On 2024-04-15 08:02, Christian König
wrote:
Am 12.04.24 um 22:12 schrieb Philip Yang:
RDMA device with limited scatter-gather capability requires physical
address contiguous VRAM buffer for RDMA peer direct access.
Add a new KFD alloc memory flag and store as new GEM bo alloc flag. When
pin this buffer object to export for RDMA peerdirect access, set
AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS flag, and then vram_mgr will set
TTM_PL_FLAG_CONTIFUOUS flag to ask VRAM buddy allocator to get
contiguous VRAM.
Remove the 2GB max memory block size limit for contiguous allocation.
I'm going to sync up with Arun on this once more, but I think we won't even need the new flag.
We will just downgrade the existing flag to be a best effort allocation for contiguous buffers and only use the TTM flag internally to signal that we need to alter it while pinning.
sure, I will rebase this patch series to "[PATCH] drm/amdgpu:
Modify the contiguous flags behaviour", this will remove the new
flag.
Will send v2 patch series after Arun's v2 patch.
Regards,
Philip
Regards,
Christian.
Signed-off-by: Philip Yang <Philip.Yang@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 7 +++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 9 +++++++--
include/uapi/drm/amdgpu_drm.h | 5 +++++
include/uapi/linux/kfd_ioctl.h | 1 +
4 files changed, 20 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 0ae9fd844623..3523b91f8add 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1470,6 +1470,9 @@ static int amdgpu_amdkfd_gpuvm_pin_bo(struct amdgpu_bo *bo, u32 domain)
if (unlikely(ret))
return ret;
+ if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS_BEST_EFFORT)
+ bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+
ret = amdgpu_bo_pin_restricted(bo, domain, 0, 0);
if (ret)
pr_err("Error in Pinning BO to domain: %d\n", domain);
@@ -1712,6 +1715,10 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
alloc_flags = AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;
alloc_flags |= (flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) ?
AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : 0;
+
+ /* For contiguous VRAM allocation */
+ if (flags & KFD_IOC_ALLOC_MEM_FLAGS_CONTIGUOUS_BEST_EFFORT)
+ alloc_flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS_BEST_EFFORT;
}
xcp_id = fpriv->xcp_id == AMDGPU_XCP_NO_PARTITION ?
0 : fpriv->xcp_id;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 8db880244324..1d6e45e238e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -516,8 +516,13 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
BUG_ON(min_block_size < mm->chunk_size);
- /* Limit maximum size to 2GiB due to SG table limitations */
- size = min(remaining_size, 2ULL << 30);
+ if (place->flags & TTM_PL_FLAG_CONTIGUOUS)
+ size = remaining_size;
+ else
+ /* Limit maximum size to 2GiB due to SG table limitations
+ * for no contiguous allocation.
+ */
+ size = min(remaining_size, 2ULL << 30);
if ((size >= (u64)pages_per_block << PAGE_SHIFT) &&
!(size & (((u64)pages_per_block << PAGE_SHIFT) - 1)))
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index ad21c613fec8..13645abb8e46 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -171,6 +171,11 @@ extern "C" {
* may override the MTYPE selected in AMDGPU_VA_OP_MAP.
*/
#define AMDGPU_GEM_CREATE_EXT_COHERENT (1 << 15)
+/* Flag that allocating the BO with best effort for contiguous VRAM.
+ * If no contiguous VRAM, fallback to scattered allocation.
+ * Pin the BO for peerdirect RDMA trigger VRAM defragmentation.
+ */
+#define AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS_BEST_EFFORT (1 << 16)
struct drm_amdgpu_gem_create_in {
/** the requested memory size */
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 2040a470ddb4..c1394c162d4e 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -407,6 +407,7 @@ struct kfd_ioctl_acquire_vm_args {
#define KFD_IOC_ALLOC_MEM_FLAGS_COHERENT (1 << 26)
#define KFD_IOC_ALLOC_MEM_FLAGS_UNCACHED (1 << 25)
#define KFD_IOC_ALLOC_MEM_FLAGS_EXT_COHERENT (1 << 24)
+#define KFD_IOC_ALLOC_MEM_FLAGS_CONTIGUOUS_BEST_EFFORT (1 << 23)
/* Allocate memory for later SVM (shared virtual memory) mapping.
*
