RDMA device with limited scatter-gather ability requires contiguous VRAM
buffer allocation for RDMA peer direct support.
Add a new KFD alloc memory flag and store as bo alloc flag
AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS. When pin this bo to export for RDMA
peerdirect access, this will set TTM_PL_FLAG_CONTIFUOUS flag, and ask
VRAM buddy allocator to get contiguous VRAM.
Signed-off-by: Philip Yang <Philip.Yang@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 4 ++++
include/uapi/linux/kfd_ioctl.h | 1 +
2 files changed, 5 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 0ae9fd844623..ef9154043757 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1712,6 +1712,10 @@ 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;
}
xcp_id = fpriv->xcp_id == AMDGPU_XCP_NO_PARTITION ?
0 : fpriv->xcp_id;
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.
*
--
2.43.2
