From 6628851159c77cf5666160e0272d46acc0772a6c Mon Sep 17 00:00:00 2001 From: Andi Shyti Date: Mon, 19 Aug 2024 13:31:40 +0200 Subject: drm/i915/gt: Continue creating engine sysfs files even after a failure The i915 driver generates sysfs entries for each engine of the GPU in /sys/class/drm/cardX/engines/. The process is straightforward: we loop over the UABI engines and for each one, we: - Create the object. - Create basic files. - If the engine supports timeslicing, create timeslice duration files. - If the engine supports preemption, create preemption-related files. - Create default value files. Currently, if any of these steps fail, the process stops, and no further sysfs files are created. However, it's not necessary to stop the process on failure. Instead, we can continue creating the remaining sysfs files for the other engines. Even if some files fail to be created, the list of engines can still be retrieved by querying i915. Signed-off-by: Andi Shyti Reviewed-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20240819113140.325235-1-andi.shyti@linux.intel.com --- drivers/gpu/drm/i915/gt/sysfs_engines.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/sysfs_engines.c b/drivers/gpu/drm/i915/gt/sysfs_engines.c index 021f51d9b456..aab2759067d2 100644 --- a/drivers/gpu/drm/i915/gt/sysfs_engines.c +++ b/drivers/gpu/drm/i915/gt/sysfs_engines.c @@ -530,9 +530,8 @@ void intel_engines_add_sysfs(struct drm_i915_private *i915) err_object: kobject_put(kobj); err_engine: - dev_err(kdev, "Failed to add sysfs engine '%s'\n", - engine->name); - break; + dev_warn(kdev, "Failed to add sysfs engine '%s'\n", + engine->name); } } } -- cgit From 3126d5fff54368288e7fe1c0fd4ecb36b868e5aa Mon Sep 17 00:00:00 2001 From: Yu Jiaoliang Date: Wed, 21 Aug 2024 16:40:36 +0200 Subject: drm/i915/gt: Use kmemdup_array instead of kmemdup for multiple allocation Let the kememdup_array() take care about multiplication and possible overflows. v2: - Change subject - Leave one blank line between the commit log and the tag section - Fix code alignment issue v3: - Fix code alignment - Apply the patch on a clean drm-tip Signed-off-by: Yu Jiaoliang Reviewed-by: Jani Nikula Reviewed-by: Andi Shyti Signed-off-by: Andi Shyti Link: https://patchwork.freedesktop.org/patch/msgid/20240821144036.343556-1-andi.shyti@linux.intel.com --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index bfe6d8fc820f..baa609bdf7cb 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -111,9 +111,8 @@ static void wa_init_finish(struct i915_wa_list *wal) { /* Trim unused entries. */ if (!IS_ALIGNED(wal->count, WA_LIST_CHUNK)) { - struct i915_wa *list = kmemdup(wal->list, - wal->count * sizeof(*list), - GFP_KERNEL); + struct i915_wa *list = kmemdup_array(wal->list, wal->count, + sizeof(*list), GFP_KERNEL); if (list) { kfree(wal->list); -- cgit From 037f93434ce9aea3dc19ba2d97e888a12e538f7b Mon Sep 17 00:00:00 2001 From: Dnyaneshwar Bhadane Date: Sun, 25 Aug 2024 17:41:56 +0530 Subject: drm/i915/gt: Whitelist COMMON_SLICE_CHICKEN1 for UMD access. As part of the recommended tuning setting, whitelist COMMON_SLICE_CHICKEN1 for MTL/ARL and DG2. The UMD will selectively enable or disable specific bits of the register based on the type of workload and its requirements. v2: Remove the KMD par of enabling specific bits(Matt R) Bspec: 68331 Signed-off-by: Dnyaneshwar Bhadane Reviewed-by: Matt Roper Signed-off-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20240825121156.2498810-1-dnyaneshwar.bhadane@intel.com --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index baa609bdf7cb..e539a656cfc3 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -2071,7 +2071,7 @@ static void dg2_whitelist_build(struct intel_engine_cs *engine) case RENDER_CLASS: /* Required by recommended tuning setting (not a workaround) */ whitelist_mcr_reg(w, XEHP_COMMON_SLICE_CHICKEN3); - + whitelist_reg(w, GEN7_COMMON_SLICE_CHICKEN1); break; default: break; @@ -2086,7 +2086,7 @@ static void xelpg_whitelist_build(struct intel_engine_cs *engine) case RENDER_CLASS: /* Required by recommended tuning setting (not a workaround) */ whitelist_mcr_reg(w, XEHP_COMMON_SLICE_CHICKEN3); - + whitelist_reg(w, GEN7_COMMON_SLICE_CHICKEN1); break; default: break; -- cgit From 54f90b03335916e21c417a31d0926841f7d97c56 Mon Sep 17 00:00:00 2001 From: John Harrison Date: Thu, 8 Aug 2024 17:06:46 -0700 Subject: drm/i915/guc: Fix missing enable of Wa_14019159160 on ARL The previous update to enable the workaround on ARL only changed two out of three places where the w/a needs to be enabled. That meant the GuC side was operational but not the KMD side. And as the KMD side is the trigger, it meant the w/a was not actually active. So fix that. Fixes: 104bcfae57d8 ("drm/i915/arl: Enable Wa_14019159160 for ARL") Cc: John Harrison Cc: Vinay Belgaumkar Cc: Daniele Ceraolo Spurio Cc: Andi Shyti Cc: Lucas De Marchi Cc: Rodrigo Vivi Cc: Matt Roper Cc: Jonathan Cavitt Cc: Nirmoy Das Cc: Shuicheng Lin Signed-off-by: John Harrison Reviewed-by: Nirmoy Das Reviewed-by: Andi Shyti Link: https://patchwork.freedesktop.org/patch/msgid/20240809000646.1747507-1-John.C.Harrison@Intel.com --- drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index c3a5d9e1288e..8322c913bc3c 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -4507,7 +4507,7 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine) /* Wa_16019325821 */ /* Wa_14019159160 */ if ((engine->class == COMPUTE_CLASS || engine->class == RENDER_CLASS) && - IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 71))) + IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 74))) engine->flags |= I915_ENGINE_USES_WA_HOLD_SWITCHOUT; /* -- cgit From 03ded4d432a1fb7bb6c44c5856d14115f6f6c3b9 Mon Sep 17 00:00:00 2001 From: Daniele Ceraolo Spurio Date: Tue, 20 Aug 2024 14:59:52 -0700 Subject: drm/i915: Do not attempt to load the GSC multiple times If the GSC FW fails to load the GSC HW hangs permanently; the only ways to recover it are FLR or D3cold entry, with the former only being supported on driver unload and the latter only on DGFX, for which we don't need to load the GSC. Therefore, if GSC fails to load there is no need to try again because the HW is stuck in the error state and the submission to load the FW would just hang the GSCCS. Note that, due to wa_14015076503, on MTL the GuC escalates all GSCCS hangs to full GT resets, which would trigger a new attempt to load the GSC FW in the post-reset HW re-init; this issue is also fixed by not attempting to load the GSC FW after an error. Fixes: 15bd4a67e914 ("drm/i915/gsc: GSC firmware loading") Signed-off-by: Daniele Ceraolo Spurio Cc: Daniele Ceraolo Spurio Cc: Alan Previn Cc: John Harrison Cc: Rodrigo Vivi Cc: # v6.3+ Reviewed-by: Jonathan Cavitt Link: https://patchwork.freedesktop.org/patch/msgid/20240820215952.2290807-1-daniele.ceraolospurio@intel.com --- drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c | 2 +- drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c index 453d855dd1de..3d3191deb0ab 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c @@ -302,7 +302,7 @@ void intel_gsc_uc_load_start(struct intel_gsc_uc *gsc) { struct intel_gt *gt = gsc_uc_to_gt(gsc); - if (!intel_uc_fw_is_loadable(&gsc->fw)) + if (!intel_uc_fw_is_loadable(&gsc->fw) || intel_uc_fw_is_in_error(&gsc->fw)) return; if (intel_gsc_uc_fw_init_done(gsc)) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h index 9a431726c8d5..ac7b3aad2222 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h @@ -258,6 +258,11 @@ static inline bool intel_uc_fw_is_running(struct intel_uc_fw *uc_fw) return __intel_uc_fw_status(uc_fw) == INTEL_UC_FIRMWARE_RUNNING; } +static inline bool intel_uc_fw_is_in_error(struct intel_uc_fw *uc_fw) +{ + return intel_uc_fw_status_to_error(__intel_uc_fw_status(uc_fw)) != 0; +} + static inline bool intel_uc_fw_is_overridden(const struct intel_uc_fw *uc_fw) { return uc_fw->user_overridden; -- cgit From 727eb1e3f014e66dcdec53afc6f5bfe0d8c0871d Mon Sep 17 00:00:00 2001 From: Raag Jadav Date: Fri, 23 Aug 2024 09:15:48 +0530 Subject: drm/i915/hwmon: expose fan speed Add hwmon support for fan1_input attribute, which will expose fan speed in RPM. With this in place we can monitor fan speed using lm-sensors tool. $ sensors i915-pci-0300 Adapter: PCI adapter in0: 653.00 mV fan1: 3833 RPM power1: N/A (max = 43.00 W) energy1: 32.02 kJ v2: Handle overflow, add mutex protection and ABI documentation Aesthetic adjustments (Riana) v3: Change rotations data type, ABI date and version v4: Fix wakeref leak Drop switch case and simplify hwm_fan_xx() (Andi) v5: Rework time calculation, aesthetic adjustments (Andy) v6: Drop redundant overflow logic (Andy) Split fan_input_read() into dedicated helper (Badal) v7: Fix undefined reference to __udivdi3 for i386 (Andy) Signed-off-by: Raag Jadav Reviewed-by: Riana Tauro Reviewed-by: Andi Shyti Reviewed-by: Badal Nilawar Signed-off-by: Anshuman Gupta Link: https://patchwork.freedesktop.org/patch/msgid/20240823034548.2670032-1-raag.jadav@intel.com --- .../ABI/testing/sysfs-driver-intel-i915-hwmon | 8 ++ drivers/gpu/drm/i915/gt/intel_gt_regs.h | 2 + drivers/gpu/drm/i915/i915_hwmon.c | 88 ++++++++++++++++++++++ 3 files changed, 98 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon index 92fe7c5c5ac1..be4141a7522f 100644 --- a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon +++ b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon @@ -75,3 +75,11 @@ Description: RO. Energy input of device or gt in microjoules. for the gt. Only supported for particular Intel i915 graphics platforms. + +What: /sys/bus/pci/drivers/i915/.../hwmon/hwmon/fan1_input +Date: November 2024 +KernelVersion: 6.12 +Contact: intel-gfx@lists.freedesktop.org +Description: RO. Fan speed of device in RPM. + + Only supported for particular Intel i915 graphics platforms. diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index e42b3a5d4e63..57a3c83d3655 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -1553,6 +1553,8 @@ #define VLV_RENDER_C0_COUNT _MMIO(0x138118) #define VLV_MEDIA_C0_COUNT _MMIO(0x13811c) +#define PCU_PWM_FAN_SPEED _MMIO(0x138140) + #define GEN12_RPSTAT1 _MMIO(0x1381b4) #define GEN12_VOLTAGE_MASK REG_GENMASK(10, 0) #define GEN12_CAGF_MASK REG_GENMASK(19, 11) diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c index 49db3e09826c..17d30f6b84b0 100644 --- a/drivers/gpu/drm/i915/i915_hwmon.c +++ b/drivers/gpu/drm/i915/i915_hwmon.c @@ -5,6 +5,7 @@ #include #include +#include #include #include "i915_drv.h" @@ -36,6 +37,7 @@ struct hwm_reg { i915_reg_t pkg_rapl_limit; i915_reg_t energy_status_all; i915_reg_t energy_status_tile; + i915_reg_t fan_speed; }; struct hwm_energy_info { @@ -43,11 +45,17 @@ struct hwm_energy_info { long accum_energy; /* Accumulated energy for energy1_input */ }; +struct hwm_fan_info { + u32 reg_val_prev; + u64 time_prev; +}; + struct hwm_drvdata { struct i915_hwmon *hwmon; struct intel_uncore *uncore; struct device *hwmon_dev; struct hwm_energy_info ei; /* Energy info for energy1_input */ + struct hwm_fan_info fi; /* Fan info for fan1_input */ char name[12]; int gt_n; bool reset_in_progress; @@ -276,6 +284,7 @@ static const struct hwmon_channel_info * const hwm_info[] = { HWMON_CHANNEL_INFO(power, HWMON_P_MAX | HWMON_P_RATED_MAX | HWMON_P_CRIT), HWMON_CHANNEL_INFO(energy, HWMON_E_INPUT), HWMON_CHANNEL_INFO(curr, HWMON_C_CRIT), + HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT), NULL }; @@ -613,6 +622,69 @@ hwm_curr_write(struct hwm_drvdata *ddat, u32 attr, long val) } } +static umode_t +hwm_fan_is_visible(const struct hwm_drvdata *ddat, u32 attr) +{ + struct i915_hwmon *hwmon = ddat->hwmon; + + if (attr == hwmon_fan_input && i915_mmio_reg_valid(hwmon->rg.fan_speed)) + return 0444; + + return 0; +} + +static int +hwm_fan_input_read(struct hwm_drvdata *ddat, long *val) +{ + struct i915_hwmon *hwmon = ddat->hwmon; + struct hwm_fan_info *fi = &ddat->fi; + u64 rotations, time_now, time; + intel_wakeref_t wakeref; + u32 reg_val; + int ret = 0; + + wakeref = intel_runtime_pm_get(ddat->uncore->rpm); + mutex_lock(&hwmon->hwmon_lock); + + reg_val = intel_uncore_read(ddat->uncore, hwmon->rg.fan_speed); + time_now = get_jiffies_64(); + + /* + * HW register value is accumulated count of pulses from + * PWM fan with the scale of 2 pulses per rotation. + */ + rotations = (reg_val - fi->reg_val_prev) / 2; + + time = jiffies_delta_to_msecs(time_now - fi->time_prev); + if (unlikely(!time)) { + ret = -EAGAIN; + goto exit; + } + + /* + * Calculate fan speed in RPM by time averaging two subsequent + * readings in minutes. + * RPM = number of rotations * msecs per minute / time in msecs + */ + *val = DIV_ROUND_UP_ULL(rotations * (MSEC_PER_SEC * 60), time); + + fi->reg_val_prev = reg_val; + fi->time_prev = time_now; +exit: + mutex_unlock(&hwmon->hwmon_lock); + intel_runtime_pm_put(ddat->uncore->rpm, wakeref); + return ret; +} + +static int +hwm_fan_read(struct hwm_drvdata *ddat, u32 attr, long *val) +{ + if (attr == hwmon_fan_input) + return hwm_fan_input_read(ddat, val); + + return -EOPNOTSUPP; +} + static umode_t hwm_is_visible(const void *drvdata, enum hwmon_sensor_types type, u32 attr, int channel) @@ -628,6 +700,8 @@ hwm_is_visible(const void *drvdata, enum hwmon_sensor_types type, return hwm_energy_is_visible(ddat, attr); case hwmon_curr: return hwm_curr_is_visible(ddat, attr); + case hwmon_fan: + return hwm_fan_is_visible(ddat, attr); default: return 0; } @@ -648,6 +722,8 @@ hwm_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, return hwm_energy_read(ddat, attr, val); case hwmon_curr: return hwm_curr_read(ddat, attr, val); + case hwmon_fan: + return hwm_fan_read(ddat, attr, val); default: return -EOPNOTSUPP; } @@ -739,12 +815,14 @@ hwm_get_preregistration_info(struct drm_i915_private *i915) hwmon->rg.pkg_rapl_limit = PCU_PACKAGE_RAPL_LIMIT; hwmon->rg.energy_status_all = PCU_PACKAGE_ENERGY_STATUS; hwmon->rg.energy_status_tile = INVALID_MMIO_REG; + hwmon->rg.fan_speed = PCU_PWM_FAN_SPEED; } else { hwmon->rg.pkg_power_sku_unit = INVALID_MMIO_REG; hwmon->rg.pkg_power_sku = INVALID_MMIO_REG; hwmon->rg.pkg_rapl_limit = INVALID_MMIO_REG; hwmon->rg.energy_status_all = INVALID_MMIO_REG; hwmon->rg.energy_status_tile = INVALID_MMIO_REG; + hwmon->rg.fan_speed = INVALID_MMIO_REG; } with_intel_runtime_pm(uncore->rpm, wakeref) { @@ -755,6 +833,16 @@ hwm_get_preregistration_info(struct drm_i915_private *i915) if (i915_mmio_reg_valid(hwmon->rg.pkg_power_sku_unit)) val_sku_unit = intel_uncore_read(uncore, hwmon->rg.pkg_power_sku_unit); + + /* + * Store the initial fan register value, so that we can use it for + * initial fan speed calculation. + */ + if (i915_mmio_reg_valid(hwmon->rg.fan_speed)) { + ddat->fi.reg_val_prev = intel_uncore_read(uncore, + hwmon->rg.fan_speed); + ddat->fi.time_prev = get_jiffies_64(); + } } hwmon->scl_shift_power = REG_FIELD_GET(PKG_PWR_UNIT, val_sku_unit); -- cgit From 596a7f1084e49cc65072c458c348861e9b9ceab9 Mon Sep 17 00:00:00 2001 From: Hongbo Li Date: Sat, 31 Aug 2024 17:46:55 +0800 Subject: drm/i915: Remove extra unlikely helper In IS_ERR, the unlikely is used for the input parameter, so these is no need to use it again outside. Signed-off-by: Hongbo Li Link: https://patchwork.freedesktop.org/patch/msgid/20240831094655.4153520-1-lihongbo22@huawei.com Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 8aff06933f54..577dbd49cf16 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -827,7 +827,7 @@ static int eb_select_context(struct i915_execbuffer *eb) struct i915_gem_context *ctx; ctx = i915_gem_context_lookup(eb->file->driver_priv, eb->args->rsvd1); - if (unlikely(IS_ERR(ctx))) + if (IS_ERR(ctx)) return PTR_ERR(ctx); eb->gem_context = ctx; -- cgit