All of lore.kernel.org
 help / color / mirror / Atom feed
From: Oded Gabbay <ogabbay@kernel.org>
To: linux-kernel@vger.kernel.org, gregkh@linuxfoundation.org,
	jgg@ziepe.ca, airlied@gmail.com
Cc: christian.koenig@amd.com, daniel.vetter@ffwll.ch,
	galpress@amazon.com, sleybo@amazon.com,
	dri-devel@lists.freedesktop.org, linux-rdma@vger.kernel.org,
	linux-media@vger.kernel.org, dledford@redhat.com,
	alexander.deucher@amd.com, leonro@nvidia.com, hch@lst.de,
	amd-gfx@lists.freedesktop.org, linaro-mm-sig@lists.linaro.org
Subject: [PATCH v7 1/2] habanalabs: define uAPI to export FD for DMA-BUF
Date: Sun,  3 Oct 2021 12:07:55 +0300	[thread overview]
Message-ID: <20211003090756.117809-2-ogabbay@kernel.org> (raw)
In-Reply-To: <20211003090756.117809-1-ogabbay@kernel.org>

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: Oded Gabbay <ogabbay@kernel.org>
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
Changes in v7:
 - Change the type of the fd variable returned from IOCTL to be __s32

 include/uapi/misc/habanalabs.h | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index ccfcb4d188fc..f980fbfb1a0e 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -959,6 +959,10 @@ 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
@@ -1030,11 +1034,26 @@ 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;
@@ -1071,6 +1090,13 @@ 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;
 	};
 };
 
-- 
2.17.1


  reply	other threads:[~2021-10-03  9:08 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-03  9:07 [PATCH v7 0/2] Add p2p via dmabuf to habanalabs Oded Gabbay
2021-10-03  9:07 ` Oded Gabbay [this message]
2021-10-03  9:07 ` [PATCH v7 2/2] habanalabs: add support for dma-buf exporter Oded Gabbay
2021-10-07 10:55 ` [PATCH v7 0/2] Add p2p via dmabuf to habanalabs Oded Gabbay

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20211003090756.117809-2-ogabbay@kernel.org \
    --to=ogabbay@kernel.org \
    --cc=airlied@gmail.com \
    --cc=alexander.deucher@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=christian.koenig@amd.com \
    --cc=daniel.vetter@ffwll.ch \
    --cc=dledford@redhat.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=galpress@amazon.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=hch@lst.de \
    --cc=jgg@ziepe.ca \
    --cc=leonro@nvidia.com \
    --cc=linaro-mm-sig@lists.linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-media@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=sleybo@amazon.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.