From 294f68063b49c06d3118d51016811063e69cf97a Mon Sep 17 00:00:00 2001 From: George Wilson Date: Tue, 2 Jul 2013 13:26:24 -0700 Subject: [PATCH] Illumos #3498 panic in arc_read() 3498 panic in arc_read(): !refcount_is_zero(&pbuf->b_hdr->b_refcnt) Reviewed by: Adam Leventhal Reviewed by: Matthew Ahrens Approved by: Richard Lowe References: illumos/illumos-gate@1b912ec7100c10e7243bf0879af0fe580e08c73d https://www.illumos.org/issues/3498 Ported-by: Brian Behlendorf Closes #1249 --- cmd/zdb/zdb.c | 7 ++-- include/sys/arc.h | 8 +---- include/sys/dmu_traverse.h | 3 +- include/sys/dsl_pool.h | 6 ---- module/zfs/arc.c | 52 ++---------------------------- module/zfs/bptree.c | 2 +- module/zfs/dbuf.c | 28 +++------------- module/zfs/dmu_diff.c | 8 ++--- module/zfs/dmu_objset.c | 12 ++----- module/zfs/dmu_send.c | 20 ++++++------ module/zfs/dmu_traverse.c | 79 ++++++++++++++++++++-------------------------- module/zfs/dsl_dataset.c | 2 +- module/zfs/dsl_scan.c | 36 +++------------------ module/zfs/spa.c | 2 +- module/zfs/zil.c | 4 +-- module/zfs/zio.c | 2 +- 16 files changed, 75 insertions(+), 196 deletions(-) diff --git a/cmd/zdb/zdb.c b/cmd/zdb/zdb.c index 75d4198..936974b 100644 --- a/cmd/zdb/zdb.c +++ b/cmd/zdb/zdb.c @@ -996,7 +996,7 @@ visit_indirect(spa_t *spa, const dnode_phys_t *dnp, arc_buf_t *buf; uint64_t fill = 0; - err = arc_read_nolock(NULL, spa, bp, arc_getbuf_func, &buf, + err = arc_read(NULL, spa, bp, arc_getbuf_func, &buf, ZIO_PRIORITY_ASYNC_READ, ZIO_FLAG_CANFAIL, &flags, zb); if (err) return (err); @@ -2048,9 +2048,8 @@ zdb_blkptr_done(zio_t *zio) mutex_exit(&spa->spa_scrub_lock); } -/* ARGSUSED */ static int -zdb_blkptr_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, arc_buf_t *pbuf, +zdb_blkptr_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, const zbookmark_t *zb, const dnode_phys_t *dnp, void *arg) { zdb_cb_t *zcb = arg; @@ -2457,7 +2456,7 @@ typedef struct zdb_ddt_entry { /* ARGSUSED */ static int zdb_ddt_add_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, - arc_buf_t *pbuf, const zbookmark_t *zb, const dnode_phys_t *dnp, void *arg) + const zbookmark_t *zb, const dnode_phys_t *dnp, void *arg) { avl_tree_t *t = arg; avl_index_t where; diff --git a/include/sys/arc.h b/include/sys/arc.h index 7911c9f..396144a 100644 --- a/include/sys/arc.h +++ b/include/sys/arc.h @@ -60,7 +60,6 @@ struct arc_buf { arc_buf_hdr_t *b_hdr; arc_buf_t *b_next; kmutex_t b_evict_lock; - krwlock_t b_data_lock; void *b_data; arc_evict_func_t *b_efunc; void *b_private; @@ -104,8 +103,6 @@ void arc_buf_add_ref(arc_buf_t *buf, void *tag); int arc_buf_remove_ref(arc_buf_t *buf, void *tag); int arc_buf_size(arc_buf_t *buf); void arc_release(arc_buf_t *buf, void *tag); -int arc_release_bp(arc_buf_t *buf, void *tag, blkptr_t *bp, spa_t *spa, - zbookmark_t *zb); int arc_released(arc_buf_t *buf); int arc_has_callback(arc_buf_t *buf); void arc_buf_freeze(arc_buf_t *buf); @@ -115,10 +112,7 @@ boolean_t arc_buf_eviction_needed(arc_buf_t *buf); int arc_referenced(arc_buf_t *buf); #endif -int arc_read(zio_t *pio, spa_t *spa, const blkptr_t *bp, arc_buf_t *pbuf, - arc_done_func_t *done, void *private, int priority, int zio_flags, - uint32_t *arc_flags, const zbookmark_t *zb); -int arc_read_nolock(zio_t *pio, spa_t *spa, const blkptr_t *bp, +int arc_read(zio_t *pio, spa_t *spa, const blkptr_t *bp, arc_done_func_t *done, void *private, int priority, int flags, uint32_t *arc_flags, const zbookmark_t *zb); zio_t *arc_write(zio_t *pio, spa_t *spa, uint64_t txg, diff --git a/include/sys/dmu_traverse.h b/include/sys/dmu_traverse.h index 3cbf42f..bc1590b 100644 --- a/include/sys/dmu_traverse.h +++ b/include/sys/dmu_traverse.h @@ -40,8 +40,7 @@ struct zilog; struct arc_buf; typedef int (blkptr_cb_t)(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, - struct arc_buf *pbuf, const zbookmark_t *zb, const struct dnode_phys *dnp, - void *arg); + const zbookmark_t *zb, const struct dnode_phys *dnp, void *arg); #define TRAVERSE_PRE (1<<0) #define TRAVERSE_POST (1<<1) diff --git a/include/sys/dsl_pool.h b/include/sys/dsl_pool.h index 96a2296..f4de774 100644 --- a/include/sys/dsl_pool.h +++ b/include/sys/dsl_pool.h @@ -147,12 +147,6 @@ void dsl_pool_willuse_space(dsl_pool_t *dp, int64_t space, dmu_tx_t *tx); void dsl_free(dsl_pool_t *dp, uint64_t txg, const blkptr_t *bpp); void dsl_free_sync(zio_t *pio, dsl_pool_t *dp, uint64_t txg, const blkptr_t *bpp); -int dsl_read(zio_t *pio, spa_t *spa, const blkptr_t *bpp, arc_buf_t *pbuf, - arc_done_func_t *done, void *private, int priority, int zio_flags, - uint32_t *arc_flags, const zbookmark_t *zb); -int dsl_read_nolock(zio_t *pio, spa_t *spa, const blkptr_t *bpp, - arc_done_func_t *done, void *private, int priority, int zio_flags, - uint32_t *arc_flags, const zbookmark_t *zb); void dsl_pool_create_origin(dsl_pool_t *dp, dmu_tx_t *tx); void dsl_pool_upgrade_clones(dsl_pool_t *dp, dmu_tx_t *tx); void dsl_pool_upgrade_dir_clones(dsl_pool_t *dp, dmu_tx_t *tx); diff --git a/module/zfs/arc.c b/module/zfs/arc.c index 2667725..de86966 100644 --- a/module/zfs/arc.c +++ b/module/zfs/arc.c @@ -884,7 +884,6 @@ buf_cons(void *vbuf, void *unused, int kmflag) bzero(buf, sizeof (arc_buf_t)); mutex_init(&buf->b_evict_lock, NULL, MUTEX_DEFAULT, NULL); - rw_init(&buf->b_data_lock, NULL, RW_DEFAULT, NULL); arc_space_consume(sizeof (arc_buf_t), ARC_SPACE_HDRS); return (0); @@ -914,7 +913,6 @@ buf_dest(void *vbuf, void *unused) arc_buf_t *buf = vbuf; mutex_destroy(&buf->b_evict_lock); - rw_destroy(&buf->b_data_lock); arc_space_return(sizeof (arc_buf_t), ARC_SPACE_HDRS); } @@ -2907,42 +2905,11 @@ arc_read_done(zio_t *zio) * * arc_read_done() will invoke all the requested "done" functions * for readers of this block. - * - * Normal callers should use arc_read and pass the arc buffer and offset - * for the bp. But if you know you don't need locking, you can use - * arc_read_bp. */ int -arc_read(zio_t *pio, spa_t *spa, const blkptr_t *bp, arc_buf_t *pbuf, - arc_done_func_t *done, void *private, int priority, int zio_flags, - uint32_t *arc_flags, const zbookmark_t *zb) -{ - int err; - - if (pbuf == NULL) { - /* - * XXX This happens from traverse callback funcs, for - * the objset_phys_t block. - */ - return (arc_read_nolock(pio, spa, bp, done, private, priority, - zio_flags, arc_flags, zb)); - } - - ASSERT(!refcount_is_zero(&pbuf->b_hdr->b_refcnt)); - ASSERT3U((char *)bp - (char *)pbuf->b_data, <, pbuf->b_hdr->b_size); - rw_enter(&pbuf->b_data_lock, RW_READER); - - err = arc_read_nolock(pio, spa, bp, done, private, priority, - zio_flags, arc_flags, zb); - rw_exit(&pbuf->b_data_lock); - - return (err); -} - -int -arc_read_nolock(zio_t *pio, spa_t *spa, const blkptr_t *bp, - arc_done_func_t *done, void *private, int priority, int zio_flags, - uint32_t *arc_flags, const zbookmark_t *zb) +arc_read(zio_t *pio, spa_t *spa, const blkptr_t *bp, arc_done_func_t *done, + void *private, int priority, int zio_flags, uint32_t *arc_flags, + const zbookmark_t *zb) { arc_buf_hdr_t *hdr; arc_buf_t *buf = NULL; @@ -3480,19 +3447,6 @@ arc_release(arc_buf_t *buf, void *tag) } } -/* - * Release this buffer. If it does not match the provided BP, fill it - * with that block's contents. - */ -/* ARGSUSED */ -int -arc_release_bp(arc_buf_t *buf, void *tag, blkptr_t *bp, spa_t *spa, - zbookmark_t *zb) -{ - arc_release(buf, tag); - return (0); -} - int arc_released(arc_buf_t *buf) { diff --git a/module/zfs/bptree.c b/module/zfs/bptree.c index 1a009cf..73922db 100644 --- a/module/zfs/bptree.c +++ b/module/zfs/bptree.c @@ -135,7 +135,7 @@ bptree_add(objset_t *os, uint64_t obj, blkptr_t *bp, uint64_t birth_txg, /* ARGSUSED */ static int -bptree_visit_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, arc_buf_t *pbuf, +bptree_visit_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, const zbookmark_t *zb, const dnode_phys_t *dnp, void *arg) { int err; diff --git a/module/zfs/dbuf.c b/module/zfs/dbuf.c index 83a8035..46f42dd 100644 --- a/module/zfs/dbuf.c +++ b/module/zfs/dbuf.c @@ -559,7 +559,6 @@ dbuf_read_impl(dmu_buf_impl_t *db, zio_t *zio, uint32_t *flags) spa_t *spa; zbookmark_t zb; uint32_t aflags = ARC_NOWAIT; - arc_buf_t *pbuf; DB_DNODE_ENTER(db); dn = DB_DNODE(db); @@ -621,14 +620,8 @@ dbuf_read_impl(dmu_buf_impl_t *db, zio_t *zio, uint32_t *flags) db->db.db_object, db->db_level, db->db_blkid); dbuf_add_ref(db, NULL); - /* ZIO_FLAG_CANFAIL callers have to check the parent zio's error */ - if (db->db_parent) - pbuf = db->db_parent->db_buf; - else - pbuf = db->db_objset->os_phys_buf; - - (void) dsl_read(zio, spa, db->db_blkptr, pbuf, + (void) arc_read(zio, spa, db->db_blkptr, dbuf_read_done, db, ZIO_PRIORITY_SYNC_READ, (*flags & DB_RF_CANFAIL) ? ZIO_FLAG_CANFAIL : ZIO_FLAG_MUSTSUCCEED, &aflags, &zb); @@ -1026,7 +1019,6 @@ void dbuf_release_bp(dmu_buf_impl_t *db) { objset_t *os; - zbookmark_t zb; DB_GET_OBJSET(&os, db); ASSERT(dsl_pool_sync_context(dmu_objset_pool(os))); @@ -1034,13 +1026,7 @@ dbuf_release_bp(dmu_buf_impl_t *db) list_link_active(&os->os_dsl_dataset->ds_synced_link)); ASSERT(db->db_parent == NULL || arc_released(db->db_parent->db_buf)); - zb.zb_objset = os->os_dsl_dataset ? - os->os_dsl_dataset->ds_object : 0; - zb.zb_object = db->db.db_object; - zb.zb_level = db->db_level; - zb.zb_blkid = db->db_blkid; - (void) arc_release_bp(db->db_buf, db, - db->db_blkptr, os->os_spa, &zb); + (void) arc_release(db->db_buf, db); } dbuf_dirty_record_t * @@ -1886,7 +1872,6 @@ dbuf_prefetch(dnode_t *dn, uint64_t blkid) if (bp && !BP_IS_HOLE(bp)) { int priority = dn->dn_type == DMU_OT_DDT_ZAP ? ZIO_PRIORITY_DDT_PREFETCH : ZIO_PRIORITY_ASYNC_READ; - arc_buf_t *pbuf; dsl_dataset_t *ds = dn->dn_objset->os_dsl_dataset; uint32_t aflags = ARC_NOWAIT | ARC_PREFETCH; zbookmark_t zb; @@ -1894,13 +1879,8 @@ dbuf_prefetch(dnode_t *dn, uint64_t blkid) SET_BOOKMARK(&zb, ds ? ds->ds_object : DMU_META_OBJSET, dn->dn_object, 0, blkid); - if (db) - pbuf = db->db_buf; - else - pbuf = dn->dn_objset->os_phys_buf; - - (void) dsl_read(NULL, dn->dn_objset->os_spa, - bp, pbuf, NULL, NULL, priority, + (void) arc_read(NULL, dn->dn_objset->os_spa, + bp, NULL, NULL, priority, ZIO_FLAG_CANFAIL | ZIO_FLAG_SPECULATIVE, &aflags, &zb); } diff --git a/module/zfs/dmu_diff.c b/module/zfs/dmu_diff.c index 22340eb..dc23778 100644 --- a/module/zfs/dmu_diff.c +++ b/module/zfs/dmu_diff.c @@ -105,7 +105,7 @@ report_dnode(struct diffarg *da, uint64_t object, dnode_phys_t *dnp) /* ARGSUSED */ static int -diff_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, arc_buf_t *pbuf, +diff_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, const zbookmark_t *zb, const dnode_phys_t *dnp, void *arg) { struct diffarg *da = arg; @@ -132,9 +132,9 @@ diff_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, arc_buf_t *pbuf, int blksz = BP_GET_LSIZE(bp); int i; - if (dsl_read(NULL, spa, bp, pbuf, - arc_getbuf_func, &abuf, ZIO_PRIORITY_ASYNC_READ, - ZIO_FLAG_CANFAIL, &aflags, zb) != 0) + if (arc_read(NULL, spa, bp, arc_getbuf_func, &abuf, + ZIO_PRIORITY_ASYNC_READ, ZIO_FLAG_CANFAIL, + &aflags, zb) != 0) return (EIO); blk = abuf->b_data; diff --git a/module/zfs/dmu_objset.c b/module/zfs/dmu_objset.c index 50673dc..ca75e52 100644 --- a/module/zfs/dmu_objset.c +++ b/module/zfs/dmu_objset.c @@ -276,12 +276,7 @@ dmu_objset_open_impl(spa_t *spa, dsl_dataset_t *ds, blkptr_t *bp, aflags |= ARC_L2CACHE; dprintf_bp(os->os_rootbp, "reading %s", ""); - /* - * XXX when bprewrite scrub can change the bp, - * and this is called from dmu_objset_open_ds_os, the bp - * could change, and we'll need a lock. - */ - err = dsl_read_nolock(NULL, spa, os->os_rootbp, + err = arc_read(NULL, spa, os->os_rootbp, arc_getbuf_func, &os->os_phys_buf, ZIO_PRIORITY_SYNC_READ, ZIO_FLAG_CANFAIL, &aflags, &zb); if (err) { @@ -1119,8 +1114,7 @@ dmu_objset_sync(objset_t *os, zio_t *pio, dmu_tx_t *tx) SET_BOOKMARK(&zb, os->os_dsl_dataset ? os->os_dsl_dataset->ds_object : DMU_META_OBJSET, ZB_ROOT_OBJECT, ZB_ROOT_LEVEL, ZB_ROOT_BLKID); - VERIFY3U(0, ==, arc_release_bp(os->os_phys_buf, &os->os_phys_buf, - os->os_rootbp, os->os_spa, &zb)); + arc_release(os->os_phys_buf, &os->os_phys_buf); dmu_write_policy(os, NULL, 0, 0, &zp); @@ -1765,7 +1759,7 @@ dmu_objset_prefetch(const char *name, void *arg) SET_BOOKMARK(&zb, ds->ds_object, ZB_ROOT_OBJECT, ZB_ROOT_LEVEL, ZB_ROOT_BLKID); - (void) dsl_read_nolock(NULL, dsl_dataset_get_spa(ds), + (void) arc_read(NULL, dsl_dataset_get_spa(ds), &ds->ds_phys->ds_bp, NULL, NULL, ZIO_PRIORITY_ASYNC_READ, ZIO_FLAG_CANFAIL | ZIO_FLAG_SPECULATIVE, diff --git a/module/zfs/dmu_send.c b/module/zfs/dmu_send.c index b256803..54e7597 100644 --- a/module/zfs/dmu_send.c +++ b/module/zfs/dmu_send.c @@ -330,7 +330,7 @@ dump_dnode(dmu_sendarg_t *dsp, uint64_t object, dnode_phys_t *dnp) /* ARGSUSED */ static int -backup_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, arc_buf_t *pbuf, +backup_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, const zbookmark_t *zb, const dnode_phys_t *dnp, void *arg) { dmu_sendarg_t *dsp = arg; @@ -359,9 +359,9 @@ backup_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, arc_buf_t *pbuf, uint32_t aflags = ARC_WAIT; arc_buf_t *abuf; - if (dsl_read(NULL, spa, bp, pbuf, - arc_getbuf_func, &abuf, ZIO_PRIORITY_ASYNC_READ, - ZIO_FLAG_CANFAIL, &aflags, zb) != 0) + if (arc_read(NULL, spa, bp, arc_getbuf_func, &abuf, + ZIO_PRIORITY_ASYNC_READ, ZIO_FLAG_CANFAIL, + &aflags, zb) != 0) return (EIO); blk = abuf->b_data; @@ -378,9 +378,9 @@ backup_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, arc_buf_t *pbuf, arc_buf_t *abuf; int blksz = BP_GET_LSIZE(bp); - if (arc_read_nolock(NULL, spa, bp, - arc_getbuf_func, &abuf, ZIO_PRIORITY_ASYNC_READ, - ZIO_FLAG_CANFAIL, &aflags, zb) != 0) + if (arc_read(NULL, spa, bp, arc_getbuf_func, &abuf, + ZIO_PRIORITY_ASYNC_READ, ZIO_FLAG_CANFAIL, + &aflags, zb) != 0) return (EIO); err = dump_spill(dsp, zb->zb_object, blksz, abuf->b_data); @@ -390,9 +390,9 @@ backup_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, arc_buf_t *pbuf, arc_buf_t *abuf; int blksz = BP_GET_LSIZE(bp); - if (dsl_read(NULL, spa, bp, pbuf, - arc_getbuf_func, &abuf, ZIO_PRIORITY_ASYNC_READ, - ZIO_FLAG_CANFAIL, &aflags, zb) != 0) { + if (arc_read(NULL, spa, bp, arc_getbuf_func, &abuf, + ZIO_PRIORITY_ASYNC_READ, ZIO_FLAG_CANFAIL, + &aflags, zb) != 0) { if (zfs_send_corrupt_data) { uint64_t *ptr; /* Send a block filled with 0x"zfs badd bloc" */ diff --git a/module/zfs/dmu_traverse.c b/module/zfs/dmu_traverse.c index 370a28a..1c39723 100644 --- a/module/zfs/dmu_traverse.c +++ b/module/zfs/dmu_traverse.c @@ -62,9 +62,9 @@ typedef struct traverse_data { } traverse_data_t; static int traverse_dnode(traverse_data_t *td, const dnode_phys_t *dnp, - arc_buf_t *buf, uint64_t objset, uint64_t object); + uint64_t objset, uint64_t object); static void prefetch_dnode_metadata(traverse_data_t *td, const dnode_phys_t *, - arc_buf_t *buf, uint64_t objset, uint64_t object); + uint64_t objset, uint64_t object); static int traverse_zil_block(zilog_t *zilog, blkptr_t *bp, void *arg, uint64_t claim_txg) @@ -81,7 +81,7 @@ traverse_zil_block(zilog_t *zilog, blkptr_t *bp, void *arg, uint64_t claim_txg) SET_BOOKMARK(&zb, td->td_objset, ZB_ZIL_OBJECT, ZB_ZIL_LEVEL, bp->blk_cksum.zc_word[ZIL_ZC_SEQ]); - (void) td->td_func(td->td_spa, zilog, bp, NULL, &zb, NULL, td->td_arg); + (void) td->td_func(td->td_spa, zilog, bp, &zb, NULL, td->td_arg); return (0); } @@ -105,7 +105,7 @@ traverse_zil_record(zilog_t *zilog, lr_t *lrc, void *arg, uint64_t claim_txg) SET_BOOKMARK(&zb, td->td_objset, lr->lr_foid, ZB_ZIL_LEVEL, lr->lr_offset / BP_GET_LSIZE(bp)); - (void) td->td_func(td->td_spa, zilog, bp, NULL, &zb, NULL, + (void) td->td_func(td->td_spa, zilog, bp, &zb, NULL, td->td_arg); } return (0); @@ -182,7 +182,7 @@ traverse_pause(traverse_data_t *td, const zbookmark_t *zb) static void traverse_prefetch_metadata(traverse_data_t *td, - arc_buf_t *pbuf, const blkptr_t *bp, const zbookmark_t *zb) + const blkptr_t *bp, const zbookmark_t *zb) { uint32_t flags = ARC_NOWAIT | ARC_PREFETCH; @@ -200,14 +200,13 @@ traverse_prefetch_metadata(traverse_data_t *td, if (BP_GET_LEVEL(bp) == 0 && BP_GET_TYPE(bp) != DMU_OT_DNODE) return; - (void) arc_read(NULL, td->td_spa, bp, - pbuf, NULL, NULL, ZIO_PRIORITY_ASYNC_READ, - ZIO_FLAG_CANFAIL, &flags, zb); + (void) arc_read(NULL, td->td_spa, bp, NULL, NULL, + ZIO_PRIORITY_ASYNC_READ, ZIO_FLAG_CANFAIL, &flags, zb); } static int traverse_visitbp(traverse_data_t *td, const dnode_phys_t *dnp, - arc_buf_t *pbuf, const blkptr_t *bp, const zbookmark_t *zb) + const blkptr_t *bp, const zbookmark_t *zb) { zbookmark_t czb; int err = 0, lasterr = 0; @@ -228,8 +227,7 @@ traverse_visitbp(traverse_data_t *td, const dnode_phys_t *dnp, } if (BP_IS_HOLE(bp)) { - err = td->td_func(td->td_spa, NULL, NULL, pbuf, zb, dnp, - td->td_arg); + err = td->td_func(td->td_spa, NULL, NULL, zb, dnp, td->td_arg); return (err); } @@ -249,7 +247,7 @@ traverse_visitbp(traverse_data_t *td, const dnode_phys_t *dnp, } if (td->td_flags & TRAVERSE_PRE) { - err = td->td_func(td->td_spa, NULL, bp, pbuf, zb, dnp, + err = td->td_func(td->td_spa, NULL, bp, zb, dnp, td->td_arg); if (err == TRAVERSE_VISIT_NO_CHILDREN) return (0); @@ -265,8 +263,7 @@ traverse_visitbp(traverse_data_t *td, const dnode_phys_t *dnp, blkptr_t *cbp; int epb = BP_GET_LSIZE(bp) >> SPA_BLKPTRSHIFT; - err = dsl_read(NULL, td->td_spa, bp, pbuf, - arc_getbuf_func, &buf, + err = arc_read(NULL, td->td_spa, bp, arc_getbuf_func, &buf, ZIO_PRIORITY_ASYNC_READ, ZIO_FLAG_CANFAIL, &flags, zb); if (err) return (err); @@ -276,7 +273,7 @@ traverse_visitbp(traverse_data_t *td, const dnode_phys_t *dnp, SET_BOOKMARK(&czb, zb->zb_objset, zb->zb_object, zb->zb_level - 1, zb->zb_blkid * epb + i); - traverse_prefetch_metadata(td, buf, &cbp[i], &czb); + traverse_prefetch_metadata(td, &cbp[i], &czb); } /* recursively visitbp() blocks below this */ @@ -284,7 +281,7 @@ traverse_visitbp(traverse_data_t *td, const dnode_phys_t *dnp, SET_BOOKMARK(&czb, zb->zb_objset, zb->zb_object, zb->zb_level - 1, zb->zb_blkid * epb + i); - err = traverse_visitbp(td, dnp, buf, &cbp[i], &czb); + err = traverse_visitbp(td, dnp, &cbp[i], &czb); if (err) { if (!hard) break; @@ -296,21 +293,20 @@ traverse_visitbp(traverse_data_t *td, const dnode_phys_t *dnp, int i; int epb = BP_GET_LSIZE(bp) >> DNODE_SHIFT; - err = dsl_read(NULL, td->td_spa, bp, pbuf, - arc_getbuf_func, &buf, + err = arc_read(NULL, td->td_spa, bp, arc_getbuf_func, &buf, ZIO_PRIORITY_ASYNC_READ, ZIO_FLAG_CANFAIL, &flags, zb); if (err) return (err); dnp = buf->b_data; for (i = 0; i < epb; i++) { - prefetch_dnode_metadata(td, &dnp[i], buf, zb->zb_objset, + prefetch_dnode_metadata(td, &dnp[i], zb->zb_objset, zb->zb_blkid * epb + i); } /* recursively visitbp() blocks below this */ for (i = 0; i < epb; i++) { - err = traverse_dnode(td, &dnp[i], buf, zb->zb_objset, + err = traverse_dnode(td, &dnp[i], zb->zb_objset, zb->zb_blkid * epb + i); if (err) { if (!hard) @@ -323,24 +319,23 @@ traverse_visitbp(traverse_data_t *td, const dnode_phys_t *dnp, objset_phys_t *osp; dnode_phys_t *dnp; - err = dsl_read_nolock(NULL, td->td_spa, bp, - arc_getbuf_func, &buf, + err = arc_read(NULL, td->td_spa, bp, arc_getbuf_func, &buf, ZIO_PRIORITY_ASYNC_READ, ZIO_FLAG_CANFAIL, &flags, zb); if (err) return (err); osp = buf->b_data; dnp = &osp->os_meta_dnode; - prefetch_dnode_metadata(td, dnp, buf, zb->zb_objset, + prefetch_dnode_metadata(td, dnp, zb->zb_objset, DMU_META_DNODE_OBJECT); if (arc_buf_size(buf) >= sizeof (objset_phys_t)) { prefetch_dnode_metadata(td, &osp->os_userused_dnode, - buf, zb->zb_objset, DMU_USERUSED_OBJECT); + zb->zb_objset, DMU_USERUSED_OBJECT); prefetch_dnode_metadata(td, &osp->os_groupused_dnode, - buf, zb->zb_objset, DMU_USERUSED_OBJECT); + zb->zb_objset, DMU_USERUSED_OBJECT); } - err = traverse_dnode(td, dnp, buf, zb->zb_objset, + err = traverse_dnode(td, dnp, zb->zb_objset, DMU_META_DNODE_OBJECT); if (err && hard) { lasterr = err; @@ -348,7 +343,7 @@ traverse_visitbp(traverse_data_t *td, const dnode_phys_t *dnp, } if (err == 0 && arc_buf_size(buf) >= sizeof (objset_phys_t)) { dnp = &osp->os_userused_dnode; - err = traverse_dnode(td, dnp, buf, zb->zb_objset, + err = traverse_dnode(td, dnp, zb->zb_objset, DMU_USERUSED_OBJECT); } if (err && hard) { @@ -357,7 +352,7 @@ traverse_visitbp(traverse_data_t *td, const dnode_phys_t *dnp, } if (err == 0 && arc_buf_size(buf) >= sizeof (objset_phys_t)) { dnp = &osp->os_groupused_dnode; - err = traverse_dnode(td, dnp, buf, zb->zb_objset, + err = traverse_dnode(td, dnp, zb->zb_objset, DMU_GROUPUSED_OBJECT); } } @@ -367,8 +362,7 @@ traverse_visitbp(traverse_data_t *td, const dnode_phys_t *dnp, post: if (err == 0 && lasterr == 0 && (td->td_flags & TRAVERSE_POST)) { - err = td->td_func(td->td_spa, NULL, bp, pbuf, zb, dnp, - td->td_arg); + err = td->td_func(td->td_spa, NULL, bp, zb, dnp, td->td_arg); if (err == ERESTART) pause = B_TRUE; } @@ -384,25 +378,25 @@ post: static void prefetch_dnode_metadata(traverse_data_t *td, const dnode_phys_t *dnp, - arc_buf_t *buf, uint64_t objset, uint64_t object) + uint64_t objset, uint64_t object) { int j; zbookmark_t czb; for (j = 0; j < dnp->dn_nblkptr; j++) { SET_BOOKMARK(&czb, objset, object, dnp->dn_nlevels - 1, j); - traverse_prefetch_metadata(td, buf, &dnp->dn_blkptr[j], &czb); + traverse_prefetch_metadata(td, &dnp->dn_blkptr[j], &czb); } if (dnp->dn_flags & DNODE_FLAG_SPILL_BLKPTR) { SET_BOOKMARK(&czb, objset, object, 0, DMU_SPILL_BLKID); - traverse_prefetch_metadata(td, buf, &dnp->dn_spill, &czb); + traverse_prefetch_metadata(td, &dnp->dn_spill, &czb); } } static int traverse_dnode(traverse_data_t *td, const dnode_phys_t *dnp, - arc_buf_t *buf, uint64_t objset, uint64_t object) + uint64_t objset, uint64_t object) { int j, err = 0, lasterr = 0; zbookmark_t czb; @@ -410,7 +404,7 @@ traverse_dnode(traverse_data_t *td, const dnode_phys_t *dnp, for (j = 0; j < dnp->dn_nblkptr; j++) { SET_BOOKMARK(&czb, objset, object, dnp->dn_nlevels - 1, j); - err = traverse_visitbp(td, dnp, buf, &dnp->dn_blkptr[j], &czb); + err = traverse_visitbp(td, dnp, &dnp->dn_blkptr[j], &czb); if (err) { if (!hard) break; @@ -420,7 +414,7 @@ traverse_dnode(traverse_data_t *td, const dnode_phys_t *dnp, if (dnp->dn_flags & DNODE_FLAG_SPILL_BLKPTR) { SET_BOOKMARK(&czb, objset, object, 0, DMU_SPILL_BLKID); - err = traverse_visitbp(td, dnp, buf, &dnp->dn_spill, &czb); + err = traverse_visitbp(td, dnp, &dnp->dn_spill, &czb); if (err) { if (!hard) return (err); @@ -433,8 +427,7 @@ traverse_dnode(traverse_data_t *td, const dnode_phys_t *dnp, /* ARGSUSED */ static int traverse_prefetcher(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, - arc_buf_t *pbuf, const zbookmark_t *zb, const dnode_phys_t *dnp, - void *arg) + const zbookmark_t *zb, const dnode_phys_t *dnp, void *arg) { prefetch_data_t *pfd = arg; uint32_t aflags = ARC_NOWAIT | ARC_PREFETCH; @@ -455,10 +448,8 @@ traverse_prefetcher(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, cv_broadcast(&pfd->pd_cv); mutex_exit(&pfd->pd_mtx); - (void) dsl_read(NULL, spa, bp, pbuf, NULL, NULL, - ZIO_PRIORITY_ASYNC_READ, - ZIO_FLAG_CANFAIL | ZIO_FLAG_SPECULATIVE, - &aflags, zb); + (void) arc_read(NULL, spa, bp, NULL, NULL, ZIO_PRIORITY_ASYNC_READ, + ZIO_FLAG_CANFAIL | ZIO_FLAG_SPECULATIVE, &aflags, zb); return (0); } @@ -476,7 +467,7 @@ traverse_prefetch_thread(void *arg) SET_BOOKMARK(&czb, td.td_objset, ZB_ROOT_OBJECT, ZB_ROOT_LEVEL, ZB_ROOT_BLKID); - (void) traverse_visitbp(&td, NULL, NULL, td.td_rootbp, &czb); + (void) traverse_visitbp(&td, NULL, td.td_rootbp, &czb); mutex_enter(&td_main->td_pfd->pd_mtx); td_main->td_pfd->pd_exited = B_TRUE; @@ -544,7 +535,7 @@ traverse_impl(spa_t *spa, dsl_dataset_t *ds, uint64_t objset, blkptr_t *rootbp, SET_BOOKMARK(czb, td->td_objset, ZB_ROOT_OBJECT, ZB_ROOT_LEVEL, ZB_ROOT_BLKID); - err = traverse_visitbp(td, NULL, NULL, rootbp, czb); + err = traverse_visitbp(td, NULL, rootbp, czb); mutex_enter(&pd->pd_mtx); pd->pd_cancel = B_TRUE; diff --git a/module/zfs/dsl_dataset.c b/module/zfs/dsl_dataset.c index c1a029b..d9e8bd3 100644 --- a/module/zfs/dsl_dataset.c +++ b/module/zfs/dsl_dataset.c @@ -1271,7 +1271,7 @@ struct killarg { /* ARGSUSED */ static int -kill_blkptr(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, arc_buf_t *pbuf, +kill_blkptr(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, const zbookmark_t *zb, const dnode_phys_t *dnp, void *arg) { struct killarg *ka = arg; diff --git a/module/zfs/dsl_scan.c b/module/zfs/dsl_scan.c index 297caa0..34a4f03 100644 --- a/module/zfs/dsl_scan.c +++ b/module/zfs/dsl_scan.c @@ -363,24 +363,6 @@ dsl_free_sync(zio_t *pio, dsl_pool_t *dp, uint64_t txg, const blkptr_t *bpp) zio_nowait(zio_free_sync(pio, dp->dp_spa, txg, bpp, pio->io_flags)); } -int -dsl_read(zio_t *pio, spa_t *spa, const blkptr_t *bpp, arc_buf_t *pbuf, - arc_done_func_t *done, void *private, int priority, int zio_flags, - uint32_t *arc_flags, const zbookmark_t *zb) -{ - return (arc_read(pio, spa, bpp, pbuf, done, private, - priority, zio_flags, arc_flags, zb)); -} - -int -dsl_read_nolock(zio_t *pio, spa_t *spa, const blkptr_t *bpp, - arc_done_func_t *done, void *private, int priority, int zio_flags, - uint32_t *arc_flags, const zbookmark_t *zb) -{ - return (arc_read_nolock(pio, spa, bpp, done, private, - priority, zio_flags, arc_flags, zb)); -} - static uint64_t dsl_scan_ds_maxtxg(dsl_dataset_t *ds) { @@ -551,12 +533,8 @@ dsl_scan_prefetch(dsl_scan_t *scn, arc_buf_t *buf, blkptr_t *bp, SET_BOOKMARK(&czb, objset, object, BP_GET_LEVEL(bp), blkid); - /* - * XXX need to make sure all of these arc_read() prefetches are - * done before setting xlateall (similar to dsl_read()) - */ (void) arc_read(scn->scn_zio_root, scn->scn_dp->dp_spa, bp, - buf, NULL, NULL, ZIO_PRIORITY_ASYNC_READ, + NULL, NULL, ZIO_PRIORITY_ASYNC_READ, ZIO_FLAG_CANFAIL | ZIO_FLAG_SCAN_THREAD, &flags, &czb); } @@ -614,8 +592,7 @@ dsl_scan_recurse(dsl_scan_t *scn, dsl_dataset_t *ds, dmu_objset_type_t ostype, blkptr_t *cbp; int epb = BP_GET_LSIZE(bp) >> SPA_BLKPTRSHIFT; - err = arc_read_nolock(NULL, dp->dp_spa, bp, - arc_getbuf_func, bufp, + err = arc_read(NULL, dp->dp_spa, bp, arc_getbuf_func, bufp, ZIO_PRIORITY_ASYNC_READ, zio_flags, &flags, zb); if (err) { scn->scn_phys.scn_errors++; @@ -637,8 +614,7 @@ dsl_scan_recurse(dsl_scan_t *scn, dsl_dataset_t *ds, dmu_objset_type_t ostype, } else if (BP_GET_TYPE(bp) == DMU_OT_USERGROUP_USED) { uint32_t flags = ARC_WAIT; - err = arc_read_nolock(NULL, dp->dp_spa, bp, - arc_getbuf_func, bufp, + err = arc_read(NULL, dp->dp_spa, bp, arc_getbuf_func, bufp, ZIO_PRIORITY_ASYNC_READ, zio_flags, &flags, zb); if (err) { scn->scn_phys.scn_errors++; @@ -650,8 +626,7 @@ dsl_scan_recurse(dsl_scan_t *scn, dsl_dataset_t *ds, dmu_objset_type_t ostype, int i, j; int epb = BP_GET_LSIZE(bp) >> DNODE_SHIFT; - err = arc_read_nolock(NULL, dp->dp_spa, bp, - arc_getbuf_func, bufp, + err = arc_read(NULL, dp->dp_spa, bp, arc_getbuf_func, bufp, ZIO_PRIORITY_ASYNC_READ, zio_flags, &flags, zb); if (err) { scn->scn_phys.scn_errors++; @@ -673,8 +648,7 @@ dsl_scan_recurse(dsl_scan_t *scn, dsl_dataset_t *ds, dmu_objset_type_t ostype, uint32_t flags = ARC_WAIT; objset_phys_t *osp; - err = arc_read_nolock(NULL, dp->dp_spa, bp, - arc_getbuf_func, bufp, + err = arc_read(NULL, dp->dp_spa, bp, arc_getbuf_func, bufp, ZIO_PRIORITY_ASYNC_READ, zio_flags, &flags, zb); if (err) { scn->scn_phys.scn_errors++; diff --git a/module/zfs/spa.c b/module/zfs/spa.c index c885e3e..e986e92 100644 --- a/module/zfs/spa.c +++ b/module/zfs/spa.c @@ -1856,7 +1856,7 @@ spa_load_verify_done(zio_t *zio) /*ARGSUSED*/ static int spa_load_verify_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp, - arc_buf_t *pbuf, const zbookmark_t *zb, const dnode_phys_t *dnp, void *arg) + const zbookmark_t *zb, const dnode_phys_t *dnp, void *arg) { if (bp != NULL) { zio_t *rio = arg; diff --git a/module/zfs/zil.c b/module/zfs/zil.c index 64de856..c179693 100644 --- a/module/zfs/zil.c +++ b/module/zfs/zil.c @@ -212,7 +212,7 @@ zil_read_log_block(zilog_t *zilog, const blkptr_t *bp, blkptr_t *nbp, void *dst, SET_BOOKMARK(&zb, bp->blk_cksum.zc_word[ZIL_ZC_OBJSET], ZB_ZIL_OBJECT, ZB_ZIL_LEVEL, bp->blk_cksum.zc_word[ZIL_ZC_SEQ]); - error = dsl_read_nolock(NULL, zilog->zl_spa, bp, arc_getbuf_func, &abuf, + error = arc_read(NULL, zilog->zl_spa, bp, arc_getbuf_func, &abuf, ZIO_PRIORITY_SYNC_READ, zio_flags, &aflags, &zb); if (error == 0) { @@ -288,7 +288,7 @@ zil_read_log_data(zilog_t *zilog, const lr_write_t *lr, void *wbuf) SET_BOOKMARK(&zb, dmu_objset_id(zilog->zl_os), lr->lr_foid, ZB_ZIL_LEVEL, lr->lr_offset / BP_GET_LSIZE(bp)); - error = arc_read_nolock(NULL, zilog->zl_spa, bp, arc_getbuf_func, &abuf, + error = arc_read(NULL, zilog->zl_spa, bp, arc_getbuf_func, &abuf, ZIO_PRIORITY_SYNC_READ, zio_flags, &aflags, &zb); if (error == 0) { diff --git a/module/zfs/zio.c b/module/zfs/zio.c index 2e11709..8cf0408 100644 --- a/module/zfs/zio.c +++ b/module/zfs/zio.c @@ -2051,7 +2051,7 @@ zio_ddt_collision(zio_t *zio, ddt_t *ddt, ddt_entry_t *dde) ddt_exit(ddt); - error = arc_read_nolock(NULL, spa, &blk, + error = arc_read(NULL, spa, &blk, arc_getbuf_func, &abuf, ZIO_PRIORITY_SYNC_READ, ZIO_FLAG_CANFAIL | ZIO_FLAG_SPECULATIVE, &aflags, &zio->io_bookmark); -- 1.8.3.1