BackPup/Linux
1
0 Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-10-07 05:31:08 -04:00
Code Issues Packages Projects Releases Wiki Activity

IB/ipath: Convert ipath_user_sdma_pin_pages() to use get_user_pages_fast()

Browse Source 
ipath_user_sdma_queue_pkts() gets called with mmap_sem held for
writing.  Except for get_user_pages() deep down in
ipath_user_sdma_pin_pages() we don't seem to need mmap_sem at all.

Even more interestingly the function ipath_user_sdma_queue_pkts() (and
also ipath_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
ipath_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.

Cc: <[email protected]>
Signed-off-by: Jan Kara <[email protected]>
Signed-off-by: Mike Marciniszyn <[email protected]>

[ Merged in fix for call to get_user_pages_fast from Tetsuo Handa
  <[email protected]>.  - Roland ]

Signed-off-by: Roland Dreier <[email protected]>
This commit is contained in:
Jan Kara authored and Roland Dreier committed 2013-11-08 14:43:11 -08:00
1 parent 959f58544b
commit 4adcf7fb67
1 file changed
+1 -6
Download Patch File Download Diff File Expand all files Collapse all files
drivers/infiniband/hw/ipath/ipath_user_sdma.c
+1 -6
View File
@@ -280,9 +280,7 @@ static int ipath_user_sdma_pin_pages(const struct ipath_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;
@@ -811,10 +809,7 @@ int ipath_user_sdma_writev(struct ipath_devdata *dd,
while (dim) {
const int mxp = 8;
down_write(&current->mm->mmap_sem);
ret = ipath_user_sdma_queue_pkts(dd, pq, &list, iov, dim, mxp);
up_write(&current->mm->mmap_sem);
if (ret <= 0)
goto done_unlock;
else {