RDMA/umem: Support importing dma-buf as user memory region

Dma-buf is a standard cross-driver buffer sharing mechanism that can be
used to support peer-to-peer access from RDMA devices.

Device memory exported via dma-buf is associated with a file descriptor.
This is passed to the user space as a property associated with the buffer
allocation. When the buffer is registered as a memory region, the file
descriptor is passed to the RDMA driver along with other parameters.

Implement the common code for importing dma-buf object and mapping dma-buf
pages.

Link: https://lore.kernel.org/r/1608067636-98073-2-git-send-email-jianxin.xiong@intel.com
Signed-off-by: Jianxin Xiong <jianxin.xiong@intel.com>
Reviewed-by: Sean Hefty <sean.hefty@intel.com>
Acked-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Acked-by: Christian Koenig <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

4 files changed, 179 insertions, 1 deletions

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 9325e189a215..04a78d9f8fe3 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -41,6 +41,7 @@ config INFINIBAND_USER_MEM
 	bool
 	depends on INFINIBAND_USER_ACCESS != n
 	depends on MMU
+	select DMA_SHARED_BUFFER
 	default y
 
 config INFINIBAND_ON_DEMAND_PAGING
diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index ccf2670ef45e..8ab4eea5a0a5 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -40,5 +40,5 @@ ib_uverbs-y :=			uverbs_main.o uverbs_cmd.o uverbs_marshall.o \
 				uverbs_std_types_srq.o \
 				uverbs_std_types_wq.o \
 				uverbs_std_types_qp.o
-ib_uverbs-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
+ib_uverbs-$(CONFIG_INFINIBAND_USER_MEM) += umem.o umem_dmabuf.o
 ib_uverbs-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 917338db7ac1..2dde99a9ba07 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -2,6 +2,7 @@
  * Copyright (c) 2005 Topspin Communications.  All rights reserved.
  * Copyright (c) 2005 Cisco Systems.  All rights reserved.
  * Copyright (c) 2005 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2020 Intel Corporation. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -278,6 +279,8 @@ void ib_umem_release(struct ib_umem *umem)
 {
 	if (!umem)
 		return;
+	if (umem->is_dmabuf)
+		return ib_umem_dmabuf_release(to_ib_umem_dmabuf(umem));
 	if (umem->is_odp)
 		return ib_umem_odp_release(to_ib_umem_odp(umem));
 
diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c
new file mode 100644
index 000000000000..f9b5162d9260
--- /dev/null
+++ b/drivers/infiniband/core/umem_dmabuf.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+/*
+ * Copyright (c) 2020 Intel Corporation. All rights reserved.
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/dma-resv.h>
+#include <linux/dma-mapping.h>
+
+#include "uverbs.h"
+
+int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf)
+{
+	struct sg_table *sgt;
+	struct scatterlist *sg;
+	struct dma_fence *fence;
+	unsigned long start, end, cur = 0;
+	unsigned int nmap = 0;
+	int i;
+
+	dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);
+
+	if (umem_dmabuf->sgt)
+		goto wait_fence;
+
+	sgt = dma_buf_map_attachment(umem_dmabuf->attach, DMA_BIDIRECTIONAL);
+	if (IS_ERR(sgt))
+		return PTR_ERR(sgt);
+
+	/* modify the sg list in-place to match umem address and length */
+
+	start = ALIGN_DOWN(umem_dmabuf->umem.address, PAGE_SIZE);
+	end = ALIGN(umem_dmabuf->umem.address + umem_dmabuf->umem.length,
+		    PAGE_SIZE);
+	for_each_sgtable_dma_sg(sgt, sg, i) {
+		if (start < cur + sg_dma_len(sg) && cur < end)
+			nmap++;
+		if (cur <= start && start < cur + sg_dma_len(sg)) {
+			unsigned long offset = start - cur;
+
+			umem_dmabuf->first_sg = sg;
+			umem_dmabuf->first_sg_offset = offset;
+			sg_dma_address(sg) += offset;
+			sg_dma_len(sg) -= offset;
+			cur += offset;
+		}
+		if (cur < end && end <= cur + sg_dma_len(sg)) {
+			unsigned long trim = cur + sg_dma_len(sg) - end;
+
+			umem_dmabuf->last_sg = sg;
+			umem_dmabuf->last_sg_trim = trim;
+			sg_dma_len(sg) -= trim;
+			break;
+		}
+		cur += sg_dma_len(sg);
+	}
+
+	umem_dmabuf->umem.sg_head.sgl = umem_dmabuf->first_sg;
+	umem_dmabuf->umem.sg_head.nents = nmap;
+	umem_dmabuf->umem.nmap = nmap;
+	umem_dmabuf->sgt = sgt;
+
+wait_fence:
+	/*
+	 * Although the sg list is valid now, the content of the pages
+	 * may be not up-to-date. Wait for the exporter to finish
+	 * the migration.
+	 */
+	fence = dma_resv_get_excl(umem_dmabuf->attach->dmabuf->resv);
+	if (fence)
+		return dma_fence_wait(fence, false);
+
+	return 0;
+}
+EXPORT_SYMBOL(ib_umem_dmabuf_map_pages);
+
+void ib_umem_dmabuf_unmap_pages(struct ib_umem_dmabuf *umem_dmabuf)
+{
+	dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);
+
+	if (!umem_dmabuf->sgt)
+		return;
+
+	/* retore the original sg list */
+	if (umem_dmabuf->first_sg) {
+		sg_dma_address(umem_dmabuf->first_sg) -=
+			umem_dmabuf->first_sg_offset;
+		sg_dma_len(umem_dmabuf->first_sg) +=
+			umem_dmabuf->first_sg_offset;
+		umem_dmabuf->first_sg = NULL;
+		umem_dmabuf->first_sg_offset = 0;
+	}
+	if (umem_dmabuf->last_sg) {
+		sg_dma_len(umem_dmabuf->last_sg) +=
+			umem_dmabuf->last_sg_trim;
+		umem_dmabuf->last_sg = NULL;
+		umem_dmabuf->last_sg_trim = 0;
+	}
+
+	dma_buf_unmap_attachment(umem_dmabuf->attach, umem_dmabuf->sgt,
+				 DMA_BIDIRECTIONAL);
+
+	umem_dmabuf->sgt = NULL;
+}
+EXPORT_SYMBOL(ib_umem_dmabuf_unmap_pages);
+
+struct ib_umem_dmabuf *ib_umem_dmabuf_get(struct ib_device *device,
+					  unsigned long offset, size_t size,
+					  int fd, int access,
+					  const struct dma_buf_attach_ops *ops)
+{
+	struct dma_buf *dmabuf;
+	struct ib_umem_dmabuf *umem_dmabuf;
+	struct ib_umem *umem;
+	unsigned long end;
+	struct ib_umem_dmabuf *ret = ERR_PTR(-EINVAL);
+
+	if (check_add_overflow(offset, (unsigned long)size, &end))
+		return ret;
+
+	if (unlikely(!ops || !ops->move_notify))
+		return ret;
+
+	dmabuf = dma_buf_get(fd);
+	if (IS_ERR(dmabuf))
+		return ERR_CAST(dmabuf);
+
+	if (dmabuf->size < end)
+		goto out_release_dmabuf;
+
+	umem_dmabuf = kzalloc(sizeof(*umem_dmabuf), GFP_KERNEL);
+	if (!umem_dmabuf) {
+		ret = ERR_PTR(-ENOMEM);
+		goto out_release_dmabuf;
+	}
+
+	umem = &umem_dmabuf->umem;
+	umem->ibdev = device;
+	umem->length = size;
+	umem->address = offset;
+	umem->writable = ib_access_writable(access);
+	umem->is_dmabuf = 1;
+
+	if (!ib_umem_num_pages(umem))
+		goto out_free_umem;
+
+	umem_dmabuf->attach = dma_buf_dynamic_attach(
+					dmabuf,
+					device->dma_device,
+					ops,
+					umem_dmabuf);
+	if (IS_ERR(umem_dmabuf->attach)) {
+		ret = ERR_CAST(umem_dmabuf->attach);
+		goto out_free_umem;
+	}
+	return umem_dmabuf;
+
+out_free_umem:
+	kfree(umem_dmabuf);
+
+out_release_dmabuf:
+	dma_buf_put(dmabuf);
+	return ret;
+}
+EXPORT_SYMBOL(ib_umem_dmabuf_get);
+
+void ib_umem_dmabuf_release(struct ib_umem_dmabuf *umem_dmabuf)
+{
+	struct dma_buf *dmabuf = umem_dmabuf->attach->dmabuf;
+
+	dma_buf_detach(dmabuf, umem_dmabuf->attach);
+	dma_buf_put(dmabuf);
+	kfree(umem_dmabuf);
+}