- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] ALSA: hda: Add missing NVIDIA HDA codec IDs" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x e0a911ac86857a73182edde9e50d9b4b949b7f01 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025071244-canon-whacky-600c@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e0a911ac86857a73182edde9e50d9b4b949b7f01 Mon Sep 17 00:00:00 2001 From: Daniel Dadap <ddadap(a)nvidia.com> Date: Thu, 26 Jun 2025 16:16:30 -0500 Subject: [PATCH] ALSA: hda: Add missing NVIDIA HDA codec IDs Add codec IDs for several NVIDIA products with HDA controllers to the snd_hda_id_hdmi[] patch table. Signed-off-by: Daniel Dadap <ddadap(a)nvidia.com> Cc: <stable(a)vger.kernel.org> Link: https://patch.msgid.link/aF24rqwMKFWoHu12@ddadap-lakeline.nvidia.com Signed-off-by: Takashi Iwai <tiwai(a)suse.de> diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 08308231b4ed..9a7793eb16e9 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4551,7 +4551,9 @@ HDA_CODEC_ENTRY(0x10de002e, "Tegra186 HDMI/DP1", patch_tegra_hdmi), HDA_CODEC_ENTRY(0x10de002f, "Tegra194 HDMI/DP2", patch_tegra_hdmi), HDA_CODEC_ENTRY(0x10de0030, "Tegra194 HDMI/DP3", patch_tegra_hdmi), HDA_CODEC_ENTRY(0x10de0031, "Tegra234 HDMI/DP", patch_tegra234_hdmi), +HDA_CODEC_ENTRY(0x10de0033, "SoC 33 HDMI/DP", patch_tegra234_hdmi), HDA_CODEC_ENTRY(0x10de0034, "Tegra264 HDMI/DP", patch_tegra234_hdmi), +HDA_CODEC_ENTRY(0x10de0035, "SoC 35 HDMI/DP", patch_tegra234_hdmi), HDA_CODEC_ENTRY(0x10de0040, "GPU 40 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0041, "GPU 41 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0042, "GPU 42 HDMI/DP", patch_nvhdmi), @@ -4590,15 +4592,32 @@ HDA_CODEC_ENTRY(0x10de0097, "GPU 97 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0098, "GPU 98 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0099, "GPU 99 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009a, "GPU 9a HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de009b, "GPU 9b HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de009c, "GPU 9c HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a1, "GPU a1 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a3, "GPU a3 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a4, "GPU a4 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a5, "GPU a5 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a6, "GPU a6 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a7, "GPU a7 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a8, "GPU a8 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a9, "GPU a9 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00aa, "GPU aa HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00ab, "GPU ab HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00ad, "GPU ad HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00ae, "GPU ae HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00af, "GPU af HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00b0, "GPU b0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00b1, "GPU b1 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c0, "GPU c0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c1, "GPU c1 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c3, "GPU c3 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c4, "GPU c4 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c5, "GPU c5 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x67663d82, "Arise 82 HDMI/DP", patch_gf_hdmi),

4 months

3
4
0 0

FAILED: patch "[PATCH] drm/amdgpu: Fix SDMA engine reset with logical instance ID" failed to apply to 6.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.15.y git checkout FETCH_HEAD git cherry-pick -x 09b585592fa481384597c81388733aed4a04dd05 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025063022-wham-parachute-8574@gregkh' --subject-prefix 'PATCH 6.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 09b585592fa481384597c81388733aed4a04dd05 Mon Sep 17 00:00:00 2001 From: Jesse Zhang <jesse.zhang(a)amd.com> Date: Wed, 11 Jun 2025 15:02:09 +0800 Subject: [PATCH] drm/amdgpu: Fix SDMA engine reset with logical instance ID This commit makes the following improvements to SDMA engine reset handling: 1. Clarifies in the function documentation that instance_id refers to a logical ID 2. Adds conversion from logical to physical instance ID before performing reset using GET_INST(SDMA0, instance_id) macro 3. Improves error messaging to indicate when a logical instance reset fails 4. Adds better code organization with blank lines for readability The change ensures proper SDMA engine reset by using the correct physical instance ID while maintaining the logical ID interface for callers. V2: Remove harvest_config check and convert directly to physical instance (Lijo) Suggested-by: Jonathan Kim <jonathan.kim(a)amd.com> Signed-off-by: Jesse Zhang <Jesse.Zhang(a)amd.com> Reviewed-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> (cherry picked from commit 5efa6217c239ed1ceec0f0414f9b6f6927387dfc) Cc: stable(a)vger.kernel.org diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c index 6716ac281c49..9b54a1ece447 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c @@ -540,8 +540,10 @@ static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id) case IP_VERSION(4, 4, 2): case IP_VERSION(4, 4, 4): case IP_VERSION(4, 4, 5): - /* For SDMA 4.x, use the existing DPM interface for backward compatibility */ - r = amdgpu_dpm_reset_sdma(adev, 1 << instance_id); + /* For SDMA 4.x, use the existing DPM interface for backward compatibility, + * we need to convert the logical instance ID to physical instance ID before reset. + */ + r = amdgpu_dpm_reset_sdma(adev, 1 << GET_INST(SDMA0, instance_id)); break; case IP_VERSION(5, 0, 0): case IP_VERSION(5, 0, 1): @@ -568,7 +570,7 @@ static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id) /** * amdgpu_sdma_reset_engine - Reset a specific SDMA engine * @adev: Pointer to the AMDGPU device - * @instance_id: ID of the SDMA engine instance to reset + * @instance_id: Logical ID of the SDMA engine instance to reset * * Returns: 0 on success, or a negative error code on failure. */ @@ -601,7 +603,7 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id) /* Perform the SDMA reset for the specified instance */ ret = amdgpu_sdma_soft_reset(adev, instance_id); if (ret) { - dev_err(adev->dev, "Failed to reset SDMA instance %u\n", instance_id); + dev_err(adev->dev, "Failed to reset SDMA logical instance %u\n", instance_id); goto exit; }

4 months

2
3
0 0

FAILED: patch "[PATCH] drm/amdkfd: Don't call mmput from MMU notifier callback" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x cf234231fcbc7d391e2135b9518613218cc5347f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025071256-province-work-ddbd@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From cf234231fcbc7d391e2135b9518613218cc5347f Mon Sep 17 00:00:00 2001 From: Philip Yang <Philip.Yang(a)amd.com> Date: Fri, 20 Jun 2025 18:32:32 -0400 Subject: [PATCH] drm/amdkfd: Don't call mmput from MMU notifier callback If the process is exiting, the mmput inside mmu notifier callback from compactd or fork or numa balancing could release the last reference of mm struct to call exit_mmap and free_pgtable, this triggers deadlock with below backtrace. The deadlock will leak kfd process as mmu notifier release is not called and cause VRAM leaking. The fix is to take mm reference mmget_non_zero when adding prange to the deferred list to pair with mmput in deferred list work. If prange split and add into pchild list, the pchild work_item.mm is not used, so remove the mm parameter from svm_range_unmap_split and svm_range_add_child. The backtrace of hung task: INFO: task python:348105 blocked for more than 64512 seconds. Call Trace: __schedule+0x1c3/0x550 schedule+0x46/0xb0 rwsem_down_write_slowpath+0x24b/0x4c0 unlink_anon_vmas+0xb1/0x1c0 free_pgtables+0xa9/0x130 exit_mmap+0xbc/0x1a0 mmput+0x5a/0x140 svm_range_cpu_invalidate_pagetables+0x2b/0x40 [amdgpu] mn_itree_invalidate+0x72/0xc0 __mmu_notifier_invalidate_range_start+0x48/0x60 try_to_unmap_one+0x10fa/0x1400 rmap_walk_anon+0x196/0x460 try_to_unmap+0xbb/0x210 migrate_page_unmap+0x54d/0x7e0 migrate_pages_batch+0x1c3/0xae0 migrate_pages_sync+0x98/0x240 migrate_pages+0x25c/0x520 compact_zone+0x29d/0x590 compact_zone_order+0xb6/0xf0 try_to_compact_pages+0xbe/0x220 __alloc_pages_direct_compact+0x96/0x1a0 __alloc_pages_slowpath+0x410/0x930 __alloc_pages_nodemask+0x3a9/0x3e0 do_huge_pmd_anonymous_page+0xd7/0x3e0 __handle_mm_fault+0x5e3/0x5f0 handle_mm_fault+0xf7/0x2e0 hmm_vma_fault.isra.0+0x4d/0xa0 walk_pmd_range.isra.0+0xa8/0x310 walk_pud_range+0x167/0x240 walk_pgd_range+0x55/0x100 __walk_page_range+0x87/0x90 walk_page_range+0xf6/0x160 hmm_range_fault+0x4f/0x90 amdgpu_hmm_range_get_pages+0x123/0x230 [amdgpu] amdgpu_ttm_tt_get_user_pages+0xb1/0x150 [amdgpu] init_user_pages+0xb1/0x2a0 [amdgpu] amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x543/0x7d0 [amdgpu] kfd_ioctl_alloc_memory_of_gpu+0x24c/0x4e0 [amdgpu] kfd_ioctl+0x29d/0x500 [amdgpu] Fixes: fa582c6f3684 ("drm/amdkfd: Use mmget_not_zero in MMU notifier") Signed-off-by: Philip Yang <Philip.Yang(a)amd.com> Reviewed-by: Felix Kuehling <felix.kuehling(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> (cherry picked from commit a29e067bd38946f752b0ef855f3dfff87e77bec7) Cc: stable(a)vger.kernel.org diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 7763e4742080..a0f22ea6d15a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1171,13 +1171,12 @@ svm_range_split_head(struct svm_range *prange, uint64_t new_start, } static void -svm_range_add_child(struct svm_range *prange, struct mm_struct *mm, - struct svm_range *pchild, enum svm_work_list_ops op) +svm_range_add_child(struct svm_range *prange, struct svm_range *pchild, enum svm_work_list_ops op) { pr_debug("add child 0x%p [0x%lx 0x%lx] to prange 0x%p child list %d\n", pchild, pchild->start, pchild->last, prange, op); - pchild->work_item.mm = mm; + pchild->work_item.mm = NULL; pchild->work_item.op = op; list_add_tail(&pchild->child_list, &prange->child_list); } @@ -2394,15 +2393,17 @@ svm_range_add_list_work(struct svm_range_list *svms, struct svm_range *prange, prange->work_item.op != SVM_OP_UNMAP_RANGE) prange->work_item.op = op; } else { - prange->work_item.op = op; - - /* Pairs with mmput in deferred_list_work */ - mmget(mm); - prange->work_item.mm = mm; - list_add_tail(&prange->deferred_list, - &prange->svms->deferred_range_list); - pr_debug("add prange 0x%p [0x%lx 0x%lx] to work list op %d\n", - prange, prange->start, prange->last, op); + /* Pairs with mmput in deferred_list_work. + * If process is exiting and mm is gone, don't update mmu notifier. + */ + if (mmget_not_zero(mm)) { + prange->work_item.mm = mm; + prange->work_item.op = op; + list_add_tail(&prange->deferred_list, + &prange->svms->deferred_range_list); + pr_debug("add prange 0x%p [0x%lx 0x%lx] to work list op %d\n", + prange, prange->start, prange->last, op); + } } spin_unlock(&svms->deferred_list_lock); } @@ -2416,8 +2417,7 @@ void schedule_deferred_list_work(struct svm_range_list *svms) } static void -svm_range_unmap_split(struct mm_struct *mm, struct svm_range *parent, - struct svm_range *prange, unsigned long start, +svm_range_unmap_split(struct svm_range *parent, struct svm_range *prange, unsigned long start, unsigned long last) { struct svm_range *head; @@ -2438,12 +2438,12 @@ svm_range_unmap_split(struct mm_struct *mm, struct svm_range *parent, svm_range_split(tail, last + 1, tail->last, &head); if (head != prange && tail != prange) { - svm_range_add_child(parent, mm, head, SVM_OP_UNMAP_RANGE); - svm_range_add_child(parent, mm, tail, SVM_OP_ADD_RANGE); + svm_range_add_child(parent, head, SVM_OP_UNMAP_RANGE); + svm_range_add_child(parent, tail, SVM_OP_ADD_RANGE); } else if (tail != prange) { - svm_range_add_child(parent, mm, tail, SVM_OP_UNMAP_RANGE); + svm_range_add_child(parent, tail, SVM_OP_UNMAP_RANGE); } else if (head != prange) { - svm_range_add_child(parent, mm, head, SVM_OP_UNMAP_RANGE); + svm_range_add_child(parent, head, SVM_OP_UNMAP_RANGE); } else if (parent != prange) { prange->work_item.op = SVM_OP_UNMAP_RANGE; } @@ -2520,14 +2520,14 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange, l = min(last, pchild->last); if (l >= s) svm_range_unmap_from_gpus(pchild, s, l, trigger); - svm_range_unmap_split(mm, prange, pchild, start, last); + svm_range_unmap_split(prange, pchild, start, last); mutex_unlock(&pchild->lock); } s = max(start, prange->start); l = min(last, prange->last); if (l >= s) svm_range_unmap_from_gpus(prange, s, l, trigger); - svm_range_unmap_split(mm, prange, prange, start, last); + svm_range_unmap_split(prange, prange, start, last); if (unmap_parent) svm_range_add_list_work(svms, prange, mm, SVM_OP_UNMAP_RANGE); @@ -2570,8 +2570,6 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni, if (range->event == MMU_NOTIFY_RELEASE) return true; - if (!mmget_not_zero(mni->mm)) - return true; start = mni->interval_tree.start; last = mni->interval_tree.last; @@ -2598,7 +2596,6 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni, } svm_range_unlock(prange); - mmput(mni->mm); return true; }

4 months

2
1
0 0

FAILED: patch "[PATCH] drm/amdkfd: Don't call mmput from MMU notifier callback" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x cf234231fcbc7d391e2135b9518613218cc5347f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025071252-fountain-preacher-2c65@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From cf234231fcbc7d391e2135b9518613218cc5347f Mon Sep 17 00:00:00 2001 From: Philip Yang <Philip.Yang(a)amd.com> Date: Fri, 20 Jun 2025 18:32:32 -0400 Subject: [PATCH] drm/amdkfd: Don't call mmput from MMU notifier callback If the process is exiting, the mmput inside mmu notifier callback from compactd or fork or numa balancing could release the last reference of mm struct to call exit_mmap and free_pgtable, this triggers deadlock with below backtrace. The deadlock will leak kfd process as mmu notifier release is not called and cause VRAM leaking. The fix is to take mm reference mmget_non_zero when adding prange to the deferred list to pair with mmput in deferred list work. If prange split and add into pchild list, the pchild work_item.mm is not used, so remove the mm parameter from svm_range_unmap_split and svm_range_add_child. The backtrace of hung task: INFO: task python:348105 blocked for more than 64512 seconds. Call Trace: __schedule+0x1c3/0x550 schedule+0x46/0xb0 rwsem_down_write_slowpath+0x24b/0x4c0 unlink_anon_vmas+0xb1/0x1c0 free_pgtables+0xa9/0x130 exit_mmap+0xbc/0x1a0 mmput+0x5a/0x140 svm_range_cpu_invalidate_pagetables+0x2b/0x40 [amdgpu] mn_itree_invalidate+0x72/0xc0 __mmu_notifier_invalidate_range_start+0x48/0x60 try_to_unmap_one+0x10fa/0x1400 rmap_walk_anon+0x196/0x460 try_to_unmap+0xbb/0x210 migrate_page_unmap+0x54d/0x7e0 migrate_pages_batch+0x1c3/0xae0 migrate_pages_sync+0x98/0x240 migrate_pages+0x25c/0x520 compact_zone+0x29d/0x590 compact_zone_order+0xb6/0xf0 try_to_compact_pages+0xbe/0x220 __alloc_pages_direct_compact+0x96/0x1a0 __alloc_pages_slowpath+0x410/0x930 __alloc_pages_nodemask+0x3a9/0x3e0 do_huge_pmd_anonymous_page+0xd7/0x3e0 __handle_mm_fault+0x5e3/0x5f0 handle_mm_fault+0xf7/0x2e0 hmm_vma_fault.isra.0+0x4d/0xa0 walk_pmd_range.isra.0+0xa8/0x310 walk_pud_range+0x167/0x240 walk_pgd_range+0x55/0x100 __walk_page_range+0x87/0x90 walk_page_range+0xf6/0x160 hmm_range_fault+0x4f/0x90 amdgpu_hmm_range_get_pages+0x123/0x230 [amdgpu] amdgpu_ttm_tt_get_user_pages+0xb1/0x150 [amdgpu] init_user_pages+0xb1/0x2a0 [amdgpu] amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x543/0x7d0 [amdgpu] kfd_ioctl_alloc_memory_of_gpu+0x24c/0x4e0 [amdgpu] kfd_ioctl+0x29d/0x500 [amdgpu] Fixes: fa582c6f3684 ("drm/amdkfd: Use mmget_not_zero in MMU notifier") Signed-off-by: Philip Yang <Philip.Yang(a)amd.com> Reviewed-by: Felix Kuehling <felix.kuehling(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> (cherry picked from commit a29e067bd38946f752b0ef855f3dfff87e77bec7) Cc: stable(a)vger.kernel.org diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 7763e4742080..a0f22ea6d15a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1171,13 +1171,12 @@ svm_range_split_head(struct svm_range *prange, uint64_t new_start, } static void -svm_range_add_child(struct svm_range *prange, struct mm_struct *mm, - struct svm_range *pchild, enum svm_work_list_ops op) +svm_range_add_child(struct svm_range *prange, struct svm_range *pchild, enum svm_work_list_ops op) { pr_debug("add child 0x%p [0x%lx 0x%lx] to prange 0x%p child list %d\n", pchild, pchild->start, pchild->last, prange, op); - pchild->work_item.mm = mm; + pchild->work_item.mm = NULL; pchild->work_item.op = op; list_add_tail(&pchild->child_list, &prange->child_list); } @@ -2394,15 +2393,17 @@ svm_range_add_list_work(struct svm_range_list *svms, struct svm_range *prange, prange->work_item.op != SVM_OP_UNMAP_RANGE) prange->work_item.op = op; } else { - prange->work_item.op = op; - - /* Pairs with mmput in deferred_list_work */ - mmget(mm); - prange->work_item.mm = mm; - list_add_tail(&prange->deferred_list, - &prange->svms->deferred_range_list); - pr_debug("add prange 0x%p [0x%lx 0x%lx] to work list op %d\n", - prange, prange->start, prange->last, op); + /* Pairs with mmput in deferred_list_work. + * If process is exiting and mm is gone, don't update mmu notifier. + */ + if (mmget_not_zero(mm)) { + prange->work_item.mm = mm; + prange->work_item.op = op; + list_add_tail(&prange->deferred_list, + &prange->svms->deferred_range_list); + pr_debug("add prange 0x%p [0x%lx 0x%lx] to work list op %d\n", + prange, prange->start, prange->last, op); + } } spin_unlock(&svms->deferred_list_lock); } @@ -2416,8 +2417,7 @@ void schedule_deferred_list_work(struct svm_range_list *svms) } static void -svm_range_unmap_split(struct mm_struct *mm, struct svm_range *parent, - struct svm_range *prange, unsigned long start, +svm_range_unmap_split(struct svm_range *parent, struct svm_range *prange, unsigned long start, unsigned long last) { struct svm_range *head; @@ -2438,12 +2438,12 @@ svm_range_unmap_split(struct mm_struct *mm, struct svm_range *parent, svm_range_split(tail, last + 1, tail->last, &head); if (head != prange && tail != prange) { - svm_range_add_child(parent, mm, head, SVM_OP_UNMAP_RANGE); - svm_range_add_child(parent, mm, tail, SVM_OP_ADD_RANGE); + svm_range_add_child(parent, head, SVM_OP_UNMAP_RANGE); + svm_range_add_child(parent, tail, SVM_OP_ADD_RANGE); } else if (tail != prange) { - svm_range_add_child(parent, mm, tail, SVM_OP_UNMAP_RANGE); + svm_range_add_child(parent, tail, SVM_OP_UNMAP_RANGE); } else if (head != prange) { - svm_range_add_child(parent, mm, head, SVM_OP_UNMAP_RANGE); + svm_range_add_child(parent, head, SVM_OP_UNMAP_RANGE); } else if (parent != prange) { prange->work_item.op = SVM_OP_UNMAP_RANGE; } @@ -2520,14 +2520,14 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange, l = min(last, pchild->last); if (l >= s) svm_range_unmap_from_gpus(pchild, s, l, trigger); - svm_range_unmap_split(mm, prange, pchild, start, last); + svm_range_unmap_split(prange, pchild, start, last); mutex_unlock(&pchild->lock); } s = max(start, prange->start); l = min(last, prange->last); if (l >= s) svm_range_unmap_from_gpus(prange, s, l, trigger); - svm_range_unmap_split(mm, prange, prange, start, last); + svm_range_unmap_split(prange, prange, start, last); if (unmap_parent) svm_range_add_list_work(svms, prange, mm, SVM_OP_UNMAP_RANGE); @@ -2570,8 +2570,6 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni, if (range->event == MMU_NOTIFY_RELEASE) return true; - if (!mmget_not_zero(mni->mm)) - return true; start = mni->interval_tree.start; last = mni->interval_tree.last; @@ -2598,7 +2596,6 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni, } svm_range_unlock(prange); - mmput(mni->mm); return true; }

4 months

2
1
0 0

FAILED: patch "[PATCH] wifi: mt76: mt7921: prevent decap offload config before STA" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 7035a082348acf1d43ffb9ff735899f8e3863f8f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025071231-projector-jubilance-2909@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7035a082348acf1d43ffb9ff735899f8e3863f8f Mon Sep 17 00:00:00 2001 From: Deren Wu <deren.wu(a)mediatek.com> Date: Sun, 25 May 2025 14:11:22 +0800 Subject: [PATCH] wifi: mt76: mt7921: prevent decap offload config before STA initialization The decap offload configuration should only be applied after the STA has been successfully initialized. Attempting to configure it earlier can lead to corruption of the MAC configuration in the chip's hardware state. Add an early check for `msta->deflink.wcid.sta` to ensure the station peer is properly initialized before proceeding with decapsulation offload configuration. Cc: stable(a)vger.kernel.org Fixes: 24299fc869f7 ("mt76: mt7921: enable rx header traslation offload") Signed-off-by: Deren Wu <deren.wu(a)mediatek.com> Link: https://patch.msgid.link/f23a72ba7a3c1ad38ba9e13bb54ef21d6ef44ffb.174814985… Signed-off-by: Felix Fietkau <nbd(a)nbd.name> diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 1fffa43379b2..77f73ae1d7ec 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -1180,6 +1180,9 @@ static void mt7921_sta_set_decap_offload(struct ieee80211_hw *hw, struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv; struct mt792x_dev *dev = mt792x_hw_dev(hw); + if (!msta->deflink.wcid.sta) + return; + mt792x_mutex_acquire(dev); if (enabled)

4 months

2
1
0 0

[PATCH 6.1.y-cip 2/5] [PARTIAL BACKPORT]drm: Add an HPD poll helper to reschedule the poll work

by Nicusor Huhulea

From: Imre Deak <imre.deak(a)intel.com> Add a helper to reschedule drm_mode_config::output_poll_work after polling has been enabled for a connector (and needing a reschedule, since previously polling was disabled for all connectors and hence output_poll_work was not running). This is needed by the next patch fixing HPD polling on i915. CC: stable(a)vger.kernel.org # 6.4+ Cc: Dmitry Baryshkov <dmitry.baryshkov(a)linaro.org> Cc: dri-devel(a)lists.freedesktop.org Reviewed-by: Jouni Högander <jouni.hogander(a)intel.com> Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov(a)linaro.org> Signed-off-by: Imre Deak <imre.deak(a)intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20230822113015.41224-1-imre.d… (cherry picked from commit fe2352fd64029918174de4b460dfe6df0c6911cd) Signed-off-by: Rodrigo Vivi <rodrigo.vivi(a)intel.com> Partial-Backport-by: Nicusor Huhulea <nicusor.huhulea(a)siemens.com> --- drivers/gpu/drm/drm_probe_helper.c | 74 +++++++++++++++++++----------- include/drm/drm_probe_helper.h | 1 + 2 files changed, 49 insertions(+), 26 deletions(-) diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 0e5eadc6d44de..787f6699971f1 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -224,6 +224,26 @@ drm_connector_mode_valid(struct drm_connector *connector, } #define DRM_OUTPUT_POLL_PERIOD (10*HZ) +static void reschedule_output_poll_work(struct drm_device *dev) +{ + unsigned long delay = DRM_OUTPUT_POLL_PERIOD; + + if (dev->mode_config.delayed_event) + /* + * FIXME: + * + * Use short (1s) delay to handle the initial delayed event. + * This delay should not be needed, but Optimus/nouveau will + * fail in a mysterious way if the delayed event is handled as + * soon as possible like it is done in + * drm_helper_probe_single_connector_modes() in case the poll + * was enabled before. + */ + delay = HZ; + + schedule_delayed_work(&dev->mode_config.output_poll_work, delay); +} + /** * drm_kms_helper_poll_enable - re-enable output polling. * @dev: drm_device @@ -244,43 +264,45 @@ drm_connector_mode_valid(struct drm_connector *connector, */ void drm_kms_helper_poll_enable(struct drm_device *dev) { - bool poll = false; + struct drm_connector *connector; struct drm_connector_list_iter conn_iter; - unsigned long delay = DRM_OUTPUT_POLL_PERIOD; if (drm_WARN_ON_ONCE(dev, !dev->mode_config.poll_enabled) || !drm_kms_helper_poll || dev->mode_config.poll_running) return; - drm_connector_list_iter_begin(dev, &conn_iter); - drm_for_each_connector_iter(connector, &conn_iter) { - if (connector->polled & (DRM_CONNECTOR_POLL_CONNECT | - DRM_CONNECTOR_POLL_DISCONNECT)) - poll = true; - } - drm_connector_list_iter_end(&conn_iter); + if (drm_kms_helper_enable_hpd(dev) || + dev->mode_config.delayed_event) + reschedule_output_poll_work(dev); - if (dev->mode_config.delayed_event) { - /* - * FIXME: - * - * Use short (1s) delay to handle the initial delayed event. - * This delay should not be needed, but Optimus/nouveau will - * fail in a mysterious way if the delayed event is handled as - * soon as possible like it is done in - * drm_helper_probe_single_connector_modes() in case the poll - * was enabled before. - */ - poll = true; - delay = HZ; - } - - if (poll) - schedule_delayed_work(&dev->mode_config.output_poll_work, delay); + dev->mode_config.poll_running = true; } EXPORT_SYMBOL(drm_kms_helper_poll_enable); +/** + * drm_kms_helper_poll_reschedule - reschedule the output polling work + * @dev: drm_device + * + * This function reschedules the output polling work, after polling for a + * connector has been enabled. + * + * Drivers must call this helper after enabling polling for a connector by + * setting %DRM_CONNECTOR_POLL_CONNECT / %DRM_CONNECTOR_POLL_DISCONNECT flags + * in drm_connector::polled. Note that after disabling polling by clearing these + * flags for a connector will stop the output polling work automatically if + * the polling is disabled for all other connectors as well. + * + * The function can be called only after polling has been enabled by calling + * drm_kms_helper_poll_init() / drm_kms_helper_poll_enable(). + */ +void drm_kms_helper_poll_reschedule(struct drm_device *dev) +{ + if (dev->mode_config.poll_running) + reschedule_output_poll_work(dev); +} +EXPORT_SYMBOL(drm_kms_helper_poll_reschedule); + static enum drm_connector_status drm_helper_probe_detect_ctx(struct drm_connector *connector, bool force) { diff --git a/include/drm/drm_probe_helper.h b/include/drm/drm_probe_helper.h index 5880daa146240..429a85f38036a 100644 --- a/include/drm/drm_probe_helper.h +++ b/include/drm/drm_probe_helper.h @@ -25,6 +25,7 @@ void drm_kms_helper_connector_hotplug_event(struct drm_connector *connector); void drm_kms_helper_poll_disable(struct drm_device *dev); void drm_kms_helper_poll_enable(struct drm_device *dev); +void drm_kms_helper_poll_reschedule(struct drm_device *dev); bool drm_kms_helper_is_poll_worker(void); enum drm_mode_status drm_crtc_helper_mode_valid_fixed(struct drm_crtc *crtc, -- 2.39.2

4 months

3
2
0 0

FAILED: patch "[PATCH] powercap: intel_rapl: Do not change CLAMPING bit if ENABLE" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 964209202ebe1569c858337441e87ef0f9d71416 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025070818-buddhism-wikipedia-516a@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 964209202ebe1569c858337441e87ef0f9d71416 Mon Sep 17 00:00:00 2001 From: Zhang Rui <rui.zhang(a)intel.com> Date: Thu, 19 Jun 2025 15:13:40 +0800 Subject: [PATCH] powercap: intel_rapl: Do not change CLAMPING bit if ENABLE bit cannot be changed PL1 cannot be disabled on some platforms. The ENABLE bit is still set after software clears it. This behavior leads to a scenario where, upon user request to disable the Power Limit through the powercap sysfs, the ENABLE bit remains set while the CLAMPING bit is inadvertently cleared. According to the Intel Software Developer's Manual, the CLAMPING bit, "When set, allows the processor to go below the OS requested P states in order to maintain the power below specified Platform Power Limit value." Thus this means the system may operate at higher power levels than intended on such platforms. Enhance the code to check ENABLE bit after writing to it, and stop further processing if ENABLE bit cannot be changed. Reported-by: Srinivas Pandruvada <srinivas.pandruvada(a)linux.intel.com> Fixes: 2d281d8196e3 ("PowerCap: Introduce Intel RAPL power capping driver") Cc: All applicable <stable(a)vger.kernel.org> Signed-off-by: Zhang Rui <rui.zhang(a)intel.com> Link: https://patch.msgid.link/20250619071340.384782-1-rui.zhang@intel.com [ rjw: Use str_enabled_disabled() instead of open-coded equivalent ] Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index e3be40adc0d7..faa0b6bc5b53 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -341,12 +341,28 @@ static int set_domain_enable(struct powercap_zone *power_zone, bool mode) { struct rapl_domain *rd = power_zone_to_rapl_domain(power_zone); struct rapl_defaults *defaults = get_defaults(rd->rp); + u64 val; int ret; cpus_read_lock(); ret = rapl_write_pl_data(rd, POWER_LIMIT1, PL_ENABLE, mode); - if (!ret && defaults->set_floor_freq) + if (ret) + goto end; + + ret = rapl_read_pl_data(rd, POWER_LIMIT1, PL_ENABLE, false, &val); + if (ret) + goto end; + + if (mode != val) { + pr_debug("%s cannot be %s\n", power_zone->name, + str_enabled_disabled(mode)); + goto end; + } + + if (defaults->set_floor_freq) defaults->set_floor_freq(rd, mode); + +end: cpus_read_unlock(); return ret;

4 months

4
5
0 0

[PATCH] ASoC: mediatek: common: fix device and OF node leak

by Johan Hovold

Make sure to drop the references to the accdet OF node and platform device taken by of_parse_phandle() and of_find_device_by_node() after looking up the sound component during probe. Fixes: cf536e2622e2 ("ASoC: mediatek: common: Handle mediatek,accdet property") Cc: stable(a)vger.kernel.org # 6.15 Cc: Nícolas F. R. A. Prado <nfraprado(a)collabora.com> Signed-off-by: Johan Hovold <johan(a)kernel.org> --- sound/soc/mediatek/common/mtk-soundcard-driver.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/soc/mediatek/common/mtk-soundcard-driver.c b/sound/soc/mediatek/common/mtk-soundcard-driver.c index 713a368f79cf..95a083939f3e 100644 --- a/sound/soc/mediatek/common/mtk-soundcard-driver.c +++ b/sound/soc/mediatek/common/mtk-soundcard-driver.c @@ -262,9 +262,13 @@ int mtk_soundcard_common_probe(struct platform_device *pdev) soc_card_data->accdet = accdet_comp; else dev_err(&pdev->dev, "No sound component found from mediatek,accdet property\n"); + + put_device(&accdet_pdev->dev); } else { dev_err(&pdev->dev, "No device found from mediatek,accdet property\n"); } + + of_node_put(accdet_node); } platform_node = of_parse_phandle(pdev->dev.of_node, "mediatek,platform", 0); -- 2.49.1

4 months

2
1
0 0

FAILED: patch "[PATCH] ALSA: hda: Add missing NVIDIA HDA codec IDs" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y git checkout FETCH_HEAD git cherry-pick -x e0a911ac86857a73182edde9e50d9b4b949b7f01 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025071243-other-defy-2a7d@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e0a911ac86857a73182edde9e50d9b4b949b7f01 Mon Sep 17 00:00:00 2001 From: Daniel Dadap <ddadap(a)nvidia.com> Date: Thu, 26 Jun 2025 16:16:30 -0500 Subject: [PATCH] ALSA: hda: Add missing NVIDIA HDA codec IDs Add codec IDs for several NVIDIA products with HDA controllers to the snd_hda_id_hdmi[] patch table. Signed-off-by: Daniel Dadap <ddadap(a)nvidia.com> Cc: <stable(a)vger.kernel.org> Link: https://patch.msgid.link/aF24rqwMKFWoHu12@ddadap-lakeline.nvidia.com Signed-off-by: Takashi Iwai <tiwai(a)suse.de> diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 08308231b4ed..9a7793eb16e9 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4551,7 +4551,9 @@ HDA_CODEC_ENTRY(0x10de002e, "Tegra186 HDMI/DP1", patch_tegra_hdmi), HDA_CODEC_ENTRY(0x10de002f, "Tegra194 HDMI/DP2", patch_tegra_hdmi), HDA_CODEC_ENTRY(0x10de0030, "Tegra194 HDMI/DP3", patch_tegra_hdmi), HDA_CODEC_ENTRY(0x10de0031, "Tegra234 HDMI/DP", patch_tegra234_hdmi), +HDA_CODEC_ENTRY(0x10de0033, "SoC 33 HDMI/DP", patch_tegra234_hdmi), HDA_CODEC_ENTRY(0x10de0034, "Tegra264 HDMI/DP", patch_tegra234_hdmi), +HDA_CODEC_ENTRY(0x10de0035, "SoC 35 HDMI/DP", patch_tegra234_hdmi), HDA_CODEC_ENTRY(0x10de0040, "GPU 40 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0041, "GPU 41 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0042, "GPU 42 HDMI/DP", patch_nvhdmi), @@ -4590,15 +4592,32 @@ HDA_CODEC_ENTRY(0x10de0097, "GPU 97 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0098, "GPU 98 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0099, "GPU 99 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009a, "GPU 9a HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de009b, "GPU 9b HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de009c, "GPU 9c HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a1, "GPU a1 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a3, "GPU a3 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a4, "GPU a4 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a5, "GPU a5 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a6, "GPU a6 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a7, "GPU a7 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a8, "GPU a8 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a9, "GPU a9 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00aa, "GPU aa HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00ab, "GPU ab HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00ad, "GPU ad HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00ae, "GPU ae HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00af, "GPU af HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00b0, "GPU b0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00b1, "GPU b1 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c0, "GPU c0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c1, "GPU c1 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c3, "GPU c3 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c4, "GPU c4 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c5, "GPU c5 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x67663d82, "Arise 82 HDMI/DP", patch_gf_hdmi),

4 months

3
3
0 0

FAILED: patch "[PATCH] drm/xe: Make WA BB part of LRC BO" failed to apply to 6.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.15.y git checkout FETCH_HEAD git cherry-pick -x afcad92411772a1f361339f22c49f855c6cc7d0f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025071259-unrelated-extrovert-b5a9@gregkh' --subject-prefix 'PATCH 6.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From afcad92411772a1f361339f22c49f855c6cc7d0f Mon Sep 17 00:00:00 2001 From: Matthew Brost <matthew.brost(a)intel.com> Date: Wed, 11 Jun 2025 20:19:25 -0700 Subject: [PATCH] drm/xe: Make WA BB part of LRC BO No idea why, but without this GuC context switches randomly fail when running IGTs in a loop. Need to follow up why this fixes the aforementioned issue but can live with a stable driver for now. Fixes: 617d824c5323 ("drm/xe: Add WA BB to capture active context utilization") Cc: stable(a)vger.kernel.org Signed-off-by: Matthew Brost <matthew.brost(a)intel.com> Reviewed-by: Lucas De Marchi <lucas.demarchi(a)intel.com> Tested-by: Shuicheng Lin <shuicheng.lin(a)intel.com> Link: https://lore.kernel.org/r/20250612031925.4009701-1-matthew.brost@intel.com (cherry picked from commit 3a1edef8f4b58b0ba826bc68bf4bce4bdf59ecf3) Signed-off-by: Lucas De Marchi <lucas.demarchi(a)intel.com> diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index bf7c3981897d..6e7b70532d11 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -40,6 +40,7 @@ #define LRC_PPHWSP_SIZE SZ_4K #define LRC_INDIRECT_RING_STATE_SIZE SZ_4K +#define LRC_WA_BB_SIZE SZ_4K static struct xe_device * lrc_to_xe(struct xe_lrc *lrc) @@ -910,7 +911,11 @@ static void xe_lrc_finish(struct xe_lrc *lrc) { xe_hw_fence_ctx_finish(&lrc->fence_ctx); xe_bo_unpin_map_no_vm(lrc->bo); - xe_bo_unpin_map_no_vm(lrc->bb_per_ctx_bo); +} + +static size_t wa_bb_offset(struct xe_lrc *lrc) +{ + return lrc->bo->size - LRC_WA_BB_SIZE; } /* @@ -943,15 +948,16 @@ static void xe_lrc_finish(struct xe_lrc *lrc) #define CONTEXT_ACTIVE 1ULL static int xe_lrc_setup_utilization(struct xe_lrc *lrc) { + const size_t max_size = LRC_WA_BB_SIZE; u32 *cmd, *buf = NULL; - if (lrc->bb_per_ctx_bo->vmap.is_iomem) { - buf = kmalloc(lrc->bb_per_ctx_bo->size, GFP_KERNEL); + if (lrc->bo->vmap.is_iomem) { + buf = kmalloc(max_size, GFP_KERNEL); if (!buf) return -ENOMEM; cmd = buf; } else { - cmd = lrc->bb_per_ctx_bo->vmap.vaddr; + cmd = lrc->bo->vmap.vaddr + wa_bb_offset(lrc); } *cmd++ = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET; @@ -974,13 +980,14 @@ static int xe_lrc_setup_utilization(struct xe_lrc *lrc) *cmd++ = MI_BATCH_BUFFER_END; if (buf) { - xe_map_memcpy_to(gt_to_xe(lrc->gt), &lrc->bb_per_ctx_bo->vmap, 0, - buf, (cmd - buf) * sizeof(*cmd)); + xe_map_memcpy_to(gt_to_xe(lrc->gt), &lrc->bo->vmap, + wa_bb_offset(lrc), buf, + (cmd - buf) * sizeof(*cmd)); kfree(buf); } - xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR, - xe_bo_ggtt_addr(lrc->bb_per_ctx_bo) | 1); + xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR, xe_bo_ggtt_addr(lrc->bo) + + wa_bb_offset(lrc) + 1); return 0; } @@ -1018,20 +1025,13 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, * FIXME: Perma-pinning LRC as we don't yet support moving GGTT address * via VM bind calls. */ - lrc->bo = xe_bo_create_pin_map(xe, tile, NULL, lrc_size, + lrc->bo = xe_bo_create_pin_map(xe, tile, NULL, + lrc_size + LRC_WA_BB_SIZE, ttm_bo_type_kernel, bo_flags); if (IS_ERR(lrc->bo)) return PTR_ERR(lrc->bo); - lrc->bb_per_ctx_bo = xe_bo_create_pin_map(xe, tile, NULL, SZ_4K, - ttm_bo_type_kernel, - bo_flags); - if (IS_ERR(lrc->bb_per_ctx_bo)) { - err = PTR_ERR(lrc->bb_per_ctx_bo); - goto err_lrc_finish; - } - lrc->size = lrc_size; lrc->ring.size = ring_size; lrc->ring.tail = 0; @@ -1819,7 +1819,8 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc) snapshot->seqno = xe_lrc_seqno(lrc); snapshot->lrc_bo = xe_bo_get(lrc->bo); snapshot->lrc_offset = xe_lrc_pphwsp_offset(lrc); - snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset; + snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset - + LRC_WA_BB_SIZE; snapshot->lrc_snapshot = NULL; snapshot->ctx_timestamp = lower_32_bits(xe_lrc_ctx_timestamp(lrc)); snapshot->ctx_job_timestamp = xe_lrc_ctx_job_timestamp(lrc); diff --git a/drivers/gpu/drm/xe/xe_lrc_types.h b/drivers/gpu/drm/xe/xe_lrc_types.h index ae24cf6f8dd9..883e550a9423 100644 --- a/drivers/gpu/drm/xe/xe_lrc_types.h +++ b/drivers/gpu/drm/xe/xe_lrc_types.h @@ -53,9 +53,6 @@ struct xe_lrc { /** @ctx_timestamp: readout value of CTX_TIMESTAMP on last update */ u64 ctx_timestamp; - - /** @bb_per_ctx_bo: buffer object for per context batch wa buffer */ - struct xe_bo *bb_per_ctx_bo; }; struct xe_lrc_snapshot;

4 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror