IB/qib: Use GFP_ATOMIC when locks are held

Author: Julia Lawall <julia.lawall@lip6.fr>

alloc_dummy_hdrq() is called with locks held and thus should not use
GFP_KERNEL.

The semantic patch that makes this report is available in
scripts/coccinelle/locks/call_kern.cocci.

Signed-off-by: Julia Lawall 
Acked-by: Mike Marciniszyn 
Signed-off-by: Roland Dreier 
---
 drivers/infiniband/hw/qib/qib_iba6120.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
 
diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c
index 4f18e2d..d0c64d5 100644
--- a/drivers/infiniband/hw/qib/qib_iba6120.c
+++ b/drivers/infiniband/hw/qib/qib_iba6120.c
@@ -2105,7 +2105,7 @@ static void alloc_dummy_hdrq(struct qib_devdata *dd)
 	dd->cspec->dummy_hdrq = dma_alloc_coherent(&dd->pcidev->dev,
 					dd->rcd[0]->rcvhdrq_size,
 					&dd->cspec->dummy_hdrq_phys,
-					GFP_KERNEL | __GFP_COMP);
+					GFP_ATOMIC | __GFP_COMP);
 	if (!dd->cspec->dummy_hdrq) {
 		qib_devinfo(dd->pcidev, "Couldn't allocate dummy hdrq\n");
 		/* fallback to just 0'ing */