Re: [PATCH] drm/amdgpu/gfx10,11: use memcpy_to/fromio for MQDs

2023-10-27 Thread Christian König

Am 26.10.23 um 20:56 schrieb Alex Deucher:

Since they were moved to VRAM, we need to use the IO
variants of memcpy.

Fixes: 1cfb4d612127 ("drm/amdgpu: put MQDs in VRAM")
Signed-off-by: Alex Deucher 


Reviewed-by: Christian König 


---
  drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 12 ++--
  drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 12 ++--
  2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c 
b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 9032d7a24d7c..306252cd67fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -6457,11 +6457,11 @@ static int gfx_v10_0_gfx_init_queue(struct amdgpu_ring 
*ring)
nv_grbm_select(adev, 0, 0, 0, 0);
mutex_unlock(>srbm_mutex);
if (adev->gfx.me.mqd_backup[mqd_idx])
-   memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, 
sizeof(*mqd));
+   memcpy_fromio(adev->gfx.me.mqd_backup[mqd_idx], mqd, 
sizeof(*mqd));
} else {
/* restore mqd with the backup copy */
if (adev->gfx.me.mqd_backup[mqd_idx])
-   memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], 
sizeof(*mqd));
+   memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], 
sizeof(*mqd));
/* reset the ring */
ring->wptr = 0;
*ring->wptr_cpu_addr = 0;
@@ -6735,7 +6735,7 @@ static int gfx_v10_0_kiq_init_queue(struct amdgpu_ring 
*ring)
if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */
/* reset MQD to a clean status */
if (adev->gfx.kiq[0].mqd_backup)
-   memcpy(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd));
+   memcpy_toio(mqd, adev->gfx.kiq[0].mqd_backup, 
sizeof(*mqd));
  
  		/* reset ring buffer */

ring->wptr = 0;
@@ -6758,7 +6758,7 @@ static int gfx_v10_0_kiq_init_queue(struct amdgpu_ring 
*ring)
mutex_unlock(>srbm_mutex);
  
  		if (adev->gfx.kiq[0].mqd_backup)

-   memcpy(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd));
+   memcpy_fromio(adev->gfx.kiq[0].mqd_backup, mqd, 
sizeof(*mqd));
}
  
  	return 0;

@@ -6779,11 +6779,11 @@ static int gfx_v10_0_kcq_init_queue(struct amdgpu_ring 
*ring)
mutex_unlock(>srbm_mutex);
  
  		if (adev->gfx.mec.mqd_backup[mqd_idx])

-   memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, 
sizeof(*mqd));
+   memcpy_fromio(adev->gfx.mec.mqd_backup[mqd_idx], mqd, 
sizeof(*mqd));
} else {
/* restore MQD to a clean status */
if (adev->gfx.mec.mqd_backup[mqd_idx])
-   memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], 
sizeof(*mqd));
+   memcpy_toio(mqd, adev->gfx.mec.mqd_backup[mqd_idx], 
sizeof(*mqd));
/* reset ring buffer */
ring->wptr = 0;
atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c 
b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 762d7a19f1be..43d066bc5245 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -3684,11 +3684,11 @@ static int gfx_v11_0_gfx_init_queue(struct amdgpu_ring 
*ring)
soc21_grbm_select(adev, 0, 0, 0, 0);
mutex_unlock(>srbm_mutex);
if (adev->gfx.me.mqd_backup[mqd_idx])
-   memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, 
sizeof(*mqd));
+   memcpy_fromio(adev->gfx.me.mqd_backup[mqd_idx], mqd, 
sizeof(*mqd));
} else {
/* restore mqd with the backup copy */
if (adev->gfx.me.mqd_backup[mqd_idx])
-   memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], 
sizeof(*mqd));
+   memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], 
sizeof(*mqd));
/* reset the ring */
ring->wptr = 0;
*ring->wptr_cpu_addr = 0;
@@ -3977,7 +3977,7 @@ static int gfx_v11_0_kiq_init_queue(struct amdgpu_ring 
*ring)
if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */
/* reset MQD to a clean status */
if (adev->gfx.kiq[0].mqd_backup)
-   memcpy(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd));
+   memcpy_toio(mqd, adev->gfx.kiq[0].mqd_backup, 
sizeof(*mqd));
  
  		/* reset ring buffer */

ring->wptr = 0;
@@ -4000,7 +4000,7 @@ static int gfx_v11_0_kiq_init_queue(struct amdgpu_ring 
*ring)
mutex_unlock(>srbm_mutex);
  
  		if (adev->gfx.kiq[0].mqd_backup)

-   memcpy(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd));
+   memcpy_fromio(adev->gfx.kiq[0].mqd_backup, mqd, 
sizeof(*mqd));
}
  
  	return 0;


[PATCH] drm/amdgpu/gfx10,11: use memcpy_to/fromio for MQDs

2023-10-26 Thread Alex Deucher
Since they were moved to VRAM, we need to use the IO
variants of memcpy.

Fixes: 1cfb4d612127 ("drm/amdgpu: put MQDs in VRAM")
Signed-off-by: Alex Deucher 
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 12 ++--
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 12 ++--
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c 
b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 9032d7a24d7c..306252cd67fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -6457,11 +6457,11 @@ static int gfx_v10_0_gfx_init_queue(struct amdgpu_ring 
*ring)
nv_grbm_select(adev, 0, 0, 0, 0);
mutex_unlock(>srbm_mutex);
if (adev->gfx.me.mqd_backup[mqd_idx])
-   memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, 
sizeof(*mqd));
+   memcpy_fromio(adev->gfx.me.mqd_backup[mqd_idx], mqd, 
sizeof(*mqd));
} else {
/* restore mqd with the backup copy */
if (adev->gfx.me.mqd_backup[mqd_idx])
-   memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], 
sizeof(*mqd));
+   memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], 
sizeof(*mqd));
/* reset the ring */
ring->wptr = 0;
*ring->wptr_cpu_addr = 0;
@@ -6735,7 +6735,7 @@ static int gfx_v10_0_kiq_init_queue(struct amdgpu_ring 
*ring)
if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */
/* reset MQD to a clean status */
if (adev->gfx.kiq[0].mqd_backup)
-   memcpy(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd));
+   memcpy_toio(mqd, adev->gfx.kiq[0].mqd_backup, 
sizeof(*mqd));
 
/* reset ring buffer */
ring->wptr = 0;
@@ -6758,7 +6758,7 @@ static int gfx_v10_0_kiq_init_queue(struct amdgpu_ring 
*ring)
mutex_unlock(>srbm_mutex);
 
if (adev->gfx.kiq[0].mqd_backup)
-   memcpy(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd));
+   memcpy_fromio(adev->gfx.kiq[0].mqd_backup, mqd, 
sizeof(*mqd));
}
 
return 0;
@@ -6779,11 +6779,11 @@ static int gfx_v10_0_kcq_init_queue(struct amdgpu_ring 
*ring)
mutex_unlock(>srbm_mutex);
 
if (adev->gfx.mec.mqd_backup[mqd_idx])
-   memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, 
sizeof(*mqd));
+   memcpy_fromio(adev->gfx.mec.mqd_backup[mqd_idx], mqd, 
sizeof(*mqd));
} else {
/* restore MQD to a clean status */
if (adev->gfx.mec.mqd_backup[mqd_idx])
-   memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], 
sizeof(*mqd));
+   memcpy_toio(mqd, adev->gfx.mec.mqd_backup[mqd_idx], 
sizeof(*mqd));
/* reset ring buffer */
ring->wptr = 0;
atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c 
b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 762d7a19f1be..43d066bc5245 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -3684,11 +3684,11 @@ static int gfx_v11_0_gfx_init_queue(struct amdgpu_ring 
*ring)
soc21_grbm_select(adev, 0, 0, 0, 0);
mutex_unlock(>srbm_mutex);
if (adev->gfx.me.mqd_backup[mqd_idx])
-   memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, 
sizeof(*mqd));
+   memcpy_fromio(adev->gfx.me.mqd_backup[mqd_idx], mqd, 
sizeof(*mqd));
} else {
/* restore mqd with the backup copy */
if (adev->gfx.me.mqd_backup[mqd_idx])
-   memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], 
sizeof(*mqd));
+   memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], 
sizeof(*mqd));
/* reset the ring */
ring->wptr = 0;
*ring->wptr_cpu_addr = 0;
@@ -3977,7 +3977,7 @@ static int gfx_v11_0_kiq_init_queue(struct amdgpu_ring 
*ring)
if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */
/* reset MQD to a clean status */
if (adev->gfx.kiq[0].mqd_backup)
-   memcpy(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd));
+   memcpy_toio(mqd, adev->gfx.kiq[0].mqd_backup, 
sizeof(*mqd));
 
/* reset ring buffer */
ring->wptr = 0;
@@ -4000,7 +4000,7 @@ static int gfx_v11_0_kiq_init_queue(struct amdgpu_ring 
*ring)
mutex_unlock(>srbm_mutex);
 
if (adev->gfx.kiq[0].mqd_backup)
-   memcpy(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd));
+   memcpy_fromio(adev->gfx.kiq[0].mqd_backup, mqd, 
sizeof(*mqd));
}
 
return 0;
@@ -4021,11 +4021,11 @@