From 6fea87637bf36bd285227f490132e83582ab7513 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Fri, 16 Dec 2022 17:12:53 +0800 Subject: [PATCH 1/8] drm/amd/pm: correct the reference clock for fan speed(rpm) calculation Correct the reference clock as 25Mhz for SMU13 fan speed calculation. Signed-off-by: Evan Quan Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.0.x, 6.1.x --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index e54b760b875b..d1f50d42288d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -1261,7 +1261,8 @@ int smu_v13_0_set_fan_speed_rpm(struct smu_context *smu, uint32_t speed) { struct amdgpu_device *adev = smu->adev; - uint32_t tach_period, crystal_clock_freq; + uint32_t crystal_clock_freq = 2500; + uint32_t tach_period; int ret; if (!speed) @@ -1271,7 +1272,6 @@ int smu_v13_0_set_fan_speed_rpm(struct smu_context *smu, if (ret) return ret; - crystal_clock_freq = amdgpu_asic_get_xclk(adev); tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed); WREG32_SOC15(THM, 0, regCG_TACH_CTRL, REG_SET_FIELD(RREG32_SOC15(THM, 0, regCG_TACH_CTRL), From 318ca20893c19ead02845a08204c3f9249bb74cd Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Wed, 4 Jan 2023 10:45:01 +0800 Subject: [PATCH 2/8] drm/amd/pm: add the missing mapping for PPT feature on SMU13.0.0 and 13.0.7 Then we are able to set a new ppt limit via the hwmon interface(power1_cap). Signed-off-by: Evan Quan Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.0.x, 6.1.x --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 1 + drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 9643b21c636a..4c20d17e7416 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -213,6 +213,7 @@ static struct cmn2asic_mapping smu_v13_0_0_feature_mask_map[SMU_FEATURE_COUNT] = FEA_MAP(SOC_PCC), [SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, [SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, + [SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT}, }; static struct cmn2asic_mapping smu_v13_0_0_table_map[SMU_TABLE_COUNT] = { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 5c6c6ad011ca..e87db7e02e8a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -192,6 +192,7 @@ static struct cmn2asic_mapping smu_v13_0_7_feature_mask_map[SMU_FEATURE_COUNT] = FEA_MAP(SOC_PCC), [SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, [SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, + [SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT}, }; static struct cmn2asic_mapping smu_v13_0_7_table_map[SMU_TABLE_COUNT] = { From 0be7ed8e7eb15282b5d0f6fdfea884db594ea9bf Mon Sep 17 00:00:00 2001 From: Luben Tuikov Date: Wed, 4 Jan 2023 17:09:02 -0500 Subject: [PATCH 3/8] drm/amdgpu: Fix potential NULL dereference MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix potential NULL dereference, in the case when "man", the resource manager might be NULL, when/if we print debug information. Cc: Alex Deucher Cc: Christian König Cc: AMD Graphics Cc: Dan Carpenter Cc: kernel test robot Fixes: 7554886daa31ea ("drm/amdgpu: Fix size validation for non-exclusive domains (v4)") Signed-off-by: Luben Tuikov Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 4e684c2afc70..25a68d8888e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -470,8 +470,9 @@ static bool amdgpu_bo_validate_size(struct amdgpu_device *adev, return true; fail: - DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size, - man->size); + if (man) + DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size, + man->size); return false; } From 1923bc5a56daeeabd7e9093bad2febcd6af2416a Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Tue, 27 Dec 2022 15:49:17 -0600 Subject: [PATCH 4/8] drm/amd: Delay removal of the firmware framebuffer Removing the firmware framebuffer from the driver means that even if the driver doesn't support the IP blocks in a GPU it will no longer be functional after the driver fails to initialize. This change will ensure that unsupported IP blocks at least cause the driver to work with the EFI framebuffer. Cc: stable@vger.kernel.org Suggested-by: Alex Deucher Reviewed-by: Alex Deucher Reviewed-by: Lijo Lazar Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 8 ++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 6 ------ 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index afe6af9c0138..2f28a8c02f64 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -36,6 +36,7 @@ #include #include +#include #include #include #include @@ -90,6 +91,8 @@ MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin"); #define AMDGPU_MAX_RETRY_LIMIT 2 #define AMDGPU_RETRY_SRIOV_RESET(r) ((r) == -EBUSY || (r) == -ETIMEDOUT || (r) == -EINVAL) +static const struct drm_driver amdgpu_kms_driver; + const char *amdgpu_asic_name[] = { "TAHITI", "PITCAIRN", @@ -3687,6 +3690,11 @@ int amdgpu_device_init(struct amdgpu_device *adev, if (r) return r; + /* Get rid of things like offb */ + r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver); + if (r) + return r; + /* Enable TMZ based on IP_VERSION */ amdgpu_gmc_tmz_set(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 1353ffd08988..cd4caaa29528 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -23,7 +23,6 @@ */ #include -#include #include #include #include @@ -2122,11 +2121,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, } #endif - /* Get rid of things like offb */ - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &amdgpu_kms_driver); - if (ret) - return ret; - adev = devm_drm_dev_alloc(&pdev->dev, &amdgpu_kms_driver, typeof(*adev), ddev); if (IS_ERR(adev)) return PTR_ERR(adev); From 99f1a36c90a7524972be5a028424c57fa17753ee Mon Sep 17 00:00:00 2001 From: YiPeng Chai Date: Fri, 6 Jan 2023 14:04:15 +0800 Subject: [PATCH 5/8] drm/amdgpu: Fixed bug on error when unloading amdgpu MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixed bug on error when unloading amdgpu. The error message is as follows: [ 377.706202] kernel BUG at drivers/gpu/drm/drm_buddy.c:278! [ 377.706215] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI [ 377.706222] CPU: 4 PID: 8610 Comm: modprobe Tainted: G IOE 6.0.0-thomas #1 [ 377.706231] Hardware name: ASUS System Product Name/PRIME Z390-A, BIOS 2004 11/02/2021 [ 377.706238] RIP: 0010:drm_buddy_free_block+0x26/0x30 [drm_buddy] [ 377.706264] Code: 00 00 00 90 0f 1f 44 00 00 48 8b 0e 89 c8 25 00 0c 00 00 3d 00 04 00 00 75 10 48 8b 47 18 48 d3 e0 48 01 47 28 e9 fa fe ff ff <0f> 0b 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 41 54 55 48 89 f5 53 [ 377.706282] RSP: 0018:ffffad2dc4683cb8 EFLAGS: 00010287 [ 377.706289] RAX: 0000000000000000 RBX: ffff8b1743bd5138 RCX: 0000000000000000 [ 377.706297] RDX: ffff8b1743bd5160 RSI: ffff8b1743bd5c78 RDI: ffff8b16d1b25f70 [ 377.706304] RBP: ffff8b1743bd59e0 R08: 0000000000000001 R09: 0000000000000001 [ 377.706311] R10: ffff8b16c8572400 R11: ffffad2dc4683cf0 R12: ffff8b16d1b25f70 [ 377.706318] R13: ffff8b16d1b25fd0 R14: ffff8b1743bd59c0 R15: ffff8b16d1b25f70 [ 377.706325] FS: 00007fec56c72c40(0000) GS:ffff8b1836500000(0000) knlGS:0000000000000000 [ 377.706334] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 377.706340] CR2: 00007f9b88c1ba50 CR3: 0000000110450004 CR4: 00000000003706e0 [ 377.706347] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.706354] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.706361] Call Trace: [ 377.706365] [ 377.706369] drm_buddy_free_list+0x2a/0x60 [drm_buddy] [ 377.706376] amdgpu_vram_mgr_fini+0xea/0x180 [amdgpu] [ 377.706572] amdgpu_ttm_fini+0x12e/0x1a0 [amdgpu] [ 377.706650] amdgpu_bo_fini+0x22/0x90 [amdgpu] [ 377.706727] gmc_v11_0_sw_fini+0x26/0x30 [amdgpu] [ 377.706821] amdgpu_device_fini_sw+0xa1/0x3c0 [amdgpu] [ 377.706897] amdgpu_driver_release_kms+0x12/0x30 [amdgpu] [ 377.706975] drm_dev_release+0x20/0x40 [drm] [ 377.707006] release_nodes+0x35/0xb0 [ 377.707014] devres_release_all+0x8b/0xc0 [ 377.707020] device_unbind_cleanup+0xe/0x70 [ 377.707027] device_release_driver_internal+0xee/0x160 [ 377.707033] driver_detach+0x44/0x90 [ 377.707039] bus_remove_driver+0x55/0xe0 [ 377.707045] pci_unregister_driver+0x3b/0x90 [ 377.707052] amdgpu_exit+0x11/0x6c [amdgpu] [ 377.707194] __x64_sys_delete_module+0x142/0x2b0 [ 377.707201] ? fpregs_assert_state_consistent+0x22/0x50 [ 377.707208] ? exit_to_user_mode_prepare+0x3e/0x190 [ 377.707215] do_syscall_64+0x38/0x90 [ 377.707221] entry_SYSCALL_64_after_hwframe+0x63/0xcd Signed-off-by: YiPeng Chai Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index faa12146635c..9fa1d814508a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -882,7 +882,7 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev) kfree(rsv); list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) { - drm_buddy_free_list(&mgr->mm, &rsv->blocks); + drm_buddy_free_list(&mgr->mm, &rsv->allocated); kfree(rsv); } drm_buddy_fini(&mgr->mm); From ba029e9991d9be90a28b6a0ceb25e9a6fb348829 Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Mon, 9 Jan 2023 14:16:42 -0500 Subject: [PATCH 6/8] drm/amdkfd: Add sync after creating vram bo There will be data corruption on vram allocated by svm if the initialization is not complete and application is writting on the memory. Adding sync to wait for the initialization completion is to resolve this issue. Signed-off-by: Eric Huang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 814f99888ab1..b94d2c1422ad 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -570,6 +570,15 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange, goto reserve_bo_failed; } + if (clear) { + r = amdgpu_bo_sync_wait(bo, AMDGPU_FENCE_OWNER_KFD, false); + if (r) { + pr_debug("failed %d to sync bo\n", r); + amdgpu_bo_unreserve(bo); + goto reserve_bo_failed; + } + } + r = dma_resv_reserve_fences(bo->tbo.base.resv, 1); if (r) { pr_debug("failed %d to reserve bo\n", r); From 972fb53d3605eb6cdf0d6ae9a52e910626a91ff7 Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Tue, 10 Jan 2023 11:33:44 +0800 Subject: [PATCH 7/8] drm/amd/pm/smu13: BACO is supported when it's in BACO state This leverages the logic in smu11. No need to talk to SMU to check BACO enablement as it's in BACO state already. Signed-off-by: Guchun Chen Reviewed-by: Kenneth Feng Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.0, 6.1 --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index d1f50d42288d..b4373b6568ae 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -2298,6 +2298,10 @@ bool smu_v13_0_baco_is_support(struct smu_context *smu) !smu_baco->platform_support) return false; + /* return true if ASIC is in BACO state already */ + if (smu_v13_0_baco_get_state(smu) == SMU_BACO_STATE_ENTER) + return true; + if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_BACO_BIT) && !smu_cmn_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT)) return false; From a6941f89d7c6a6ba49316bbd7da2fb2f719119a7 Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Thu, 5 Jan 2023 14:01:18 -0500 Subject: [PATCH 8/8] drm/amdkfd: Fix NULL pointer error for GC 11.0.1 on mGPU The point bo->kfd_bo is NULL for queue's write pointer BO when creating queue on mGPU. To avoid using the pointer fixes the error. Signed-off-by: Eric Huang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index b15091d8310d..3b5c53712d31 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -2099,7 +2099,7 @@ int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_b } amdgpu_amdkfd_remove_eviction_fence( - bo, bo->kfd_bo->process_info->eviction_fence); + bo, bo->vm_bo->vm->process_info->eviction_fence); amdgpu_bo_unreserve(bo); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index ecb4c3abc629..c06ada0844ba 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -200,7 +200,7 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, queue_input.wptr_addr = (uint64_t)q->properties.write_ptr; if (q->wptr_bo) { - wptr_addr_off = (uint64_t)q->properties.write_ptr - (uint64_t)q->wptr_bo->kfd_bo->va; + wptr_addr_off = (uint64_t)q->properties.write_ptr & (PAGE_SIZE - 1); queue_input.wptr_mc_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off; }