[PATCH 3/4] drm/amdgpu: use amdgpu_device_vram_access in amdgpu_ttm_vram_read
This speeds up the access quite a bit from 2.2 MB/s to
2.9 MB/s on 32bit and 12,8 MB/s on 64bit.
Signed-off-by: Christian König
Reviewed-by: Alex Deucher
Acked-by: Jonathan Kim
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 27 ++---
1 file changed, 11 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index ae1b00def5d8..58d143b24ba0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -59,6 +59,8 @@
#include "amdgpu_ras.h"
#include "bif/bif_4_1_d.h"
+#define AMDGPU_TTM_VRAM_MAX_DW_READ(size_t)128
+
static int amdgpu_map_buffer(struct ttm_buffer_object *bo,
struct ttm_mem_reg *mem, unsigned num_pages,
uint64_t offset, unsigned window,
@@ -2255,27 +2257,20 @@ static ssize_t amdgpu_ttm_vram_read(struct file *f,
char __user *buf,
if (*pos >= adev->gmc.mc_vram_size)
return -ENXIO;
+ size = min(size, (size_t)(adev->gmc.mc_vram_size - *pos));
while (size) {
- unsigned long flags;
- uint32_t value;
-
- if (*pos >= adev->gmc.mc_vram_size)
- return result;
-
- spin_lock_irqsave(>mmio_idx_lock, flags);
- WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)*pos) | 0x8000);
- WREG32_NO_KIQ(mmMM_INDEX_HI, *pos >> 31);
- value = RREG32_NO_KIQ(mmMM_DATA);
- spin_unlock_irqrestore(>mmio_idx_lock, flags);
+ size_t bytes = min(size, AMDGPU_TTM_VRAM_MAX_DW_READ * 4);
+ uint32_t value[AMDGPU_TTM_VRAM_MAX_DW_READ];
- r = put_user(value, (uint32_t *)buf);
+ amdgpu_device_vram_access(adev, *pos, value, bytes, false);
+ r = copy_to_user(buf, value, bytes);
if (r)
return r;
- result += 4;
- buf += 4;
- *pos += 4;
- size -= 4;
+ result += bytes;
+ buf += bytes;
+ *pos += bytes;
+ size -= bytes;
}
return result;
--
2.17.1
___
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
[PATCH 3/4] drm/amdgpu: use amdgpu_device_vram_access in amdgpu_ttm_vram_read
This speeds up the access quite a bit from 2.2 MB/s to
2.9 MB/s on 32bit and 12,8 MB/s on 64bit.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 27 ++---
1 file changed, 11 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index ae1b00def5d8..58d143b24ba0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -59,6 +59,8 @@
#include "amdgpu_ras.h"
#include "bif/bif_4_1_d.h"
+#define AMDGPU_TTM_VRAM_MAX_DW_READ(size_t)128
+
static int amdgpu_map_buffer(struct ttm_buffer_object *bo,
struct ttm_mem_reg *mem, unsigned num_pages,
uint64_t offset, unsigned window,
@@ -2255,27 +2257,20 @@ static ssize_t amdgpu_ttm_vram_read(struct file *f,
char __user *buf,
if (*pos >= adev->gmc.mc_vram_size)
return -ENXIO;
+ size = min(size, (size_t)(adev->gmc.mc_vram_size - *pos));
while (size) {
- unsigned long flags;
- uint32_t value;
-
- if (*pos >= adev->gmc.mc_vram_size)
- return result;
-
- spin_lock_irqsave(>mmio_idx_lock, flags);
- WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)*pos) | 0x8000);
- WREG32_NO_KIQ(mmMM_INDEX_HI, *pos >> 31);
- value = RREG32_NO_KIQ(mmMM_DATA);
- spin_unlock_irqrestore(>mmio_idx_lock, flags);
+ size_t bytes = min(size, AMDGPU_TTM_VRAM_MAX_DW_READ * 4);
+ uint32_t value[AMDGPU_TTM_VRAM_MAX_DW_READ];
- r = put_user(value, (uint32_t *)buf);
+ amdgpu_device_vram_access(adev, *pos, value, bytes, false);
+ r = copy_to_user(buf, value, bytes);
if (r)
return r;
- result += 4;
- buf += 4;
- *pos += 4;
- size -= 4;
+ result += bytes;
+ buf += bytes;
+ *pos += bytes;
+ size -= bytes;
}
return result;
--
2.17.1
___
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
