[PATCH] staging: vc04_services: Fix bulk cache maintenance

[Phil Elwell]

vchiq_arm supports transfers less than one page and at arbitrary
alignment, using the dma-mapping API to perform its cache maintenance
(even though the VPU drives the DMA hardware). Read (DMA_FROM_DEVICE)
operations use cache invalidation for speed, falling back to
clean+invalidate on partial cache lines, with writes (DMA_TO_DEVICE)
using flushes.

If a read transfer has ends which aren't page-aligned, performing cache
maintenance as if they were whole pages can lead to memory corruption
since the partial cache lines at the ends (and any cache lines before or
after the transfer area) will be invalidated. This bug was masked until
the disabling of the cache flush in flush_dcache_page().

Honouring the requested transfer start- and end-points prevents the
corruption.

Fixes: cf9caf192988 ("staging: vc04_services: Replace dmac_map_area with dmac_map_sg")
Signed-off-by: Phil Elwell <phil at raspberrypi.org>
---
 .../interface/vchiq_arm/vchiq_2835_arm.c           | 31 +++++++++++++---------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c
index 3aeffcb..02e9736 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c
@@ -501,8 +501,15 @@ int vchiq_platform_init(struct platform_device *pdev, VCHIQ_STATE_T *state)
 	 */
 	sg_init_table(scatterlist, num_pages);
 	/* Now set the pages for each scatterlist */
-	for (i = 0; i < num_pages; i++)
-		sg_set_page(scatterlist + i, pages[i], PAGE_SIZE, 0);
+	for (i = 0; i < num_pages; i++)	{
+		unsigned int len = PAGE_SIZE - offset;
+
+		if (len > count)
+			len = count;
+		sg_set_page(scatterlist + i, pages[i], len, offset);
+		offset = 0;
+		count -= len;
+	}
 
 	dma_buffers = dma_map_sg(g_dev,
 				 scatterlist,
@@ -523,20 +530,20 @@ int vchiq_platform_init(struct platform_device *pdev, VCHIQ_STATE_T *state)
 		u32 addr = sg_dma_address(sg);
 
 		/* Note: addrs is the address + page_count - 1
-		 * The firmware expects the block to be page
+		 * The firmware expects blocks after the first to be page-
 		 * aligned and a multiple of the page size
 		 */
 		WARN_ON(len == 0);
-		WARN_ON(len & ~PAGE_MASK);
-		WARN_ON(addr & ~PAGE_MASK);
+		WARN_ON(i && (i != (dma_buffers - 1)) && (len & ~PAGE_MASK));
+		WARN_ON(i && (addr & ~PAGE_MASK));
 		if (k > 0 &&
-		    ((addrs[k - 1] & PAGE_MASK) |
-			((addrs[k - 1] & ~PAGE_MASK) + 1) << PAGE_SHIFT)
-		    == addr) {
-			addrs[k - 1] += (len >> PAGE_SHIFT);
-		} else {
-			addrs[k++] = addr | ((len >> PAGE_SHIFT) - 1);
-		}
+		    ((addrs[k - 1] & PAGE_MASK) +
+		     (((addrs[k - 1] & ~PAGE_MASK) + 1) << PAGE_SHIFT))
+		    == (addr & PAGE_MASK))
+			addrs[k - 1] += ((len + PAGE_SIZE - 1) >> PAGE_SHIFT);
+		else
+			addrs[k++] = (addr & PAGE_MASK) |
+				(((len + PAGE_SIZE - 1) >> PAGE_SHIFT) - 1);
 	}
 
 	/* Partial cache lines (fragments) require special measures */
-- 
1.9.1