This is a note to let you know that I've just added the patch titled drm/amdgpu: Increase tlb flush timeout for sriov to the 5.19-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: drm-amdgpu-increase-tlb-flush-timeout-for-sriov.patch and it can be found in the queue-5.19 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. commit 5012463e2cbbb2674d2426b1b85efdda5eddca5e Author: Dusica Milinkovic <Dusica.Milinkovic@xxxxxxx> Date: Wed Aug 10 09:43:15 2022 +0200 drm/amdgpu: Increase tlb flush timeout for sriov [ Upstream commit 373008bfc9cdb0f050258947fa5a095f0657e1bc ] [Why] During multi-vf executing benchmark (Luxmark) observed kiq error timeout. It happenes because all of VFs do the tlb invalidation at the same time. Although each VF has the invalidate register set, from hardware side the invalidate requests are queue to execute. [How] In case of 12 VF increase timeout on 12*100ms Signed-off-by: Dusica Milinkovic <Dusica.Milinkovic@xxxxxxx> Acked-by: Shaoyun Liu <shaoyun.liu@xxxxxxx> Acked-by: Alex Deucher <alexander.deucher@xxxxxxx> Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx> Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 30ce6bb6fa77a..310754b1f6702 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -313,7 +313,7 @@ enum amdgpu_kiq_irq { AMDGPU_CP_KIQ_IRQ_DRIVER0 = 0, AMDGPU_CP_KIQ_IRQ_LAST }; - +#define SRIOV_USEC_TIMEOUT 1200000 /* wait 12 * 100ms for SRIOV */ #define MAX_KIQ_REG_WAIT 5000 /* in usecs, 5ms */ #define MAX_KIQ_REG_BAILOUT_INTERVAL 5 /* in msecs, 5ms */ #define MAX_KIQ_REG_TRY 1000 diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 9077dfccaf3cf..809408c8c79a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -416,6 +416,7 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint32_t seq; uint16_t queried_pasid; bool ret; + u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT : adev->usec_timeout; struct amdgpu_ring *ring = &adev->gfx.kiq.ring; struct amdgpu_kiq *kiq = &adev->gfx.kiq; @@ -434,7 +435,7 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev, amdgpu_ring_commit(ring); spin_unlock(&adev->gfx.kiq.ring_lock); - r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout); + r = amdgpu_fence_wait_polling(ring, seq, usec_timeout); if (r < 1) { dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r); return -ETIME; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 22761a3bb8181..566c1243c051b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -896,6 +896,7 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint32_t seq; uint16_t queried_pasid; bool ret; + u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT : adev->usec_timeout; struct amdgpu_ring *ring = &adev->gfx.kiq.ring; struct amdgpu_kiq *kiq = &adev->gfx.kiq; @@ -935,7 +936,7 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev, amdgpu_ring_commit(ring); spin_unlock(&adev->gfx.kiq.ring_lock); - r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout); + r = amdgpu_fence_wait_polling(ring, seq, usec_timeout); if (r < 1) { dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r); up_read(&adev->reset_domain->sem);