[PATCH AUTOSEL 5.10 08/11] drm/amdgpu: Increase tlb flush timeout for sriov

From: Sasha Levin
Date: Wed Aug 24 2022 - 21:44:09 EST


From: Dusica Milinkovic <Dusica.Milinkovic@xxxxxxx>

[ 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>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 +-
drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 3 ++-
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 3 ++-
3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index d949d6c52f24..ff5555353eb4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -283,7 +283,7 @@ 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 80 /* 20 -> 80 */
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 150fa5258fb6..2aa9242c58ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -371,6 +371,7 @@ 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;

@@ -389,7 +390,7 @@ 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 3a864041968f..1673bf3bae55 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -839,6 +839,7 @@ 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;

@@ -878,7 +879,7 @@ 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_sem);
--
2.35.1