diff options
author | Jason Gunthorpe <jgg@mellanox.com> | 2019-10-01 12:38:18 -0300 |
---|---|---|
committer | Jason Gunthorpe <jgg@mellanox.com> | 2019-10-04 15:54:21 -0300 |
commit | 9dc775e7f5508f848661bbfb2e15683affb85f24 (patch) | |
tree | aeb8c269379663f95cb5a03a9d2b1a7b264d8a01 /drivers/infiniband/core/umem_odp.c | |
parent | f28b1932eaae183b80bd8c7abecae167a0e5c61a (diff) |
RDMA/odp: Lift umem_mutex out of ib_umem_odp_unmap_dma_pages()
This fixes a race of the form:
CPU0 CPU1
mlx5_ib_invalidate_range() mlx5_ib_invalidate_range()
// This one actually makes npages == 0
ib_umem_odp_unmap_dma_pages()
if (npages == 0 && !dying)
// This one does nothing
ib_umem_odp_unmap_dma_pages()
if (npages == 0 && !dying)
dying = 1;
dying = 1;
schedule_work(&umem_odp->work);
// Double schedule of the same work
schedule_work(&umem_odp->work); // BOOM
npages and dying must be read and written under the umem_mutex lock.
Since whenever ib_umem_odp_unmap_dma_pages() is called mlx5 must also call
mlx5_ib_update_xlt, and both need to be done in the same locking region,
hoist the lock out of unmap.
This avoids an expensive double critical section in
mlx5_ib_invalidate_range().
Fixes: 81713d3788d2 ("IB/mlx5: Add implicit MR support")
Link: https://lore.kernel.org/r/20191001153821.23621-4-jgg@ziepe.ca
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Diffstat (limited to 'drivers/infiniband/core/umem_odp.c')
-rw-r--r-- | drivers/infiniband/core/umem_odp.c | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index f67a30fda1ed..163ff7ba92b7 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -451,8 +451,10 @@ void ib_umem_odp_release(struct ib_umem_odp *umem_odp) * that the hardware will not attempt to access the MR any more. */ if (!umem_odp->is_implicit_odp) { + mutex_lock(&umem_odp->umem_mutex); ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp), ib_umem_end(umem_odp)); + mutex_unlock(&umem_odp->umem_mutex); kvfree(umem_odp->dma_list); kvfree(umem_odp->page_list); } @@ -719,6 +721,8 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt, u64 addr; struct ib_device *dev = umem_odp->umem.ibdev; + lockdep_assert_held(&umem_odp->umem_mutex); + virt = max_t(u64, virt, ib_umem_start(umem_odp)); bound = min_t(u64, bound, ib_umem_end(umem_odp)); /* Note that during the run of this function, the @@ -726,7 +730,6 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt, * faults from completion. We might be racing with other * invalidations, so we must make sure we free each page only * once. */ - mutex_lock(&umem_odp->umem_mutex); for (addr = virt; addr < bound; addr += BIT(umem_odp->page_shift)) { idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift; if (umem_odp->page_list[idx]) { @@ -757,7 +760,6 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt, umem_odp->npages--; } } - mutex_unlock(&umem_odp->umem_mutex); } EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages); |