[PATCH 3.16 009/254] scsi: use dma_get_cache_alignment() as minimum DMA alignment

[Ben Hutchings]

3.16.55-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Huacai Chen <chenhc@xxxxxxxxxx>

commit 90addc6b3c9cda0146fbd62a08e234c2b224a80c upstream.

In non-coherent DMA mode, kernel uses cache flushing operations to
maintain I/O coherency, so scsi's block queue should be aligned to the
value returned by dma_get_cache_alignment().  Otherwise, If a DMA buffer
and a kernel structure share a same cache line, and if the kernel
structure has dirty data, cache_invalidate (no writeback) will cause
data corruption.

Signed-off-by: Huacai Chen <chenhc@xxxxxxxxxx>
[hch: rebased and updated the comment and changelog]
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
 drivers/scsi/scsi_lib.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1671,11 +1671,13 @@ struct request_queue *__scsi_alloc_queue
 		q->limits.cluster = 0;
 
 	/*
-	 * set a reasonable default alignment on word boundaries: the
-	 * host and device may alter it using
-	 * blk_queue_update_dma_alignment() later.
+	 * Set a reasonable default alignment:  The larger of 32-byte (dword),
+	 * which is a common minimum for HBAs, and the minimum DMA alignment,
+	 * which is set by the platform.
+	 *
+	 * Devices that require a bigger alignment can increase it later.
 	 */
-	blk_queue_dma_alignment(q, 0x03);
+	blk_queue_dma_alignment(q, max(4, dma_get_cache_alignment()) - 1);
 
 	return q;
 }