Contributors: 17
Author Tokens Token Proportion Commits Commit Proportion
Jianxin Xiong 809 54.77% 1 3.23%
Gal Pressman 237 16.05% 1 3.23%
Jake Moroni 114 7.72% 5 16.13%
Roland Dreier 103 6.97% 4 12.90%
Yishai Hadas 97 6.57% 2 6.45%
Jason Gunthorpe 71 4.81% 5 16.13%
Moni Shoua 12 0.81% 1 3.23%
Maor Gottlieb 8 0.54% 2 6.45%
Christian König 6 0.41% 2 6.45%
Bryan O'Sullivan 5 0.34% 1 3.23%
Greg Kroah-Hartman 4 0.27% 1 3.23%
Gerd Hoffmann 3 0.20% 1 3.23%
Jack Morgenstein 3 0.20% 1 3.23%
Haggai Eran 2 0.14% 1 3.23%
Peter Zijlstra 1 0.07% 1 3.23%
Kees Cook 1 0.07% 1 3.23%
Linus Torvalds 1 0.07% 1 3.23%
Total 1477 31


// 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 <linux/module.h>

#include "uverbs.h"

MODULE_IMPORT_NS("DMA_BUF");

int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf)
{
	struct sg_table *sgt;
	struct scatterlist *sg;
	unsigned long start, end, cur = 0;
	unsigned int nmap = 0;
	long ret;
	int i;

	dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);

	if (umem_dmabuf->revoked)
		return -EINVAL;

	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.sgt_append.sgt.sgl = umem_dmabuf->first_sg;
	umem_dmabuf->umem.sgt_append.sgt.nents = 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.
	 */
	ret = dma_resv_wait_timeout(umem_dmabuf->attach->dmabuf->resv,
				     DMA_RESV_USAGE_KERNEL,
				     false, MAX_SCHEDULE_TIMEOUT);
	if (ret < 0)
		return ret;
	if (ret == 0)
		return -ETIMEDOUT;
	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);

static struct ib_umem_dmabuf *
ib_umem_dmabuf_get_with_dma_device(struct ib_device *device,
				   struct device *dma_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;

	dmabuf = dma_buf_get(fd);
	if (IS_ERR(dmabuf))
		return ERR_CAST(dmabuf);

	if (dmabuf->size < end)
		goto out_release_dmabuf;

	umem_dmabuf = kzalloc_obj(*umem_dmabuf);
	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,
					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;
}

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)
{
	return ib_umem_dmabuf_get_with_dma_device(device, device->dma_device,
						  offset, size, fd, access, ops);
}
EXPORT_SYMBOL(ib_umem_dmabuf_get);

static struct dma_buf_attach_ops ib_umem_dmabuf_attach_pinned_ops = {
	.allow_peer2peer = true,
};

static void ib_umem_dmabuf_revoke_locked(struct dma_buf_attachment *attach)
{
	struct ib_umem_dmabuf *umem_dmabuf = attach->importer_priv;

	dma_resv_assert_held(attach->dmabuf->resv);

	if (umem_dmabuf->revoked)
		return;

	if (umem_dmabuf->pinned_revoke)
		umem_dmabuf->pinned_revoke(umem_dmabuf->private);

	ib_umem_dmabuf_unmap_pages(umem_dmabuf);
	if (umem_dmabuf->pinned) {
		dma_buf_unpin(umem_dmabuf->attach);
		umem_dmabuf->pinned = 0;
	}
	umem_dmabuf->revoked = 1;
}

static struct dma_buf_attach_ops ib_umem_dmabuf_attach_pinned_revocable_ops = {
	.allow_peer2peer = true,
	.invalidate_mappings = ib_umem_dmabuf_revoke_locked,
};

static struct ib_umem_dmabuf *
ib_umem_dmabuf_get_pinned_and_lock(struct ib_device *device,
				   struct device *dma_device,
				   unsigned long offset,
				   size_t size, int fd, int access,
				   const struct dma_buf_attach_ops *ops)
{
	struct ib_umem_dmabuf *umem_dmabuf;
	int err;

	umem_dmabuf =
		ib_umem_dmabuf_get_with_dma_device(device, dma_device, offset,
						   size, fd, access, ops);
	if (IS_ERR(umem_dmabuf))
		return umem_dmabuf;

	dma_resv_lock(umem_dmabuf->attach->dmabuf->resv, NULL);
	err = dma_buf_pin(umem_dmabuf->attach);
	if (err)
		goto err_release;
	umem_dmabuf->pinned = 1;

	err = ib_umem_dmabuf_map_pages(umem_dmabuf);
	if (err)
		goto err_release;

	return umem_dmabuf;

err_release:
	dma_resv_unlock(umem_dmabuf->attach->dmabuf->resv);
	ib_umem_release(&umem_dmabuf->umem);
	return ERR_PTR(err);
}

struct ib_umem_dmabuf *
ib_umem_dmabuf_get_pinned_with_dma_device(struct ib_device *device,
					  struct device *dma_device,
					  unsigned long offset, size_t size,
					  int fd, int access)
{
	struct ib_umem_dmabuf *umem_dmabuf =
		ib_umem_dmabuf_get_pinned_and_lock(device, dma_device, offset,
						   size, fd, access,
						   &ib_umem_dmabuf_attach_pinned_ops);
	if (IS_ERR(umem_dmabuf))
		return umem_dmabuf;

	dma_resv_unlock(umem_dmabuf->attach->dmabuf->resv);
	return umem_dmabuf;
}
EXPORT_SYMBOL(ib_umem_dmabuf_get_pinned_with_dma_device);

/**
 * ib_umem_dmabuf_get_pinned_revocable_and_lock - Map & pin a revocable dmabuf
 * @device: IB device.
 * @offset: Start offset.
 * @size: Length.
 * @fd: dmabuf fd.
 * @access: Access flags.
 *
 * Obtains a umem from a dmabuf for drivers/devices that can support revocation.
 *
 * Returns with dma_resv_lock held upon success. The driver must set the revoke
 * callback prior to unlock by calling ib_umem_dmabuf_set_revoke_locked().
 *
 * When a revocation occurs, the revoke callback will be called. The driver must
 * ensure that the region is no longer accessed when the callback returns. Any
 * subsequent access attempts should also probably cause an AE for MRs.
 *
 * If the umem is used for an MR, the driver must ensure that the key remains in
 * use such that it cannot be obtained by a new region until this region is
 * fully deregistered (i.e., ibv_dereg_mr). If a driver needs to serialize with
 * revoke calls, it can use dma_resv_lock.
 *
 * If successful, then the revoke callback may be called at any time and will
 * also be called automatically upon ib_umem_release (serialized). The revoke
 * callback will be called one time at most.
 *
 * Return: A pointer to ib_umem_dmabuf on success, or an ERR_PTR on failure.
 */
struct ib_umem_dmabuf *
ib_umem_dmabuf_get_pinned_revocable_and_lock(struct ib_device *device,
					     unsigned long offset, size_t size,
					     int fd, int access)
{
	const struct dma_buf_attach_ops *ops =
		&ib_umem_dmabuf_attach_pinned_revocable_ops;

	return ib_umem_dmabuf_get_pinned_and_lock(device, device->dma_device,
						  offset, size, fd, access,
						  ops);
}
EXPORT_SYMBOL(ib_umem_dmabuf_get_pinned_revocable_and_lock);

void ib_umem_dmabuf_set_revoke_locked(struct ib_umem_dmabuf *umem_dmabuf,
				      void (*revoke)(void *priv), void *priv)
{
	dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);

	umem_dmabuf->pinned_revoke = revoke;
	umem_dmabuf->private = priv;
}
EXPORT_SYMBOL(ib_umem_dmabuf_set_revoke_locked);

struct ib_umem_dmabuf *ib_umem_dmabuf_get_pinned(struct ib_device *device,
						 unsigned long offset,
						 size_t size, int fd,
						 int access)
{
	return ib_umem_dmabuf_get_pinned_with_dma_device(device, device->dma_device,
							 offset, size, fd, access);
}
EXPORT_SYMBOL(ib_umem_dmabuf_get_pinned);

void ib_umem_dmabuf_revoke_lock(struct ib_umem_dmabuf *umem_dmabuf)
{
	struct dma_buf *dmabuf = umem_dmabuf->attach->dmabuf;

	dma_resv_lock(dmabuf->resv, NULL);
}
EXPORT_SYMBOL(ib_umem_dmabuf_revoke_lock);

void ib_umem_dmabuf_revoke_unlock(struct ib_umem_dmabuf *umem_dmabuf)
{
	struct dma_buf *dmabuf = umem_dmabuf->attach->dmabuf;

	dma_resv_unlock(dmabuf->resv);
}
EXPORT_SYMBOL(ib_umem_dmabuf_revoke_unlock);

void ib_umem_dmabuf_revoke(struct ib_umem_dmabuf *umem_dmabuf)
{
	struct dma_buf *dmabuf = umem_dmabuf->attach->dmabuf;

	dma_resv_lock(dmabuf->resv, NULL);
	ib_umem_dmabuf_revoke_locked(umem_dmabuf->attach);
	dma_resv_unlock(dmabuf->resv);
}
EXPORT_SYMBOL(ib_umem_dmabuf_revoke);

void ib_umem_dmabuf_release(struct ib_umem_dmabuf *umem_dmabuf)
{
	struct dma_buf *dmabuf = umem_dmabuf->attach->dmabuf;

	ib_umem_dmabuf_revoke(umem_dmabuf);

	dma_buf_detach(dmabuf, umem_dmabuf->attach);
	dma_buf_put(dmabuf);
	kfree(umem_dmabuf);
}