async_tx: use GFP_NOWAIT rather than GFP_IO

commit b02bab6b upstream.

These async_XX functions are called from md/raid5 in an atomic
section, between get_cpu() and put_cpu(), so they must not sleep.
So use GFP_NOWAIT rather than GFP_IO.

Dan Williams writes: Longer term async_tx needs to be merged into md
directly as we can allocate this unmap data statically per-stripe
rather than per request.

Fixed: 7476bd79 ("async_pq: convert to dmaengine_unmap_data")
Reported-and-tested-by: Stanislav Samsonov <slava@annapurnalabs.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>

crypto/async_tx/async_memcpy.c

@@ -53,7 +53,7 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 	struct dmaengine_unmap_data *unmap = NULL;
 
 	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT);
 
 	if (unmap && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
 		unsigned long dma_prep_flags = 0;

crypto/async_tx/async_pq.c

@@ -188,7 +188,7 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 	BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks)));
 
 	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
 
 	/* XORing P/Q is only implemented in software */
 	if (unmap && !(submit->flags & ASYNC_TX_PQ_XOR_DST) &&
@@ -307,7 +307,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 	BUG_ON(disks < 4);
 
 	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
 
 	if (unmap && disks <= dma_maxpq(device, 0) &&
 	    is_dma_pq_aligned(device, offset, 0, len)) {

crypto/async_tx/async_raid6_recov.c

@@ -41,7 +41,7 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
 	u8 *a, *b, *c;
 
 	if (dma)
-		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOWAIT);
 
 	if (unmap) {
 		struct device *dev = dma->dev;
@@ -105,7 +105,7 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 	u8 *d, *s;
 
 	if (dma)
-		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOWAIT);
 
 	if (unmap) {
 		dma_addr_t dma_dest[2];

crypto/async_tx/async_xor.c

@@ -182,7 +182,7 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	BUG_ON(src_cnt <= 1);
 
 	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOWAIT);
 
 	if (unmap && is_dma_xor_aligned(device, offset, 0, len)) {
 		struct dma_async_tx_descriptor *tx;
@@ -278,7 +278,7 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 	BUG_ON(src_cnt <= 1);
 
 	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOWAIT);
 
 	if (unmap && src_cnt <= device->max_xor &&
 	    is_dma_xor_aligned(device, offset, 0, len)) {