[Patch V3] drm/amdgpu: Increase tlb flush timeout for sriov

[Liu, Shaoyun]

[AMD Official Use Only - General]

>From HW point of view , the  maximum VF number can reach 16  instead  of 12 . Although currently no product will use the 16 VFs  together,  not sure about the future.
You can added Acked-by me.  I will let Alex & Christion decide whether accept this change.

Regards
Shaoyun.liu



-----Original Message-----
From: amd-gfx <amd-gfx-bounces at lists.freedesktop.org> On Behalf Of Dusica Milinkovic
Sent: Thursday, August 11, 2022 6:01 AM
To: amd-gfx at lists.freedesktop.org
Cc: Milinkovic, Dusica <Dusica.Milinkovic at amd.com>
Subject: [Patch V3] drm/amdgpu: Increase tlb flush timeout for sriov

[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 at amd.com>
---
 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 5a639c857bd0..79bb6fd83094 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -320,7 +320,7 @@ 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);
--
2.25.1