From 58d7e65e3f2a7540273e8f71b7f2de00286baa25 Mon Sep 17 00:00:00 2001
From: Dusica Milinkovic <Dusica.Milinkovic@amd.com>
Date: Wed, 10 Aug 2022 09:43:15 +0200
Subject: drm/amdgpu: Increase tlb flush timeout for sriov
Git-commit: 373008bfc9cdb0f050258947fa5a095f0657e1bc
Patch-mainline: v6.0-rc2
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225 jsc#PED-2849
[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@amd.com>
Acked-by: Shaoyun Liu <shaoyun.liu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
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 e146810c700b..d597e2656c47 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -317,7 +317,7 @@ 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 9ae8cdaa033e..f513e2c2e964 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -419,6 +419,7 @@ 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;
@@ -437,7 +438,7 @@ 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 ab89d91975ab..4603653916f5 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);
--
2.38.1