[PATCH v2 1/6] drm/amdgpu: Support contiguous VRAM allocation

[Philip Yang]

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.

Remove the 2GB max memory block size limit for contiguous allocation.

Signed-off-by: Philip Yang <Philip.Yang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 4 ++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c     | 9 +++++++--
 include/uapi/linux/kfd_ioctl.h                   | 1 +
 3 files changed, 12 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..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/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 4be8b091099a..2f2ae7177771 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -532,8 +532,13 @@ 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/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