3 files changed, 96 insertions, 33 deletions

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 66d4aa8799b7..9651c0a5abe0 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -8,6 +8,7 @@
 #include <linux/blkdev.h>
 #include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
 #include <linux/gcd.h>
+#include <linux/lcm.h>
 
 #include "blk.h"
 
@@ -490,18 +491,31 @@ EXPORT_SYMBOL(blk_queue_stack_limits);
 
 /**
  * blk_stack_limits - adjust queue_limits for stacked devices
- * @t:	the stacking driver limits (top)
- * @b:  the underlying queue limits (bottom)
+ * @t:	the stacking driver limits (top device)
+ * @b:  the underlying queue limits (bottom, component device)
  * @offset:  offset to beginning of data within component device
  *
  * Description:
- *    Merges two queue_limit structs.  Returns 0 if alignment didn't
- *    change.  Returns -1 if adding the bottom device caused
- *    misalignment.
+ *    This function is used by stacking drivers like MD and DM to ensure
+ *    that all component devices have compatible block sizes and
+ *    alignments.  The stacking driver must provide a queue_limits
+ *    struct (top) and then iteratively call the stacking function for
+ *    all component (bottom) devices.  The stacking function will
+ *    attempt to combine the values and ensure proper alignment.
+ *
+ *    Returns 0 if the top and bottom queue_limits are compatible.  The
+ *    top device's block sizes and alignment offsets may be adjusted to
+ *    ensure alignment with the bottom device. If no compatible sizes
+ *    and alignments exist, -1 is returned and the resulting top
+ *    queue_limits will have the misaligned flag set to indicate that
+ *    the alignment_offset is undefined.
  */
 int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		     sector_t offset)
 {
+	sector_t alignment;
+	unsigned int top, bottom, ret = 0;
+
 	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
 	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
 	t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
@@ -518,6 +532,26 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->max_segment_size = min_not_zero(t->max_segment_size,
 					   b->max_segment_size);
 
+	t->misaligned |= b->misaligned;
+
+	alignment = queue_limit_alignment_offset(b, offset);
+
+	/* Bottom device has different alignment.  Check that it is
+	 * compatible with the current top alignment.
+	 */
+	if (t->alignment_offset != alignment) {
+
+		top = max(t->physical_block_size, t->io_min)
+			+ t->alignment_offset;
+		bottom = max(b->physical_block_size, b->io_min) + alignment;
+
+		/* Verify that top and bottom intervals line up */
+		if (max(top, bottom) & (min(top, bottom) - 1)) {
+			t->misaligned = 1;
+			ret = -1;
+		}
+	}
+
 	t->logical_block_size = max(t->logical_block_size,
 				    b->logical_block_size);
 
@@ -525,41 +559,72 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 				     b->physical_block_size);
 
 	t->io_min = max(t->io_min, b->io_min);
+	t->io_opt = lcm(t->io_opt, b->io_opt);
+
 	t->no_cluster |= b->no_cluster;
 
-	/* Bottom device offset aligned? */
-	if (offset &&
-	    (offset & (b->physical_block_size - 1)) != b->alignment_offset) {
+	/* Physical block size a multiple of the logical block size? */
+	if (t->physical_block_size & (t->logical_block_size - 1)) {
+		t->physical_block_size = t->logical_block_size;
 		t->misaligned = 1;
-		return -1;
+		ret = -1;
 	}
 
-	/* If top has no alignment offset, inherit from bottom */
-	if (!t->alignment_offset)
-		t->alignment_offset =
-			b->alignment_offset & (b->physical_block_size - 1);
+	/* Minimum I/O a multiple of the physical block size? */
+	if (t->io_min & (t->physical_block_size - 1)) {
+		t->io_min = t->physical_block_size;
+		t->misaligned = 1;
+		ret = -1;
+	}
 
-	/* Top device aligned on logical block boundary? */
-	if (t->alignment_offset & (t->logical_block_size - 1)) {
+	/* Optimal I/O a multiple of the physical block size? */
+	if (t->io_opt & (t->physical_block_size - 1)) {
+		t->io_opt = 0;
 		t->misaligned = 1;
-		return -1;
+		ret = -1;
 	}
 
-	/* Find lcm() of optimal I/O size */
-	if (t->io_opt && b->io_opt)
-		t->io_opt = (t->io_opt * b->io_opt) / gcd(t->io_opt, b->io_opt);
-	else if (b->io_opt)
-		t->io_opt = b->io_opt;
+	/* Find lowest common alignment_offset */
+	t->alignment_offset = lcm(t->alignment_offset, alignment)
+		& (max(t->physical_block_size, t->io_min) - 1);
 
-	/* Verify that optimal I/O size is a multiple of io_min */
-	if (t->io_min && t->io_opt % t->io_min)
-		return -1;
+	/* Verify that new alignment_offset is on a logical block boundary */
+	if (t->alignment_offset & (t->logical_block_size - 1)) {
+		t->misaligned = 1;
+		ret = -1;
+	}
 
-	return 0;
+	/* Discard */
+	t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
+					      b->max_discard_sectors);
+
+	return ret;
 }
 EXPORT_SYMBOL(blk_stack_limits);
 
 /**
+ * bdev_stack_limits - adjust queue limits for stacked drivers
+ * @t:	the stacking driver limits (top device)
+ * @bdev:  the component block_device (bottom)
+ * @start:  first data sector within component device
+ *
+ * Description:
+ *    Merges queue limits for a top device and a block_device.  Returns
+ *    0 if alignment didn't change.  Returns -1 if adding the bottom
+ *    device caused misalignment.
+ */
+int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
+		      sector_t start)
+{
+	struct request_queue *bq = bdev_get_queue(bdev);
+
+	start += get_start_sect(bdev);
+
+	return blk_stack_limits(t, &bq->limits, start << 9);
+}
+EXPORT_SYMBOL(bdev_stack_limits);
+
+/**
  * disk_stack_limits - adjust queue limits for stacked drivers
  * @disk:  MD/DM gendisk (top)
  * @bdev:  the underlying block device (bottom)
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 1ba7e0aca878..4f0c06c7a338 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -109,6 +109,7 @@ void blk_rq_timed_out_timer(unsigned long data)
 	struct request_queue *q = (struct request_queue *) data;
 	unsigned long flags, next = 0;
 	struct request *rq, *tmp;
+	int next_set = 0;
 
 	spin_lock_irqsave(q->queue_lock, flags);
 
@@ -122,16 +123,13 @@ void blk_rq_timed_out_timer(unsigned long data)
 			if (blk_mark_rq_complete(rq))
 				continue;
 			blk_rq_timed_out(rq);
-		} else if (!next || time_after(next, rq->deadline))
+		} else if (!next_set || time_after(next, rq->deadline)) {
 			next = rq->deadline;
+			next_set = 1;
+		}
 	}
 
-	/*
-	 * next can never be 0 here with the list non-empty, since we always
-	 * bump ->deadline to 1 so we can detect if the timer was ever added
-	 * or not. See comment in blk_add_timer()
-	 */
-	if (next)
+	if (next_set)
 		mod_timer(&q->timeout, round_jiffies_up(next));
 
 	spin_unlock_irqrestore(q->queue_lock, flags);
diff --git a/block/bsg.c b/block/bsg.c
index 0676301f16d0..7154a7a7e9ca 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -424,7 +424,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	/*
 	 * fill in all the output members
 	 */
-	hdr->device_status = status_byte(rq->errors);
+	hdr->device_status = rq->errors & 0xff;
 	hdr->transport_status = host_byte(rq->errors);
 	hdr->driver_status = driver_byte(rq->errors);
 	hdr->info = 0;