From 4d5f872dbc755114628c236e17421629ec522203 Mon Sep 17 00:00:00 2001 From: Iswara Nagulendran Date: Thu, 16 Mar 2023 16:29:06 -0400 Subject: drm/amd/display: Adding support for VESA SCR [HOW&WHY] Write DPCD 721 bit 7 to high, and the appropriate luminance level to DPCD 734-736 if bit 4 from DPCD register 734 is high, indicating that the panel luminance control is enabled from the panel side. Reviewed-by: Anthony Koo Acked-by: Qingqing Zhuo Signed-off-by: Iswara Nagulendran Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- include/drm/display/drm_dp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h index 358db4a9f167..d735073fdd81 100644 --- a/include/drm/display/drm_dp.h +++ b/include/drm/display/drm_dp.h @@ -983,6 +983,7 @@ #define DP_EDP_GENERAL_CAP_2 0x703 # define DP_EDP_OVERDRIVE_ENGINE_ENABLED (1 << 0) +# define DP_EDP_PANEL_LUMINANCE_CONTROL_CAPABLE (1 << 4) #define DP_EDP_GENERAL_CAP_3 0x704 /* eDP 1.4 */ # define DP_EDP_X_REGION_CAP_MASK (0xf << 0) @@ -1008,6 +1009,7 @@ # define DP_EDP_DYNAMIC_BACKLIGHT_ENABLE (1 << 4) # define DP_EDP_REGIONAL_BACKLIGHT_ENABLE (1 << 5) # define DP_EDP_UPDATE_REGION_BRIGHTNESS (1 << 6) /* eDP 1.4 */ +# define DP_EDP_PANEL_LUMINANCE_CONTROL_ENABLE (1 << 7) #define DP_EDP_BACKLIGHT_BRIGHTNESS_MSB 0x722 #define DP_EDP_BACKLIGHT_BRIGHTNESS_LSB 0x723 @@ -1032,6 +1034,7 @@ #define DP_EDP_DBC_MINIMUM_BRIGHTNESS_SET 0x732 #define DP_EDP_DBC_MAXIMUM_BRIGHTNESS_SET 0x733 +#define DP_EDP_PANEL_TARGET_LUMINANCE_VALUE 0x734 #define DP_EDP_REGIONAL_BACKLIGHT_BASE 0x740 /* eDP 1.4 */ #define DP_EDP_REGIONAL_BACKLIGHT_0 0x741 /* eDP 1.4 */ -- cgit v1.2.3 From 4f18b9a6711adbc7c76993c734a94ee3f5c61791 Mon Sep 17 00:00:00 2001 From: Bas Nieuwenhuizen Date: Thu, 13 Apr 2023 16:22:53 +0200 Subject: drm/amdgpu: Add support for querying the max ibs in a submission. (v3) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This info would be used by radv to figure out when we need to split a submission into multiple submissions. radv currently has a limit of 192 which seems to work for most gfx submissions, but is way too high for e.g. compute or sdma. Userspace is available at https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3 v3: Completely rewrote based on suggestion of making it a separate query. Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2498 Reviewed-by: Christian König Signed-off-by: Bas Nieuwenhuizen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 9 +++++++++ include/uapi/drm/amdgpu_drm.h | 2 ++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 0efb38539d70..1a2e342af1c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -1140,6 +1140,15 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) kfree(caps); return r; } + case AMDGPU_INFO_MAX_IBS: { + uint32_t max_ibs[AMDGPU_HW_IP_NUM]; + + for (i = 0; i < AMDGPU_HW_IP_NUM; ++i) + max_ibs[i] = amdgpu_ring_max_ibs(i); + + return copy_to_user(out, max_ibs, + min((size_t)size, sizeof(max_ibs))) ? -EFAULT : 0; + } default: DRM_DEBUG_KMS("Invalid request %d\n", info->query); return -EINVAL; diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index b6eb90df5d05..6981e59a9401 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -876,6 +876,8 @@ struct drm_amdgpu_cs_chunk_data { #define AMDGPU_INFO_VIDEO_CAPS_DECODE 0 /* Subquery id: Encode */ #define AMDGPU_INFO_VIDEO_CAPS_ENCODE 1 +/* Query the max number of IBs per gang per submission */ +#define AMDGPU_INFO_MAX_IBS 0x22 #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT 0 #define AMDGPU_INFO_MMR_SE_INDEX_MASK 0xff -- cgit v1.2.3 From 043dc33f443fd7abaf3fe076897503ce3d5dbc26 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 9 Mar 2023 13:48:11 -0500 Subject: drm/amdgpu/UAPI: add new CS chunk for GFX shadow buffers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For GFX11, the UMD needs to allocate some shadow buffers to be used for preemption. The UMD allocates the buffers and passes the GPU virtual address to the kernel since the kernel will program the packet that specified these addresses as part of its IB submission frame. v2: UMD passes shadow init to tell kernel when to initialize the shadow Reviewed-by: Christian König Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 6981e59a9401..fc094653b13f 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -592,6 +592,7 @@ struct drm_amdgpu_gem_va { #define AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES 0x07 #define AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT 0x08 #define AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL 0x09 +#define AMDGPU_CHUNK_ID_CP_GFX_SHADOW 0x0a struct drm_amdgpu_cs_chunk { __u32 chunk_id; @@ -708,6 +709,15 @@ struct drm_amdgpu_cs_chunk_data { }; }; +#define AMDGPU_CS_CHUNK_CP_GFX_SHADOW_FLAGS_INIT_SHADOW 0x1 + +struct drm_amdgpu_cs_chunk_cp_gfx_shadow { + __u64 shadow_va; + __u64 csa_va; + __u64 gds_va; + __u64 flags; +}; + /* * Query h/w info: Flag that this is integrated (a.h.a. fusion) GPU * -- cgit v1.2.3 From edd9038000352ba846cba9dfb84d8c397c3b6499 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 9 Mar 2023 13:43:13 -0500 Subject: drm/amdgpu: add UAPI to query GFX shadow sizes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add UAPI to query the GFX shadow buffer requirements for preemption on GFX11. UMDs need to specify the shadow areas for preemption. v2: move into existing asic info query drop GDS as its use is determined by the UMD (Marek) v3: Update comments to note that alignment is base virtual alignment (Alex) Reviewed-by: Marek Olšák Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index fc094653b13f..cc78528c3b4b 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1138,6 +1138,14 @@ struct drm_amdgpu_info_device { __u64 mall_size; /* AKA infinity cache */ /* high 32 bits of the rb pipes mask */ __u32 enabled_rb_pipes_mask_hi; + /* shadow area size for gfx11 */ + __u32 shadow_size; + /* shadow area base virtual alignment for gfx11 */ + __u32 shadow_alignment; + /* context save area size for gfx11 */ + __u32 csa_size; + /* context save area base virtual alignment for gfx11 */ + __u32 csa_alignment; }; struct drm_amdgpu_info_hw_ip { -- cgit v1.2.3 From 489763af891d5dc35c0b64e18af284d6591286cf Mon Sep 17 00:00:00 2001 From: Pierre-Eric Pelloux-Prayer Date: Mon, 24 Apr 2023 19:25:32 +0200 Subject: drm/amdgpu: add new flag to AMDGPU_CTX_QUERY2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit OpenGL EXT_robustness extension expects the driver to stop reporting GUILTY_CONTEXT_RESET when the reset has completed and the GPU is ready to accept submission again. This commit adds a AMDGPU_CTX_QUERY2_FLAGS_RESET_IN_PROGRESS flag, that let the UMD know that the reset is still not finished. Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290 Reviewed-by: Christian König Reviewed-by: André Almeida Signed-off-by: Pierre-Eric Pelloux-Prayer Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 3 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 ++- include/uapi/drm/amdgpu_drm.h | 2 ++ 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index d2139ac12159..e1f642a3dc2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -576,6 +576,9 @@ static int amdgpu_ctx_query2(struct amdgpu_device *adev, if (atomic_read(&ctx->guilty)) out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_GUILTY; + if (amdgpu_in_reset(adev)) + out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RESET_IN_PROGRESS; + if (adev->ras_enabled && con) { /* Return the cached values in O(1), * and schedule delayed work to cache diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index b987022e11b4..45544ebe576e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -111,9 +111,10 @@ * tcp_cache_size, num_sqc_per_wgp, sqc_data_cache_size, sqc_inst_cache_size, * gl1c_cache_size, gl2c_cache_size, mall_size, enabled_rb_pipes_mask_hi * 3.53.0 - Support for GFX11 CP GFX shadowing + * 3.54.0 - Add AMDGPU_CTX_QUERY2_FLAGS_RESET_IN_PROGRESS support */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 53 +#define KMS_DRIVER_MINOR 54 #define KMS_DRIVER_PATCHLEVEL 0 unsigned int amdgpu_vram_limit = UINT_MAX; diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index cc78528c3b4b..79b14828d542 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -245,6 +245,8 @@ union drm_amdgpu_bo_list { /* indicate some errors are detected by RAS */ #define AMDGPU_CTX_QUERY2_FLAGS_RAS_CE (1<<3) #define AMDGPU_CTX_QUERY2_FLAGS_RAS_UE (1<<4) +/* indicate that the reset hasn't completed yet */ +#define AMDGPU_CTX_QUERY2_FLAGS_RESET_IN_PROGRESS (1<<5) /* Context priority level */ #define AMDGPU_CTX_PRIORITY_UNSET -2048 -- cgit v1.2.3 From 1d74159021e9a4e58c422f0b91e2a6fcb884c54f Mon Sep 17 00:00:00 2001 From: Mukul Joshi Date: Tue, 25 Apr 2023 14:11:56 -0400 Subject: drm/ttm: Helper function to get TTM mem limit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a helper function to get TTM memory limit. This is needed by KFD to set its own internal memory limits. Signed-off-by: Mukul Joshi Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/ttm/ttm_tt.c | 6 ++++++ include/drm/ttm/ttm_tt.h | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index ab725d9d14a6..feac2f2c736e 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -450,3 +450,9 @@ ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt, return &iter_tt->base; } EXPORT_SYMBOL(ttm_kmap_iter_tt_init); + +unsigned long ttm_tt_pages_limit(void) +{ + return ttm_pages_limit; +} +EXPORT_SYMBOL(ttm_tt_pages_limit); diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 977ca195a536..a4eff85b1f44 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -222,7 +222,7 @@ void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages); struct ttm_kmap_iter *ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt, struct ttm_tt *tt); - +unsigned long ttm_tt_pages_limit(void); #if IS_ENABLED(CONFIG_AGP) #include -- cgit v1.2.3 From ef75a6ef37235e211bbdb17c25e5f79c55df1750 Mon Sep 17 00:00:00 2001 From: Rajneesh Bhardwaj Date: Thu, 3 Mar 2022 10:56:05 -0500 Subject: drm/amdkfd: Update coherence settings for svm ranges Recently introduced commit "drm/amdgpu: Set cache coherency for GC 9.4.3" did not update the settings applicable for svm ranges. Add the coherence settings for svm ranges for GFX IP 9.4.3. Reviewed-by: Amber Lin Signed-off-by: Rajneesh Bhardwaj Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 17 +++++++++++++++++ include/uapi/linux/kfd_ioctl.h | 2 ++ 2 files changed, 19 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 96ccff79902c..4b4f3bf8b823 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1159,6 +1159,7 @@ svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange, uint64_t pte_flags; bool snoop = (domain != SVM_RANGE_VRAM_DOMAIN); bool coherent = flags & KFD_IOCTL_SVM_FLAG_COHERENT; + bool uncached = flags & KFD_IOCTL_SVM_FLAG_UNCACHED; if (domain == SVM_RANGE_VRAM_DOMAIN) bo_adev = amdgpu_ttm_adev(prange->svm_bo->bo->tbo.bdev); @@ -1198,6 +1199,22 @@ svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange, AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; } break; + case IP_VERSION(9, 4, 3): + //TODO: Need more work for handling multiple memory partitions + //e.g. NPS4. Current approch is only applicable without memory + //partitions. + snoop = true; + if (uncached) + mapping_flags |= AMDGPU_VM_MTYPE_UC; + /* local HBM region close to partition*/ + else if (bo_adev == adev) + mapping_flags |= AMDGPU_VM_MTYPE_RW; + /* local HBM region far from partition or remote XGMI GPU or + * system memory + */ + else + mapping_flags |= AMDGPU_VM_MTYPE_NC; + break; default: mapping_flags |= coherent ? AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 2da5c3ad71bd..2a9671e1ddb5 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -623,6 +623,8 @@ enum kfd_mmio_remap { #define KFD_IOCTL_SVM_FLAG_GPU_READ_MOSTLY 0x00000020 /* Keep GPU memory mapping always valid as if XNACK is disable */ #define KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED 0x00000040 +/* Uncached access to memory */ +#define KFD_IOCTL_SVM_FLAG_UNCACHED 0x00000080 /** * kfd_ioctl_svm_op - SVM ioctl operations -- cgit v1.2.3 From 4482d3c94d7f1d6912521e6de23bb051bfcd084d Mon Sep 17 00:00:00 2001 From: Rajneesh Bhardwaj Date: Wed, 12 Oct 2022 21:58:29 -0400 Subject: drm/ttm: add NUMA node id to the pool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows backing ttm_tt structure with pages from different NUMA pools. Tested-by: Graham Sider Reviewed-by: Felix Kuehling Signed-off-by: Christian König Signed-off-by: Rajneesh Bhardwaj Signed-off-by: Alex Deucher --- drivers/gpu/drm/ttm/ttm_device.c | 2 +- drivers/gpu/drm/ttm/ttm_pool.c | 13 ++++++++----- include/drm/ttm/ttm_pool.h | 4 +++- 3 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index 64a59f46f6c3..43e27ab77f95 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -213,7 +213,7 @@ int ttm_device_init(struct ttm_device *bdev, struct ttm_device_funcs *funcs, bdev->funcs = funcs; ttm_sys_man_init(bdev); - ttm_pool_init(&bdev->pool, dev, use_dma_alloc, use_dma32); + ttm_pool_init(&bdev->pool, dev, NUMA_NO_NODE, use_dma_alloc, use_dma32); bdev->vma_manager = vma_manager; spin_lock_init(&bdev->lru_lock); diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 18c342a919a2..afc4476c446f 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -98,7 +98,7 @@ static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags, __GFP_KSWAPD_RECLAIM; if (!pool->use_dma_alloc) { - p = alloc_pages(gfp_flags, order); + p = alloc_pages_node(pool->nid, gfp_flags, order); if (p) p->private = order; return p; @@ -292,7 +292,7 @@ static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool, enum ttm_caching caching, unsigned int order) { - if (pool->use_dma_alloc) + if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) return &pool->caching[caching].orders[order]; #ifdef CONFIG_X86 @@ -550,29 +550,32 @@ EXPORT_SYMBOL(ttm_pool_free); * * @pool: the pool to initialize * @dev: device for DMA allocations and mappings + * @nid: NUMA node to use for allocations * @use_dma_alloc: true if coherent DMA alloc should be used * @use_dma32: true if GFP_DMA32 should be used * * Initialize the pool and its pool types. */ void ttm_pool_init(struct ttm_pool *pool, struct device *dev, - bool use_dma_alloc, bool use_dma32) + int nid, bool use_dma_alloc, bool use_dma32) { unsigned int i, j; WARN_ON(!dev && use_dma_alloc); pool->dev = dev; + pool->nid = nid; pool->use_dma_alloc = use_dma_alloc; pool->use_dma32 = use_dma32; - if (use_dma_alloc) { + if (use_dma_alloc || nid != NUMA_NO_NODE) { for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) for (j = 0; j < TTM_DIM_ORDER; ++j) ttm_pool_type_init(&pool->caching[i].orders[j], pool, i, j); } } +EXPORT_SYMBOL(ttm_pool_init); /** * ttm_pool_fini - Cleanup a pool @@ -586,7 +589,7 @@ void ttm_pool_fini(struct ttm_pool *pool) { unsigned int i, j; - if (pool->use_dma_alloc) { + if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) { for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) for (j = 0; j < TTM_DIM_ORDER; ++j) ttm_pool_type_fini(&pool->caching[i].orders[j]); diff --git a/include/drm/ttm/ttm_pool.h b/include/drm/ttm/ttm_pool.h index ef09b23d29e3..23bd8be6d4f8 100644 --- a/include/drm/ttm/ttm_pool.h +++ b/include/drm/ttm/ttm_pool.h @@ -61,12 +61,14 @@ struct ttm_pool_type { * struct ttm_pool - Pool for all caching and orders * * @dev: the device we allocate pages for + * @nid: which numa node to use * @use_dma_alloc: if coherent DMA allocations should be used * @use_dma32: if GFP_DMA32 should be used * @caching: pools for each caching/order */ struct ttm_pool { struct device *dev; + int nid; bool use_dma_alloc; bool use_dma32; @@ -81,7 +83,7 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, void ttm_pool_free(struct ttm_pool *pool, struct ttm_tt *tt); void ttm_pool_init(struct ttm_pool *pool, struct device *dev, - bool use_dma_alloc, bool use_dma32); + int nid, bool use_dma_alloc, bool use_dma32); void ttm_pool_fini(struct ttm_pool *pool); int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m); -- cgit v1.2.3 From ba3c87fffb79311f54464288c66421d19c2c1234 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 2 Jun 2023 12:58:05 -0400 Subject: amd/amdkfd: drop unused KFD_IOCTL_SVM_FLAG_UNCACHED flag Was leftover from GC 9.4.3 bring up and is currently unused. Drop it for now. Cc: Philip.Yang@amd.com Cc: rajneesh.bhardwaj@amd.com Cc: Felix.Kuehling@amd.com Reviewed-by: Rajneesh Bhardwaj Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +- include/uapi/linux/kfd_ioctl.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 615eab3f78c9..5ff1a5a89d96 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1154,7 +1154,7 @@ svm_range_get_pte_flags(struct kfd_node *node, uint64_t pte_flags; bool snoop = (domain != SVM_RANGE_VRAM_DOMAIN); bool coherent = flags & KFD_IOCTL_SVM_FLAG_COHERENT; - bool uncached = flags & KFD_IOCTL_SVM_FLAG_UNCACHED; + bool uncached = false; /*flags & KFD_IOCTL_SVM_FLAG_UNCACHED;*/ unsigned int mtype_local; if (domain == SVM_RANGE_VRAM_DOMAIN) diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 2a9671e1ddb5..2da5c3ad71bd 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -623,8 +623,6 @@ enum kfd_mmio_remap { #define KFD_IOCTL_SVM_FLAG_GPU_READ_MOSTLY 0x00000020 /* Keep GPU memory mapping always valid as if XNACK is disable */ #define KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED 0x00000040 -/* Uncached access to memory */ -#define KFD_IOCTL_SVM_FLAG_UNCACHED 0x00000080 /** * kfd_ioctl_svm_op - SVM ioctl operations -- cgit v1.2.3 From 4f98cf2baf9faee5b6f2f7889dad7c0f7686a787 Mon Sep 17 00:00:00 2001 From: Jonathan Kim Date: Wed, 2 Mar 2022 14:30:12 -0500 Subject: drm/amdkfd: add debug and runtime enable interface Introduce the GPU debug operations interface. For ROCm-GDB to extend the GNU Debugger's ability to inspect the AMD GPU instruction set, provide the necessary interface to allow the debugger to HW debug-mode set and query exceptions per HSA queue, process or device. The runtime_enable interface coordinates exception handling with the HSA runtime. Usage is available in the kern docs at uapi/linux/kfd_ioctl.h. Signed-off-by: Jonathan Kim Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 48 +++ include/uapi/linux/kfd_ioctl.h | 668 ++++++++++++++++++++++++++++++- 2 files changed, 715 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index a9efff94390b..00e34125987c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -2729,6 +2729,48 @@ static int kfd_ioctl_criu(struct file *filep, struct kfd_process *p, void *data) return ret; } +static int kfd_ioctl_runtime_enable(struct file *filep, struct kfd_process *p, void *data) +{ + return 0; +} + +static int kfd_ioctl_set_debug_trap(struct file *filep, struct kfd_process *p, void *data) +{ + struct kfd_ioctl_dbg_trap_args *args = data; + int r = 0; + + if (sched_policy == KFD_SCHED_POLICY_NO_HWS) { + pr_err("Debugging does not support sched_policy %i", sched_policy); + return -EINVAL; + } + + switch (args->op) { + case KFD_IOC_DBG_TRAP_ENABLE: + case KFD_IOC_DBG_TRAP_DISABLE: + case KFD_IOC_DBG_TRAP_SEND_RUNTIME_EVENT: + case KFD_IOC_DBG_TRAP_SET_EXCEPTIONS_ENABLED: + case KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_OVERRIDE: + case KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_MODE: + case KFD_IOC_DBG_TRAP_SUSPEND_QUEUES: + case KFD_IOC_DBG_TRAP_RESUME_QUEUES: + case KFD_IOC_DBG_TRAP_SET_NODE_ADDRESS_WATCH: + case KFD_IOC_DBG_TRAP_CLEAR_NODE_ADDRESS_WATCH: + case KFD_IOC_DBG_TRAP_SET_FLAGS: + case KFD_IOC_DBG_TRAP_QUERY_DEBUG_EVENT: + case KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO: + case KFD_IOC_DBG_TRAP_GET_QUEUE_SNAPSHOT: + case KFD_IOC_DBG_TRAP_GET_DEVICE_SNAPSHOT: + pr_warn("Debugging not supported yet\n"); + r = -EACCES; + break; + default: + pr_err("Invalid option: %i\n", args->op); + r = -EINVAL; + } + + return r; +} + #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \ [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \ .cmd_drv = 0, .name = #ioctl} @@ -2841,6 +2883,12 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_EXPORT_DMABUF, kfd_ioctl_export_dmabuf, 0), + + AMDKFD_IOCTL_DEF(AMDKFD_IOC_RUNTIME_ENABLE, + kfd_ioctl_runtime_enable, 0), + + AMDKFD_IOCTL_DEF(AMDKFD_IOC_DBG_TRAP, + kfd_ioctl_set_debug_trap, 0), }; #define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls) diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 2da5c3ad71bd..32913d674d38 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -110,6 +110,32 @@ struct kfd_ioctl_get_available_memory_args { __u32 pad; }; +struct kfd_dbg_device_info_entry { + __u64 exception_status; + __u64 lds_base; + __u64 lds_limit; + __u64 scratch_base; + __u64 scratch_limit; + __u64 gpuvm_base; + __u64 gpuvm_limit; + __u32 gpu_id; + __u32 location_id; + __u32 vendor_id; + __u32 device_id; + __u32 revision_id; + __u32 subsystem_vendor_id; + __u32 subsystem_device_id; + __u32 fw_version; + __u32 gfx_target_version; + __u32 simd_count; + __u32 max_waves_per_simd; + __u32 array_count; + __u32 simd_arrays_per_engine; + __u32 num_xcc; + __u32 capability; + __u32 debug_prop; +}; + /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ #define KFD_IOC_CACHE_POLICY_COHERENT 0 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1 @@ -773,6 +799,640 @@ struct kfd_ioctl_set_xnack_mode_args { __s32 xnack_enabled; }; +/* Wave launch override modes */ +enum kfd_dbg_trap_override_mode { + KFD_DBG_TRAP_OVERRIDE_OR = 0, + KFD_DBG_TRAP_OVERRIDE_REPLACE = 1 +}; + +/* Wave launch overrides */ +enum kfd_dbg_trap_mask { + KFD_DBG_TRAP_MASK_FP_INVALID = 1, + KFD_DBG_TRAP_MASK_FP_INPUT_DENORMAL = 2, + KFD_DBG_TRAP_MASK_FP_DIVIDE_BY_ZERO = 4, + KFD_DBG_TRAP_MASK_FP_OVERFLOW = 8, + KFD_DBG_TRAP_MASK_FP_UNDERFLOW = 16, + KFD_DBG_TRAP_MASK_FP_INEXACT = 32, + KFD_DBG_TRAP_MASK_INT_DIVIDE_BY_ZERO = 64, + KFD_DBG_TRAP_MASK_DBG_ADDRESS_WATCH = 128, + KFD_DBG_TRAP_MASK_DBG_MEMORY_VIOLATION = 256, + KFD_DBG_TRAP_MASK_TRAP_ON_WAVE_START = (1 << 30), + KFD_DBG_TRAP_MASK_TRAP_ON_WAVE_END = (1 << 31) +}; + +/* Wave launch modes */ +enum kfd_dbg_trap_wave_launch_mode { + KFD_DBG_TRAP_WAVE_LAUNCH_MODE_NORMAL = 0, + KFD_DBG_TRAP_WAVE_LAUNCH_MODE_HALT = 1, + KFD_DBG_TRAP_WAVE_LAUNCH_MODE_DEBUG = 3 +}; + +/* Address watch modes */ +enum kfd_dbg_trap_address_watch_mode { + KFD_DBG_TRAP_ADDRESS_WATCH_MODE_READ = 0, + KFD_DBG_TRAP_ADDRESS_WATCH_MODE_NONREAD = 1, + KFD_DBG_TRAP_ADDRESS_WATCH_MODE_ATOMIC = 2, + KFD_DBG_TRAP_ADDRESS_WATCH_MODE_ALL = 3 +}; + +/* Additional wave settings */ +enum kfd_dbg_trap_flags { + KFD_DBG_TRAP_FLAG_SINGLE_MEM_OP = 1, +}; + +/* Trap exceptions */ +enum kfd_dbg_trap_exception_code { + EC_NONE = 0, + /* per queue */ + EC_QUEUE_WAVE_ABORT = 1, + EC_QUEUE_WAVE_TRAP = 2, + EC_QUEUE_WAVE_MATH_ERROR = 3, + EC_QUEUE_WAVE_ILLEGAL_INSTRUCTION = 4, + EC_QUEUE_WAVE_MEMORY_VIOLATION = 5, + EC_QUEUE_WAVE_APERTURE_VIOLATION = 6, + EC_QUEUE_PACKET_DISPATCH_DIM_INVALID = 16, + EC_QUEUE_PACKET_DISPATCH_GROUP_SEGMENT_SIZE_INVALID = 17, + EC_QUEUE_PACKET_DISPATCH_CODE_INVALID = 18, + EC_QUEUE_PACKET_RESERVED = 19, + EC_QUEUE_PACKET_UNSUPPORTED = 20, + EC_QUEUE_PACKET_DISPATCH_WORK_GROUP_SIZE_INVALID = 21, + EC_QUEUE_PACKET_DISPATCH_REGISTER_INVALID = 22, + EC_QUEUE_PACKET_VENDOR_UNSUPPORTED = 23, + EC_QUEUE_PREEMPTION_ERROR = 30, + EC_QUEUE_NEW = 31, + /* per device */ + EC_DEVICE_QUEUE_DELETE = 32, + EC_DEVICE_MEMORY_VIOLATION = 33, + EC_DEVICE_RAS_ERROR = 34, + EC_DEVICE_FATAL_HALT = 35, + EC_DEVICE_NEW = 36, + /* per process */ + EC_PROCESS_RUNTIME = 48, + EC_PROCESS_DEVICE_REMOVE = 49, + EC_MAX +}; + +/* Mask generated by ecode in kfd_dbg_trap_exception_code */ +#define KFD_EC_MASK(ecode) (1ULL << (ecode - 1)) + +/* Masks for exception code type checks below */ +#define KFD_EC_MASK_QUEUE (KFD_EC_MASK(EC_QUEUE_WAVE_ABORT) | \ + KFD_EC_MASK(EC_QUEUE_WAVE_TRAP) | \ + KFD_EC_MASK(EC_QUEUE_WAVE_MATH_ERROR) | \ + KFD_EC_MASK(EC_QUEUE_WAVE_ILLEGAL_INSTRUCTION) | \ + KFD_EC_MASK(EC_QUEUE_WAVE_MEMORY_VIOLATION) | \ + KFD_EC_MASK(EC_QUEUE_WAVE_APERTURE_VIOLATION) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_DIM_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_GROUP_SEGMENT_SIZE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_CODE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_RESERVED) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_UNSUPPORTED) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_WORK_GROUP_SIZE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_REGISTER_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_VENDOR_UNSUPPORTED) | \ + KFD_EC_MASK(EC_QUEUE_PREEMPTION_ERROR) | \ + KFD_EC_MASK(EC_QUEUE_NEW)) +#define KFD_EC_MASK_DEVICE (KFD_EC_MASK(EC_DEVICE_QUEUE_DELETE) | \ + KFD_EC_MASK(EC_DEVICE_RAS_ERROR) | \ + KFD_EC_MASK(EC_DEVICE_FATAL_HALT) | \ + KFD_EC_MASK(EC_DEVICE_MEMORY_VIOLATION) | \ + KFD_EC_MASK(EC_DEVICE_NEW)) +#define KFD_EC_MASK_PROCESS (KFD_EC_MASK(EC_PROCESS_RUNTIME) | \ + KFD_EC_MASK(EC_PROCESS_DEVICE_REMOVE)) + +/* Checks for exception code types for KFD search */ +#define KFD_DBG_EC_TYPE_IS_QUEUE(ecode) \ + (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE)) +#define KFD_DBG_EC_TYPE_IS_DEVICE(ecode) \ + (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE)) +#define KFD_DBG_EC_TYPE_IS_PROCESS(ecode) \ + (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS)) + + +/* Runtime enable states */ +enum kfd_dbg_runtime_state { + DEBUG_RUNTIME_STATE_DISABLED = 0, + DEBUG_RUNTIME_STATE_ENABLED = 1, + DEBUG_RUNTIME_STATE_ENABLED_BUSY = 2, + DEBUG_RUNTIME_STATE_ENABLED_ERROR = 3 +}; + +/* Runtime enable status */ +struct kfd_runtime_info { + __u64 r_debug; + __u32 runtime_state; + __u32 ttmp_setup; +}; + +/* Enable modes for runtime enable */ +#define KFD_RUNTIME_ENABLE_MODE_ENABLE_MASK 1 +#define KFD_RUNTIME_ENABLE_MODE_TTMP_SAVE_MASK 2 + +/** + * kfd_ioctl_runtime_enable_args - Arguments for runtime enable + * + * Coordinates debug exception signalling and debug device enablement with runtime. + * + * @r_debug - pointer to user struct for sharing information between ROCr and the debuggger + * @mode_mask - mask to set mode + * KFD_RUNTIME_ENABLE_MODE_ENABLE_MASK - enable runtime for debugging, otherwise disable + * KFD_RUNTIME_ENABLE_MODE_TTMP_SAVE_MASK - enable trap temporary setup (ignore on disable) + * @capabilities_mask - mask to notify runtime on what KFD supports + * + * Return - 0 on SUCCESS. + * - EBUSY if runtime enable call already pending. + * - EEXIST if user queues already active prior to call. + * If process is debug enabled, runtime enable will enable debug devices and + * wait for debugger process to send runtime exception EC_PROCESS_RUNTIME + * to unblock - see kfd_ioctl_dbg_trap_args. + * + */ +struct kfd_ioctl_runtime_enable_args { + __u64 r_debug; + __u32 mode_mask; + __u32 capabilities_mask; +}; + +/* Queue information */ +struct kfd_queue_snapshot_entry { + __u64 exception_status; + __u64 ring_base_address; + __u64 write_pointer_address; + __u64 read_pointer_address; + __u64 ctx_save_restore_address; + __u32 queue_id; + __u32 gpu_id; + __u32 ring_size; + __u32 queue_type; + __u32 ctx_save_restore_area_size; + __u32 reserved; +}; + +/* Queue status return for suspend/resume */ +#define KFD_DBG_QUEUE_ERROR_BIT 30 +#define KFD_DBG_QUEUE_INVALID_BIT 31 +#define KFD_DBG_QUEUE_ERROR_MASK (1 << KFD_DBG_QUEUE_ERROR_BIT) +#define KFD_DBG_QUEUE_INVALID_MASK (1 << KFD_DBG_QUEUE_INVALID_BIT) + +/* Context save area header information */ +struct kfd_context_save_area_header { + struct { + __u32 control_stack_offset; + __u32 control_stack_size; + __u32 wave_state_offset; + __u32 wave_state_size; + } wave_state; + __u32 debug_offset; + __u32 debug_size; + __u64 err_payload_addr; + __u32 err_event_id; + __u32 reserved1; +}; + +/* + * Debug operations + * + * For specifics on usage and return values, see documentation per operation + * below. Otherwise, generic error returns apply: + * - ESRCH if the process to debug does not exist. + * + * - EINVAL (with KFD_IOC_DBG_TRAP_ENABLE exempt) if operation + * KFD_IOC_DBG_TRAP_ENABLE has not succeeded prior. + * Also returns this error if GPU hardware scheduling is not supported. + * + * - EPERM (with KFD_IOC_DBG_TRAP_DISABLE exempt) if target process is not + * PTRACE_ATTACHED. KFD_IOC_DBG_TRAP_DISABLE is exempt to allow + * clean up of debug mode as long as process is debug enabled. + * + * - EACCES if any DBG_HW_OP (debug hardware operation) is requested when + * AMDKFD_IOC_RUNTIME_ENABLE has not succeeded prior. + * + * - ENODEV if any GPU does not support debugging on a DBG_HW_OP call. + * + * - Other errors may be returned when a DBG_HW_OP occurs while the GPU + * is in a fatal state. + * + */ +enum kfd_dbg_trap_operations { + KFD_IOC_DBG_TRAP_ENABLE = 0, + KFD_IOC_DBG_TRAP_DISABLE = 1, + KFD_IOC_DBG_TRAP_SEND_RUNTIME_EVENT = 2, + KFD_IOC_DBG_TRAP_SET_EXCEPTIONS_ENABLED = 3, + KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_OVERRIDE = 4, /* DBG_HW_OP */ + KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_MODE = 5, /* DBG_HW_OP */ + KFD_IOC_DBG_TRAP_SUSPEND_QUEUES = 6, /* DBG_HW_OP */ + KFD_IOC_DBG_TRAP_RESUME_QUEUES = 7, /* DBG_HW_OP */ + KFD_IOC_DBG_TRAP_SET_NODE_ADDRESS_WATCH = 8, /* DBG_HW_OP */ + KFD_IOC_DBG_TRAP_CLEAR_NODE_ADDRESS_WATCH = 9, /* DBG_HW_OP */ + KFD_IOC_DBG_TRAP_SET_FLAGS = 10, + KFD_IOC_DBG_TRAP_QUERY_DEBUG_EVENT = 11, + KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO = 12, + KFD_IOC_DBG_TRAP_GET_QUEUE_SNAPSHOT = 13, + KFD_IOC_DBG_TRAP_GET_DEVICE_SNAPSHOT = 14 +}; + +/** + * kfd_ioctl_dbg_trap_enable_args + * + * Arguments for KFD_IOC_DBG_TRAP_ENABLE. + * + * Enables debug session for target process. Call @op KFD_IOC_DBG_TRAP_DISABLE in + * kfd_ioctl_dbg_trap_args to disable debug session. + * + * @exception_mask (IN) - exceptions to raise to the debugger + * @rinfo_ptr (IN) - pointer to runtime info buffer (see kfd_runtime_info) + * @rinfo_size (IN/OUT) - size of runtime info buffer in bytes + * @dbg_fd (IN) - fd the KFD will nofify the debugger with of raised + * exceptions set in exception_mask. + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * Copies KFD saved kfd_runtime_info to @rinfo_ptr on enable. + * Size of kfd_runtime saved by the KFD returned to @rinfo_size. + * - EBADF if KFD cannot get a reference to dbg_fd. + * - EFAULT if KFD cannot copy runtime info to rinfo_ptr. + * - EINVAL if target process is already debug enabled. + * + */ +struct kfd_ioctl_dbg_trap_enable_args { + __u64 exception_mask; + __u64 rinfo_ptr; + __u32 rinfo_size; + __u32 dbg_fd; +}; + +/** + * kfd_ioctl_dbg_trap_send_runtime_event_args + * + * + * Arguments for KFD_IOC_DBG_TRAP_SEND_RUNTIME_EVENT. + * Raises exceptions to runtime. + * + * @exception_mask (IN) - exceptions to raise to runtime + * @gpu_id (IN) - target device id + * @queue_id (IN) - target queue id + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * - ENODEV if gpu_id not found. + * If exception_mask contains EC_PROCESS_RUNTIME, unblocks pending + * AMDKFD_IOC_RUNTIME_ENABLE call - see kfd_ioctl_runtime_enable_args. + * All other exceptions are raised to runtime through err_payload_addr. + * See kfd_context_save_area_header. + */ +struct kfd_ioctl_dbg_trap_send_runtime_event_args { + __u64 exception_mask; + __u32 gpu_id; + __u32 queue_id; +}; + +/** + * kfd_ioctl_dbg_trap_set_exceptions_enabled_args + * + * Arguments for KFD_IOC_SET_EXCEPTIONS_ENABLED + * Set new exceptions to be raised to the debugger. + * + * @exception_mask (IN) - new exceptions to raise the debugger + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + */ +struct kfd_ioctl_dbg_trap_set_exceptions_enabled_args { + __u64 exception_mask; +}; + +/** + * kfd_ioctl_dbg_trap_set_wave_launch_override_args + * + * Arguments for KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_OVERRIDE + * Enable HW exceptions to raise trap. + * + * @override_mode (IN) - see kfd_dbg_trap_override_mode + * @enable_mask (IN/OUT) - reference kfd_dbg_trap_mask. + * IN is the override modes requested to be enabled. + * OUT is referenced in Return below. + * @support_request_mask (IN/OUT) - reference kfd_dbg_trap_mask. + * IN is the override modes requested for support check. + * OUT is referenced in Return below. + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * Previous enablement is returned in @enable_mask. + * Actual override support is returned in @support_request_mask. + * - EINVAL if override mode is not supported. + * - EACCES if trap support requested is not actually supported. + * i.e. enable_mask (IN) is not a subset of support_request_mask (OUT). + * Otherwise it is considered a generic error (see kfd_dbg_trap_operations). + */ +struct kfd_ioctl_dbg_trap_set_wave_launch_override_args { + __u32 override_mode; + __u32 enable_mask; + __u32 support_request_mask; + __u32 pad; +}; + +/** + * kfd_ioctl_dbg_trap_set_wave_launch_mode_args + * + * Arguments for KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_MODE + * Set wave launch mode. + * + * @mode (IN) - see kfd_dbg_trap_wave_launch_mode + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + */ +struct kfd_ioctl_dbg_trap_set_wave_launch_mode_args { + __u32 launch_mode; + __u32 pad; +}; + +/** + * kfd_ioctl_dbg_trap_suspend_queues_ags + * + * Arguments for KFD_IOC_DBG_TRAP_SUSPEND_QUEUES + * Suspend queues. + * + * @exception_mask (IN) - raised exceptions to clear + * @queue_array_ptr (IN) - pointer to array of queue ids (u32 per queue id) + * to suspend + * @num_queues (IN) - number of queues to suspend in @queue_array_ptr + * @grace_period (IN) - wave time allowance before preemption + * per 1K GPU clock cycle unit + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Destruction of a suspended queue is blocked until the queue is + * resumed. This allows the debugger to access queue information and + * the its context save area without running into a race condition on + * queue destruction. + * Automatically copies per queue context save area header information + * into the save area base + * (see kfd_queue_snapshot_entry and kfd_context_save_area_header). + * + * Return - Number of queues suspended on SUCCESS. + * . KFD_DBG_QUEUE_ERROR_MASK and KFD_DBG_QUEUE_INVALID_MASK masked + * for each queue id in @queue_array_ptr array reports unsuccessful + * suspend reason. + * KFD_DBG_QUEUE_ERROR_MASK = HW failure. + * KFD_DBG_QUEUE_INVALID_MASK = queue does not exist, is new or + * is being destroyed. + */ +struct kfd_ioctl_dbg_trap_suspend_queues_args { + __u64 exception_mask; + __u64 queue_array_ptr; + __u32 num_queues; + __u32 grace_period; +}; + +/** + * kfd_ioctl_dbg_trap_resume_queues_args + * + * Arguments for KFD_IOC_DBG_TRAP_RESUME_QUEUES + * Resume queues. + * + * @queue_array_ptr (IN) - pointer to array of queue ids (u32 per queue id) + * to resume + * @num_queues (IN) - number of queues to resume in @queue_array_ptr + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - Number of queues resumed on SUCCESS. + * KFD_DBG_QUEUE_ERROR_MASK and KFD_DBG_QUEUE_INVALID_MASK mask + * for each queue id in @queue_array_ptr array reports unsuccessful + * resume reason. + * KFD_DBG_QUEUE_ERROR_MASK = HW failure. + * KFD_DBG_QUEUE_INVALID_MASK = queue does not exist. + */ +struct kfd_ioctl_dbg_trap_resume_queues_args { + __u64 queue_array_ptr; + __u32 num_queues; + __u32 pad; +}; + +/** + * kfd_ioctl_dbg_trap_set_node_address_watch_args + * + * Arguments for KFD_IOC_DBG_TRAP_SET_NODE_ADDRESS_WATCH + * Sets address watch for device. + * + * @address (IN) - watch address to set + * @mode (IN) - see kfd_dbg_trap_address_watch_mode + * @mask (IN) - watch address mask + * @gpu_id (IN) - target gpu to set watch point + * @id (OUT) - watch id allocated + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * Allocated watch ID returned to @id. + * - ENODEV if gpu_id not found. + * - ENOMEM if watch IDs can be allocated + */ +struct kfd_ioctl_dbg_trap_set_node_address_watch_args { + __u64 address; + __u32 mode; + __u32 mask; + __u32 gpu_id; + __u32 id; +}; + +/** + * kfd_ioctl_dbg_trap_clear_node_address_watch_args + * + * Arguments for KFD_IOC_DBG_TRAP_CLEAR_NODE_ADDRESS_WATCH + * Clear address watch for device. + * + * @gpu_id (IN) - target device to clear watch point + * @id (IN) - allocated watch id to clear + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * - ENODEV if gpu_id not found. + * - EINVAL if watch ID has not been allocated. + */ +struct kfd_ioctl_dbg_trap_clear_node_address_watch_args { + __u32 gpu_id; + __u32 id; +}; + +/** + * kfd_ioctl_dbg_trap_set_flags_args + * + * Arguments for KFD_IOC_DBG_TRAP_SET_FLAGS + * Sets flags for wave behaviour. + * + * @flags (IN/OUT) - IN = flags to enable, OUT = flags previously enabled + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * - EACCESS if any debug device does not allow flag options. + */ +struct kfd_ioctl_dbg_trap_set_flags_args { + __u32 flags; + __u32 pad; +}; + +/** + * kfd_ioctl_dbg_trap_query_debug_event_args + * + * Arguments for KFD_IOC_DBG_TRAP_QUERY_DEBUG_EVENT + * + * Find one or more raised exceptions. This function can return multiple + * exceptions from a single queue or a single device with one call. To find + * all raised exceptions, this function must be called repeatedly until it + * returns -EAGAIN. Returned exceptions can optionally be cleared by + * setting the corresponding bit in the @exception_mask input parameter. + * However, clearing an exception prevents retrieving further information + * about it with KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO. + * + * @exception_mask (IN/OUT) - exception to clear (IN) and raised (OUT) + * @gpu_id (OUT) - gpu id of exceptions raised + * @queue_id (OUT) - queue id of exceptions raised + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on raised exception found + * Raised exceptions found are returned in @exception mask + * with reported source id returned in @gpu_id or @queue_id. + * - EAGAIN if no raised exception has been found + */ +struct kfd_ioctl_dbg_trap_query_debug_event_args { + __u64 exception_mask; + __u32 gpu_id; + __u32 queue_id; +}; + +/** + * kfd_ioctl_dbg_trap_query_exception_info_args + * + * Arguments KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO + * Get additional info on raised exception. + * + * @info_ptr (IN) - pointer to exception info buffer to copy to + * @info_size (IN/OUT) - exception info buffer size (bytes) + * @source_id (IN) - target gpu or queue id + * @exception_code (IN) - target exception + * @clear_exception (IN) - clear raised @exception_code exception + * (0 = false, 1 = true) + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * If @exception_code is EC_DEVICE_MEMORY_VIOLATION, copy @info_size(OUT) + * bytes of memory exception data to @info_ptr. + * If @exception_code is EC_PROCESS_RUNTIME, copy saved + * kfd_runtime_info to @info_ptr. + * Actual required @info_ptr size (bytes) is returned in @info_size. + */ +struct kfd_ioctl_dbg_trap_query_exception_info_args { + __u64 info_ptr; + __u32 info_size; + __u32 source_id; + __u32 exception_code; + __u32 clear_exception; +}; + +/** + * kfd_ioctl_dbg_trap_get_queue_snapshot_args + * + * Arguments KFD_IOC_DBG_TRAP_GET_QUEUE_SNAPSHOT + * Get queue information. + * + * @exception_mask (IN) - exceptions raised to clear + * @snapshot_buf_ptr (IN) - queue snapshot entry buffer (see kfd_queue_snapshot_entry) + * @num_queues (IN/OUT) - number of queue snapshot entries + * The debugger specifies the size of the array allocated in @num_queues. + * KFD returns the number of queues that actually existed. If this is + * larger than the size specified by the debugger, KFD will not overflow + * the array allocated by the debugger. + * + * @entry_size (IN/OUT) - size per entry in bytes + * The debugger specifies sizeof(struct kfd_queue_snapshot_entry) in + * @entry_size. KFD returns the number of bytes actually populated per + * entry. The debugger should use the KFD_IOCTL_MINOR_VERSION to determine, + * which fields in struct kfd_queue_snapshot_entry are valid. This allows + * growing the ABI in a backwards compatible manner. + * Note that entry_size(IN) should still be used to stride the snapshot buffer in the + * event that it's larger than actual kfd_queue_snapshot_entry. + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * Copies @num_queues(IN) queue snapshot entries of size @entry_size(IN) + * into @snapshot_buf_ptr if @num_queues(IN) > 0. + * Otherwise return @num_queues(OUT) queue snapshot entries that exist. + */ +struct kfd_ioctl_dbg_trap_queue_snapshot_args { + __u64 exception_mask; + __u64 snapshot_buf_ptr; + __u32 num_queues; + __u32 entry_size; +}; + +/** + * kfd_ioctl_dbg_trap_get_device_snapshot_args + * + * Arguments for KFD_IOC_DBG_TRAP_GET_DEVICE_SNAPSHOT + * Get device information. + * + * @exception_mask (IN) - exceptions raised to clear + * @snapshot_buf_ptr (IN) - pointer to snapshot buffer (see kfd_dbg_device_info_entry) + * @num_devices (IN/OUT) - number of debug devices to snapshot + * The debugger specifies the size of the array allocated in @num_devices. + * KFD returns the number of devices that actually existed. If this is + * larger than the size specified by the debugger, KFD will not overflow + * the array allocated by the debugger. + * + * @entry_size (IN/OUT) - size per entry in bytes + * The debugger specifies sizeof(struct kfd_dbg_device_info_entry) in + * @entry_size. KFD returns the number of bytes actually populated. The + * debugger should use KFD_IOCTL_MINOR_VERSION to determine, which fields + * in struct kfd_dbg_device_info_entry are valid. This allows growing the + * ABI in a backwards compatible manner. + * Note that entry_size(IN) should still be used to stride the snapshot buffer in the + * event that it's larger than actual kfd_dbg_device_info_entry. + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * Copies @num_devices(IN) device snapshot entries of size @entry_size(IN) + * into @snapshot_buf_ptr if @num_devices(IN) > 0. + * Otherwise return @num_devices(OUT) queue snapshot entries that exist. + */ +struct kfd_ioctl_dbg_trap_device_snapshot_args { + __u64 exception_mask; + __u64 snapshot_buf_ptr; + __u32 num_devices; + __u32 entry_size; +}; + +/** + * kfd_ioctl_dbg_trap_args + * + * Arguments to debug target process. + * + * @pid - target process to debug + * @op - debug operation (see kfd_dbg_trap_operations) + * + * @op determines which union struct args to use. + * Refer to kern docs for each kfd_ioctl_dbg_trap_*_args struct. + */ +struct kfd_ioctl_dbg_trap_args { + __u32 pid; + __u32 op; + + union { + struct kfd_ioctl_dbg_trap_enable_args enable; + struct kfd_ioctl_dbg_trap_send_runtime_event_args send_runtime_event; + struct kfd_ioctl_dbg_trap_set_exceptions_enabled_args set_exceptions_enabled; + struct kfd_ioctl_dbg_trap_set_wave_launch_override_args launch_override; + struct kfd_ioctl_dbg_trap_set_wave_launch_mode_args launch_mode; + struct kfd_ioctl_dbg_trap_suspend_queues_args suspend_queues; + struct kfd_ioctl_dbg_trap_resume_queues_args resume_queues; + struct kfd_ioctl_dbg_trap_set_node_address_watch_args set_node_address_watch; + struct kfd_ioctl_dbg_trap_clear_node_address_watch_args clear_node_address_watch; + struct kfd_ioctl_dbg_trap_set_flags_args set_flags; + struct kfd_ioctl_dbg_trap_query_debug_event_args query_debug_event; + struct kfd_ioctl_dbg_trap_query_exception_info_args query_exception_info; + struct kfd_ioctl_dbg_trap_queue_snapshot_args queue_snapshot; + struct kfd_ioctl_dbg_trap_device_snapshot_args device_snapshot; + }; +}; + #define AMDKFD_IOCTL_BASE 'K' #define AMDKFD_IO(nr) _IO(AMDKFD_IOCTL_BASE, nr) #define AMDKFD_IOR(nr, type) _IOR(AMDKFD_IOCTL_BASE, nr, type) @@ -887,7 +1547,13 @@ struct kfd_ioctl_set_xnack_mode_args { #define AMDKFD_IOC_EXPORT_DMABUF \ AMDKFD_IOWR(0x24, struct kfd_ioctl_export_dmabuf_args) +#define AMDKFD_IOC_RUNTIME_ENABLE \ + AMDKFD_IOWR(0x25, struct kfd_ioctl_runtime_enable_args) + +#define AMDKFD_IOC_DBG_TRAP \ + AMDKFD_IOWR(0x26, struct kfd_ioctl_dbg_trap_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x25 +#define AMDKFD_COMMAND_END 0x27 #endif -- cgit v1.2.3 From d230f1bfe7a1977565ce1e2804ddb7b7a3d911ff Mon Sep 17 00:00:00 2001 From: Jonathan Kim Date: Fri, 25 Mar 2022 12:39:06 -0400 Subject: drm/amdkfd: display debug capabilities Expose debug capabilities in the KFD topology node's HSA capabilities and debug properties flags. Ensure correct capabilities are exposed based on firmware support. Flag definitions can be referenced in uapi/linux/kfd_sysfs.h. Signed-off-by: Jonathan Kim Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 101 ++++++++++++++++++++++++++++-- drivers/gpu/drm/amd/amdkfd/kfd_topology.h | 6 ++ include/uapi/linux/kfd_sysfs.h | 15 +++++ 3 files changed, 117 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 8302d8967158..3def25b2bdbb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -535,6 +535,8 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr, dev->gpu->kfd->mec_fw_version); sysfs_show_32bit_prop(buffer, offs, "capability", dev->node_props.capability); + sysfs_show_64bit_prop(buffer, offs, "debug_prop", + dev->node_props.debug_prop); sysfs_show_32bit_prop(buffer, offs, "sdma_fw_version", dev->gpu->kfd->sdma_fw_version); sysfs_show_64bit_prop(buffer, offs, "unique_id", @@ -1857,6 +1859,97 @@ err: return res; } +static void kfd_topology_set_dbg_firmware_support(struct kfd_topology_device *dev) +{ + bool firmware_supported = true; + + if (KFD_GC_VERSION(dev->gpu) >= IP_VERSION(11, 0, 0) && + KFD_GC_VERSION(dev->gpu) < IP_VERSION(12, 0, 0)) { + firmware_supported = + (dev->gpu->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 9; + goto out; + } + + /* + * Note: Any unlisted devices here are assumed to support exception handling. + * Add additional checks here as needed. + */ + switch (KFD_GC_VERSION(dev->gpu)) { + case IP_VERSION(9, 0, 1): + firmware_supported = dev->gpu->kfd->mec_fw_version >= 459 + 32768; + break; + case IP_VERSION(9, 1, 0): + case IP_VERSION(9, 2, 1): + case IP_VERSION(9, 2, 2): + case IP_VERSION(9, 3, 0): + case IP_VERSION(9, 4, 0): + firmware_supported = dev->gpu->kfd->mec_fw_version >= 459; + break; + case IP_VERSION(9, 4, 1): + firmware_supported = dev->gpu->kfd->mec_fw_version >= 60; + break; + case IP_VERSION(9, 4, 2): + firmware_supported = dev->gpu->kfd->mec_fw_version >= 51; + break; + case IP_VERSION(10, 1, 10): + case IP_VERSION(10, 1, 2): + case IP_VERSION(10, 1, 1): + firmware_supported = dev->gpu->kfd->mec_fw_version >= 144; + break; + case IP_VERSION(10, 3, 0): + case IP_VERSION(10, 3, 2): + case IP_VERSION(10, 3, 1): + case IP_VERSION(10, 3, 4): + case IP_VERSION(10, 3, 5): + firmware_supported = dev->gpu->kfd->mec_fw_version >= 89; + break; + case IP_VERSION(10, 1, 3): + case IP_VERSION(10, 3, 3): + firmware_supported = false; + break; + default: + break; + } + +out: + if (firmware_supported) + dev->node_props.capability |= HSA_CAP_TRAP_DEBUG_FIRMWARE_SUPPORTED; +} + +static void kfd_topology_set_capabilities(struct kfd_topology_device *dev) +{ + dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_2_0 << + HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) & + HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK); + + dev->node_props.capability |= HSA_CAP_TRAP_DEBUG_SUPPORT | + HSA_CAP_TRAP_DEBUG_WAVE_LAUNCH_TRAP_OVERRIDE_SUPPORTED | + HSA_CAP_TRAP_DEBUG_WAVE_LAUNCH_MODE_SUPPORTED; + + if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(10, 0, 0)) { + dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX9 | + HSA_DBG_WATCH_ADDR_MASK_HI_BIT; + + if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(9, 4, 2)) + dev->node_props.debug_prop |= + HSA_DBG_DISPATCH_INFO_ALWAYS_VALID; + else + dev->node_props.capability |= + HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED; + } else { + dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX10 | + HSA_DBG_WATCH_ADDR_MASK_HI_BIT; + + if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(11, 0, 0)) + dev->node_props.debug_prop |= HSA_DBG_DISPATCH_INFO_ALWAYS_VALID; + else + dev->node_props.capability |= + HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED; + } + + kfd_topology_set_dbg_firmware_support(dev); +} + int kfd_topology_add_device(struct kfd_node *gpu) { uint32_t gpu_id; @@ -1967,13 +2060,11 @@ int kfd_topology_add_device(struct kfd_node *gpu) HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK); break; default: - if (KFD_GC_VERSION(dev->gpu) >= IP_VERSION(9, 0, 1)) - dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_2_0 << - HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) & - HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK); - else + if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(9, 0, 1)) WARN(1, "Unexpected ASIC family %u", dev->gpu->adev->asic_type); + else + kfd_topology_set_capabilities(dev); } /* diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h index 3b8afb6aba79..cba2cd5ed9d1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h @@ -31,6 +31,11 @@ #define KFD_TOPOLOGY_PUBLIC_NAME_SIZE 32 +#define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX9 6 +#define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX10 7 +#define HSA_DBG_WATCH_ADDR_MASK_HI_BIT \ + (29 << HSA_DBG_WATCH_ADDR_MASK_HI_BIT_SHIFT) + struct kfd_node_properties { uint64_t hive_id; uint32_t cpu_cores_count; @@ -42,6 +47,7 @@ struct kfd_node_properties { uint32_t cpu_core_id_base; uint32_t simd_id_base; uint32_t capability; + uint64_t debug_prop; uint32_t max_waves_per_simd; uint32_t lds_size_in_kb; uint32_t gds_size_in_kb; diff --git a/include/uapi/linux/kfd_sysfs.h b/include/uapi/linux/kfd_sysfs.h index 3e330f368917..a51b7331e0b4 100644 --- a/include/uapi/linux/kfd_sysfs.h +++ b/include/uapi/linux/kfd_sysfs.h @@ -43,6 +43,11 @@ #define HSA_CAP_DOORBELL_TYPE_2_0 0x2 #define HSA_CAP_AQL_QUEUE_DOUBLE_MAP 0x00004000 +#define HSA_CAP_TRAP_DEBUG_SUPPORT 0x00008000 +#define HSA_CAP_TRAP_DEBUG_WAVE_LAUNCH_TRAP_OVERRIDE_SUPPORTED 0x00010000 +#define HSA_CAP_TRAP_DEBUG_WAVE_LAUNCH_MODE_SUPPORTED 0x00020000 +#define HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED 0x00040000 + /* Old buggy user mode depends on this being 0 */ #define HSA_CAP_RESERVED_WAS_SRAM_EDCSUPPORTED 0x00080000 @@ -53,8 +58,18 @@ #define HSA_CAP_SRAM_EDCSUPPORTED 0x04000000 #define HSA_CAP_SVMAPI_SUPPORTED 0x08000000 #define HSA_CAP_FLAGS_COHERENTHOSTACCESS 0x10000000 +#define HSA_CAP_TRAP_DEBUG_FIRMWARE_SUPPORTED 0x20000000 #define HSA_CAP_RESERVED 0xe00f8000 +/* debug_prop bits in node properties */ +#define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_MASK 0x0000000f +#define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_SHIFT 0 +#define HSA_DBG_WATCH_ADDR_MASK_HI_BIT_MASK 0x000003f0 +#define HSA_DBG_WATCH_ADDR_MASK_HI_BIT_SHIFT 4 +#define HSA_DBG_DISPATCH_INFO_ALWAYS_VALID 0x00000400 +#define HSA_DBG_WATCHPOINTS_EXCLUSIVE 0x00000800 +#define HSA_DBG_RESERVED 0xfffffffffffff000ull + /* Heap types in memory properties */ #define HSA_MEM_HEAP_TYPE_SYSTEM 0 #define HSA_MEM_HEAP_TYPE_FB_PUBLIC 1 -- cgit v1.2.3 From a159afdad2f6b97e4d18549cff2b53d17e68a412 Mon Sep 17 00:00:00 2001 From: Jonathan Kim Date: Tue, 10 May 2022 12:51:26 -0400 Subject: drm/amdkfd: bump kfd ioctl minor version for debug api availability Bump the minor version to declare debugging capability is now available. Signed-off-by: Jonathan Kim Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 1 - include/uapi/linux/kfd_ioctl.h | 3 ++- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index f54ff5c3387d..cce2abe12e1b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -2984,7 +2984,6 @@ static int kfd_ioctl_set_debug_trap(struct file *filep, struct kfd_process *p, v if (!r) target->exception_enable_mask = args->enable.exception_mask; - pr_warn("Debug functions limited\n"); break; case KFD_IOC_DBG_TRAP_DISABLE: r = kfd_dbg_trap_disable(target); diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 32913d674d38..1781e7669982 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -38,9 +38,10 @@ * - 1.10 - Add SMI profiler event log * - 1.11 - Add unified memory for ctx save/restore area * - 1.12 - Add DMA buf export ioctl + * - 1.13 - Add debugger API */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 12 +#define KFD_IOCTL_MINOR_VERSION 13 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ -- cgit v1.2.3 From 1626761ee4406c51d5afe9d47dd41a29e2049b71 Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Fri, 3 Feb 2023 02:07:42 +0000 Subject: drm/connector: Convert DRM_MODE_COLORIMETRY to enum MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows us to use strongly typed arguments. v2: - Bring NO_DATA back - Provide explicit enum values v3: - Drop unnecessary '&' from kerneldoc (emersion) v4: - Fix Normal Colorimetry comment Signed-off-by: Harry Wentland Reviewed-by: Simon Ser Reviewed-by: Sebastian Wick Reviewed-by: Pekka Paalanen Reviewed-by: Joshua Ashton Cc: Pekka Paalanen Cc: Sebastian Wick Cc: Vitaly.Prosyak@amd.com Cc: Uma Shankar Cc: Ville Syrjälä Cc: Joshua Ashton Cc: Simon Ser Cc: Melissa Wen Cc: dri-devel@lists.freedesktop.org Cc: amd-gfx@lists.freedesktop.org Signed-off-by: Alex Deucher --- include/drm/display/drm_dp.h | 2 +- include/drm/drm_connector.h | 49 ++++++++++++++++++++++---------------------- 2 files changed, 26 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h index d735073fdd81..ccbf0c0934c3 100644 --- a/include/drm/display/drm_dp.h +++ b/include/drm/display/drm_dp.h @@ -1636,7 +1636,7 @@ enum dp_pixelformat { * * This enum is used to indicate DP VSC SDP Colorimetry formats. * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] and a name of enum member follows DRM_MODE_COLORIMETRY definition. + * DB18] and a name of enum member follows enum drm_colorimetry definition. * * @DP_COLORIMETRY_DEFAULT: sRGB (IEC 61966-2-1) or * ITU-R BT.601 colorimetry format diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 7b5048516185..31ecd36bc7ea 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -427,29 +427,30 @@ enum drm_privacy_screen_status { * a colorspace property which will be created and exposed to * userspace. */ - -/* For Default case, driver will set the colorspace */ -#define DRM_MODE_COLORIMETRY_DEFAULT 0 -/* CEA 861 Normal Colorimetry options */ -#define DRM_MODE_COLORIMETRY_NO_DATA 0 -#define DRM_MODE_COLORIMETRY_SMPTE_170M_YCC 1 -#define DRM_MODE_COLORIMETRY_BT709_YCC 2 -/* CEA 861 Extended Colorimetry Options */ -#define DRM_MODE_COLORIMETRY_XVYCC_601 3 -#define DRM_MODE_COLORIMETRY_XVYCC_709 4 -#define DRM_MODE_COLORIMETRY_SYCC_601 5 -#define DRM_MODE_COLORIMETRY_OPYCC_601 6 -#define DRM_MODE_COLORIMETRY_OPRGB 7 -#define DRM_MODE_COLORIMETRY_BT2020_CYCC 8 -#define DRM_MODE_COLORIMETRY_BT2020_RGB 9 -#define DRM_MODE_COLORIMETRY_BT2020_YCC 10 -/* Additional Colorimetry extension added as part of CTA 861.G */ -#define DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65 11 -#define DRM_MODE_COLORIMETRY_DCI_P3_RGB_THEATER 12 -/* Additional Colorimetry Options added for DP 1.4a VSC Colorimetry Format */ -#define DRM_MODE_COLORIMETRY_RGB_WIDE_FIXED 13 -#define DRM_MODE_COLORIMETRY_RGB_WIDE_FLOAT 14 -#define DRM_MODE_COLORIMETRY_BT601_YCC 15 +enum drm_colorspace { + /* For Default case, driver will set the colorspace */ + DRM_MODE_COLORIMETRY_DEFAULT = 0, + /* CEA 861 Normal Colorimetry options */ + DRM_MODE_COLORIMETRY_NO_DATA = 0, + DRM_MODE_COLORIMETRY_SMPTE_170M_YCC = 1, + DRM_MODE_COLORIMETRY_BT709_YCC = 2, + /* CEA 861 Extended Colorimetry Options */ + DRM_MODE_COLORIMETRY_XVYCC_601 = 3, + DRM_MODE_COLORIMETRY_XVYCC_709 = 4, + DRM_MODE_COLORIMETRY_SYCC_601 = 5, + DRM_MODE_COLORIMETRY_OPYCC_601 = 6, + DRM_MODE_COLORIMETRY_OPRGB = 7, + DRM_MODE_COLORIMETRY_BT2020_CYCC = 8, + DRM_MODE_COLORIMETRY_BT2020_RGB = 9, + DRM_MODE_COLORIMETRY_BT2020_YCC = 10, + /* Additional Colorimetry extension added as part of CTA 861.G */ + DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65 = 11, + DRM_MODE_COLORIMETRY_DCI_P3_RGB_THEATER = 12, + /* Additional Colorimetry Options added for DP 1.4a VSC Colorimetry Format */ + DRM_MODE_COLORIMETRY_RGB_WIDE_FIXED = 13, + DRM_MODE_COLORIMETRY_RGB_WIDE_FLOAT = 14, + DRM_MODE_COLORIMETRY_BT601_YCC = 15, +}; /** * enum drm_bus_flags - bus_flags info for &drm_display_info @@ -901,7 +902,7 @@ struct drm_connector_state { * colorspace change on Sink. This is most commonly used to switch * to wider color gamuts like BT2020. */ - u32 colorspace; + enum drm_colorspace colorspace; /** * @writeback_job: Writeback job for writeback connectors -- cgit v1.2.3 From f96c61fe0383d73732aba72fabb7e2c7ce0b0835 Mon Sep 17 00:00:00 2001 From: Joshua Ashton Date: Fri, 3 Feb 2023 02:07:43 +0000 Subject: drm/connector: Add enum documentation to drm_colorspace MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To match the other enums, and add more information about these values. v2: - Specify where an enum entry comes from - Clarify DEFAULT and NO_DATA behavior - BT.2020 CYCC is "constant luminance" - correct type for BT.601 v4: - drop DP/HDMI clarifications that might create more questions than answers v5: - Add note on YCC and RGB variants Signed-off-by: Joshua Ashton Signed-off-by: Harry Wentland Reviewed-by: Harry Wentland Reviewed-by: Sebastian Wick Acked-by: Pekka Paalanen Reviewed-by: Simon Ser Cc: Pekka Paalanen Cc: Sebastian Wick Cc: Vitaly.Prosyak@amd.com Cc: Uma Shankar Cc: Ville Syrjälä Cc: Joshua Ashton Cc: Simon Ser Cc: Melissa Wen Cc: dri-devel@lists.freedesktop.org Cc: amd-gfx@lists.freedesktop.org Signed-off-by: Alex Deucher --- include/drm/drm_connector.h | 70 +++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 68 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 31ecd36bc7ea..e338432580e0 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -419,13 +419,79 @@ enum drm_privacy_screen_status { PRIVACY_SCREEN_ENABLED_LOCKED, }; -/* - * This is a consolidated colorimetry list supported by HDMI and +/** + * enum drm_colorspace - color space + * + * This enum is a consolidated colorimetry list supported by HDMI and * DP protocol standard. The respective connectors will register * a property with the subset of this list (supported by that * respective protocol). Userspace will set the colorspace through * a colorspace property which will be created and exposed to * userspace. + * + * DP definitions come from the DP v2.0 spec + * HDMI definitions come from the CTA-861-H spec + * + * A note on YCC and RGB variants: + * + * Since userspace is not aware of the encoding on the wire + * (RGB or YCbCr), drivers are free to pick the appropriate + * variant, regardless of what userspace selects. E.g., if + * BT2020_RGB is selected by userspace a driver will pick + * BT2020_YCC if the encoding on the wire is YUV444 or YUV420. + * + * @DRM_MODE_COLORIMETRY_DEFAULT: + * Driver specific behavior. + * @DRM_MODE_COLORIMETRY_NO_DATA: + * Driver specific behavior. + * @DRM_MODE_COLORIMETRY_SMPTE_170M_YCC: + * (HDMI) + * SMPTE ST 170M colorimetry format + * @DRM_MODE_COLORIMETRY_BT709_YCC: + * (HDMI, DP) + * ITU-R BT.709 colorimetry format + * @DRM_MODE_COLORIMETRY_XVYCC_601: + * (HDMI, DP) + * xvYCC601 colorimetry format + * @DRM_MODE_COLORIMETRY_XVYCC_709: + * (HDMI, DP) + * xvYCC709 colorimetry format + * @DRM_MODE_COLORIMETRY_SYCC_601: + * (HDMI, DP) + * sYCC601 colorimetry format + * @DRM_MODE_COLORIMETRY_OPYCC_601: + * (HDMI, DP) + * opYCC601 colorimetry format + * @DRM_MODE_COLORIMETRY_OPRGB: + * (HDMI, DP) + * opRGB colorimetry format + * @DRM_MODE_COLORIMETRY_BT2020_CYCC: + * (HDMI, DP) + * ITU-R BT.2020 Y'c C'bc C'rc (constant luminance) colorimetry format + * @DRM_MODE_COLORIMETRY_BT2020_RGB: + * (HDMI, DP) + * ITU-R BT.2020 R' G' B' colorimetry format + * @DRM_MODE_COLORIMETRY_BT2020_YCC: + * (HDMI, DP) + * ITU-R BT.2020 Y' C'b C'r colorimetry format + * @DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65: + * (HDMI) + * SMPTE ST 2113 P3D65 colorimetry format + * @DRM_MODE_COLORIMETRY_DCI_P3_RGB_THEATER: + * (HDMI) + * SMPTE ST 2113 P3DCI colorimetry format + * @DRM_MODE_COLORIMETRY_RGB_WIDE_FIXED: + * (DP) + * RGB wide gamut fixed point colorimetry format + * @DRM_MODE_COLORIMETRY_RGB_WIDE_FLOAT: + * (DP) + * RGB wide gamut floating point + * (scRGB (IEC 61966-2-2)) colorimetry format + * @DRM_MODE_COLORIMETRY_BT601_YCC: + * (DP) + * ITU-R BT.601 colorimetry format + * The DP spec does not say whether this is the 525 or the 625 + * line version. */ enum drm_colorspace { /* For Default case, driver will set the colorspace */ -- cgit v1.2.3 From c627087cb164d1675323c7942fa29bded4263dfc Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Tue, 29 Nov 2022 15:16:31 -0500 Subject: drm/connector: Use common colorspace_names array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We an use bitfields to track the support ones for HDMI and DP. This allows us to print colorspaces in a consistent manner without needing to know whether we're dealing with DP or HDMI. v4: - Rename _MAX to _COUNT and leave comment to indicate it's not a valid value - Fix misplaced function doc v6: - Drop magic in drm_mode_create_colorspace_property for dealing with "0" supported_colorspaces. Expect the caller to always provide a non-zero supported_colorspaces. - Improve error checking and logging Signed-off-by: Harry Wentland Reviewed-by: Sebastian Wick Reviewed-by: Joshua Ashton Reviewed-by: Simon Ser Cc: Pekka Paalanen Cc: Sebastian Wick Cc: Vitaly.Prosyak@amd.com Cc: Uma Shankar Cc: Ville Syrjälä Cc: Joshua Ashton Cc: Jani Nikula Cc: Simon Ser Cc: Melissa Wen Cc: dri-devel@lists.freedesktop.org Cc: amd-gfx@lists.freedesktop.org Signed-off-by: Alex Deucher --- drivers/gpu/drm/drm_connector.c | 130 ++++++++++++++++++++++++---------------- include/drm/drm_connector.h | 2 + 2 files changed, 79 insertions(+), 53 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 614dd9fd4d3f..b823b10ed697 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -1055,64 +1055,70 @@ static const struct drm_prop_enum_list drm_dp_subconnector_enum_list[] = { DRM_ENUM_NAME_FN(drm_get_dp_subconnector_name, drm_dp_subconnector_enum_list) -static const struct drm_prop_enum_list hdmi_colorspaces[] = { + +static const char * const colorspace_names[] = { /* For Default case, driver will set the colorspace */ - { DRM_MODE_COLORIMETRY_DEFAULT, "Default" }, + [DRM_MODE_COLORIMETRY_DEFAULT] = "Default", /* Standard Definition Colorimetry based on CEA 861 */ - { DRM_MODE_COLORIMETRY_SMPTE_170M_YCC, "SMPTE_170M_YCC" }, - { DRM_MODE_COLORIMETRY_BT709_YCC, "BT709_YCC" }, + [DRM_MODE_COLORIMETRY_SMPTE_170M_YCC] = "SMPTE_170M_YCC", + [DRM_MODE_COLORIMETRY_BT709_YCC] = "BT709_YCC", /* Standard Definition Colorimetry based on IEC 61966-2-4 */ - { DRM_MODE_COLORIMETRY_XVYCC_601, "XVYCC_601" }, + [DRM_MODE_COLORIMETRY_XVYCC_601] = "XVYCC_601", /* High Definition Colorimetry based on IEC 61966-2-4 */ - { DRM_MODE_COLORIMETRY_XVYCC_709, "XVYCC_709" }, + [DRM_MODE_COLORIMETRY_XVYCC_709] = "XVYCC_709", /* Colorimetry based on IEC 61966-2-1/Amendment 1 */ - { DRM_MODE_COLORIMETRY_SYCC_601, "SYCC_601" }, + [DRM_MODE_COLORIMETRY_SYCC_601] = "SYCC_601", /* Colorimetry based on IEC 61966-2-5 [33] */ - { DRM_MODE_COLORIMETRY_OPYCC_601, "opYCC_601" }, + [DRM_MODE_COLORIMETRY_OPYCC_601] = "opYCC_601", /* Colorimetry based on IEC 61966-2-5 */ - { DRM_MODE_COLORIMETRY_OPRGB, "opRGB" }, + [DRM_MODE_COLORIMETRY_OPRGB] = "opRGB", /* Colorimetry based on ITU-R BT.2020 */ - { DRM_MODE_COLORIMETRY_BT2020_CYCC, "BT2020_CYCC" }, + [DRM_MODE_COLORIMETRY_BT2020_CYCC] = "BT2020_CYCC", /* Colorimetry based on ITU-R BT.2020 */ - { DRM_MODE_COLORIMETRY_BT2020_RGB, "BT2020_RGB" }, + [DRM_MODE_COLORIMETRY_BT2020_RGB] = "BT2020_RGB", /* Colorimetry based on ITU-R BT.2020 */ - { DRM_MODE_COLORIMETRY_BT2020_YCC, "BT2020_YCC" }, + [DRM_MODE_COLORIMETRY_BT2020_YCC] = "BT2020_YCC", /* Added as part of Additional Colorimetry Extension in 861.G */ - { DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65, "DCI-P3_RGB_D65" }, - { DRM_MODE_COLORIMETRY_DCI_P3_RGB_THEATER, "DCI-P3_RGB_Theater" }, + [DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65] = "DCI-P3_RGB_D65", + [DRM_MODE_COLORIMETRY_DCI_P3_RGB_THEATER] = "DCI-P3_RGB_Theater", + [DRM_MODE_COLORIMETRY_RGB_WIDE_FIXED] = "RGB_WIDE_FIXED", + /* Colorimetry based on scRGB (IEC 61966-2-2) */ + [DRM_MODE_COLORIMETRY_RGB_WIDE_FLOAT] = "RGB_WIDE_FLOAT", + [DRM_MODE_COLORIMETRY_BT601_YCC] = "BT601_YCC", }; +static const u32 hdmi_colorspaces = + BIT(DRM_MODE_COLORIMETRY_SMPTE_170M_YCC) | + BIT(DRM_MODE_COLORIMETRY_BT709_YCC) | + BIT(DRM_MODE_COLORIMETRY_XVYCC_601) | + BIT(DRM_MODE_COLORIMETRY_XVYCC_709) | + BIT(DRM_MODE_COLORIMETRY_SYCC_601) | + BIT(DRM_MODE_COLORIMETRY_OPYCC_601) | + BIT(DRM_MODE_COLORIMETRY_OPRGB) | + BIT(DRM_MODE_COLORIMETRY_BT2020_CYCC) | + BIT(DRM_MODE_COLORIMETRY_BT2020_RGB) | + BIT(DRM_MODE_COLORIMETRY_BT2020_YCC) | + BIT(DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65) | + BIT(DRM_MODE_COLORIMETRY_DCI_P3_RGB_THEATER); + /* * As per DP 1.4a spec, 2.2.5.7.5 VSC SDP Payload for Pixel Encoding/Colorimetry * Format Table 2-120 */ -static const struct drm_prop_enum_list dp_colorspaces[] = { - /* For Default case, driver will set the colorspace */ - { DRM_MODE_COLORIMETRY_DEFAULT, "Default" }, - { DRM_MODE_COLORIMETRY_RGB_WIDE_FIXED, "RGB_Wide_Gamut_Fixed_Point" }, - /* Colorimetry based on scRGB (IEC 61966-2-2) */ - { DRM_MODE_COLORIMETRY_RGB_WIDE_FLOAT, "RGB_Wide_Gamut_Floating_Point" }, - /* Colorimetry based on IEC 61966-2-5 */ - { DRM_MODE_COLORIMETRY_OPRGB, "opRGB" }, - /* Colorimetry based on SMPTE RP 431-2 */ - { DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65, "DCI-P3_RGB_D65" }, - /* Colorimetry based on ITU-R BT.2020 */ - { DRM_MODE_COLORIMETRY_BT2020_RGB, "BT2020_RGB" }, - { DRM_MODE_COLORIMETRY_BT601_YCC, "BT601_YCC" }, - { DRM_MODE_COLORIMETRY_BT709_YCC, "BT709_YCC" }, - /* Standard Definition Colorimetry based on IEC 61966-2-4 */ - { DRM_MODE_COLORIMETRY_XVYCC_601, "XVYCC_601" }, - /* High Definition Colorimetry based on IEC 61966-2-4 */ - { DRM_MODE_COLORIMETRY_XVYCC_709, "XVYCC_709" }, - /* Colorimetry based on IEC 61966-2-1/Amendment 1 */ - { DRM_MODE_COLORIMETRY_SYCC_601, "SYCC_601" }, - /* Colorimetry based on IEC 61966-2-5 [33] */ - { DRM_MODE_COLORIMETRY_OPYCC_601, "opYCC_601" }, - /* Colorimetry based on ITU-R BT.2020 */ - { DRM_MODE_COLORIMETRY_BT2020_CYCC, "BT2020_CYCC" }, - /* Colorimetry based on ITU-R BT.2020 */ - { DRM_MODE_COLORIMETRY_BT2020_YCC, "BT2020_YCC" }, -}; +static const u32 dp_colorspaces = + BIT(DRM_MODE_COLORIMETRY_RGB_WIDE_FIXED) | + BIT(DRM_MODE_COLORIMETRY_RGB_WIDE_FLOAT) | + BIT(DRM_MODE_COLORIMETRY_OPRGB) | + BIT(DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65) | + BIT(DRM_MODE_COLORIMETRY_BT2020_RGB) | + BIT(DRM_MODE_COLORIMETRY_BT601_YCC) | + BIT(DRM_MODE_COLORIMETRY_BT709_YCC) | + BIT(DRM_MODE_COLORIMETRY_XVYCC_601) | + BIT(DRM_MODE_COLORIMETRY_XVYCC_709) | + BIT(DRM_MODE_COLORIMETRY_SYCC_601) | + BIT(DRM_MODE_COLORIMETRY_OPYCC_601) | + BIT(DRM_MODE_COLORIMETRY_BT2020_CYCC) | + BIT(DRM_MODE_COLORIMETRY_BT2020_YCC); /** * DOC: standard connector properties @@ -2136,27 +2142,49 @@ EXPORT_SYMBOL(drm_mode_create_aspect_ratio_property); */ static int drm_mode_create_colorspace_property(struct drm_connector *connector, - const struct drm_prop_enum_list *colorspaces, - int size) + u32 supported_colorspaces) { struct drm_device *dev = connector->dev; + u32 colorspaces = supported_colorspaces | BIT(DRM_MODE_COLORIMETRY_DEFAULT); + struct drm_prop_enum_list enum_list[DRM_MODE_COLORIMETRY_COUNT]; + int i, len; if (connector->colorspace_property) return 0; - if (!colorspaces) - return 0; + if (!supported_colorspaces) { + drm_err(dev, "No supported colorspaces provded on [CONNECTOR:%d:%s]\n", + connector->base.id, connector->name); + return -EINVAL; + } + + if ((supported_colorspaces & -BIT(DRM_MODE_COLORIMETRY_COUNT)) != 0) { + drm_err(dev, "Unknown colorspace provded on [CONNECTOR:%d:%s]\n", + connector->base.id, connector->name); + return -EINVAL; + } + + len = 0; + for (i = 0; i < DRM_MODE_COLORIMETRY_COUNT; i++) { + if ((colorspaces & BIT(i)) == 0) + continue; + + enum_list[len].type = i; + enum_list[len].name = colorspace_names[i]; + len++; + } connector->colorspace_property = drm_property_create_enum(dev, DRM_MODE_PROP_ENUM, "Colorspace", - colorspaces, - size); + enum_list, + len); if (!connector->colorspace_property) return -ENOMEM; return 0; } + /** * drm_mode_create_hdmi_colorspace_property - create hdmi colorspace property * @connector: connector to create the Colorspace property on. @@ -2169,9 +2197,7 @@ static int drm_mode_create_colorspace_property(struct drm_connector *connector, */ int drm_mode_create_hdmi_colorspace_property(struct drm_connector *connector) { - return drm_mode_create_colorspace_property(connector, - hdmi_colorspaces, - ARRAY_SIZE(hdmi_colorspaces)); + return drm_mode_create_colorspace_property(connector, hdmi_colorspaces); } EXPORT_SYMBOL(drm_mode_create_hdmi_colorspace_property); @@ -2187,9 +2213,7 @@ EXPORT_SYMBOL(drm_mode_create_hdmi_colorspace_property); */ int drm_mode_create_dp_colorspace_property(struct drm_connector *connector) { - return drm_mode_create_colorspace_property(connector, - dp_colorspaces, - ARRAY_SIZE(dp_colorspaces)); + return drm_mode_create_colorspace_property(connector, dp_colorspaces); } EXPORT_SYMBOL(drm_mode_create_dp_colorspace_property); diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index e338432580e0..6eb8e2d5d20f 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -516,6 +516,8 @@ enum drm_colorspace { DRM_MODE_COLORIMETRY_RGB_WIDE_FIXED = 13, DRM_MODE_COLORIMETRY_RGB_WIDE_FLOAT = 14, DRM_MODE_COLORIMETRY_BT601_YCC = 15, + /* not a valid value; merely used for counting */ + DRM_MODE_COLORIMETRY_COUNT }; /** -- cgit v1.2.3 From 035d53e0f36da6ce49abf7bea3d9b30a075ff247 Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Wed, 30 Nov 2022 16:11:30 -0500 Subject: drm/connector: Print connector colorspace in state debugfs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit v3: Fix kerneldocs (kernel test robot) v4: Avoid returning NULL from drm_get_colorspace_name Signed-off-by: Harry Wentland Reviewed-by: Sebastian Wick Reviewed-by: Joshua Ashton Reviewed-by: Simon Ser Cc: Pekka Paalanen Cc: Sebastian Wick Cc: Vitaly.Prosyak@amd.com Cc: Uma Shankar Cc: Ville Syrjälä Cc: Joshua Ashton Cc: Jani Nikula Cc: Simon Ser Cc: Melissa Wen Cc: dri-devel@lists.freedesktop.org Cc: amd-gfx@lists.freedesktop.org Signed-off-by: Alex Deucher --- drivers/gpu/drm/drm_atomic.c | 1 + drivers/gpu/drm/drm_connector.c | 15 +++++++++++++++ include/drm/drm_connector.h | 1 + 3 files changed, 17 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index b4c6ffc438da..2c454568a607 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -1131,6 +1131,7 @@ static void drm_atomic_connector_print_state(struct drm_printer *p, drm_printf(p, "\tcrtc=%s\n", state->crtc ? state->crtc->name : "(null)"); drm_printf(p, "\tself_refresh_aware=%d\n", state->self_refresh_aware); drm_printf(p, "\tmax_requested_bpc=%d\n", state->max_requested_bpc); + drm_printf(p, "\tcolorspace=%s\n", drm_get_colorspace_name(state->colorspace)); if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) if (state->writeback_job && state->writeback_job->fb) diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index b823b10ed697..e1d7a40e1776 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -1087,6 +1087,21 @@ static const char * const colorspace_names[] = { [DRM_MODE_COLORIMETRY_BT601_YCC] = "BT601_YCC", }; +/** + * drm_get_colorspace_name - return a string for color encoding + * @colorspace: color space to compute name of + * + * In contrast to the other drm_get_*_name functions this one here returns a + * const pointer and hence is threadsafe. + */ +const char *drm_get_colorspace_name(enum drm_colorspace colorspace) +{ + if (colorspace < ARRAY_SIZE(colorspace_names) && colorspace_names[colorspace]) + return colorspace_names[colorspace]; + else + return "(null)"; +} + static const u32 hdmi_colorspaces = BIT(DRM_MODE_COLORIMETRY_SMPTE_170M_YCC) | BIT(DRM_MODE_COLORIMETRY_BT709_YCC) | diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 6eb8e2d5d20f..880220321867 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -2078,6 +2078,7 @@ void drm_connector_list_iter_end(struct drm_connector_list_iter *iter); bool drm_connector_has_possible_encoder(struct drm_connector *connector, struct drm_encoder *encoder); +const char *drm_get_colorspace_name(enum drm_colorspace colorspace); /** * drm_for_each_connector_iter - connector_list iterator macro -- cgit v1.2.3 From c265f340eaa87aa5f979adfb23d7463af67b7f27 Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Tue, 29 Nov 2022 15:16:31 -0500 Subject: drm/connector: Allow drivers to pass list of supported colorspaces MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drivers might not support all colorspaces defined in dp_colorspaces and hdmi_colorspaces. This results in undefined behavior when userspace is setting an unsupported colorspace. Allow drivers to pass the list of supported colorspaces when creating the colorspace property. v2: - Use 0 to indicate support for all colorspaces (Jani) - Print drm_dbg_kms message when drivers pass 0 to signal that drivers should specify supported colorspaecs explicity (Jani) v3: - Move changes to create a common colorspace_names array to separate patch v6: - Avoid magic when passing 0 for supported_colorspaces; be explicit in treating it as "all DP/HDMI" Signed-off-by: Harry Wentland Reviewed-by: Sebastian Wick Reviewed-by: Joshua Ashton Reviewed-by: Simon Ser Cc: Pekka Paalanen Cc: Sebastian Wick Cc: Vitaly.Prosyak@amd.com Cc: Uma Shankar Cc: Ville Syrjälä Cc: Joshua Ashton Cc: Jani Nikula Cc: Simon Ser Cc: Melissa Wen Cc: dri-devel@lists.freedesktop.org Cc: amd-gfx@lists.freedesktop.org Signed-off-by: Alex Deucher --- drivers/gpu/drm/drm_connector.c | 24 ++++++++++++++++++++---- drivers/gpu/drm/i915/display/intel_connector.c | 4 ++-- drivers/gpu/drm/vc4/vc4_hdmi.c | 2 +- include/drm/drm_connector.h | 7 +++++-- 4 files changed, 28 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index e1d7a40e1776..3ed4cfcb350c 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -2210,9 +2210,17 @@ static int drm_mode_create_colorspace_property(struct drm_connector *connector, * Returns: * Zero on success, negative errno on failure. */ -int drm_mode_create_hdmi_colorspace_property(struct drm_connector *connector) +int drm_mode_create_hdmi_colorspace_property(struct drm_connector *connector, + u32 supported_colorspaces) { - return drm_mode_create_colorspace_property(connector, hdmi_colorspaces); + u32 colorspaces; + + if (supported_colorspaces) + colorspaces = supported_colorspaces & hdmi_colorspaces; + else + colorspaces = hdmi_colorspaces; + + return drm_mode_create_colorspace_property(connector, colorspaces); } EXPORT_SYMBOL(drm_mode_create_hdmi_colorspace_property); @@ -2226,9 +2234,17 @@ EXPORT_SYMBOL(drm_mode_create_hdmi_colorspace_property); * Returns: * Zero on success, negative errno on failure. */ -int drm_mode_create_dp_colorspace_property(struct drm_connector *connector) +int drm_mode_create_dp_colorspace_property(struct drm_connector *connector, + u32 supported_colorspaces) { - return drm_mode_create_colorspace_property(connector, dp_colorspaces); + u32 colorspaces; + + if (supported_colorspaces) + colorspaces = supported_colorspaces & dp_colorspaces; + else + colorspaces = dp_colorspaces; + + return drm_mode_create_colorspace_property(connector, colorspaces); } EXPORT_SYMBOL(drm_mode_create_dp_colorspace_property); diff --git a/drivers/gpu/drm/i915/display/intel_connector.c b/drivers/gpu/drm/i915/display/intel_connector.c index 257afac34839..3abfe29d0b44 100644 --- a/drivers/gpu/drm/i915/display/intel_connector.c +++ b/drivers/gpu/drm/i915/display/intel_connector.c @@ -280,14 +280,14 @@ intel_attach_aspect_ratio_property(struct drm_connector *connector) void intel_attach_hdmi_colorspace_property(struct drm_connector *connector) { - if (!drm_mode_create_hdmi_colorspace_property(connector)) + if (!drm_mode_create_hdmi_colorspace_property(connector, 0)) drm_connector_attach_colorspace_property(connector); } void intel_attach_dp_colorspace_property(struct drm_connector *connector) { - if (!drm_mode_create_dp_colorspace_property(connector)) + if (!drm_mode_create_dp_colorspace_property(connector, 0)) drm_connector_attach_colorspace_property(connector); } diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 06713d8b82b5..482397d5cb48 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -631,7 +631,7 @@ static int vc4_hdmi_connector_init(struct drm_device *dev, if (ret) return ret; - ret = drm_mode_create_hdmi_colorspace_property(connector); + ret = drm_mode_create_hdmi_colorspace_property(connector, 0); if (ret) return ret; diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 880220321867..3cea00346205 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -30,6 +30,7 @@ #include #include #include +#include #include @@ -1994,8 +1995,10 @@ int drm_connector_attach_hdr_output_metadata_property(struct drm_connector *conn bool drm_connector_atomic_hdr_metadata_equal(struct drm_connector_state *old_state, struct drm_connector_state *new_state); int drm_mode_create_aspect_ratio_property(struct drm_device *dev); -int drm_mode_create_hdmi_colorspace_property(struct drm_connector *connector); -int drm_mode_create_dp_colorspace_property(struct drm_connector *connector); +int drm_mode_create_hdmi_colorspace_property(struct drm_connector *connector, + u32 supported_colorspaces); +int drm_mode_create_dp_colorspace_property(struct drm_connector *connector, + u32 supported_colorspaces); int drm_mode_create_content_type_property(struct drm_device *dev); int drm_mode_create_suggested_offset_properties(struct drm_device *dev); -- cgit v1.2.3 From 9d65b1b4bcf3918164e17365eec169875eef8ee3 Mon Sep 17 00:00:00 2001 From: Shiwu Zhang Date: Tue, 23 May 2023 12:02:32 +0800 Subject: drm/amdgpu: add the accelerator PCIe class Add the accelerator PCIe class and match the class in amdgpu for 0x1002 devices of that class. From PCI spec: "PCI Code and ID Assignment, r1.9, sec 1, 1.19" Signed-off-by: Shiwu Zhang Acked-by: Lijo Lazar Acked-by: Bjorn Helgaas # pci_ids.h Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 2 +- drivers/gpu/drm/amd/include/amd_shared.h | 1 - include/linux/pci_ids.h | 3 +++ 4 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index b8a1e4571cd9..8e58d187b173 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2044,7 +2044,7 @@ static const struct pci_device_id pciidlist[] = { .driver_data = CHIP_IP_DISCOVERY }, { PCI_DEVICE(0x1002, PCI_ANY_ID), - .class = AMD_ACCELERATOR_PROCESSING << 8, + .class = PCI_CLASS_ACCELERATOR_PROCESSING << 8, .class_mask = 0xffffff, .driver_data = CHIP_IP_DISCOVERY }, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 0f1ca0136f50..25b4d7f0bd35 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -57,7 +57,7 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev) /* enable virtual display */ if (adev->asic_type != CHIP_ALDEBARAN && adev->asic_type != CHIP_ARCTURUS && - ((adev->pdev->class >> 8) != AMD_ACCELERATOR_PROCESSING)) { + ((adev->pdev->class >> 8) != PCI_CLASS_ACCELERATOR_PROCESSING)) { if (adev->mode_info.num_crtc == 0) adev->mode_info.num_crtc = 1; adev->enable_virtual_display = true; diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 57d95e2cc54b..f175e65b853a 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -27,7 +27,6 @@ #define AMD_MAX_USEC_TIMEOUT 1000000 /* 1000 ms */ -#define AMD_ACCELERATOR_PROCESSING 0x1200 /* hardcoded pci class */ /* * Chip flags diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 45c3d62e616d..0fbfbda3dc26 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -151,6 +151,9 @@ #define PCI_CLASS_SP_DPIO 0x1100 #define PCI_CLASS_SP_OTHER 0x1180 +#define PCI_BASE_CLASS_ACCELERATOR 0x12 +#define PCI_CLASS_ACCELERATOR_PROCESSING 0x1200 + #define PCI_CLASS_OTHERS 0xff /* Vendors and devices. Sort key: vendor first, device next. */ -- cgit v1.2.3