/encrypted-keys/ecryptfs_format.h +++ b/security/keys/encrypted-keys/ecryptfs_format.h @@ -4,7 +4,7 @@ * * Copyright (C) 2006 International Business Machines Corp. * Copyright (C) 2010 Politecnico di Torino, Italy - * TORSEC group -- http://security.polito.it + * TORSEC group -- https://security.polito.it * * Authors: * Michael A. Halcrow diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c index f6797ba44bf7..3c2e9d5e21fd 100644 --- a/security/keys/encrypted-keys/encrypted.c +++ b/security/keys/encrypted-keys/encrypted.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2010 IBM Corporation * Copyright (C) 2010 Politecnico di Torino, Italy - * TORSEC group -- http://security.polito.it + * TORSEC group -- https://security.polito.it * * Authors: * Mimi Zohar diff --git a/security/keys/encrypted-keys/masterkey_trusted.c b/security/keys/encrypted-keys/masterkey_trusted.c index c68528aa49c6..e6d22ce77e98 100644 --- a/security/keys/encrypted-keys/masterkey_trusted.c +++ b/security/keys/encrypted-keys/masterkey_trusted.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2010 IBM Corporation * Copyright (C) 2010 Politecnico di Torino, Italy - * TORSEC group -- http://security.polito.it + * TORSEC group -- https://security.polito.it * * Authors: * Mimi Zohar From bb22d80b47d5dd641d09d31946c4be0f610f3f45 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 17 Jul 2020 16:36:40 -0700 Subject: [PATCH 282/291] LSM: drop duplicated words in header file comments Drop the doubled words "the" and "and" in comments. Signed-off-by: Randy Dunlap Acked-by: Serge Hallyn Cc: linux-security-module@vger.kernel.org Signed-off-by: James Morris --- include/linux/lsm_hook_defs.h | 2 +- include/linux/lsm_hooks.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 5616b2567aa7..dec0e5186834 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -15,7 +15,7 @@ */ /* - * The macro LSM_HOOK is used to define the data structures required by the + * The macro LSM_HOOK is used to define the data structures required by * the LSM framework using the pattern: * * LSM_HOOK(, , , args...) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 988ca0df7824..afd2c5becec5 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -798,7 +798,7 @@ * structure. Note that the security field was not added directly to the * socket structure, but rather, the socket security information is stored * in the associated inode. Typically, the inode alloc_security hook will - * allocate and and attach security information to + * allocate and attach security information to * SOCK_INODE(sock)->i_security. This hook may be used to update the * SOCK_INODE(sock)->i_security field with additional information that * wasn't available when the inode was allocated. From 1e3e792650d2c0df8dd796906275b7c79e278664 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 10 Aug 2020 08:44:43 -0400 Subject: [PATCH 283/291] vdpa_sim: init iommu lock The patch adding the iommu lock did not initialize it. The struct is zero-initialized so this is mostly a problem when using lockdep. Reported-by: kernel test robot Cc: Max Gurtovoy Fixes: 0ea9ee430e74 ("vdpasim: protect concurrent access to iommu iotlb") Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index df3224b138ee..604d9d25ca47 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -358,6 +358,7 @@ static struct vdpasim *vdpasim_create(void) INIT_WORK(&vdpasim->work, vdpasim_work); spin_lock_init(&vdpasim->lock); + spin_lock_init(&vdpasim->iommu_lock); dev = &vdpasim->vdpa.dev; dev->coherent_dma_mask = DMA_BIT_MASK(64); From 05acc4beb24c7e5ed3ae20a3d3ab2b29b40cb385 Mon Sep 17 00:00:00 2001 From: Alex Dewar Date: Thu, 6 Aug 2020 19:56:15 +0100 Subject: [PATCH 284/291] vdpa/mlx5: Fix uninitialised variable in core/mr.c If the kernel is unable to allocate memory for the variable dmr then err will be returned without being set. Set err to -ENOMEM in this case. Fixes: 94abbccdf291 ("vdpa/mlx5: Add shared memory registration code") Addresses-Coverity: ("Uninitialized variables") Signed-off-by: Alex Dewar Link: https://lore.kernel.org/r/20200806185625.67344-1-alex.dewar@gmx.co.uk Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang Acked-by: Eli Cohen --- drivers/vdpa/mlx5/core/mr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index f5dec0274133..ef1c550f8266 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -319,8 +319,10 @@ static int add_direct_chain(struct mlx5_vdpa_dev *mvdev, u64 start, u64 size, u8 while (size) { sz = (u32)min_t(u64, MAX_KLM_SIZE, size); dmr = kzalloc(sizeof(*dmr), GFP_KERNEL); - if (!dmr) + if (!dmr) { + err = -ENOMEM; goto err_alloc; + } dmr->start = st; dmr->end = st + sz; From f31231bf26a523de8aad4488643a98174c0d6bb2 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 6 Aug 2020 17:08:28 +0100 Subject: [PATCH 285/291] vdpa/mlx5: fix memory allocation failure checks The memory allocation failure checking for in and out is currently checking if the pointers are valid rather than the contents of what they point to. Hence the null check on failed memory allocations is incorrect. Fix this by adding the missing indirection in the check. Also for the default case, just set the *in and *out to null as these don't have any thing allocated to kfree. Finally remove the redundant *in and *out check as these have been already done on each allocation in the case statement. Addresses-Coverity: ("Null pointer dereference") Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices") Signed-off-by: Colin Ian King Link: https://lore.kernel.org/r/20200806160828.90463-1-colin.king@canonical.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang Acked-by: Eli Cohen --- drivers/vdpa/mlx5/net/mlx5_vnet.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 3ec44a4f0e45..55bc58e1dae9 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -867,7 +867,7 @@ static void alloc_inout(struct mlx5_vdpa_net *ndev, int cmd, void **in, int *inl *outlen = MLX5_ST_SZ_BYTES(qp_2rst_out); *in = kzalloc(*inlen, GFP_KERNEL); *out = kzalloc(*outlen, GFP_KERNEL); - if (!in || !out) + if (!*in || !*out) goto outerr; MLX5_SET(qp_2rst_in, *in, opcode, cmd); @@ -879,7 +879,7 @@ static void alloc_inout(struct mlx5_vdpa_net *ndev, int cmd, void **in, int *inl *outlen = MLX5_ST_SZ_BYTES(rst2init_qp_out); *in = kzalloc(*inlen, GFP_KERNEL); *out = kzalloc(MLX5_ST_SZ_BYTES(rst2init_qp_out), GFP_KERNEL); - if (!in || !out) + if (!*in || !*out) goto outerr; MLX5_SET(rst2init_qp_in, *in, opcode, cmd); @@ -896,7 +896,7 @@ static void alloc_inout(struct mlx5_vdpa_net *ndev, int cmd, void **in, int *inl *outlen = MLX5_ST_SZ_BYTES(init2rtr_qp_out); *in = kzalloc(*inlen, GFP_KERNEL); *out = kzalloc(MLX5_ST_SZ_BYTES(init2rtr_qp_out), GFP_KERNEL); - if (!in || !out) + if (!*in || !*out) goto outerr; MLX5_SET(init2rtr_qp_in, *in, opcode, cmd); @@ -914,7 +914,7 @@ static void alloc_inout(struct mlx5_vdpa_net *ndev, int cmd, void **in, int *inl *outlen = MLX5_ST_SZ_BYTES(rtr2rts_qp_out); *in = kzalloc(*inlen, GFP_KERNEL); *out = kzalloc(MLX5_ST_SZ_BYTES(rtr2rts_qp_out), GFP_KERNEL); - if (!in || !out) + if (!*in || !*out) goto outerr; MLX5_SET(rtr2rts_qp_in, *in, opcode, cmd); @@ -927,16 +927,15 @@ static void alloc_inout(struct mlx5_vdpa_net *ndev, int cmd, void **in, int *inl MLX5_SET(qpc, qpc, rnr_retry, 7); break; default: - goto outerr; + goto outerr_nullify; } - if (!*in || !*out) - goto outerr; return; outerr: kfree(*in); kfree(*out); +outerr_nullify: *in = NULL; *out = NULL; } From 2874211fcdb751e2962d68cdb9783fa1ff8eb340 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 8 Aug 2020 12:32:41 +0300 Subject: [PATCH 286/291] vdpa/mlx5: Fix pointer math in mlx5_vdpa_get_config() There is a pointer math bug here so if "offset" is non-zero then this will copy memory from beyond the end of the array. Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20200808093241.GB115053@mwanda Signed-off-by: Michael S. Tsirkin Acked-by: Eli Cohen Cc: Jason Wang ; Parav Pandit ; virtualization@lists.linux-foundation.org; linux-kernel@vger.kernel.org; kernel-janitors@vger.kernel.org Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices") Signed-off-by: Dan Carpenter --- drivers/vdpa/mlx5/net/mlx5_vnet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 55bc58e1dae9..c6b9ec47e51d 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1757,7 +1757,7 @@ static void mlx5_vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); if (offset + len < sizeof(struct virtio_net_config)) - memcpy(buf, &ndev->config + offset, len); + memcpy(buf, (u8 *)&ndev->config + offset, len); } static void mlx5_vdpa_set_config(struct vdpa_device *vdev, unsigned int offset, const void *buf, From 3df14264ad9930733a8166e5bd0eccc1727564bb Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 10 Aug 2020 08:48:22 +0000 Subject: [PATCH 287/291] recordmcount: Fix build failure on non arm64 Commit ea0eada45632 leads to the following build failure on powerpc: HOSTCC scripts/recordmcount scripts/recordmcount.c: In function 'arm64_is_fake_mcount': scripts/recordmcount.c:440: error: 'R_AARCH64_CALL26' undeclared (first use in this function) scripts/recordmcount.c:440: error: (Each undeclared identifier is reported only once scripts/recordmcount.c:440: error: for each function it appears in.) make[2]: *** [scripts/recordmcount] Error 1 Make sure R_AARCH64_CALL26 is always defined. Fixes: ea0eada45632 ("recordmcount: only record relocation of type R_AARCH64_CALL26 on arm64.") Signed-off-by: Christophe Leroy Acked-by: Steven Rostedt (VMware) Acked-by: Gregory Herrero Cc: Gregory Herrero Link: https://lore.kernel.org/r/5ca1be21fa6ebf73203b45fd9aadd2bafb5e6b15.1597049145.git.christophe.leroy@csgroup.eu Signed-off-by: Catalin Marinas --- scripts/recordmcount.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index e59022b3f125..b9c2ee7ab43f 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -42,6 +42,8 @@ #define R_ARM_THM_CALL 10 #define R_ARM_CALL 28 +#define R_AARCH64_CALL26 283 + static int fd_map; /* File descriptor for file being modified. */ static int mmap_failed; /* Boolean flag. */ static char gpfx; /* prefix for global symbol name (sometimes '_') */ From cf16fe9243bfa2863491026fc727618c7c593c84 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 6 Apr 2020 17:45:52 +0300 Subject: [PATCH 288/291] vdpa: Fix pointer math bug in vdpasim_get_config() If "offset" is non-zero then we end up copying from beyond the end of the config because of pointer math. We can fix this by casting the struct to a u8 pointer. Fixes: 2c53d0f64c06 ("vdpasim: vDPA device simulator") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20200406144552.GF68494@mwanda Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 604d9d25ca47..62d640327145 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -558,7 +558,7 @@ static void vdpasim_get_config(struct vdpa_device *vdpa, unsigned int offset, struct vdpasim *vdpasim = vdpa_to_sim(vdpa); if (offset + len < sizeof(struct virtio_net_config)) - memcpy(buf, &vdpasim->config + offset, len); + memcpy(buf, (u8 *)&vdpasim->config + offset, len); } static void vdpasim_set_config(struct vdpa_device *vdpa, unsigned int offset, From 8a7c3213db068135e816a6a517157de6443290d6 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 10 Aug 2020 09:13:10 -0400 Subject: [PATCH 289/291] vdpa/mlx5: fix up endian-ness for mtu VDPA mlx5 accesses config space as native endian - this is wrong since it's a modern device and actually uses LE. It only supports modern guests so we could punt and just force LE, but let's use the full virtio APIs since people tend to copy/paste code, and this is not data path anyway. Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/mlx5/net/mlx5_vnet.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index c6b9ec47e51d..9df69d5efe8c 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -137,6 +137,7 @@ struct mlx5_vdpa_net { struct mlx5_fc *rx_counter; struct mlx5_flow_handle *rx_rule; bool setup; + u16 mtu; }; static void free_resources(struct mlx5_vdpa_net *ndev); @@ -1506,6 +1507,13 @@ static void teardown_virtqueues(struct mlx5_vdpa_net *ndev) } } +/* TODO: cross-endian support */ +static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev) +{ + return virtio_legacy_is_little_endian() || + (mvdev->actual_features & (1ULL << VIRTIO_F_VERSION_1)); +} + static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); @@ -1519,6 +1527,8 @@ static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features) return err; ndev->mvdev.actual_features = features & ndev->mvdev.mlx_features; + ndev->config.mtu = __cpu_to_virtio16(mlx5_vdpa_is_little_endian(mvdev), + ndev->mtu); return err; } @@ -1925,7 +1935,7 @@ void *mlx5_vdpa_add_dev(struct mlx5_core_dev *mdev) init_mvqs(ndev); mutex_init(&ndev->reslock); config = &ndev->config; - err = mlx5_query_nic_vport_mtu(mdev, &config->mtu); + err = mlx5_query_nic_vport_mtu(mdev, &ndev->mtu); if (err) goto err_mtu; From e3c3155bc95ab6a7b21ac40418bf80bedb204949 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 21 Jul 2020 21:10:26 +0900 Subject: [PATCH 290/291] zonefs: add zone-capacity support In the zoned storage model, the sectors within a zone are typically all writeable. With the introduction of the Zoned Namespace (ZNS) Command Set in the NVM Express organization, the model was extended to have a specific writeable capacity. This zone capacity can be less than the overall zone size for a NVMe ZNS device or null_blk in zoned-mode. For other ZBC/ZAC devices the zone capacity is always equal to the zone size. Use the zone capacity field instead from blk_zone for determining the maximum inode size and inode blocks in zonefs. Signed-off-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Damien Le Moal --- fs/zonefs/super.c | 16 ++++++++++++---- fs/zonefs/zonefs.h | 3 +++ 2 files changed, 15 insertions(+), 4 deletions(-) diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 4a0bff65d3d6..8ec7c8f109d7 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -335,7 +335,7 @@ static void zonefs_io_error(struct inode *inode, bool write) struct zonefs_sb_info *sbi = ZONEFS_SB(sb); unsigned int noio_flag; unsigned int nr_zones = - zi->i_max_size >> (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + zi->i_zone_size >> (sbi->s_zone_sectors_shift + SECTOR_SHIFT); struct zonefs_ioerr_data err = { .inode = inode, .write = write, @@ -398,7 +398,7 @@ static int zonefs_file_truncate(struct inode *inode, loff_t isize) goto unlock; ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector, - zi->i_max_size >> SECTOR_SHIFT, GFP_NOFS); + zi->i_zone_size >> SECTOR_SHIFT, GFP_NOFS); if (ret) { zonefs_err(inode->i_sb, "Zone management operation at %llu failed %d", @@ -1053,14 +1053,16 @@ static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, zi->i_ztype = type; zi->i_zsector = zone->start; + zi->i_zone_size = zone->len << SECTOR_SHIFT; + zi->i_max_size = min_t(loff_t, MAX_LFS_FILESIZE, - zone->len << SECTOR_SHIFT); + zone->capacity << SECTOR_SHIFT); zi->i_wpoffset = zonefs_check_zone_condition(inode, zone, true, true); inode->i_uid = sbi->s_uid; inode->i_gid = sbi->s_gid; inode->i_size = zi->i_wpoffset; - inode->i_blocks = zone->len; + inode->i_blocks = zi->i_max_size >> SECTOR_SHIFT; inode->i_op = &zonefs_file_inode_operations; inode->i_fop = &zonefs_file_operations; @@ -1167,12 +1169,18 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd, if (zonefs_zone_type(next) != type) break; zone->len += next->len; + zone->capacity += next->capacity; if (next->cond == BLK_ZONE_COND_READONLY && zone->cond != BLK_ZONE_COND_OFFLINE) zone->cond = BLK_ZONE_COND_READONLY; else if (next->cond == BLK_ZONE_COND_OFFLINE) zone->cond = BLK_ZONE_COND_OFFLINE; } + if (zone->capacity != zone->len) { + zonefs_err(sb, "Invalid conventional zone capacity\n"); + ret = -EINVAL; + goto free; + } } /* diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h index ad17fef7ce91..55b39970acb2 100644 --- a/fs/zonefs/zonefs.h +++ b/fs/zonefs/zonefs.h @@ -56,6 +56,9 @@ struct zonefs_inode_info { /* File maximum size */ loff_t i_max_size; + /* File zone size */ + loff_t i_zone_size; + /* * To serialise fully against both syscall and mmap based IO and * sequential file truncation, two locks are used. For serializing From 4c96870e58f8bce1c7eba5f92ec69089ae6798f4 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 21 Jul 2020 21:10:27 +0900 Subject: [PATCH 291/291] zonefs: update documentation to reflect zone size vs capacity Update the zonefs documentation to reflect the difference between a zone's size and it's capacity. The maximum file size in zonefs is the zones capacity, for ZBC and ZAC based devices, which do not have a separate zone capacity, the zone capacity is equal to the zone size. Signed-off-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Damien Le Moal --- Documentation/filesystems/zonefs.rst | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/Documentation/filesystems/zonefs.rst b/Documentation/filesystems/zonefs.rst index 71d845c6a700..6c18bc8ce332 100644 --- a/Documentation/filesystems/zonefs.rst +++ b/Documentation/filesystems/zonefs.rst @@ -110,14 +110,14 @@ contain files named "0", "1", "2", ... The file numbers also represent increasing zone start sector on the device. All read and write operations to zone files are not allowed beyond the file -maximum size, that is, beyond the zone size. Any access exceeding the zone -size is failed with the -EFBIG error. +maximum size, that is, beyond the zone capacity. Any access exceeding the zone +capacity is failed with the -EFBIG error. Creating, deleting, renaming or modifying any attribute of files and sub-directories is not allowed. The number of blocks of a file as reported by stat() and fstat() indicates the -size of the file zone, or in other words, the maximum file size. +capacity of the zone file, or in other words, the maximum file size. Conventional zone files ----------------------- @@ -156,8 +156,8 @@ all accepted. Truncating sequential zone files is allowed only down to 0, in which case, the zone is reset to rewind the file zone write pointer position to the start of -the zone, or up to the zone size, in which case the file's zone is transitioned -to the FULL state (finish zone operation). +the zone, or up to the zone capacity, in which case the file's zone is +transitioned to the FULL state (finish zone operation). Format options -------------- @@ -324,7 +324,7 @@ file size set to 0. This is necessary as the write pointer of read-only zones is defined as invalib by the ZBC and ZAC standards, making it impossible to discover the amount of data that has been written to the zone. In the case of a read-only zone discovered at run-time, as indicated in the previous section. -the size of the zone file is left unchanged from its last updated value. +The size of the zone file is left unchanged from its last updated value. Zonefs User Space Tools ======================= @@ -401,8 +401,9 @@ append-writes to the file:: # ls -l /mnt/seq/0 -rw-r----- 1 root root 0 Nov 25 13:49 /mnt/seq/0 -Since files are statically mapped to zones on the disk, the number of blocks of -a file as reported by stat() and fstat() indicates the size of the file zone:: +Since files are statically mapped to zones on the disk, the number of blocks +of a file as reported by stat() and fstat() indicates the capacity of the file +zone:: # stat /mnt/seq/0 File: /mnt/seq/0 @@ -416,5 +417,6 @@ a file as reported by stat() and fstat() indicates the size of the file zone:: The number of blocks of the file ("Blocks") in units of 512B blocks gives the maximum file size of 524288 * 512 B = 256 MB, corresponding to the device zone -size in this example. Of note is that the "IO block" field always indicates the -minimum I/O size for writes and corresponds to the device physical sector size. +capacity in this example. Of note is that the "IO block" field always +indicates the minimum I/O size for writes and corresponds to the device +physical sector size.