Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD updates from Shaohua Li:

 - Add Partial Parity Log (ppl) feature found in Intel IMSM raid array
   by Artur Paszkiewicz. This feature is another way to close RAID5
   writehole. The Linux implementation is also available for normal
   RAID5 array if specific superblock bit is set.

 - A number of md-cluser fixes and enabling md-cluster array resize from
   Guoqing Jiang

 - A bunch of patches from Ming Lei and Neil Brown to rewrite MD bio
   handling related code. Now MD doesn't directly access bio bvec,
   bi_phys_segments and uses modern bio API for bio split.

 - Improve RAID5 IO pattern to improve performance for hard disk based
   RAID5/6 from me.

 - Several patches from Song Liu to speed up raid5-cache recovery and
   allow raid5 cache feature disabling in runtime.

 - Fix a performance regression in raid1 resync from Xiao Ni.

 - Other cleanup and fixes from various people.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md: (84 commits)
  md/raid10: skip spare disk as 'first' disk
  md/raid1: Use a new variable to count flighting sync requests
  md: clear WantReplacement once disk is removed
  md/raid1/10: remove unused queue
  md: handle read-only member devices better.
  md/raid10: wait up frozen array in handle_write_completed
  uapi: fix linux/raid/md_p.h userspace compilation error
  md-cluster: Fix a memleak in an error handling path
  md: support disabling of create-on-open semantics.
  md: allow creation of mdNNN arrays via md_mod/parameters/new_array
  raid5-ppl: use a single mempool for ppl_io_unit and header_page
  md/raid0: fix up bio splitting.
  md/linear: improve bio splitting.
  md/raid5: make chunk_aligned_read() split bios more cleanly.
  md/raid10: simplify handle_read_error()
  md/raid10: simplify the splitting of requests.
  md/raid1: factor out flush_bio_list()
  md/raid1: simplify handle_read_error().
  Revert "block: introduce bio_copy_data_partial"
  md/raid1: simplify alloc_behind_master_bio()
  ...

3 files changed, 44 insertions, 13 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 4931756d86d9..d1b04b0e99cf 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -183,7 +183,7 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter,
 
 #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len)
 
-static inline unsigned __bio_segments(struct bio *bio, struct bvec_iter *bvec)
+static inline unsigned bio_segments(struct bio *bio)
 {
 	unsigned segs = 0;
 	struct bio_vec bv;
@@ -205,17 +205,12 @@ static inline unsigned __bio_segments(struct bio *bio, struct bvec_iter *bvec)
 		break;
 	}
 
-	__bio_for_each_segment(bv, bio, iter, *bvec)
+	bio_for_each_segment(bv, bio, iter)
 		segs++;
 
 	return segs;
 }
 
-static inline unsigned bio_segments(struct bio *bio)
-{
-	return __bio_segments(bio, &bio->bi_iter);
-}
-
 /*
  * get a reference to a bio, so it won't disappear. the intended use is
  * something like:
@@ -389,8 +384,6 @@ extern void bio_put(struct bio *);
 extern void __bio_clone_fast(struct bio *, struct bio *);
 extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
 extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
-extern struct bio *bio_clone_bioset_partial(struct bio *, gfp_t,
-					    struct bio_set *, int, int);
 
 extern struct bio_set *fs_bio_set;
 
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 3a481a49546e..c13dceb87b60 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -99,6 +99,7 @@ int __must_check percpu_ref_init(struct percpu_ref *ref,
 void percpu_ref_exit(struct percpu_ref *ref);
 void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_switch);
+void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref);
 void percpu_ref_switch_to_percpu(struct percpu_ref *ref);
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill);
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index 9930f3e9040f..d500bd224979 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -242,10 +242,18 @@ struct mdp_superblock_1 {
 
 	__le32	chunksize;	/* in 512byte sectors */
 	__le32	raid_disks;
-	__le32	bitmap_offset;	/* sectors after start of superblock that bitmap starts
-				 * NOTE: signed, so bitmap can be before superblock
-				 * only meaningful of feature_map[0] is set.
-				 */
+	union {
+		__le32	bitmap_offset;	/* sectors after start of superblock that bitmap starts
+					 * NOTE: signed, so bitmap can be before superblock
+					 * only meaningful of feature_map[0] is set.
+					 */
+
+		/* only meaningful when feature_map[MD_FEATURE_PPL] is set */
+		struct {
+			__le16 offset; /* sectors from start of superblock that ppl starts (signed) */
+			__le16 size; /* ppl size in sectors */
+		} ppl;
+	};
 
 	/* These are only valid with feature bit '4' */
 	__le32	new_level;	/* new level we are reshaping to		*/
@@ -318,6 +326,7 @@ struct mdp_superblock_1 {
 					     */
 #define MD_FEATURE_CLUSTERED		256 /* clustered MD */
 #define	MD_FEATURE_JOURNAL		512 /* support write cache */
+#define	MD_FEATURE_PPL			1024 /* support PPL */
 #define	MD_FEATURE_ALL			(MD_FEATURE_BITMAP_OFFSET	\
 					|MD_FEATURE_RECOVERY_OFFSET	\
 					|MD_FEATURE_RESHAPE_ACTIVE	\
@@ -328,6 +337,7 @@ struct mdp_superblock_1 {
 					|MD_FEATURE_RECOVERY_BITMAP	\
 					|MD_FEATURE_CLUSTERED		\
 					|MD_FEATURE_JOURNAL		\
+					|MD_FEATURE_PPL			\
 					)
 
 struct r5l_payload_header {
@@ -388,4 +398,31 @@ struct r5l_meta_block {
 
 #define R5LOG_VERSION 0x1
 #define R5LOG_MAGIC 0x6433c509
+
+struct ppl_header_entry {
+	__le64 data_sector;	/* raid sector of the new data */
+	__le32 pp_size;		/* length of partial parity */
+	__le32 data_size;	/* length of data */
+	__le32 parity_disk;	/* member disk containing parity */
+	__le32 checksum;	/* checksum of partial parity data for this
+				 * entry (~crc32c) */
+} __attribute__ ((__packed__));
+
+#define PPL_HEADER_SIZE 4096
+#define PPL_HDR_RESERVED 512
+#define PPL_HDR_ENTRY_SPACE \
+	(PPL_HEADER_SIZE - PPL_HDR_RESERVED - 4 * sizeof(__le32) - sizeof(__le64))
+#define PPL_HDR_MAX_ENTRIES \
+	(PPL_HDR_ENTRY_SPACE / sizeof(struct ppl_header_entry))
+
+struct ppl_header {
+	__u8 reserved[PPL_HDR_RESERVED];/* reserved space, fill with 0xff */
+	__le32 signature;		/* signature (family number of volume) */
+	__le32 padding;			/* zero pad */
+	__le64 generation;		/* generation number of the header */
+	__le32 entries_count;		/* number of entries in entry array */
+	__le32 checksum;		/* checksum of the header (~crc32c) */
+	struct ppl_header_entry entries[PPL_HDR_MAX_ENTRIES];
+} __attribute__ ((__packed__));
+
 #endif