mirror of
https://github.com/torvalds/linux.git
synced 2024-11-18 10:01:43 +00:00
e6fb246cca
Now that the SRCU stuff has been removed the entire MR destroy logic can be made a lot simpler. Currently there are many different ways to destroy a MR and it makes it really hard to do this task correctly. Route all destruction through mlx5_ib_dereg_mr() and make it work for all situations. Since it turns out all the different MR types do basically the same thing this removes a lot of knowledge of MR internals from ODP and leaves ODP just exporting an operation to clean up children. This fixes a few weird corner cases bugs and firmly uses the correct ordering of the MR destruction: - Stop parallel access to the mkey via the ODP xarray - Stop DMA - Release the umem - Clean up ODP children - Free/Recycle the MR Link: https://lore.kernel.org/r/20210304120745.1090751-4-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
179 lines
4.3 KiB
C
179 lines
4.3 KiB
C
// 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_resv_lock(dmabuf->resv, NULL);
|
|
ib_umem_dmabuf_unmap_pages(umem_dmabuf);
|
|
dma_resv_unlock(dmabuf->resv);
|
|
|
|
dma_buf_detach(dmabuf, umem_dmabuf->attach);
|
|
dma_buf_put(dmabuf);
|
|
kfree(umem_dmabuf);
|
|
}
|