md/r5cache: State machine for raid5-cache write back mode

This patch adds state machine for raid5-cache. With log device, the
raid456 array could operate in two different modes (r5c_journal_mode):
  - write-back (R5C_MODE_WRITE_BACK)
  - write-through (R5C_MODE_WRITE_THROUGH)

Existing code of raid5-cache only has write-through mode. For write-back
cache, it is necessary to extend the state machine.

With write-back cache, every stripe could operate in two different
phases:
  - caching
  - writing-out

In caching phase, the stripe handles writes as:
  - write to journal
  - return IO

In writing-out phase, the stripe behaviors as a stripe in write through
mode R5C_MODE_WRITE_THROUGH.

STRIPE_R5C_CACHING is added to sh->state to differentiate caching and
writing-out phase.

Please note: this is a "no-op" patch for raid5-cache write-through
mode.

The following detailed explanation is copied from the raid5-cache.c:

/*
 * raid5 cache state machine
 *
 * With rhe RAID cache, each stripe works in two phases:
 *      - caching phase
 *      - writing-out phase
 *
 * These two phases are controlled by bit STRIPE_R5C_CACHING:
 *   if STRIPE_R5C_CACHING == 0, the stripe is in writing-out phase
 *   if STRIPE_R5C_CACHING == 1, the stripe is in caching phase
 *
 * When there is no journal, or the journal is in write-through mode,
 * the stripe is always in writing-out phase.
 *
 * For write-back journal, the stripe is sent to caching phase on write
 * (r5c_handle_stripe_dirtying). r5c_make_stripe_write_out() kicks off
 * the write-out phase by clearing STRIPE_R5C_CACHING.
 *
 * Stripes in caching phase do not write the raid disks. Instead, all
 * writes are committed from the log device. Therefore, a stripe in
 * caching phase handles writes as:
 *      - write to log device
 *      - return IO
 *
 * Stripes in writing-out phase handle writes as:
 *      - calculate parity
 *      - write pending data and parity to journal
 *      - write data and parity to raid disks
 *      - return IO for pending writes
 */

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>

1 files changed, 30 insertions, 1 deletions

diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index ffc13c4d7e63..c9590a8e1425 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -264,6 +264,7 @@ struct stripe_head_state {
 	int syncing, expanding, expanded, replacing;
 	int locked, uptodate, to_read, to_write, failed, written;
 	int to_fill, compute, req_compute, non_overwrite;
+	int injournal;
 	int failed_num[2];
 	int p_failed, q_failed;
 	int dec_preread_active;
@@ -313,6 +314,11 @@ enum r5dev_flags {
 			 */
 	R5_Discard,	/* Discard the stripe */
 	R5_SkipCopy,	/* Don't copy data from bio to stripe cache */
+	R5_InJournal,	/* data being written is in the journal device.
+			 * if R5_InJournal is set for parity pd_idx, all the
+			 * data and parity being written are in the journal
+			 * device
+			 */
 };
 
 /*
@@ -345,7 +351,23 @@ enum {
 	STRIPE_BITMAP_PENDING,	/* Being added to bitmap, don't add
 				 * to batch yet.
 				 */
-	STRIPE_LOG_TRAPPED, /* trapped into log */
+	STRIPE_LOG_TRAPPED,	/* trapped into log (see raid5-cache.c)
+				 * this bit is used in two scenarios:
+				 *
+				 * 1. write-out phase
+				 *  set in first entry of r5l_write_stripe
+				 *  clear in second entry of r5l_write_stripe
+				 *  used to bypass logic in handle_stripe
+				 *
+				 * 2. caching phase
+				 *  set in r5c_try_caching_write()
+				 *  clear when journal write is done
+				 *  used to initiate r5c_cache_data()
+				 *  also used to bypass logic in handle_stripe
+				 */
+	STRIPE_R5C_CACHING,	/* the stripe is in caching phase
+				 * see more detail in the raid5-cache.c
+				 */
 };
 
 #define STRIPE_EXPAND_SYNC_FLAGS \
@@ -710,4 +732,11 @@ extern void r5l_stripe_write_finished(struct stripe_head *sh);
 extern int r5l_handle_flush_request(struct r5l_log *log, struct bio *bio);
 extern void r5l_quiesce(struct r5l_log *log, int state);
 extern bool r5l_log_disk_error(struct r5conf *conf);
+extern bool r5c_is_writeback(struct r5l_log *log);
+extern int
+r5c_try_caching_write(struct r5conf *conf, struct stripe_head *sh,
+		      struct stripe_head_state *s, int disks);
+extern void
+r5c_finish_stripe_write_out(struct r5conf *conf, struct stripe_head *sh,
+			    struct stripe_head_state *s);
 #endif