Patch "mm: cma: align to physical address, not CMA region position" has been added to the 3.18-stable tree

This is a note to let you know that I've just added the patch titled

mm: cma: align to physical address, not CMA region position

to the 3.18-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
mm-cma-align-to-physical-address-not-cma-region-position.patch
and it can be found in the queue-3.18 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

From: Gregory Fong <[email protected]>
Date: Fri, 12 Dec 2014 16:54:48 -0800
Subject: mm: cma: align to physical address, not CMA region position

From: Gregory Fong <[email protected]>

commit b5be83e308f70e16c63c4e520ea7bb03ef57c46f upstream.

The alignment in cma_alloc() was done w.r.t. the bitmap. This is a problem when, for example:

- a device requires 16M (order 12) alignment
- the CMA region is not 16 M aligned

In such a case, can result with the CMA region starting at, say, 0x2f800000 but any allocation you make from there will be aligned from there. Requesting an allocation of 32 M with 16 M alignment will result in an allocation from 0x2f800000 to 0x31800000, which doesn't work very well if your strange device requires 16M alignment.

Change to use bitmap_find_next_zero_area_off() to account for the difference in alignment at reserve-time and alloc-time.

---
 mm/cma.c |   19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

@@ -63,6 +63,17 @@ static unsigned long cma_bitmap_aligned_
 	return (1UL << (align_order - cma->order_per_bit)) - 1;
 }
 
+static unsigned long cma_bitmap_aligned_offset(struct cma *cma, int align_order)
+{
+	unsigned int alignment;
+
+	if (align_order <= cma->order_per_bit)
+		return 0;
+	alignment = 1UL << (align_order - cma->order_per_bit);
+	return ALIGN(cma->base_pfn, alignment) -
+		(cma->base_pfn >> cma->order_per_bit);
+}
+
 static unsigned long cma_bitmap_maxno(struct cma *cma)
 {
 	return cma->count >> cma->order_per_bit;

@@ -341,7 +352,7 @@ err:
  */
 struct page *cma_alloc(struct cma *cma, int count, unsigned int align)
 {
-	unsigned long mask, pfn, start = 0;
+	unsigned long mask, offset, pfn, start = 0;
 	unsigned long bitmap_maxno, bitmap_no, bitmap_count;
 	struct page *page = NULL;
 	int ret;

@@ -356,13 +367,15 @@ struct page *cma_alloc(struct cma *cma,
 		return NULL;
 
 	mask = cma_bitmap_aligned_mask(cma, align);
+	offset = cma_bitmap_aligned_offset(cma, align);
 	bitmap_maxno = cma_bitmap_maxno(cma);
 	bitmap_count = cma_bitmap_pages_to_bits(cma, count);
 
 	for (;;) {
 		mutex_lock(&cma->lock);
-		bitmap_no = bitmap_find_next_zero_area(cma->bitmap,
-				bitmap_maxno, start, bitmap_count, mask);
+		bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap,
+				bitmap_maxno, start, bitmap_count, mask,
+				offset);
 		if (bitmap_no >= bitmap_maxno) {
 			mutex_unlock(&cma->lock);
 			break;

Patches currently in stable-queue which might be from [email protected] are

queue-3.18/lib-bitmap-add-alignment-offset-for-bitmap_find_next_zero_area.patch queue-3.18/mm-cma-fix-cma-aligned-offset-calculation.patch queue-3.18/mm-cma-align-to-physical-address-not-cma-region-position.patch queue-3.18/mm-cma-constify-and-use-correct-signness-in-mm-cma.c.patch