path: root/drivers/infiniband
diff options
authorJan Kara <jack@suse.cz>2013-10-04 09:29:12 -0400
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2014-02-20 11:06:12 -0800
commit2d9258e499abbbe55fb60a26995e378f2b51d513 (patch)
treed8be92adc241ffa02b12b261658b5fe808559728 /drivers/infiniband
parentb0d4c0f8122abd6069312ccc20089d5c1c19c772 (diff)
IB/qib: Convert qib_user_sdma_pin_pages() to use get_user_pages_fast()
commit 603e7729920e42b3c2f4dbfab9eef4878cb6e8fa upstream. qib_user_sdma_queue_pkts() gets called with mmap_sem held for writing. Except for get_user_pages() deep down in qib_user_sdma_pin_pages() we don't seem to need mmap_sem at all. Even more interestingly the function qib_user_sdma_queue_pkts() (and also qib_user_sdma_coalesce() called somewhat later) call copy_from_user() which can hit a page fault and we deadlock on trying to get mmap_sem when handling that fault. So just make qib_user_sdma_pin_pages() use get_user_pages_fast() and leave mmap_sem locking for mm. This deadlock has actually been observed in the wild when the node is under memory pressure. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Roland Dreier <roland@purestorage.com> [Backported to 3.10: (Thanks to Ben Huthings) - Adjust context - Adjust indentation and nr_pages argument in qib_user_sdma_pin_pages()] Signed-off-by: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'drivers/infiniband')
1 files changed, 1 insertions, 5 deletions
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index 82442085cbe6..573b4601d5b9 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -284,8 +284,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
int j;
int ret;
- ret = get_user_pages(current, current->mm, addr,
- npages, 0, 1, pages, NULL);
+ ret = get_user_pages_fast(addr, npages, 0, pages);
if (ret != npages) {
int i;
@@ -830,10 +829,7 @@ int qib_user_sdma_writev(struct qib_ctxtdata *rcd,
while (dim) {
const int mxp = 8;
- down_write(&current->mm->mmap_sem);
ret = qib_user_sdma_queue_pkts(dd, pq, &list, iov, dim, mxp);
- up_write(&current->mm->mmap_sem);
if (ret <= 0)
goto done_unlock;
else {