habanalabs: define uAPI to export FD for DMA-BUF

User process might want to share the device memory with another
driver/device, and to allow it to access it over PCIe (P2P).

To enable this, we utilize the dma-buf mechanism and add a dma-buf
exporter support, so the other driver can import the device memory and
access it.

The device memory is allocated using our existing allocation uAPI,
where the user will get a handle that represents the allocation.

The user will then need to call the new
uAPI (HL_MEM_OP_EXPORT_DMABUF_FD) and give the handle as a parameter.

The driver will return a FD that represents the DMA-BUF object that
was created to match that allocation.
Signed-off-by: NOded Gabbay <ogabbay@kernel.org>
Reviewed-by: NTomer Tayar <ttayar@habana.ai>
Reviewed-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

include/uapi/misc/habanalabs.h

@@ -960,6 +960,10 @@ union hl_wait_cs_args {
 #define HL_MEM_OP_UNMAP			3
 /* Opcode to map a hw block */
 #define HL_MEM_OP_MAP_BLOCK		4
+/* Opcode to create DMA-BUF object for an existing device memory allocation
+ * and to export an FD of that DMA-BUF back to the caller
+ */
+#define HL_MEM_OP_EXPORT_DMABUF_FD	5
 
 /* Memory flags */
 #define HL_MEM_CONTIGUOUS	0x1
@@ -1031,11 +1035,26 @@ struct hl_mem_in {
 			/* Virtual address returned from HL_MEM_OP_MAP */
 			__u64 device_virt_addr;
 		} unmap;
+
+		/* HL_MEM_OP_EXPORT_DMABUF_FD */
+		struct {
+			/* Handle returned from HL_MEM_OP_ALLOC. In Gaudi,
+			 * where we don't have MMU for the device memory, the
+			 * driver expects a physical address (instead of
+			 * a handle) in the device memory space.
+			 */
+			__u64 handle;
+			/* Size of memory allocation. Relevant only for GAUDI */
+			__u64 mem_size;
+		} export_dmabuf_fd;
 	};
 
 	/* HL_MEM_OP_* */
 	__u32 op;
-	/* HL_MEM_* flags */
+	/* HL_MEM_* flags.
+	 * For the HL_MEM_OP_EXPORT_DMABUF_FD opcode, this field holds the
+	 * DMA-BUF file/FD flags.
+	 */
 	__u32 flags;
 	/* Context ID - Currently not in use */
 	__u32 ctx_id;
@@ -1072,6 +1091,13 @@ struct hl_mem_out {
 
 			__u32 pad;
 		};
+
+		/* Returned in HL_MEM_OP_EXPORT_DMABUF_FD. Represents the
+		 * DMA-BUF object that was created to describe a memory
+		 * allocation on the device's memory space. The FD should be
+		 * passed to the importer driver
+		 */
+		__s32 fd;
 	};
 };