Merge tag 'md/4.4' of git://neil.brown.name/md

Pull md updates from Neil Brown:
 "Two major components to this update.

   1) The clustered-raid1 support from SUSE is nearly complete.  There
      are a few outstanding issues being worked on.  Maybe half a dozen
      patches will bring this to a usable state.

   2) The first stage of journalled-raid5 support from Facebook makes an
      appearance.  With a journal device configured (typically NVRAM or
      SSD), the "RAID5 write hole" should be closed - a crash during
      degraded operations cannot result in data corruption.

      The next stage will be to use the journal as a write-behind cache
      so that latency can be reduced and in some cases throughput
      increased by performing more full-stripe writes.

* tag 'md/4.4' of git://neil.brown.name/md: (66 commits)
  MD: when RAID journal is missing/faulty, block RESTART_ARRAY_RW
  MD: set journal disk ->raid_disk
  MD: kick out journal disk if it's not fresh
  raid5-cache: start raid5 readonly if journal is missing
  MD: add new bit to indicate raid array with journal
  raid5-cache: IO error handling
  raid5: journal disk can't be removed
  raid5-cache: add trim support for log
  MD: fix info output for journal disk
  raid5-cache: use bio chaining
  raid5-cache: small log->seq cleanup
  raid5-cache: new helper: r5_reserve_log_entry
  raid5-cache: inline r5l_alloc_io_unit into r5l_new_meta
  raid5-cache: take rdev->data_offset into account early on
  raid5-cache: refactor bio allocation
  raid5-cache: clean up r5l_get_meta
  raid5-cache: simplify state machine when caches flushes are not needed
  raid5-cache: factor out a helper to run all stripes for an I/O unit
  raid5-cache: rename flushed_ios to finished_ios
  raid5-cache: free I/O units earlier
  ...

1 files changed, 72 insertions, 1 deletions

diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index 2ae6131e69a5..c3e654c6d518 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -89,6 +89,12 @@
 				   * read requests will only be sent here in
 				   * dire need
 				   */
+#define MD_DISK_JOURNAL		18 /* disk is used as the write journal in RAID-5/6 */
+
+#define MD_DISK_ROLE_SPARE	0xffff
+#define MD_DISK_ROLE_FAULTY	0xfffe
+#define MD_DISK_ROLE_JOURNAL	0xfffd
+#define MD_DISK_ROLE_MAX	0xff00 /* max value of regular disk role */
 
 typedef struct mdp_device_descriptor_s {
 	__u32 number;		/* 0 Device number in the entire set	      */
@@ -252,7 +258,10 @@ struct mdp_superblock_1 {
 	__le64	data_offset;	/* sector start of data, often 0 */
 	__le64	data_size;	/* sectors in this device that can be used for data */
 	__le64	super_offset;	/* sector start of this superblock */
-	__le64	recovery_offset;/* sectors before this offset (from data_offset) have been recovered */
+	union {
+		__le64	recovery_offset;/* sectors before this offset (from data_offset) have been recovered */
+		__le64	journal_tail;/* journal tail of journal device (from data_offset) */
+	};
 	__le32	dev_number;	/* permanent identifier of this  device - not role in raid */
 	__le32	cnt_corrected_read; /* number of read errors that were corrected by re-writing */
 	__u8	device_uuid[16]; /* user-space setable, ignored by kernel */
@@ -302,6 +311,8 @@ struct mdp_superblock_1 {
 #define	MD_FEATURE_RECOVERY_BITMAP	128 /* recovery that is happening
 					     * is guided by bitmap.
 					     */
+#define MD_FEATURE_CLUSTERED		256 /* clustered MD */
+#define	MD_FEATURE_JOURNAL		512 /* support write cache */
 #define	MD_FEATURE_ALL			(MD_FEATURE_BITMAP_OFFSET	\
 					|MD_FEATURE_RECOVERY_OFFSET	\
 					|MD_FEATURE_RESHAPE_ACTIVE	\
@@ -310,6 +321,66 @@ struct mdp_superblock_1 {
 					|MD_FEATURE_RESHAPE_BACKWARDS	\
 					|MD_FEATURE_NEW_OFFSET		\
 					|MD_FEATURE_RECOVERY_BITMAP	\
+					|MD_FEATURE_CLUSTERED		\
+					|MD_FEATURE_JOURNAL		\
 					)
 
+struct r5l_payload_header {
+	__le16 type;
+	__le16 flags;
+} __attribute__ ((__packed__));
+
+enum r5l_payload_type {
+	R5LOG_PAYLOAD_DATA = 0,
+	R5LOG_PAYLOAD_PARITY = 1,
+	R5LOG_PAYLOAD_FLUSH = 2,
+};
+
+struct r5l_payload_data_parity {
+	struct r5l_payload_header header;
+	__le32 size;		/* sector. data/parity size. each 4k
+				 * has a checksum */
+	__le64 location;	/* sector. For data, it's raid sector. For
+				 * parity, it's stripe sector */
+	__le32 checksum[];
+} __attribute__ ((__packed__));
+
+enum r5l_payload_data_parity_flag {
+	R5LOG_PAYLOAD_FLAG_DISCARD = 1, /* payload is discard */
+	/*
+	 * RESHAPED/RESHAPING is only set when there is reshape activity. Note,
+	 * both data/parity of a stripe should have the same flag set
+	 *
+	 * RESHAPED: reshape is running, and this stripe finished reshape
+	 * RESHAPING: reshape is running, and this stripe isn't reshaped
+	 */
+	R5LOG_PAYLOAD_FLAG_RESHAPED = 2,
+	R5LOG_PAYLOAD_FLAG_RESHAPING = 3,
+};
+
+struct r5l_payload_flush {
+	struct r5l_payload_header header;
+	__le32 size; /* flush_stripes size, bytes */
+	__le64 flush_stripes[];
+} __attribute__ ((__packed__));
+
+enum r5l_payload_flush_flag {
+	R5LOG_PAYLOAD_FLAG_FLUSH_STRIPE = 1, /* data represents whole stripe */
+};
+
+struct r5l_meta_block {
+	__le32 magic;
+	__le32 checksum;
+	__u8 version;
+	__u8 __zero_pading_1;
+	__le16 __zero_pading_2;
+	__le32 meta_size; /* whole size of the block */
+
+	__le64 seq;
+	__le64 position; /* sector, start from rdev->data_offset, current position */
+	struct r5l_payload_header payloads[];
+} __attribute__ ((__packed__));
+
+#define R5LOG_VERSION 0x1
+#define R5LOG_MAGIC 0x6433c509
 #endif