diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2025-12-20 12:08:02 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2025-12-20 12:08:02 -0800 |
| commit | a0bdd554a8214651717964e947c415cfac8114a2 (patch) | |
| tree | c14b06c77e3b0bea9fc1bfd5752c34722170b0c7 /drivers/gpu/drm/amd | |
| parent | fa084c35afa13ab07a860ef0936cd987f9aa0460 (diff) | |
| parent | f66ac60dee28d092bc6a3af33a04147bfcb6ba30 (diff) | |
| download | linux-next-a0bdd554a8214651717964e947c415cfac8114a2.tar.gz linux-next-a0bdd554a8214651717964e947c415cfac8114a2.zip | |
Merge tag 'drm-fixes-2025-12-20' of https://gitlab.freedesktop.org/drm/kernel
Pull drm fixes from Dave Airlie:
"rc2 fixes for the week, mostly xe, with amdgpu as usual. Then a
smattering of small fixes across the core/tests/panel and amdxdna.
I expect things will be quiet for rc3/4 as teams take a break, and I'm
travelling but will keep an eye on things.
core:
- fix gem handle leak on DRM_IOCTL_GEM_CHANGE_HANDLE
tests:
- add EDEADLK handling
amdgpu:
- Fix no_console_suspend handling
- DCN 3.5.x seamless boot fixes
- DP audio fix
- Fix race in GPU recovery
- SMU 14 OD fix
amdkfd:
- Event fix
xe:
- Limit num_syncs to prevent oversized kernel allocations
- Disallow 0 OA property values
- Disallow 0 EU stall property values
- Fix kobject leak
- Workaround
- Loop variable reference fix
- Fix a CONFIG corner-case incorrect number of argument
- Skip reason prefix while emitting array
- VF migration fix
- Fix context in mei interrupt top half
- Don't include the CCS metadata in the dma-buf sg-table
- VF queueing recovery work fix
- Increase TDF timeout
- GT reset registers vs scheduler ordering fix
- Adjust long-running workload timeslices
- Always set OA_OAGLBCTXCTRL_COUNTER_RESUME
- Fix a return value
- Drop preempt-fences when destroying imported dma-bufs
- Use usleep_range for accurate long-running workload timeslicing
amdxdna:
- don't load virtualized
panel:
- fix visionox-rm69299 Kconfig dependency
- sony-td4353-jdi probing fix"
* tag 'drm-fixes-2025-12-20' of https://gitlab.freedesktop.org/drm/kernel: (34 commits)
drm/xe: Use usleep_range for accurate long-running workload timeslicing
drm/xe: Drop preempt-fences when destroying imported dma-bufs.
drm/xe/eustall: Disallow 0 EU stall property values
drm/xe/oa: Disallow 0 OA property values
drm/xe/xe_sriov_vfio: Fix return value in xe_sriov_vfio_migration_supported()
drm/xe/oa: Always set OAG_OAGLBCTXCTRL_COUNTER_RESUME
drm/xe: Adjust long-running workload timeslices to reasonable values
drm/xe/oa: Limit num_syncs to prevent oversized allocations
drm/xe: Limit num_syncs to prevent oversized allocations
drm/amdkfd: Fix improper NULL termination of queue restore SMI event string
drm/amd/pm: restore SCLK settings after S0ix resume
drm/amdgpu: fix a job->pasid access race in gpu recovery
drm/amd/display: Fix DP no audio issue
drm/amd/display: Fix scratch registers offsets for DCN351
drm/amd/display: Fix scratch registers offsets for DCN35
drm/amd: Resume the device in thaw() callback when console suspend is disabled
drm/panel: visionox-rm69299: Depend on BACKLIGHT_CLASS_DEVICE
accel/amdxdna: Block running under a hypervisor
drm/panel: sony-td4353-jdi: Enable prepare_prev_first
drm/xe: Restore engine registers before restarting schedulers after GT reset
...
Diffstat (limited to 'drivers/gpu/drm/amd')
8 files changed, 62 insertions, 21 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 58c3ffe707d1..12201b8e99b3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -6613,6 +6613,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, struct amdgpu_hive_info *hive = NULL; int r = 0; bool need_emergency_restart = false; + /* save the pasid here as the job may be freed before the end of the reset */ + int pasid = job ? job->pasid : -EINVAL; /* * If it reaches here because of hang/timeout and a RAS error is @@ -6713,8 +6715,12 @@ end_reset: if (!r) { struct amdgpu_task_info *ti = NULL; - if (job) - ti = amdgpu_vm_get_task_info_pasid(adev, job->pasid); + /* + * The job may already be freed at this point via the sched tdr workqueue so + * use the cached pasid. + */ + if (pasid >= 0) + ti = amdgpu_vm_get_task_info_pasid(adev, pasid); drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, ti ? &ti->task : NULL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 2dfbddcef9ab..848e6b7db482 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -33,6 +33,7 @@ #include <drm/drm_vblank.h> #include <linux/cc_platform.h> +#include <linux/console.h> #include <linux/dynamic_debug.h> #include <linux/module.h> #include <linux/mmu_notifier.h> @@ -2704,7 +2705,9 @@ static int amdgpu_pmops_thaw(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); /* do not resume device if it's normal hibernation */ - if (!pm_hibernate_is_recovering() && !pm_hibernation_mode_is_suspend()) + if (console_suspend_enabled && + !pm_hibernate_is_recovering() && + !pm_hibernation_mode_is_suspend()) return 0; return amdgpu_device_resume(drm_dev, true); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index a499449fcb06..d2bc169e84b0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -312,7 +312,7 @@ void kfd_smi_event_queue_restore(struct kfd_node *node, pid_t pid) { kfd_smi_event_add(pid, node, KFD_SMI_EVENT_QUEUE_RESTORE, KFD_EVENT_FMT_QUEUE_RESTORE(ktime_get_boottime_ns(), pid, - node->id, 0)); + node->id, '0')); } void kfd_smi_event_queue_restore_rescheduled(struct mm_struct *mm) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 4986f12dc9df..0cdd8c74abdf 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1118,13 +1118,13 @@ void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx) if (dc->current_state->res_ctx.pipe_ctx[i].stream_res.audio != NULL) num_audio++; } + if (num_audio >= 1 && clk_mgr->funcs->enable_pme_wa) { + /*wake AZ from D3 first before access az endpoint*/ + clk_mgr->funcs->enable_pme_wa(clk_mgr); + } pipe_ctx->stream_res.audio->funcs->az_enable(pipe_ctx->stream_res.audio); - if (num_audio >= 1 && clk_mgr->funcs->enable_pme_wa) - /*this is the first audio. apply the PME w/a in order to wake AZ from D3*/ - clk_mgr->funcs->enable_pme_wa(clk_mgr); - link_hwss->enable_audio_packet(pipe_ctx); if (pipe_ctx->stream_res.audio) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index ef69898d2cc5..d056e5fd5458 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -203,12 +203,12 @@ enum dcn35_clk_src_array_id { NBIO_BASE_INNER(seg) #define NBIO_SR(reg_name)\ - REG_STRUCT.reg_name = NBIO_BASE(regBIF_BX2_ ## reg_name ## _BASE_IDX) + \ - regBIF_BX2_ ## reg_name + REG_STRUCT.reg_name = NBIO_BASE(regBIF_BX1_ ## reg_name ## _BASE_IDX) + \ + regBIF_BX1_ ## reg_name #define NBIO_SR_ARR(reg_name, id)\ - REG_STRUCT[id].reg_name = NBIO_BASE(regBIF_BX2_ ## reg_name ## _BASE_IDX) + \ - regBIF_BX2_ ## reg_name + REG_STRUCT[id].reg_name = NBIO_BASE(regBIF_BX1_ ## reg_name ## _BASE_IDX) + \ + regBIF_BX1_ ## reg_name #define bios_regs_init() \ ( \ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c index f3c614c4490c..9fab3169069c 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c @@ -183,12 +183,12 @@ enum dcn351_clk_src_array_id { NBIO_BASE_INNER(seg) #define NBIO_SR(reg_name)\ - REG_STRUCT.reg_name = NBIO_BASE(regBIF_BX2_ ## reg_name ## _BASE_IDX) + \ - regBIF_BX2_ ## reg_name + REG_STRUCT.reg_name = NBIO_BASE(regBIF_BX1_ ## reg_name ## _BASE_IDX) + \ + regBIF_BX1_ ## reg_name #define NBIO_SR_ARR(reg_name, id)\ - REG_STRUCT[id].reg_name = NBIO_BASE(regBIF_BX2_ ## reg_name ## _BASE_IDX) + \ - regBIF_BX2_ ## reg_name + REG_STRUCT[id].reg_name = NBIO_BASE(regBIF_BX1_ ## reg_name ## _BASE_IDX) + \ + regBIF_BX1_ ## reg_name #define bios_regs_init() \ ( \ diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c index f9b0938c57ea..f2a16dfee599 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c @@ -1939,6 +1939,11 @@ int smu_v14_0_od_edit_dpm_table(struct smu_context *smu, dev_err(smu->adev->dev, "Set soft max sclk failed!"); return ret; } + if (smu->gfx_actual_hard_min_freq != smu->gfx_default_hard_min_freq || + smu->gfx_actual_soft_max_freq != smu->gfx_default_soft_max_freq) + smu->user_dpm_profile.user_od = true; + else + smu->user_dpm_profile.user_od = false; break; default: return -ENOSYS; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c index b1bd946d8e30..97414bc39764 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c @@ -1514,9 +1514,10 @@ static int smu_v14_0_1_set_fine_grain_gfx_freq_parameters(struct smu_context *sm smu->gfx_default_hard_min_freq = clk_table->MinGfxClk; smu->gfx_default_soft_max_freq = clk_table->MaxGfxClk; - smu->gfx_actual_hard_min_freq = 0; - smu->gfx_actual_soft_max_freq = 0; - + if (smu->gfx_actual_hard_min_freq == 0) + smu->gfx_actual_hard_min_freq = smu->gfx_default_hard_min_freq; + if (smu->gfx_actual_soft_max_freq == 0) + smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq; return 0; } @@ -1526,8 +1527,10 @@ static int smu_v14_0_0_set_fine_grain_gfx_freq_parameters(struct smu_context *sm smu->gfx_default_hard_min_freq = clk_table->MinGfxClk; smu->gfx_default_soft_max_freq = clk_table->MaxGfxClk; - smu->gfx_actual_hard_min_freq = 0; - smu->gfx_actual_soft_max_freq = 0; + if (smu->gfx_actual_hard_min_freq == 0) + smu->gfx_actual_hard_min_freq = smu->gfx_default_hard_min_freq; + if (smu->gfx_actual_soft_max_freq == 0) + smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq; return 0; } @@ -1665,6 +1668,29 @@ static int smu_v14_0_common_set_mall_enable(struct smu_context *smu) return ret; } +static int smu_v14_0_0_restore_user_od_settings(struct smu_context *smu) +{ + int ret; + + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinGfxClk, + smu->gfx_actual_hard_min_freq, + NULL); + if (ret) { + dev_err(smu->adev->dev, "Failed to restore hard min sclk!\n"); + return ret; + } + + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxGfxClk, + smu->gfx_actual_soft_max_freq, + NULL); + if (ret) { + dev_err(smu->adev->dev, "Failed to restore soft max sclk!\n"); + return ret; + } + + return 0; +} + static const struct pptable_funcs smu_v14_0_0_ppt_funcs = { .check_fw_status = smu_v14_0_check_fw_status, .check_fw_version = smu_v14_0_check_fw_version, @@ -1688,6 +1714,7 @@ static const struct pptable_funcs smu_v14_0_0_ppt_funcs = { .mode2_reset = smu_v14_0_0_mode2_reset, .get_dpm_ultimate_freq = smu_v14_0_common_get_dpm_ultimate_freq, .set_soft_freq_limited_range = smu_v14_0_0_set_soft_freq_limited_range, + .restore_user_od_settings = smu_v14_0_0_restore_user_od_settings, .od_edit_dpm_table = smu_v14_0_od_edit_dpm_table, .print_clk_levels = smu_v14_0_0_print_clk_levels, .force_clk_levels = smu_v14_0_0_force_clk_levels, |
