From b2ef808786d93df36585cee42cfb973fc41636eb Mon Sep 17 00:00:00 2001 From: Christian König Date: Mon, 26 Aug 2024 14:25:38 +0200 Subject: drm/sched: add optional errno to drm_sched_start() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current implementation of drm_sched_start uses a hardcoded -ECANCELED to dispose of a job when the parent/hw fence is NULL. This results in drm_sched_job_done being called with -ECANCELED for each job with a NULL parent in the pending list, making it difficult to distinguish between recovery methods, whether a queue reset or a full GPU reset was used. To improve this, we first try a soft recovery for timeout jobs and use the error code -ENODATA. If soft recovery fails, we proceed with a queue reset, where the error code remains -ENODATA for the job. Finally, for a full GPU reset, we use error codes -ECANCELED or -ETIME. This patch adds an error code parameter to drm_sched_start, allowing us to differentiate between queue reset and GPU reset failures. This enables user mode and test applications to validate the expected correctness of the requested operation. After a successful queue reset, the only way to continue normal operation is to call drm_sched_job_done with the specific error code -ENODATA. v1: Initial implementation by Jesse utilized amdgpu_device_lock_reset_domain and amdgpu_device_unlock_reset_domain to allow user mode to track the queue reset status and distinguish between queue reset and GPU reset. v2: Christian suggested using the error codes -ENODATA for queue reset and -ECANCELED or -ETIME for GPU reset, returned to amdgpu_cs_wait_ioctl. v3: To meet the requirements, we introduce a new function drm_sched_start_ex with an additional parameter to set dma_fence_set_error, allowing us to handle the specific error codes appropriately and dispose of bad jobs with the selected error code depending on whether it was a queue reset or GPU reset. v4: Alex suggested using a new name, drm_sched_start_with_recovery_error, which more accurately describes the function's purpose. Additionally, it was recommended to add documentation details about the new method. v5: Fixed declaration of new function drm_sched_start_with_recovery_error.(Alex) v6 (chk): rebase on upstream changes, cleanup the commit message, drop the new function again and update all callers, apply the errno also to scheduler fences with hw fences v7 (chk): rebased Signed-off-by: Jesse Zhang Signed-off-by: Vitaly Prosyak Signed-off-by: Christian König Acked-by: Daniel Vetter Reviewed-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20240826122541.85663-1-christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_job.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 597489dea114..3bb9d1ca74b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -87,7 +87,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) atomic_inc(&ring->adev->gpu_reset_counter); amdgpu_fence_driver_force_completion(ring); if (amdgpu_ring_sched_ready(ring)) - drm_sched_start(&ring->sched); + drm_sched_start(&ring->sched, 0); goto exit; } } -- cgit From fa73462dc0482644416c2a2ee042c11d93a89663 Mon Sep 17 00:00:00 2001 From: Sunil Khatri Date: Tue, 24 Sep 2024 21:30:17 +0530 Subject: drm/amdgpu: update the handle ptr in dump_ip_state MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Update the ptr handle to amdgpu_ip_block ptr in all the functions. Signed-off-by: Sunil Khatri Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c | 4 ++-- drivers/gpu/drm/amd/include/amd_shared.h | 4 +++- 22 files changed, 43 insertions(+), 41 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_job.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index de1f2cabdddd..1c5a4c697c7c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5358,7 +5358,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, for (i = 0; i < tmp_adev->num_ip_blocks; i++) if (tmp_adev->ip_blocks[i].version->funcs->dump_ip_state) tmp_adev->ip_blocks[i].version->funcs - ->dump_ip_state((void *)tmp_adev); + ->dump_ip_state((void *)&tmp_adev->ip_blocks[i]); dev_info(tmp_adev->dev, "Dumping IP State Completed\n"); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 16f2605ac50b..e3bb234753ef 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -42,7 +42,7 @@ static void amdgpu_job_do_core_dump(struct amdgpu_device *adev, for (i = 0; i < adev->num_ip_blocks; i++) if (adev->ip_blocks[i].version->funcs->dump_ip_state) adev->ip_blocks[i].version->funcs - ->dump_ip_state((void *)adev); + ->dump_ip_state((void *)&adev->ip_blocks[i]); dev_info(adev->dev, "Dumping IP State Completed\n"); amdgpu_coredump(adev, true, false, job); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 45ed97038df0..61300eb88ab4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -9632,9 +9632,9 @@ static void gfx_v10_ip_print(void *handle, struct drm_printer *p) } } -static void gfx_v10_ip_dump(void *handle) +static void gfx_v10_ip_dump(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; uint32_t i, j, k, reg, index = 0; uint32_t reg_count = ARRAY_SIZE(gc_reg_list_10_1); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 33fd2da49a2a..acf2e7634200 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -6705,9 +6705,9 @@ static void gfx_v11_ip_print(void *handle, struct drm_printer *p) } } -static void gfx_v11_ip_dump(void *handle) +static void gfx_v11_ip_dump(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; uint32_t i, j, k, reg, index = 0; uint32_t reg_count = ARRAY_SIZE(gc_reg_list_11_0); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 47b47d21f464..13baa6868a78 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -5102,9 +5102,9 @@ static void gfx_v12_ip_print(void *handle, struct drm_printer *p) } } -static void gfx_v12_ip_dump(void *handle) +static void gfx_v12_ip_dump(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; uint32_t i, j, k, reg, index = 0; uint32_t reg_count = ARRAY_SIZE(gc_reg_list_12_0); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 3a3ef93f2f43..fb4402f9bd8d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -7377,9 +7377,9 @@ static void gfx_v9_ip_print(void *handle, struct drm_printer *p) } -static void gfx_v9_ip_dump(void *handle) +static void gfx_v9_ip_dump(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; uint32_t i, j, k, reg, index = 0; uint32_t reg_count = ARRAY_SIZE(gc_reg_list_9); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 59d0c34aeacf..3d48eb281e99 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -4645,9 +4645,9 @@ static void gfx_v9_4_3_ip_print(void *handle, struct drm_printer *p) } } -static void gfx_v9_4_3_ip_dump(void *handle) +static void gfx_v9_4_3_ip_dump(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; uint32_t i, j, k; uint32_t num_xcc, reg, num_inst; uint32_t xcc_id, xcc_offset, inst_offset; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 23ef4eb36b40..50ad06f06c62 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -2371,9 +2371,9 @@ static void sdma_v4_0_print_ip_state(void *handle, struct drm_printer *p) } } -static void sdma_v4_0_dump_ip_state(void *handle) +static void sdma_v4_0_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; uint32_t instance_offset; uint32_t reg_count = ARRAY_SIZE(sdma_reg_list_4_0); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c index c77889040760..487cc0992263 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c @@ -1878,9 +1878,9 @@ static void sdma_v4_4_2_print_ip_state(void *handle, struct drm_printer *p) } } -static void sdma_v4_4_2_dump_ip_state(void *handle) +static void sdma_v4_4_2_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; uint32_t instance_offset; uint32_t reg_count = ARRAY_SIZE(sdma_reg_list_4_4_2); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index e813da1e48aa..4dc8ff761888 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -1822,9 +1822,9 @@ static void sdma_v5_0_print_ip_state(void *handle, struct drm_printer *p) } } -static void sdma_v5_0_dump_ip_state(void *handle) +static void sdma_v5_0_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; uint32_t instance_offset; uint32_t reg_count = ARRAY_SIZE(sdma_reg_list_5_0); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index bc9b240a3488..d19dde1d6fc5 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -1757,9 +1757,9 @@ static void sdma_v5_2_print_ip_state(void *handle, struct drm_printer *p) } } -static void sdma_v5_2_dump_ip_state(void *handle) +static void sdma_v5_2_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; uint32_t instance_offset; uint32_t reg_count = ARRAY_SIZE(sdma_reg_list_5_2); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index 581fa550ef29..ed7413c1954c 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1624,9 +1624,9 @@ static void sdma_v6_0_print_ip_state(void *handle, struct drm_printer *p) } } -static void sdma_v6_0_dump_ip_state(void *handle) +static void sdma_v6_0_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; uint32_t instance_offset; uint32_t reg_count = ARRAY_SIZE(sdma_reg_list_6_0); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index a8763496aed3..9e8b1ec4e6cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -1559,9 +1559,9 @@ static void sdma_v7_0_print_ip_state(void *handle, struct drm_printer *p) } } -static void sdma_v7_0_dump_ip_state(void *handle) +static void sdma_v7_0_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; uint32_t instance_offset; uint32_t reg_count = ARRAY_SIZE(sdma_reg_list_7_0); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index ecdfbfefd66a..78dfcd02d8da 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -1957,9 +1957,9 @@ static void vcn_v1_0_print_ip_state(void *handle, struct drm_printer *p) } } -static void vcn_v1_0_dump_ip_state(void *handle) +static void vcn_v1_0_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; bool is_powered; uint32_t inst_off; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index bfd067e2d2f1..5d6accdba480 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -2066,9 +2066,9 @@ static void vcn_v2_0_print_ip_state(void *handle, struct drm_printer *p) } } -static void vcn_v2_0_dump_ip_state(void *handle) +static void vcn_v2_0_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; bool is_powered; uint32_t inst_off; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 04e9e806e318..8896c25fd1d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -1958,9 +1958,9 @@ static void vcn_v2_5_print_ip_state(void *handle, struct drm_printer *p) } } -static void vcn_v2_5_dump_ip_state(void *handle) +static void vcn_v2_5_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; bool is_powered; uint32_t inst_off; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 65dd68b32280..3009f52f62d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -2284,9 +2284,9 @@ static void vcn_v3_0_print_ip_state(void *handle, struct drm_printer *p) } } -static void vcn_v3_0_dump_ip_state(void *handle) +static void vcn_v3_0_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; bool is_powered; uint32_t inst_off; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 26c6f10a8c8f..17ea10c14e29 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -2190,9 +2190,9 @@ static void vcn_v4_0_print_ip_state(void *handle, struct drm_printer *p) } } -static void vcn_v4_0_dump_ip_state(void *handle) +static void vcn_v4_0_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; bool is_powered; uint32_t inst_off; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c index 0fda70336300..742bf09ae195 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c @@ -1765,9 +1765,9 @@ static void vcn_v4_0_3_print_ip_state(void *handle, struct drm_printer *p) } } -static void vcn_v4_0_3_dump_ip_state(void *handle) +static void vcn_v4_0_3_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; bool is_powered; uint32_t inst_off, inst_id; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c index 9d4f5352a62c..3fb8b218e278 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c @@ -1648,9 +1648,9 @@ static void vcn_v4_0_5_print_ip_state(void *handle, struct drm_printer *p) } } -static void vcn_v4_0_5_dump_ip_state(void *handle) +static void vcn_v4_0_5_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; bool is_powered; uint32_t inst_off; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c index c305386358b4..25ae338df346 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c @@ -1375,9 +1375,9 @@ static void vcn_v5_0_print_ip_state(void *handle, struct drm_printer *p) } } -static void vcn_v5_0_dump_ip_state(void *handle) +static void vcn_v5_0_dump_ip_state(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, j; bool is_powered; uint32_t inst_off; diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 3f91926a50e9..cbb19895ddaf 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -375,6 +375,8 @@ enum amd_dpm_forced_level; * making calls to hooks from each IP block. This list is ordered to ensure * that the driver initializes the IP blocks in a safe sequence. */ +struct amdgpu_ip_block; + struct amd_ip_funcs { char *name; int (*early_init)(void *handle); @@ -399,7 +401,7 @@ struct amd_ip_funcs { int (*set_powergating_state)(void *handle, enum amd_powergating_state state); void (*get_clockgating_state)(void *handle, u64 *flags); - void (*dump_ip_state)(void *handle); + void (*dump_ip_state)(struct amdgpu_ip_block *ip_block); void (*print_ip_state)(void *handle, struct drm_printer *p); }; -- cgit From 871f44b4ba74a676ef2f0528a3efc591346fa92a Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Tue, 24 Sep 2024 10:51:44 +0100 Subject: drm/amdgpu: Drop impossible condition from amdgpu_job_prepare_job MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fence has been initialised to NULL so no need to test it. Reviewed-by: Christian König Signed-off-by: Tvrtko Ursulin Cc: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_job.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index e3bb234753ef..b550a31f4457 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -356,7 +356,7 @@ amdgpu_job_prepare_job(struct drm_sched_job *sched_job, if (r) goto error; - if (!fence && job->gang_submit) + if (job->gang_submit) fence = amdgpu_device_switch_gang(ring->adev, job->gang_submit); while (!fence && job->vm && !job->vmid) { -- cgit From 89cfa73b612a711ad19c6323814f4d28535a0fca Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Tue, 24 Sep 2024 10:51:45 +0100 Subject: drm/amdgpu: Remove the while loop from amdgpu_job_prepare_job MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While loop makes it sound like amdgpu_vmid_grab() potentially needs to be called multiple times to produce a fence, while in reality all code paths either return an error, assign a valid job->vmid or assign a vmid which will be valid once the returned fence signals. Therefore we can remove the loop to make it clear the call does not need to be repeated. Reviewed-by: Christian König Signed-off-by: Tvrtko Ursulin Cc: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_job.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index b550a31f4457..102742f1faa2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -359,7 +359,7 @@ amdgpu_job_prepare_job(struct drm_sched_job *sched_job, if (job->gang_submit) fence = amdgpu_device_switch_gang(ring->adev, job->gang_submit); - while (!fence && job->vm && !job->vmid) { + if (!fence && job->vm && !job->vmid) { r = amdgpu_vmid_grab(job->vm, ring, job, &fence); if (r) { dev_err(ring->adev->dev, "Error getting VM ID (%d)\n", r); -- cgit From 35984fd4a093ccb9e0bb82db4cac5c1bf2df7d93 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 15 Oct 2024 14:13:58 -0400 Subject: drm/amdgpu: add ring reset messages Add messages to make it clear when a per ring reset happens. This is helpful for debugging and aligns with other reset methods. v2: add ring name in success/fail messages (Lijo) Reviewed-by: Lijo Lazar Reviewed-by: Kent Russell (v1) Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_job.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 102742f1faa2..cbae2fc7b94e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -137,6 +137,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) /* attempt a per ring reset */ if (amdgpu_gpu_recovery && ring->funcs->reset) { + dev_err(adev->dev, "Starting %s ring reset\n", s_job->sched->name); /* stop the scheduler, but don't mess with the * bad job yet because if ring reset fails * we'll fall back to full GPU reset. @@ -150,8 +151,10 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) amdgpu_fence_driver_force_completion(ring); if (amdgpu_ring_sched_ready(ring)) drm_sched_start(&ring->sched); + dev_err(adev->dev, "Ring %s reset success\n", ring->sched.name); goto exit; } + dev_err(adev->dev, "Ring %s reset failure\n", ring->sched.name); } if (amdgpu_device_should_recover_gpu(ring->adev)) { -- cgit