Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull block layer fixes from Jens Axboe:
 "A small collection of fixes that should go in before -rc1.  The pull
  request contains:

   - A two patch fix for a regression with block enabled tagging caused
     by a commit in the initial pull request.  One patch is from Martin
     and ensures that SCSI doesn't truncate 64-bit block flags, the
     other one is from me and prevents us from double using struct
     request queuelist for both completion and busy tags.  This caused
     anything from a boot crash for some, to crashes under load.

   - A blk-mq fix for a potential soft stall when hot unplugging CPUs
     with busy IO.

   - percpu_counter fix is listed in here, that caused a suspend issue
     with virtio-blk due to percpu counters having an inconsistent state
     during CPU removal.  Andrew sent this in separately a few days ago,
     but it's here.  JFYI.

   - A few fixes for block integrity from Martin.

   - A ratelimit fix for loop from Mike Galbraith, to avoid spewing too
     much in error cases"

* 'for-linus' of git://git.kernel.dk/linux-block:
  block: fix regression with block enabled tagging
  scsi: Make sure cmd_flags are 64-bit
  block: Ensure we only enable integrity metadata for reads and writes
  block: Fix integrity verification
  block: Fix for_each_bvec()
  drivers/block/loop.c: ratelimit error messages
  blk-mq: fix potential stall during CPU unplug with IO pending
  percpu_counter: fix bad counter state during suspend

include/linux/bio.h

@@ -216,9 +216,9 @@ static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter,
 }
 
 #define for_each_bvec(bvl, bio_vec, iter, start)			\
-	for ((iter) = start;						\
-	     (bvl) = bvec_iter_bvec((bio_vec), (iter)),			\
-		(iter).bi_size;						\
+	for (iter = (start);						\
+	     (iter).bi_size &&						\
+		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
 	     bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len))
 
 

include/linux/blk_types.h

@@ -189,6 +189,7 @@ enum rq_flag_bits {
 	__REQ_KERNEL, 		/* direct IO to kernel pages */
 	__REQ_PM,		/* runtime pm request */
 	__REQ_END,		/* last of chain of requests */
+	__REQ_HASHED,		/* on IO scheduler merge hash */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -241,5 +242,6 @@ enum rq_flag_bits {
 #define REQ_KERNEL		(1ULL << __REQ_KERNEL)
 #define REQ_PM			(1ULL << __REQ_PM)
 #define REQ_END			(1ULL << __REQ_END)
+#define REQ_HASHED		(1ULL << __REQ_HASHED)
 
 #endif /* __LINUX_BLK_TYPES_H */

include/linux/blkdev.h

@@ -118,7 +118,18 @@ struct request {
 	struct bio *bio;
 	struct bio *biotail;
 
-	struct hlist_node hash;	/* merge hash */
+	/*
+	 * The hash is used inside the scheduler, and killed once the
+	 * request reaches the dispatch list. The ipi_list is only used
+	 * to queue the request for softirq completion, which is long
+	 * after the request has been unhashed (and even removed from
+	 * the dispatch list).
+	 */
+	union {
+		struct hlist_node hash;	/* merge hash */
+		struct list_head ipi_list;
+	};
+
 	/*
 	 * The rb_node is only used inside the io scheduler, requests
 	 * are pruned when moved to the dispatch queue. So let the