From 33ba6129208475ec3aeffe6e9dad9f9afe022405 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 3 Oct 2016 09:11:22 -0700 Subject: [PATCH] xfs: connect refcount adjust functions to upper layers Plumb in the upper level interface to schedule and finish deferred refcount operations via the deferred ops mechanism. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_defer.h | 1 + fs/xfs/libxfs/xfs_refcount.c | 174 ++++++++++++++++++++++++++++++++ fs/xfs/libxfs/xfs_refcount.h | 13 +++ fs/xfs/xfs_error.h | 4 +- fs/xfs/xfs_refcount_item.c | 86 +++++++++++++++- fs/xfs/xfs_super.c | 1 + fs/xfs/xfs_trace.h | 3 + fs/xfs/xfs_trans.h | 8 +- fs/xfs/xfs_trans_refcount.c | 188 ++++++++++++++++++++++++++++++++++- 9 files changed, 472 insertions(+), 6 deletions(-) diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index e96533d178cf..4d94a869e581 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -51,6 +51,7 @@ struct xfs_defer_pending { * find all the space it needs. */ enum xfs_defer_ops_type { + XFS_DEFER_OPS_TYPE_REFCOUNT, XFS_DEFER_OPS_TYPE_RMAP, XFS_DEFER_OPS_TYPE_FREE, XFS_DEFER_OPS_TYPE_MAX, diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index f522fe130a16..4a31a7c2f2c4 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -989,3 +989,177 @@ out_error: error, _RET_IP_); return error; } + +/* Clean up after calling xfs_refcount_finish_one. */ +void +xfs_refcount_finish_one_cleanup( + struct xfs_trans *tp, + struct xfs_btree_cur *rcur, + int error) +{ + struct xfs_buf *agbp; + + if (rcur == NULL) + return; + agbp = rcur->bc_private.a.agbp; + xfs_btree_del_cursor(rcur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); + if (error) + xfs_trans_brelse(tp, agbp); +} + +/* + * Process one of the deferred refcount operations. We pass back the + * btree cursor to maintain our lock on the btree between calls. + * This saves time and eliminates a buffer deadlock between the + * superblock and the AGF because we'll always grab them in the same + * order. + */ +int +xfs_refcount_finish_one( + struct xfs_trans *tp, + struct xfs_defer_ops *dfops, + enum xfs_refcount_intent_type type, + xfs_fsblock_t startblock, + xfs_extlen_t blockcount, + xfs_fsblock_t *new_fsb, + xfs_extlen_t *new_len, + struct xfs_btree_cur **pcur) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_btree_cur *rcur; + struct xfs_buf *agbp = NULL; + int error = 0; + xfs_agnumber_t agno; + xfs_agblock_t bno; + xfs_agblock_t new_agbno; + unsigned long nr_ops = 0; + int shape_changes = 0; + + agno = XFS_FSB_TO_AGNO(mp, startblock); + ASSERT(agno != NULLAGNUMBER); + bno = XFS_FSB_TO_AGBNO(mp, startblock); + + trace_xfs_refcount_deferred(mp, XFS_FSB_TO_AGNO(mp, startblock), + type, XFS_FSB_TO_AGBNO(mp, startblock), + blockcount); + + if (XFS_TEST_ERROR(false, mp, + XFS_ERRTAG_REFCOUNT_FINISH_ONE, + XFS_RANDOM_REFCOUNT_FINISH_ONE)) + return -EIO; + + /* + * If we haven't gotten a cursor or the cursor AG doesn't match + * the startblock, get one now. + */ + rcur = *pcur; + if (rcur != NULL && rcur->bc_private.a.agno != agno) { + nr_ops = rcur->bc_private.a.priv.refc.nr_ops; + shape_changes = rcur->bc_private.a.priv.refc.shape_changes; + xfs_refcount_finish_one_cleanup(tp, rcur, 0); + rcur = NULL; + *pcur = NULL; + } + if (rcur == NULL) { + error = xfs_alloc_read_agf(tp->t_mountp, tp, agno, + XFS_ALLOC_FLAG_FREEING, &agbp); + if (error) + return error; + if (!agbp) + return -EFSCORRUPTED; + + rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, dfops); + if (!rcur) { + error = -ENOMEM; + goto out_cur; + } + rcur->bc_private.a.priv.refc.nr_ops = nr_ops; + rcur->bc_private.a.priv.refc.shape_changes = shape_changes; + } + *pcur = rcur; + + switch (type) { + case XFS_REFCOUNT_INCREASE: + error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno, + new_len, XFS_REFCOUNT_ADJUST_INCREASE, dfops, NULL); + *new_fsb = XFS_AGB_TO_FSB(mp, agno, new_agbno); + break; + case XFS_REFCOUNT_DECREASE: + error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno, + new_len, XFS_REFCOUNT_ADJUST_DECREASE, dfops, NULL); + *new_fsb = XFS_AGB_TO_FSB(mp, agno, new_agbno); + break; + default: + ASSERT(0); + error = -EFSCORRUPTED; + } + if (!error && *new_len > 0) + trace_xfs_refcount_finish_one_leftover(mp, agno, type, + bno, blockcount, new_agbno, *new_len); + return error; + +out_cur: + xfs_trans_brelse(tp, agbp); + + return error; +} + +/* + * Record a refcount intent for later processing. + */ +static int +__xfs_refcount_add( + struct xfs_mount *mp, + struct xfs_defer_ops *dfops, + enum xfs_refcount_intent_type type, + xfs_fsblock_t startblock, + xfs_extlen_t blockcount) +{ + struct xfs_refcount_intent *ri; + + trace_xfs_refcount_defer(mp, XFS_FSB_TO_AGNO(mp, startblock), + type, XFS_FSB_TO_AGBNO(mp, startblock), + blockcount); + + ri = kmem_alloc(sizeof(struct xfs_refcount_intent), + KM_SLEEP | KM_NOFS); + INIT_LIST_HEAD(&ri->ri_list); + ri->ri_type = type; + ri->ri_startblock = startblock; + ri->ri_blockcount = blockcount; + + xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list); + return 0; +} + +/* + * Increase the reference count of the blocks backing a file's extent. + */ +int +xfs_refcount_increase_extent( + struct xfs_mount *mp, + struct xfs_defer_ops *dfops, + struct xfs_bmbt_irec *PREV) +{ + if (!xfs_sb_version_hasreflink(&mp->m_sb)) + return 0; + + return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_INCREASE, + PREV->br_startblock, PREV->br_blockcount); +} + +/* + * Decrease the reference count of the blocks backing a file's extent. + */ +int +xfs_refcount_decrease_extent( + struct xfs_mount *mp, + struct xfs_defer_ops *dfops, + struct xfs_bmbt_irec *PREV) +{ + if (!xfs_sb_version_hasreflink(&mp->m_sb)) + return 0; + + return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_DECREASE, + PREV->br_startblock, PREV->br_blockcount); +} diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index 67b1c13fb714..0a1f290269df 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -41,4 +41,17 @@ struct xfs_refcount_intent { xfs_extlen_t ri_blockcount; }; +extern int xfs_refcount_increase_extent(struct xfs_mount *mp, + struct xfs_defer_ops *dfops, struct xfs_bmbt_irec *irec); +extern int xfs_refcount_decrease_extent(struct xfs_mount *mp, + struct xfs_defer_ops *dfops, struct xfs_bmbt_irec *irec); + +extern void xfs_refcount_finish_one_cleanup(struct xfs_trans *tp, + struct xfs_btree_cur *rcur, int error); +extern int xfs_refcount_finish_one(struct xfs_trans *tp, + struct xfs_defer_ops *dfops, enum xfs_refcount_intent_type type, + xfs_fsblock_t startblock, xfs_extlen_t blockcount, + xfs_fsblock_t *new_fsb, xfs_extlen_t *new_len, + struct xfs_btree_cur **pcur); + #endif /* __XFS_REFCOUNT_H__ */ diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h index d9675c646572..641e090f3bea 100644 --- a/fs/xfs/xfs_error.h +++ b/fs/xfs/xfs_error.h @@ -93,7 +93,8 @@ extern void xfs_verifier_error(struct xfs_buf *bp); #define XFS_ERRTAG_FREE_EXTENT 22 #define XFS_ERRTAG_RMAP_FINISH_ONE 23 #define XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE 24 -#define XFS_ERRTAG_MAX 25 +#define XFS_ERRTAG_REFCOUNT_FINISH_ONE 25 +#define XFS_ERRTAG_MAX 26 /* * Random factors for above tags, 1 means always, 2 means 1/2 time, etc. @@ -123,6 +124,7 @@ extern void xfs_verifier_error(struct xfs_buf *bp); #define XFS_RANDOM_FREE_EXTENT 1 #define XFS_RANDOM_RMAP_FINISH_ONE 1 #define XFS_RANDOM_REFCOUNT_CONTINUE_UPDATE 1 +#define XFS_RANDOM_REFCOUNT_FINISH_ONE 1 #ifdef DEBUG extern int xfs_error_test_active; diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 599a8d2271f9..82153e2a057c 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -396,9 +396,20 @@ xfs_cui_recover( { int i; int error = 0; + unsigned int refc_type; struct xfs_phys_extent *refc; xfs_fsblock_t startblock_fsb; bool op_ok; + struct xfs_cud_log_item *cudp; + struct xfs_trans *tp; + struct xfs_btree_cur *rcur = NULL; + enum xfs_refcount_intent_type type; + xfs_fsblock_t firstfsb; + xfs_fsblock_t new_fsb; + xfs_extlen_t new_len; + struct xfs_bmbt_irec irec; + struct xfs_defer_ops dfops; + bool requeue_only = false; ASSERT(!test_bit(XFS_CUI_RECOVERED, &cuip->cui_flags)); @@ -437,7 +448,80 @@ xfs_cui_recover( } } + /* + * Under normal operation, refcount updates are deferred, so we + * wouldn't be adding them directly to a transaction. All + * refcount updates manage reservation usage internally and + * dynamically by deferring work that won't fit in the + * transaction. Normally, any work that needs to be deferred + * gets attached to the same defer_ops that scheduled the + * refcount update. However, we're in log recovery here, so we + * we create our own defer_ops and use that to finish up any + * work that doesn't fit. + */ + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); + if (error) + return error; + cudp = xfs_trans_get_cud(tp, cuip); + + xfs_defer_init(&dfops, &firstfsb); + for (i = 0; i < cuip->cui_format.cui_nextents; i++) { + refc = &cuip->cui_format.cui_extents[i]; + refc_type = refc->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK; + switch (refc_type) { + case XFS_REFCOUNT_INCREASE: + case XFS_REFCOUNT_DECREASE: + case XFS_REFCOUNT_ALLOC_COW: + case XFS_REFCOUNT_FREE_COW: + type = refc_type; + break; + default: + error = -EFSCORRUPTED; + goto abort_error; + } + if (requeue_only) { + new_fsb = refc->pe_startblock; + new_len = refc->pe_len; + } else + error = xfs_trans_log_finish_refcount_update(tp, cudp, + &dfops, type, refc->pe_startblock, refc->pe_len, + &new_fsb, &new_len, &rcur); + if (error) + goto abort_error; + + /* Requeue what we didn't finish. */ + if (new_len > 0) { + irec.br_startblock = new_fsb; + irec.br_blockcount = new_len; + switch (type) { + case XFS_REFCOUNT_INCREASE: + error = xfs_refcount_increase_extent( + tp->t_mountp, &dfops, &irec); + break; + case XFS_REFCOUNT_DECREASE: + error = xfs_refcount_decrease_extent( + tp->t_mountp, &dfops, &irec); + break; + default: + ASSERT(0); + } + if (error) + goto abort_error; + requeue_only = true; + } + } + + xfs_refcount_finish_one_cleanup(tp, rcur, error); + error = xfs_defer_finish(&tp, &dfops, NULL); + if (error) + goto abort_error; set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags); - xfs_cui_release(cuip); + error = xfs_trans_commit(tp); + return error; + +abort_error: + xfs_refcount_finish_one_cleanup(tp, rcur, error); + xfs_defer_cancel(&dfops); + xfs_trans_cancel(tp); return error; } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index abe69c656ed0..62346223d04f 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1903,6 +1903,7 @@ init_xfs_fs(void) xfs_extent_free_init_defer_op(); xfs_rmap_update_init_defer_op(); + xfs_refcount_update_init_defer_op(); xfs_dir_startup(); diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index e306e83539db..9c9acef13616 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -2931,6 +2931,9 @@ DEFINE_AG_ERROR_EVENT(xfs_refcount_find_right_extent_error); DEFINE_AG_EXTENT_EVENT(xfs_refcount_find_shared); DEFINE_AG_EXTENT_EVENT(xfs_refcount_find_shared_result); DEFINE_AG_ERROR_EVENT(xfs_refcount_find_shared_error); +#define DEFINE_REFCOUNT_DEFERRED_EVENT DEFINE_PHYS_EXTENT_DEFERRED_EVENT +DEFINE_REFCOUNT_DEFERRED_EVENT(xfs_refcount_defer); +DEFINE_REFCOUNT_DEFERRED_EVENT(xfs_refcount_deferred); TRACE_EVENT(xfs_refcount_finish_one_leftover, TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index fe69e2048978..475636b13c48 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -37,6 +37,8 @@ struct xfs_rud_log_item; struct xfs_rui_log_item; struct xfs_btree_cur; struct xfs_cui_log_item; +struct xfs_cud_log_item; +struct xfs_defer_ops; typedef struct xfs_log_item { struct list_head li_ail; /* AIL pointers */ @@ -252,11 +254,13 @@ int xfs_trans_log_finish_rmap_update(struct xfs_trans *tp, /* refcount updates */ enum xfs_refcount_intent_type; +void xfs_refcount_update_init_defer_op(void); struct xfs_cud_log_item *xfs_trans_get_cud(struct xfs_trans *tp, struct xfs_cui_log_item *cuip); int xfs_trans_log_finish_refcount_update(struct xfs_trans *tp, - struct xfs_cud_log_item *cudp, + struct xfs_cud_log_item *cudp, struct xfs_defer_ops *dfops, enum xfs_refcount_intent_type type, xfs_fsblock_t startblock, - xfs_extlen_t blockcount, struct xfs_btree_cur **pcur); + xfs_extlen_t blockcount, xfs_fsblock_t *new_fsb, + xfs_extlen_t *new_len, struct xfs_btree_cur **pcur); #endif /* __XFS_TRANS_H__ */ diff --git a/fs/xfs/xfs_trans_refcount.c b/fs/xfs/xfs_trans_refcount.c index b18d548c1aae..94c1877af834 100644 --- a/fs/xfs/xfs_trans_refcount.c +++ b/fs/xfs/xfs_trans_refcount.c @@ -56,15 +56,18 @@ int xfs_trans_log_finish_refcount_update( struct xfs_trans *tp, struct xfs_cud_log_item *cudp, + struct xfs_defer_ops *dop, enum xfs_refcount_intent_type type, xfs_fsblock_t startblock, xfs_extlen_t blockcount, + xfs_fsblock_t *new_fsb, + xfs_extlen_t *new_len, struct xfs_btree_cur **pcur) { int error; - /* XXX: leave this empty for now */ - error = -EFSCORRUPTED; + error = xfs_refcount_finish_one(tp, dop, type, startblock, + blockcount, new_fsb, new_len, pcur); /* * Mark the transaction dirty, even on error. This ensures the @@ -78,3 +81,184 @@ xfs_trans_log_finish_refcount_update( return error; } + +/* Sort refcount intents by AG. */ +static int +xfs_refcount_update_diff_items( + void *priv, + struct list_head *a, + struct list_head *b) +{ + struct xfs_mount *mp = priv; + struct xfs_refcount_intent *ra; + struct xfs_refcount_intent *rb; + + ra = container_of(a, struct xfs_refcount_intent, ri_list); + rb = container_of(b, struct xfs_refcount_intent, ri_list); + return XFS_FSB_TO_AGNO(mp, ra->ri_startblock) - + XFS_FSB_TO_AGNO(mp, rb->ri_startblock); +} + +/* Get an CUI. */ +STATIC void * +xfs_refcount_update_create_intent( + struct xfs_trans *tp, + unsigned int count) +{ + struct xfs_cui_log_item *cuip; + + ASSERT(tp != NULL); + ASSERT(count > 0); + + cuip = xfs_cui_init(tp->t_mountp, count); + ASSERT(cuip != NULL); + + /* + * Get a log_item_desc to point at the new item. + */ + xfs_trans_add_item(tp, &cuip->cui_item); + return cuip; +} + +/* Set the phys extent flags for this reverse mapping. */ +static void +xfs_trans_set_refcount_flags( + struct xfs_phys_extent *refc, + enum xfs_refcount_intent_type type) +{ + refc->pe_flags = 0; + switch (type) { + case XFS_REFCOUNT_INCREASE: + case XFS_REFCOUNT_DECREASE: + case XFS_REFCOUNT_ALLOC_COW: + case XFS_REFCOUNT_FREE_COW: + refc->pe_flags |= type; + break; + default: + ASSERT(0); + } +} + +/* Log refcount updates in the intent item. */ +STATIC void +xfs_refcount_update_log_item( + struct xfs_trans *tp, + void *intent, + struct list_head *item) +{ + struct xfs_cui_log_item *cuip = intent; + struct xfs_refcount_intent *refc; + uint next_extent; + struct xfs_phys_extent *ext; + + refc = container_of(item, struct xfs_refcount_intent, ri_list); + + tp->t_flags |= XFS_TRANS_DIRTY; + cuip->cui_item.li_desc->lid_flags |= XFS_LID_DIRTY; + + /* + * atomic_inc_return gives us the value after the increment; + * we want to use it as an array index so we need to subtract 1 from + * it. + */ + next_extent = atomic_inc_return(&cuip->cui_next_extent) - 1; + ASSERT(next_extent < cuip->cui_format.cui_nextents); + ext = &cuip->cui_format.cui_extents[next_extent]; + ext->pe_startblock = refc->ri_startblock; + ext->pe_len = refc->ri_blockcount; + xfs_trans_set_refcount_flags(ext, refc->ri_type); +} + +/* Get an CUD so we can process all the deferred refcount updates. */ +STATIC void * +xfs_refcount_update_create_done( + struct xfs_trans *tp, + void *intent, + unsigned int count) +{ + return xfs_trans_get_cud(tp, intent); +} + +/* Process a deferred refcount update. */ +STATIC int +xfs_refcount_update_finish_item( + struct xfs_trans *tp, + struct xfs_defer_ops *dop, + struct list_head *item, + void *done_item, + void **state) +{ + struct xfs_refcount_intent *refc; + xfs_fsblock_t new_fsb; + xfs_extlen_t new_aglen; + int error; + + refc = container_of(item, struct xfs_refcount_intent, ri_list); + error = xfs_trans_log_finish_refcount_update(tp, done_item, dop, + refc->ri_type, + refc->ri_startblock, + refc->ri_blockcount, + &new_fsb, &new_aglen, + (struct xfs_btree_cur **)state); + /* Did we run out of reservation? Requeue what we didn't finish. */ + if (!error && new_aglen > 0) { + ASSERT(refc->ri_type == XFS_REFCOUNT_INCREASE || + refc->ri_type == XFS_REFCOUNT_DECREASE); + refc->ri_startblock = new_fsb; + refc->ri_blockcount = new_aglen; + return -EAGAIN; + } + kmem_free(refc); + return error; +} + +/* Clean up after processing deferred refcounts. */ +STATIC void +xfs_refcount_update_finish_cleanup( + struct xfs_trans *tp, + void *state, + int error) +{ + struct xfs_btree_cur *rcur = state; + + xfs_refcount_finish_one_cleanup(tp, rcur, error); +} + +/* Abort all pending CUIs. */ +STATIC void +xfs_refcount_update_abort_intent( + void *intent) +{ + xfs_cui_release(intent); +} + +/* Cancel a deferred refcount update. */ +STATIC void +xfs_refcount_update_cancel_item( + struct list_head *item) +{ + struct xfs_refcount_intent *refc; + + refc = container_of(item, struct xfs_refcount_intent, ri_list); + kmem_free(refc); +} + +static const struct xfs_defer_op_type xfs_refcount_update_defer_type = { + .type = XFS_DEFER_OPS_TYPE_REFCOUNT, + .max_items = XFS_CUI_MAX_FAST_EXTENTS, + .diff_items = xfs_refcount_update_diff_items, + .create_intent = xfs_refcount_update_create_intent, + .abort_intent = xfs_refcount_update_abort_intent, + .log_item = xfs_refcount_update_log_item, + .create_done = xfs_refcount_update_create_done, + .finish_item = xfs_refcount_update_finish_item, + .finish_cleanup = xfs_refcount_update_finish_cleanup, + .cancel_item = xfs_refcount_update_cancel_item, +}; + +/* Register the deferred op type. */ +void +xfs_refcount_update_init_defer_op(void) +{ + xfs_defer_init_op_type(&xfs_refcount_update_defer_type); +}