@@ -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
@@ -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
@@ -43,6 +44,7 @@
#include <rdma/ib_umem_odp.h>
#include "uverbs.h"
+#include "umem_dmabuf.h"
static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int dirty)
{
@@ -278,6 +280,8 @@ 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));
new file mode 100644
@@ -0,0 +1,184 @@
+// 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"
+#include "umem_dmabuf.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;
+ unsigned int nmap;
+ int i;
+
+ dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);
+
+ if (umem_dmabuf->sgt)
+ return 0;
+
+ 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);
+ cur = 0;
+ nmap = 0;
+ 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;
+
+ /*
+ * 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)
+ 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 *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;
+ long ret;
+
+ if (check_add_overflow(offset, (unsigned long)size, &end))
+ return ERR_PTR(-EINVAL);
+
+ if (unlikely(PAGE_ALIGN(end) < PAGE_SIZE))
+ return ERR_PTR(-EINVAL);
+
+ if (unlikely(!ops || !ops->move_notify))
+ return ERR_PTR(-EINVAL);
+
+ umem_dmabuf = kzalloc(sizeof(*umem_dmabuf), GFP_KERNEL);
+ if (!umem_dmabuf)
+ return ERR_PTR(-ENOMEM);
+
+ umem = &umem_dmabuf->umem;
+ umem->ibdev = device;
+ umem->length = size;
+ umem->address = offset;
+ umem->writable = ib_access_writable(access);
+ umem->is_dmabuf = 1;
+
+ if (unlikely(!ib_umem_num_pages(umem))) {
+ ret = -EINVAL;
+ goto out_free_umem;
+ }
+
+ dmabuf = dma_buf_get(fd);
+ if (IS_ERR(dmabuf)) {
+ ret = PTR_ERR(dmabuf);
+ goto out_free_umem;
+ }
+
+ if (dmabuf->size < offset + size) {
+ ret = -EINVAL;
+ goto out_release_dmabuf;
+ }
+
+ umem_dmabuf->attach = dma_buf_dynamic_attach(
+ dmabuf,
+ device->dma_device,
+ ops,
+ umem_dmabuf);
+ if (IS_ERR(umem_dmabuf->attach)) {
+ ret = PTR_ERR(umem_dmabuf->attach);
+ goto out_release_dmabuf;
+ }
+
+ return umem;
+
+out_release_dmabuf:
+ dma_buf_put(dmabuf);
+
+out_free_umem:
+ kfree(umem_dmabuf);
+ return ERR_PTR(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);
+}
new file mode 100644
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
+/*
+ * Copyright (c) 2020 Intel Corporation. All rights reserved.
+ */
+
+#ifndef UMEM_DMABUF_H
+#define UMEM_DMABUF_H
+
+void ib_umem_dmabuf_release(struct ib_umem_dmabuf *umem_dmabuf);
+
+#endif /* UMEM_DMABUF_H */
@@ -1,6 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
/*
* Copyright (c) 2007 Cisco Systems. All rights reserved.
+ * Copyright (c) 2020 Intel Corporation. All rights reserved.
*/
#ifndef IB_UMEM_H
@@ -13,6 +14,7 @@
struct ib_ucontext;
struct ib_umem_odp;
+struct dma_buf_attach_ops;
struct ib_umem {
struct ib_device *ibdev;
@@ -22,12 +24,29 @@ struct ib_umem {
unsigned long address;
u32 writable : 1;
u32 is_odp : 1;
+ u32 is_dmabuf : 1;
struct work_struct work;
struct sg_table sg_head;
int nmap;
unsigned int sg_nents;
};
+struct ib_umem_dmabuf {
+ struct ib_umem umem;
+ struct dma_buf_attachment *attach;
+ struct sg_table *sgt;
+ struct scatterlist *first_sg;
+ struct scatterlist *last_sg;
+ unsigned long first_sg_offset;
+ unsigned long last_sg_trim;
+ void *private;
+};
+
+static inline struct ib_umem_dmabuf *to_ib_umem_dmabuf(struct ib_umem *umem)
+{
+ return container_of(umem, struct ib_umem_dmabuf, umem);
+}
+
/* Returns the offset of the umem start relative to the first page. */
static inline int ib_umem_offset(struct ib_umem *umem)
{
@@ -79,6 +98,12 @@ int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
unsigned long pgsz_bitmap,
unsigned long virt);
+struct ib_umem *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);
+int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf);
+void ib_umem_dmabuf_unmap_pages(struct ib_umem_dmabuf *umem_dmabuf);
#else /* CONFIG_INFINIBAND_USER_MEM */
@@ -101,7 +126,19 @@ static inline unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
{
return 0;
}
+static inline struct ib_umem *ib_umem_dmabuf_get(struct ib_device *device,
+ unsigned long offset,
+ size_t size, int fd,
+ int access,
+ struct dma_buf_attach_ops *ops)
+{
+ return ERR_PTR(-EINVAL);
+}
+static inline int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf)
+{
+ return -EINVAL;
+}
+static inline void ib_umem_dmabuf_unmap_pages(struct ib_umem_dmabuf *umem_dmabuf) { }
#endif /* CONFIG_INFINIBAND_USER_MEM */
-
#endif /* IB_UMEM_H */