On 2021-05-23 1:10 p.m., Christian
König wrote:
Am 21.05.21 um 21:28 schrieb philip yang:
This simply the logic, several comments inline.
Thanks,
Philip
On 2021-05-21 9:52 a.m., Christian König wrote:
Access to the mm_node is now forbidden. So instead of hand wiring thatThe prange->ttm_res valid check is not needed because we already check svm_range_vram_node_new return value
use the cursor functionality.
Signed-off-by: Christian König<christian.koe...@amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 76 +++---------------------
1 file changed, 9 insertions(+), 67 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index fd8f544f0de2..cb28d1e660af 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -29,6 +29,7 @@
#include "amdgpu_object.h"
#include "amdgpu_vm.h"
#include "amdgpu_mn.h"
+#include "amdgpu_res_cursor.h"
#include "kfd_priv.h"
#include "kfd_svm.h"
#include "kfd_migrate.h"
@@ -205,34 +206,6 @@ svm_migrate_copy_done(struct amdgpu_device *adev, struct dma_fence *mfence)
return r;
}
-static uint64_t
-svm_migrate_node_physical_addr(struct amdgpu_device *adev,
- struct drm_mm_node **mm_node, uint64_t *offset)
-{
- struct drm_mm_node *node = *mm_node;
- uint64_t pos = *offset;
-
- if (node->start == AMDGPU_BO_INVALID_OFFSET) {
- pr_debug("drm node is not validated\n");
- return 0;
- }
-
- pr_debug("vram node start 0x%llx npages 0x%llx\n", node->start,
- node->size);
-
- if (pos >= node->size) {
- do {
- pos -= node->size;
- node++;
- } while (pos >= node->size);
-
- *mm_node = node;
- *offset = pos;
- }
-
- return (node->start + pos) << PAGE_SHIFT;
-}
-
unsigned long
svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr)
{
@@ -297,11 +270,9 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
{
uint64_t npages = migrate->cpages;
struct device *dev = adev->dev;
- struct drm_mm_node *node;
+ struct amdgpu_res_cursor cursor;
dma_addr_t *src;
uint64_t *dst;
- uint64_t vram_addr;
- uint64_t offset;
uint64_t i, j;
int r;
@@ -317,19 +288,12 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
goto out;
}
- node = prange->ttm_res->mm_node;
- offset = prange->offset;
- vram_addr = svm_migrate_node_physical_addr(adev, &node, &offset);
- if (!vram_addr) {
- WARN_ONCE(1, "vram node address is 0\n");
- r = -ENOMEM;
- goto out;
- }
-
+ amdgpu_res_first(prange->ttm_res, prange->offset, npages << PAGE_SHIFT,
prange->offset<< PAGE_SHIFT
amdgpu_res_first takes start and size in bytes, prange->offset use page aligned offset
Ah, yes good point.
+ &cursor);Here to handle cross mm_node case.
for (i = j = 0; i < npages; i++) {
struct page *spage;
- dst[i] = vram_addr + (j << PAGE_SHIFT);
+ dst[i] = cursor.start + (j << PAGE_SHIFT);
migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);
svm_migrate_get_vram_page(prange, migrate->dst[i]);
@@ -354,18 +318,10 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
mfence);
if (r)
goto out_free_vram_pages;
- offset += j;
- vram_addr = (node->start + offset) << PAGE_SHIFT;
+ amdgpu_res_next(&cursor, j << PAGE_SHIFT);
j = 0;
} else {
- offset++;
- vram_addr += PAGE_SIZE;
- }
- if (offset >= node->size) {
- node++;
- pr_debug("next node size 0x%llx\n", node->size);
- vram_addr = node->start << PAGE_SHIFT;
- offset = 0;
+ amdgpu_res_next(&cursor, PAGE_SIZE);
}
continue;
}
@@ -373,22 +329,8 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
pr_debug("dma mapping src to 0x%llx, page_to_pfn 0x%lx\n",
src[i] >> PAGE_SHIFT, page_to_pfn(spage));
- if (j + offset >= node->size - 1 && i < npages - 1) {
- r = svm_migrate_copy_memory_gart(adev, src + i - j,
- dst + i - j, j + 1,
- FROM_RAM_TO_VRAM,
- mfence);
- if (r)
- goto out_free_vram_pages;
-
- node++;
- pr_debug("next node size 0x%llx\n", node->size);
- vram_addr = node->start << PAGE_SHIFT;
- offset = 0;
- j = 0;
- } else {
- j++;
- }
+ amdgpu_res_next(&cursor, PAGE_SIZE);
+ j++;
if (j >= cursor->size - 1 && i < npages - 1) {
r = svm_migrate_copy_memory_gart(adev, src + i - j,
dst + i - j, j + 1,
FROM_RAM_TO_VRAM,
mfence);
if (r)
goto out_free_vram_pages;
amdgpu_res_next(&cursor, (j + 1) * PAGE_SIZE);
j= 0;
} else {
j++;
}
Yeah, that was the point I couldn't understand. Why would we want that anyway?
svm_migrate_copy_memory_gart uses sdma to copy from system memory
to vram, system memory is gart mapping paged memory, and vram is
direct mapping, physically continuous memory. We have to call
svm_migrate_copy_memory_gart to setup new sdma for two cases:
1. system memory pages array, if src page is not MIGRATE_PFN_VALID
2. if dst vram page cross mm_nodes, physical vram address is not
continuous.
This if is for case 2.
Regards,
Philip
Regards,
Christian.
}
r = svm_migrate_copy_memory_gart(adev, src + i - j, dst + i - j, j,
_______________________________________________ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx