drm/amdgpu:implement new gpu recover(v2)
Subsystems (2)
PATCH 1/5 drm/amdgpu:implement new gpu recover(v2)
1,new imple names amdgpu_gpu_recover which gives more hint on what it does compared with gpu_reset
2,gpu_recover unify bare-metal and SR-IOV, only the reset part is implemented differently
3,gpu_recover will increase hang job karma and its context guilty if exceeds limit, which will be canceled in run_job() routine of gpu scheduler with an error "-ECANCELED" set.
4,gpu_recover knows if this reset comes with VRAM lost or not and all jobs will be canceled in run_job() in sched recovery if VRAM lost hit.
v2:
move gpu_scheduler.c change into another patch do VRAM_RECOVERY if VRAM_LOST flag bit set after reset
--- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 4 + drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 253 +++++++++++++++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 18 +- 3 files changed, 273 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +4 -0
@@ -178,6 +178,10 @@ extern int amdgpu_cik_support;#define CIK_CURSOR_WIDTH 128#define CIK_CURSOR_HEIGHT 128 +/* GPU RESET flags */ +#define AMDGPU_RESET_INFO_VRAM_LOST (1 << 0) +#define AMDGPU_RESET_INFO_FULLRESET (1 << 1) +struct amdgpu_device ;struct amdgpu_ib ;struct amdgpu_cs_parser ;
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +253 -0
259 lines not on this page · raw message
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +16 -2
@@ -177,6 +177,19 @@ static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)return fence; } +/* Guilty for jobs with a guilty user context, +* or jobs whose karma exceed the limit from a kernel context, +* or jobs that encountered VRAM LOST issue +*/ +static bool amdgpu_job_need_canceled (struct amdgpu_job *job) { +if (job->base.s_entity->guilty &&atomic_read (job->base.s_entity->guilty) ==1 ) +return true; +else if (job->vram_lost_counter !=atomic_read (&job->adev->vram_lost_counter)) +return true; + +return false; +} +static struct dma_fence *amdgpu_job_run (struct amd_sched_job *sched_job) {struct dma_fence *fence =NULL ;
@@ -194,8 +207,9 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)BUG_ON (amdgpu_sync_peek_fence (&job->sync,NULL ));trace_amdgpu_sched_run_job (job); -/* skip ib schedule when vram is lost */ -if (job->vram_lost_counter !=atomic_read (&adev->vram_lost_counter)) { + +if (amdgpu_job_need_canceled (job)) { +/* skip ib schedule if looks needed, and set error */ dma_fence_set_error (&job->base.s_fence->finished, -ECANCELED );DRM_ERROR ("Skip scheduling IBs!\n" ); }else {
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1508834534-16471-1-git-send-email-Monk.Liu-5C7GfCeVMHo@public.gmane.org
PATCH 2/5 amd/scheduler:remove error message if no hw fence
because no hw fence may also comes from a gpu recover and job skip event, doesn't mean really bad thing
--- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 2 -- 1 file changed, 2 deletions(-)
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +0 -2
@@ -525,7 +525,6 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) r);dma_fence_put (fence); }else { -DRM_ERROR ("Failed to run job!\n" );amd_sched_process_job (NULL , &s_fence->cb); }spin_lock (&sched->job_list_lock);
@@ -664,7 +663,6 @@ static int amd_sched_main(void *param) r);dma_fence_put (fence); }else { -DRM_ERROR ("Failed to run job!\n" );amd_sched_process_job (NULL , &s_fence->cb); }
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1508834534-16471-2-git-send-email-Monk.Liu-5C7GfCeVMHo@public.gmane.org
Christian König
Reviewed-byRe: [PATCH 2/5] amd/scheduler:remove error message if no hw fence
Am 24.10.2017 um 10:42 schrieb Monk Liu:
Quoted 5 lines
because no hw fence may also comes from a gpu recover and job skip event, doesn't mean really bad thing
Change-Id I4d6e5824dfe050bb3ca6ea0ad74828720bc374acSigned-off-by Monk Liu <[email protected]>
Quoted 17 lines
--- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 2 -- 1 file changed, 2 deletions(-)drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +0
-1@@ -525,7 +525,6 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) r);dma_fence_put (fence); }else { -DRM_ERROR ("Failed to run job!\n" );amd_sched_process_job (NULL , &s_fence->cb); }spin_lock (&sched->job_list_lock);
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c static int amd_sched_main(void *param) · line 668
Quoted 7 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +0
-1@@ -664,7 +663,6 @@ static int amd_sched_main(void *param) r);dma_fence_put (fence); }else { -DRM_ERROR ("Failed to run job!\n" );amd_sched_process_job (NULL , &s_fence->cb); }
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 3/5 drm/amdgpu:use new gpu recover routine
In reply to a message not in the archiveretire gpu_reset and sriov_gpu_reset and use new implemented amdgpu_gpu_recover
--- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 307 +---------------------------- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 10 +- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 5 +- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 1 - drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 2 +- drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 2 +- 8 files changed, 19 insertions(+), 312 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +1 -1
@@ -1844,7 +1844,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)#define amdgpu_psp_check_fw_loading_status (adev, i) (adev)->firmware.funcs->check_fw_loading_status((adev), (i))/* Common functions */ -int amdgpu_gpu_reset (struct amdgpu_device *adev); +int amdgpu_gpu_recover (struct amdgpu_device *adev,struct amdgpu_job * job);bool amdgpu_need_backup (struct amdgpu_device *adev);void amdgpu_pci_config_reset (struct amdgpu_device *adev);bool amdgpu_need_post (struct amdgpu_device *adev);
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +9 -298
319 lines not on this page · raw message
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +5 -5
@@ -694,25 +694,25 @@ static int amdgpu_debugfs_fence_info(struct seq_file *m, void *data) }/** -* amdgpu_debugfs_gpu_reset - manually trigger a gpu reset +* amdgpu_debugfs_gpu_recover - manually trigger a gpu reset & recover * * Manually trigger a gpu reset at the next fence wait. */ -static int amdgpu_debugfs_gpu_reset (struct seq_file *m,void *data) +static int amdgpu_debugfs_gpu_recover (struct seq_file *m,void *data) {struct drm_info_node *node = (struct drm_info_node *) m->private;struct drm_device *dev = node->minor->dev;struct amdgpu_device *adev = dev->dev_private; -seq_printf (m,"gpu reset\n" ); -amdgpu_gpu_reset (adev); +seq_printf (m,"gpu recover\n" ); +amdgpu_gpu_recover (adev,NULL );return 0 ; }static const struct drm_info_list amdgpu_debugfs_fence_list[] = { {"amdgpu_fence_info" , &amdgpu_debugfs_fence_info,0 ,NULL }, - {"amdgpu_gpu_reset" , &amdgpu_debugfs_gpu_reset,0 ,NULL } + {"amdgpu_gpu_recover" , &amdgpu_debugfs_gpu_recover,0 ,NULL } };static const struct drm_info_list amdgpu_debugfs_fence_list_sriov[] = {
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +1 -1
@@ -88,7 +88,7 @@ static void amdgpu_irq_reset_work_func(struct work_struct *work) reset_work);if (!amdgpu_sriov_vf (adev)) -amdgpu_gpu_reset (adev); +amdgpu_gpu_recover (adev,NULL ); }/* Disable *all* interrupts */
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +1 -4
@@ -37,10 +37,7 @@ static void amdgpu_job_timedout(struct amd_sched_job *s_job)atomic_read (&job->ring->fence_drv.last_seq), job->ring->fence_drv.sync_seq); -if (amdgpu_sriov_vf (job->adev)) -amdgpu_sriov_gpu_reset (job->adev, job); -else -amdgpu_gpu_reset (job->adev); +amdgpu_gpu_recover (job->adev, job); } int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +0 -1
@@ -285,7 +285,6 @@ void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v);int amdgpu_virt_request_full_gpu (struct amdgpu_device *adev,bool init);int amdgpu_virt_release_full_gpu (struct amdgpu_device *adev,bool init);int amdgpu_virt_reset_gpu (struct amdgpu_device *adev); -int amdgpu_sriov_gpu_reset (struct amdgpu_device *adev,struct amdgpu_job *job);int amdgpu_virt_alloc_mm_table (struct amdgpu_device *adev);void amdgpu_virt_free_mm_table (struct amdgpu_device *adev); int amdgpu_virt_fw_reserve_get_checksum(void *obj, unsigned long obj_size,
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +1 -1
@@ -254,7 +254,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work) }/* Trigger recovery due to world switch failure */ -amdgpu_sriov_gpu_reset (adev,NULL ); +amdgpu_gpu_recover (adev,NULL ); } static int xgpu_ai_set_mailbox_rcv_irq(struct amdgpu_device *adev,
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c +1 -1
@@ -514,7 +514,7 @@ static void xgpu_vi_mailbox_flr_work(struct work_struct *work) }/* Trigger recovery due to world switch failure */ -amdgpu_sriov_gpu_reset (adev,NULL ); +amdgpu_gpu_recover (adev,NULL ); } static int xgpu_vi_set_mailbox_rcv_irq(struct amdgpu_device *adev,
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 4/5 drm/amdgpu:cleanup in_sriov_reset and lock_reset
In reply to a message not in the archivesince now gpu reset is unified with gpu_recover
for both bare-metal and SR-IOV:
1)rename in_sriov_reset to in_gpu_reset
2)move lock_reset from adev->virt to adev
--- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 3 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 9 +++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 2 -- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 1 - drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 6 +++--- 8 files changed, 15 insertions(+), 16 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +2 -1
@@ -1650,7 +1650,8 @@ struct amdgpu_device {/* record last mm index being written through WREG32*/ unsigned long last_mm_index; -bool in_sriov_reset; +bool in_gpu_reset; +struct mutex lock_reset; };static inline struct amdgpu_device *amdgpu_ttm_adev (struct ttm_bo_device *bdev)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +5 -4
@@ -2161,6 +2161,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,mutex_init (&adev->mn_lock);mutex_init (&adev->virt.vf_errors.lock);hash_init (adev->mn_hash); +mutex_init (&adev->lock_reset);amdgpu_check_arguments (adev);
@@ -2963,9 +2964,9 @@ int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job *job)dev_info (adev->dev,"GPU reset begin!\n" ); -mutex_lock (&adev->virt.lock_reset); +mutex_lock (&adev->lock_reset);atomic_inc (&adev->gpu_reset_counter); - adev->in_sriov_reset =1 ; + adev->in_gpu_reset =1 ;/* block TTM */ resched =ttm_bo_lock_delayed_workqueue (&adev->mman.bdev);
@@ -3075,8 +3076,8 @@ int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job *job) }amdgpu_vf_error_trans_all (adev); - adev->in_sriov_reset =0 ; -mutex_unlock (&adev->virt.lock_reset); + adev->in_gpu_reset =0 ; +mutex_unlock (&adev->lock_reset);return r; }
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +1 -1
@@ -264,7 +264,7 @@ static int psp_hw_start(struct psp_context *psp)struct amdgpu_device *adev = psp->adev;int ret; -if (!amdgpu_sriov_vf (adev) || !adev->in_sriov_reset) { +if (!amdgpu_sriov_vf (adev) || !adev->in_gpu_reset) { ret =psp_bootloader_load_sysdrv (psp);if (ret)return ret;
drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +1 -1
@@ -370,7 +370,7 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev)return 0 ; } -if (!amdgpu_sriov_vf (adev) || !adev->in_sriov_reset) { +if (!amdgpu_sriov_vf (adev) || !adev->in_gpu_reset) { err = amdgpu_bo_create(adev, adev->firmware.fw_size, PAGE_SIZE, true, amdgpu_sriov_vf(adev) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT, AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +0 -2
@@ -107,8 +107,6 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev) adev->enable_virtual_display = true; adev->cg_flags =0 ; adev->pg_flags =0 ; - -mutex_init (&adev->virt.lock_reset); }uint32_t amdgpu_virt_kiq_rreg (struct amdgpu_device *adev,uint32_t reg)
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +0 -1
@@ -238,7 +238,6 @@ struct amdgpu_virt {uint64_t csa_vmid0_addr;bool chained_ib_support;uint32_t reg_val_offs; -struct mutex lock_reset;struct amdgpu_irq_src ack_irq;struct amdgpu_irq_src rcv_irq;struct work_struct flr_work;
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +3 -3
@@ -4807,7 +4807,7 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)gfx_v8_0_kiq_setting (ring); -if (adev->in_sriov_reset) {/* for GPU_RESET case */ +if (adev->in_gpu_reset) {/* for GPU_RESET case */ /* reset MQD to a clean status */ if (adev->gfx.mec.mqd_backup[mqd_idx])memcpy (mqd, adev->gfx.mec.mqd_backup[mqd_idx],sizeof (struct vi_mqd_allocation ));
@@ -4844,7 +4844,7 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)struct vi_mqd *mqd = ring->mqd_ptr;int mqd_idx = ring - &adev->gfx.compute_ring[0 ]; -if (!adev->in_sriov_reset && !adev->gfx.in_suspend) { +if (!adev->in_gpu_reset && !adev->gfx.in_suspend) {memset ((void *)mqd,0 ,sizeof (struct vi_mqd_allocation )); ((struct vi_mqd_allocation *)mqd)->dynamic_cu_mask =0xFFFFFFFF ; ((struct vi_mqd_allocation *)mqd)->dynamic_rb_mask =0xFFFFFFFF ;
@@ -4856,7 +4856,7 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)if (adev->gfx.mec.mqd_backup[mqd_idx])memcpy (adev->gfx.mec.mqd_backup[mqd_idx], mqd,sizeof (struct vi_mqd_allocation )); - }else if (adev->in_sriov_reset) {/* for GPU_RESET case */ + }else if (adev->in_gpu_reset) {/* for GPU_RESET case */ /* reset MQD to a clean status */ if (adev->gfx.mec.mqd_backup[mqd_idx])memcpy (mqd, adev->gfx.mec.mqd_backup[mqd_idx],sizeof (struct vi_mqd_allocation ));
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +3 -3
@@ -2732,7 +2732,7 @@ static int gfx_v9_0_kiq_init_queue(struct amdgpu_ring *ring)gfx_v9_0_kiq_setting (ring); -if (adev->in_sriov_reset) {/* for GPU_RESET case */ +if (adev->in_gpu_reset) {/* for GPU_RESET case */ /* reset MQD to a clean status */ if (adev->gfx.mec.mqd_backup[mqd_idx])memcpy (mqd, adev->gfx.mec.mqd_backup[mqd_idx],sizeof (struct v9_mqd_allocation ));
@@ -2770,7 +2770,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)struct v9_mqd *mqd = ring->mqd_ptr;int mqd_idx = ring - &adev->gfx.compute_ring[0 ]; -if (!adev->in_sriov_reset && !adev->gfx.in_suspend) { +if (!adev->in_gpu_reset && !adev->gfx.in_suspend) {memset ((void *)mqd,0 ,sizeof (struct v9_mqd_allocation )); ((struct v9_mqd_allocation *)mqd)->dynamic_cu_mask =0xFFFFFFFF ; ((struct v9_mqd_allocation *)mqd)->dynamic_rb_mask =0xFFFFFFFF ;
@@ -2782,7 +2782,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)if (adev->gfx.mec.mqd_backup[mqd_idx])memcpy (adev->gfx.mec.mqd_backup[mqd_idx], mqd,sizeof (struct v9_mqd_allocation )); - }else if (adev->in_sriov_reset) {/* for GPU_RESET case */ + }else if (adev->in_gpu_reset) {/* for GPU_RESET case */ /* reset MQD to a clean status */ if (adev->gfx.mec.mqd_backup[mqd_idx])memcpy (mqd, adev->gfx.mec.mqd_backup[mqd_idx],sizeof (struct v9_mqd_allocation ));
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 5/5 drm/amdgpu:cleanup ucode_init_bo
In reply to a message not in the archive1,no sriov check since gpu recover is unified 2,need CPU_ACCESS_REQUIRED flag for VRAM if SRIOV because otherwise after following PIN the first allocated VRAM bo is wasted due to some TTM mgr reason.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +2 -1
@@ -370,9 +370,10 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev)return 0 ; } -if (!amdgpu_sriov_vf (adev) || !adev->in_gpu_reset) { +if (!adev->in_gpu_reset) { err =amdgpu_bo_create (adev, adev->firmware.fw_size,PAGE_SIZE , true,amdgpu_sriov_vf (adev) ?AMDGPU_GEM_DOMAIN_VRAM :AMDGPU_GEM_DOMAIN_GTT , +amdgpu_sriov_vf (adev) ?AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED :AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS ,NULL ,NULL ,0 , bo);if (err) {
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx