/* * CDDL HEADER START * * The contents of this file are subject to the terms of the * Common Development and Distribution License (the "License"). * You may not use this file except in compliance with the License. * * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE * or http://www.opensolaris.org/os/licensing. * See the License for the specific language governing permissions * and limitations under the License. * * When distributing Covered Code, include this CDDL HEADER in each * file and include the License file at usr/src/OPENSOLARIS.LICENSE. * If applicable, add the following below this CDDL HEADER, with the * fields enclosed by brackets "[]" replaced with your own identifying * information: Portions Copyright [yyyy] [name of copyright owner] * * CDDL HEADER END */ /* * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved. * Copyright 2011 Nexenta Systems, Inc. All rights reserved. * Copyright (c) 2012, 2017 by Delphix. All rights reserved. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include typedef void (*dmu_tx_hold_func_t)(dmu_tx_t *tx, struct dnode *dn, uint64_t arg1, uint64_t arg2); dmu_tx_stats_t dmu_tx_stats = { { "dmu_tx_assigned", KSTAT_DATA_UINT64 }, { "dmu_tx_delay", KSTAT_DATA_UINT64 }, { "dmu_tx_error", KSTAT_DATA_UINT64 }, { "dmu_tx_suspended", KSTAT_DATA_UINT64 }, { "dmu_tx_group", KSTAT_DATA_UINT64 }, { "dmu_tx_memory_reserve", KSTAT_DATA_UINT64 }, { "dmu_tx_memory_reclaim", KSTAT_DATA_UINT64 }, { "dmu_tx_dirty_throttle", KSTAT_DATA_UINT64 }, { "dmu_tx_dirty_delay", KSTAT_DATA_UINT64 }, { "dmu_tx_dirty_over_max", KSTAT_DATA_UINT64 }, { "dmu_tx_dirty_frees_delay", KSTAT_DATA_UINT64 }, { "dmu_tx_quota", KSTAT_DATA_UINT64 }, }; static kstat_t *dmu_tx_ksp; dmu_tx_t * dmu_tx_create_dd(dsl_dir_t *dd) { dmu_tx_t *tx = kmem_zalloc(sizeof (dmu_tx_t), KM_SLEEP); tx->tx_dir = dd; if (dd != NULL) tx->tx_pool = dd->dd_pool; list_create(&tx->tx_holds, sizeof (dmu_tx_hold_t), offsetof(dmu_tx_hold_t, txh_node)); list_create(&tx->tx_callbacks, sizeof (dmu_tx_callback_t), offsetof(dmu_tx_callback_t, dcb_node)); tx->tx_start = gethrtime(); return (tx); } dmu_tx_t * dmu_tx_create(objset_t *os) { dmu_tx_t *tx = dmu_tx_create_dd(os->os_dsl_dataset->ds_dir); tx->tx_objset = os; return (tx); } dmu_tx_t * dmu_tx_create_assigned(struct dsl_pool *dp, uint64_t txg) { dmu_tx_t *tx = dmu_tx_create_dd(NULL); TXG_VERIFY(dp->dp_spa, txg); tx->tx_pool = dp; tx->tx_txg = txg; tx->tx_anyobj = TRUE; return (tx); } int dmu_tx_is_syncing(dmu_tx_t *tx) { return (tx->tx_anyobj); } int dmu_tx_private_ok(dmu_tx_t *tx) { return (tx->tx_anyobj); } static dmu_tx_hold_t * dmu_tx_hold_dnode_impl(dmu_tx_t *tx, dnode_t *dn, enum dmu_tx_hold_type type, uint64_t arg1, uint64_t arg2) { dmu_tx_hold_t *txh; if (dn != NULL) { (void) zfs_refcount_add(&dn->dn_holds, tx); if (tx->tx_txg != 0) { mutex_enter(&dn->dn_mtx); /* * dn->dn_assigned_txg == tx->tx_txg doesn't pose a * problem, but there's no way for it to happen (for * now, at least). */ ASSERT(dn->dn_assigned_txg == 0); dn->dn_assigned_txg = tx->tx_txg; (void) zfs_refcount_add(&dn->dn_tx_holds, tx); mutex_exit(&dn->dn_mtx); } } txh = kmem_zalloc(sizeof (dmu_tx_hold_t), KM_SLEEP); txh->txh_tx = tx; txh->txh_dnode = dn; zfs_refcount_create(&txh->txh_space_towrite); zfs_refcount_create(&txh->txh_memory_tohold); txh->txh_type = type; txh->txh_arg1 = arg1; txh->txh_arg2 = arg2; list_insert_tail(&tx->tx_holds, txh); return (txh); } static dmu_tx_hold_t * dmu_tx_hold_object_impl(dmu_tx_t *tx, objset_t *os, uint64_t object, enum dmu_tx_hold_type type, uint64_t arg1, uint64_t arg2) { dnode_t *dn = NULL; dmu_tx_hold_t *txh; int err; if (object != DMU_NEW_OBJECT) { err = dnode_hold(os, object, FTAG, &dn); if (err != 0) { tx->tx_err = err; return (NULL); } } txh = dmu_tx_hold_dnode_impl(tx, dn, type, arg1, arg2); if (dn != NULL) dnode_rele(dn, FTAG); return (txh); } void dmu_tx_add_new_object(dmu_tx_t *tx, dnode_t *dn) { /* * If we're syncing, they can manipulate any object anyhow, and * the hold on the dnode_t can cause problems. */ if (!dmu_tx_is_syncing(tx)) (void) dmu_tx_hold_dnode_impl(tx, dn, THT_NEWOBJECT, 0, 0); } /* * This function reads specified data from disk. The specified data will * be needed to perform the transaction -- i.e, it will be read after * we do dmu_tx_assign(). There are two reasons that we read the data now * (before dmu_tx_assign()): * * 1. Reading it now has potentially better performance. The transaction * has not yet been assigned, so the TXG is not held open, and also the * caller typically has less locks held when calling dmu_tx_hold_*() than * after the transaction has been assigned. This reduces the lock (and txg) * hold times, thus reducing lock contention. * * 2. It is easier for callers (primarily the ZPL) to handle i/o errors * that are detected before they start making changes to the DMU state * (i.e. now). Once the transaction has been assigned, and some DMU * state has been changed, it can be difficult to recover from an i/o * error (e.g. to undo the changes already made in memory at the DMU * layer). Typically code to do so does not exist in the caller -- it * assumes that the data has already been cached and thus i/o errors are * not possible. * * It has been observed that the i/o initiated here can be a performance * problem, and it appears to be optional, because we don't look at the * data which is read. However, removing this read would only serve to * move the work elsewhere (after the dmu_tx_assign()), where it may * have a greater impact on performance (in addition to the impact on * fault tolerance noted above). */ static int dmu_tx_check_ioerr(zio_t *zio, dnode_t *dn, int level, uint64_t blkid) { int err; dmu_buf_impl_t *db; rw_enter(&dn->dn_struct_rwlock, RW_READER); db = dbuf_hold_level(dn, level, blkid, FTAG); rw_exit(&dn->dn_struct_rwlock); if (db == NULL) return (SET_ERROR(EIO)); err = dbuf_read(db, zio, DB_RF_CANFAIL | DB_RF_NOPREFETCH); dbuf_rele(db, FTAG); return (err); } /* ARGSUSED */ static void dmu_tx_count_write(dmu_tx_hold_t *txh, uint64_t off, uint64_t len) { dnode_t *dn = txh->txh_dnode; int err = 0; if (len == 0) return; (void) zfs_refcount_add_many(&txh->txh_space_towrite, len, FTAG); if (zfs_refcount_count(&txh->txh_space_towrite) > 2 * DMU_MAX_ACCESS) err = SET_ERROR(EFBIG); if (dn == NULL) return; /* * For i/o error checking, read the blocks that will be needed * to perform the write: the first and last level-0 blocks (if * they are not aligned, i.e. if they are partial-block writes), * and all the level-1 blocks. */ if (dn->dn_maxblkid == 0) { if (off < dn->dn_datablksz && (off > 0 || len < dn->dn_datablksz)) { err = dmu_tx_check_ioerr(NULL, dn, 0, 0); if (err != 0) { txh->txh_tx->tx_err = err; } } } else { zio_t *zio = zio_root(dn->dn_objset->os_spa, NULL, NULL, ZIO_FLAG_CANFAIL); /* first level-0 block */ uint64_t start = off >> dn->dn_datablkshift; if (P2PHASE(off, dn->dn_datablksz) || len < dn->dn_datablksz) { err = dmu_tx_check_ioerr(zio, dn, 0, start); if (err != 0) { txh->txh_tx->tx_err = err; } } /* last level-0 block */ uint64_t end = (off + len - 1) >> dn->dn_datablkshift; if (end != start && end <= dn->dn_maxblkid && P2PHASE(off + len, dn->dn_datablksz)) { err = dmu_tx_check_ioerr(zio, dn, 0, end); if (err != 0) { txh->txh_tx->tx_err = err; } } /* level-1 blocks */ if (dn->dn_nlevels > 1) { int shft = dn->dn_indblkshift - SPA_BLKPTRSHIFT; for (uint64_t i = (start >> shft) + 1; i < end >> shft; i++) { err = dmu_tx_check_ioerr(zio, dn, 1, i); if (err != 0) { txh->txh_tx->tx_err = err; } } } err = zio_wait(zio); if (err != 0) { txh->txh_tx->tx_err = err; } } } static void dmu_tx_count_dnode(dmu_tx_hold_t *txh) { (void) zfs_refcount_add_many(&txh->txh_space_towrite, DNODE_MIN_SIZE, FTAG); } void dmu_tx_hold_write(dmu_tx_t *tx, uint64_t object, uint64_t off, int len) { dmu_tx_hold_t *txh; ASSERT0(tx->tx_txg); ASSERT3U(len, <=, DMU_MAX_ACCESS); ASSERT(len == 0 || UINT64_MAX - off >= len - 1); txh = dmu_tx_hold_object_impl(tx, tx->tx_objset, object, THT_WRITE, off, len); if (txh != NULL) { dmu_tx_count_write(txh, off, len); dmu_tx_count_dnode(txh); } } void dmu_tx_hold_write_by_dnode(dmu_tx_t *tx, dnode_t *dn, uint64_t off, int len) { dmu_tx_hold_t *txh; ASSERT0(tx->tx_txg); ASSERT3U(len, <=, DMU_MAX_ACCESS); ASSERT(len == 0 || UINT64_MAX - off >= len - 1); txh = dmu_tx_hold_dnode_impl(tx, dn, THT_WRITE, off, len); if (txh != NULL) { dmu_tx_count_write(txh, off, len); dmu_tx_count_dnode(txh); } } /* * This function marks the transaction as being a "net free". The end * result is that refquotas will be disabled for this transaction, and * this transaction will be able to use half of the pool space overhead * (see dsl_pool_adjustedsize()). Therefore this function should only * be called for transactions that we expect will not cause a net increase * in the amount of space used (but it's OK if that is occasionally not true). */ void dmu_tx_mark_netfree(dmu_tx_t *tx) { tx->tx_netfree = B_TRUE; } static void dmu_tx_hold_free_impl(dmu_tx_hold_t *txh, uint64_t off, uint64_t len) { dmu_tx_t *tx = txh->txh_tx; dnode_t *dn = txh->txh_dnode; int err; ASSERT(tx->tx_txg == 0); dmu_tx_count_dnode(txh); if (off >= (dn->dn_maxblkid + 1) * dn->dn_datablksz) return; if (len == DMU_OBJECT_END) len = (dn->dn_maxblkid + 1) * dn->dn_datablksz - off; dmu_tx_count_dnode(txh); /* * For i/o error checking, we read the first and last level-0 * blocks if they are not aligned, and all the level-1 blocks. * * Note: dbuf_free_range() assumes that we have not instantiated * any level-0 dbufs that will be completely freed. Therefore we must * exercise care to not read or count the first and last blocks * if they are blocksize-aligned. */ if (dn->dn_datablkshift == 0) { if (off != 0 || len < dn->dn_datablksz) dmu_tx_count_write(txh, 0, dn->dn_datablksz); } else { /* first block will be modified if it is not aligned */ if (!IS_P2ALIGNED(off, 1 << dn->dn_datablkshift)) dmu_tx_count_write(txh, off, 1); /* last block will be modified if it is not aligned */ if (!IS_P2ALIGNED(off + len, 1 << dn->dn_datablkshift)) dmu_tx_count_write(txh, off + len, 1); } /* * Check level-1 blocks. */ if (dn->dn_nlevels > 1) { int shift = dn->dn_datablkshift + dn->dn_indblkshift - SPA_BLKPTRSHIFT; uint64_t start = off >> shift; uint64_t end = (off + len) >> shift; ASSERT(dn->dn_indblkshift != 0); /* * dnode_reallocate() can result in an object with indirect * blocks having an odd data block size. In this case, * just check the single block. */ if (dn->dn_datablkshift == 0) start = end = 0; zio_t *zio = zio_root(tx->tx_pool->dp_spa, NULL, NULL, ZIO_FLAG_CANFAIL); for (uint64_t i = start; i <= end; i++) { uint64_t ibyte = i << shift; err = dnode_next_offset(dn, 0, &ibyte, 2, 1, 0); i = ibyte >> shift; if (err == ESRCH || i > end) break; if (err != 0) { tx->tx_err = err; (void) zio_wait(zio); return; } (void) zfs_refcount_add_many(&txh->txh_memory_tohold, 1 << dn->dn_indblkshift, FTAG); err = dmu_tx_check_ioerr(zio, dn, 1, i); if (err != 0) { tx->tx_err = err; (void) zio_wait(zio); return; } } err = zio_wait(zio); if (err != 0) { tx->tx_err = err; return; } } } void dmu_tx_hold_free(dmu_tx_t *tx, uint64_t object, uint64_t off, uint64_t len) { dmu_tx_hold_t *txh; txh = dmu_tx_hold_object_impl(tx, tx->tx_objset, object, THT_FREE, off, len); if (txh != NULL) (void) dmu_tx_hold_free_impl(txh, off, len); } void dmu_tx_hold_free_by_dnode(dmu_tx_t *tx, dnode_t *dn, uint64_t off, uint64_t len) { dmu_tx_hold_t *txh; txh = dmu_tx_hold_dnode_impl(tx, dn, THT_FREE, off, len); if (txh != NULL) (void) dmu_tx_hold_free_impl(txh, off, len); } static void dmu_tx_hold_zap_impl(dmu_tx_hold_t *txh, const char *name) { dmu_tx_t *tx = txh->txh_tx; dnode_t *dn = txh->txh_dnode; int err; ASSERT(tx->tx_txg == 0); dmu_tx_count_dnode(txh); /* * Modifying a almost-full microzap is around the worst case (128KB) * * If it is a fat zap, the worst case would be 7*16KB=112KB: * - 3 blocks overwritten: target leaf, ptrtbl block, header block * - 4 new blocks written if adding: * - 2 blocks for possibly split leaves, * - 2 grown ptrtbl blocks */ (void) zfs_refcount_add_many(&txh->txh_space_towrite, MZAP_MAX_BLKSZ, FTAG); if (dn == NULL) return; ASSERT3U(DMU_OT_BYTESWAP(dn->dn_type), ==, DMU_BSWAP_ZAP); if (dn->dn_maxblkid == 0 || name == NULL) { /* * This is a microzap (only one block), or we don't know * the name. Check the first block for i/o errors. */ err = dmu_tx_check_ioerr(NULL, dn, 0, 0); if (err != 0) { tx->tx_err = err; } } else { /* * Access the name so that we'll check for i/o errors to * the leaf blocks, etc. We ignore ENOENT, as this name * may not yet exist. */ err = zap_lookup_by_dnode(dn, name, 8, 0, NULL); if (err == EIO || err == ECKSUM || err == ENXIO) { tx->tx_err = err; } } } void dmu_tx_hold_zap(dmu_tx_t *tx, uint64_t object, int add, const char *name) { dmu_tx_hold_t *txh; ASSERT0(tx->tx_txg); txh = dmu_tx_hold_object_impl(tx, tx->tx_objset, object, THT_ZAP, add, (uintptr_t)name); if (txh != NULL) dmu_tx_hold_zap_impl(txh, name); } void dmu_tx_hold_zap_by_dnode(dmu_tx_t *tx, dnode_t *dn, int add, const char *name) { dmu_tx_hold_t *txh; ASSERT0(tx->tx_txg); ASSERT(dn != NULL); txh = dmu_tx_hold_dnode_impl(tx, dn, THT_ZAP, add, (uintptr_t)name); if (txh != NULL) dmu_tx_hold_zap_impl(txh, name); } void dmu_tx_hold_bonus(dmu_tx_t *tx, uint64_t object) { dmu_tx_hold_t *txh; ASSERT(tx->tx_txg == 0); txh = dmu_tx_hold_object_impl(tx, tx->tx_objset, object, THT_BONUS, 0, 0); if (txh) dmu_tx_count_dnode(txh); } void dmu_tx_hold_bonus_by_dnode(dmu_tx_t *tx, dnode_t *dn) { dmu_tx_hold_t *txh; ASSERT0(tx->tx_txg); txh = dmu_tx_hold_dnode_impl(tx, dn, THT_BONUS, 0, 0); if (txh) dmu_tx_count_dnode(txh); } void dmu_tx_hold_space(dmu_tx_t *tx, uint64_t space) { dmu_tx_hold_t *txh; ASSERT(tx->tx_txg == 0); txh = dmu_tx_hold_object_impl(tx, tx->tx_objset, DMU_NEW_OBJECT, THT_SPACE, space, 0); if (txh) { (void) zfs_refcount_add_many( &txh->txh_space_towrite, space, FTAG); } } #ifdef ZFS_DEBUG void dmu_tx_dirty_buf(dmu_tx_t *tx, dmu_buf_impl_t *db) { boolean_t match_object = B_FALSE; boolean_t match_offset = B_FALSE; DB_DNODE_ENTER(db); dnode_t *dn = DB_DNODE(db); ASSERT(tx->tx_txg != 0); ASSERT(tx->tx_objset == NULL || dn->dn_objset == tx->tx_objset); ASSERT3U(dn->dn_object, ==, db->db.db_object); if (tx->tx_anyobj) { DB_DNODE_EXIT(db); return; } /* XXX No checking on the meta dnode for now */ if (db->db.db_object == DMU_META_DNODE_OBJECT) { DB_DNODE_EXIT(db); return; } for (dmu_tx_hold_t *txh = list_head(&tx->tx_holds); txh != NULL; txh = list_next(&tx->tx_holds, txh)) { ASSERT3U(dn->dn_assigned_txg, ==, tx->tx_txg); if (txh->txh_dnode == dn && txh->txh_type != THT_NEWOBJECT) match_object = TRUE; if (txh->txh_dnode == NULL || txh->txh_dnode == dn) { int datablkshift = dn->dn_datablkshift ? dn->dn_datablkshift : SPA_MAXBLOCKSHIFT; int epbs = dn->dn_indblkshift - SPA_BLKPTRSHIFT; int shift = datablkshift + epbs * db->db_level; uint64_t beginblk = shift >= 64 ? 0 : (txh->txh_arg1 >> shift); uint64_t endblk = shift >= 64 ? 0 : ((txh->txh_arg1 + txh->txh_arg2 - 1) >> shift); uint64_t blkid = db->db_blkid; /* XXX txh_arg2 better not be zero... */ dprintf("found txh type %x beginblk=%llx endblk=%llx\n", txh->txh_type, beginblk, endblk); switch (txh->txh_type) { case THT_WRITE: if (blkid >= beginblk && blkid <= endblk) match_offset = TRUE; /* * We will let this hold work for the bonus * or spill buffer so that we don't need to * hold it when creating a new object. */ if (blkid == DMU_BONUS_BLKID || blkid == DMU_SPILL_BLKID) match_offset = TRUE; /* * They might have to increase nlevels, * thus dirtying the new TLIBs. Or the * might have to change the block size, * thus dirying the new lvl=0 blk=0. */ if (blkid == 0) match_offset = TRUE; break; case THT_FREE: /* * We will dirty all the level 1 blocks in * the free range and perhaps the first and * last level 0 block. */ if (blkid >= beginblk && (blkid <= endblk || txh->txh_arg2 == DMU_OBJECT_END)) match_offset = TRUE; break; case THT_SPILL: if (blkid == DMU_SPILL_BLKID) match_offset = TRUE; break; case THT_BONUS: if (blkid == DMU_BONUS_BLKID) match_offset = TRUE; break; case THT_ZAP: match_offset = TRUE; break; case THT_NEWOBJECT: match_object = TRUE; break; default: cmn_err(CE_PANIC, "bad txh_type %d", txh->txh_type); } } if (match_object && match_offset) { DB_DNODE_EXIT(db); return; } } DB_DNODE_EXIT(db); panic("dirtying dbuf obj=%llx lvl=%u blkid=%llx but not tx_held\n", (u_longlong_t)db->db.db_object, db->db_level, (u_longlong_t)db->db_blkid); } #endif /* * If we can't do 10 iops, something is wrong. Let us go ahead * and hit zfs_dirty_data_max. */ hrtime_t zfs_delay_max_ns = 100 * MICROSEC; /* 100 milliseconds */ int zfs_delay_resolution_ns = 100 * 1000; /* 100 microseconds */ /* * We delay transactions when we've determined that the backend storage * isn't able to accommodate the rate of incoming writes. * * If there is already a transaction waiting, we delay relative to when * that transaction finishes waiting. This way the calculated min_time * is independent of the number of threads concurrently executing * transactions. * * If we are the only waiter, wait relative to when the transaction * started, rather than the current time. This credits the transaction for * "time already served", e.g. reading indirect blocks. * * The minimum time for a transaction to take is calculated as: * min_time = scale * (dirty - min) / (max - dirty) * min_time is then capped at zfs_delay_max_ns. * * The delay has two degrees of freedom that can be adjusted via tunables. * The percentage of dirty data at which we start to delay is defined by * zfs_delay_min_dirty_percent. This should typically be at or above * zfs_vdev_async_write_active_max_dirty_percent so that we only start to * delay after writing at full speed has failed to keep up with the incoming * write rate. The scale of the curve is defined by zfs_delay_scale. Roughly * speaking, this variable determines the amount of delay at the midpoint of * the curve. * * delay * 10ms +-------------------------------------------------------------*+ * | *| * 9ms + *+ * | *| * 8ms + *+ * | * | * 7ms + * + * | * | * 6ms + * + * | * | * 5ms + * + * | * | * 4ms + * + * | * | * 3ms + * + * | * | * 2ms + (midpoint) * + * | | ** | * 1ms + v *** + * | zfs_delay_scale ----------> ******** | * 0 +-------------------------------------*********----------------+ * 0% <- zfs_dirty_data_max -> 100% * * Note that since the delay is added to the outstanding time remaining on the * most recent transaction, the delay is effectively the inverse of IOPS. * Here the midpoint of 500us translates to 2000 IOPS. The shape of the curve * was chosen such that small changes in the amount of accumulated dirty data * in the first 3/4 of the curve yield relatively small differences in the * amount of delay. * * The effects can be easier to understand when the amount of delay is * represented on a log scale: * * delay * 100ms +-------------------------------------------------------------++ * + + * | | * + *+ * 10ms + *+ * + ** + * | (midpoint) ** | * + | ** + * 1ms + v **** + * + zfs_delay_scale ----------> ***** + * | **** | * + **** + * 100us + ** + * + * + * | * | * + * + * 10us + * + * + + * | | * + + * +--------------------------------------------------------------+ * 0% <- zfs_dirty_data_max -> 100% * * Note here that only as the amount of dirty data approaches its limit does * the delay start to increase rapidly. The goal of a properly tuned system * should be to keep the amount of dirty data out of that range by first * ensuring that the appropriate limits are set for the I/O scheduler to reach * optimal throughput on the backend storage, and then by changing the value * of zfs_delay_scale to increase the steepness of the curve. */ static void dmu_tx_delay(dmu_tx_t *tx, uint64_t dirty) { dsl_pool_t *dp = tx->tx_pool; uint64_t delay_min_bytes = zfs_dirty_data_max * zfs_delay_min_dirty_percent / 100; hrtime_t wakeup, min_tx_time, now; if (dirty <= delay_min_bytes) return; /* * The caller has already waited until we are under the max. * We make them pass us the amount of dirty data so we don't * have to handle the case of it being >= the max, which could * cause a divide-by-zero if it's == the max. */ ASSERT3U(dirty, <, zfs_dirty_data_max); now = gethrtime(); min_tx_time = zfs_delay_scale * (dirty - delay_min_bytes) / (zfs_dirty_data_max - dirty); min_tx_time = MIN(min_tx_time, zfs_delay_max_ns); if (now > tx->tx_start + min_tx_time) return; DTRACE_PROBE3(delay__mintime, dmu_tx_t *, tx, uint64_t, dirty, uint64_t, min_tx_time); mutex_enter(&dp->dp_lock); wakeup = MAX(tx->tx_start + min_tx_time, dp->dp_last_wakeup + min_tx_time); dp->dp_last_wakeup = wakeup; mutex_exit(&dp->dp_lock); zfs_sleep_until(wakeup); } /* * This routine attempts to assign the transaction to a transaction group. * To do so, we must determine if there is sufficient free space on disk. * * If this is a "netfree" transaction (i.e. we called dmu_tx_mark_netfree() * on it), then it is assumed that there is sufficient free space, * unless there's insufficient slop space in the pool (see the comment * above spa_slop_shift in spa_misc.c). * * If it is not a "netfree" transaction, then if the data already on disk * is over the allowed usage (e.g. quota), this will fail with EDQUOT or * ENOSPC. Otherwise, if the current rough estimate of pending changes, * plus the rough estimate of this transaction's changes, may exceed the * allowed usage, then this will fail with ERESTART, which will cause the * caller to wait for the pending changes to be written to disk (by waiting * for the next TXG to open), and then check the space usage again. * * The rough estimate of pending changes is comprised of the sum of: * * - this transaction's holds' txh_space_towrite * * - dd_tempreserved[], which is the sum of in-flight transactions' * holds' txh_space_towrite (i.e. those transactions that have called * dmu_tx_assign() but not yet called dmu_tx_commit()). * * - dd_space_towrite[], which is the amount of dirtied dbufs. * * Note that all of these values are inflated by spa_get_worst_case_asize(), * which means that we may get ERESTART well before we are actually in danger * of running out of space, but this also mitigates any small inaccuracies * in the rough estimate (e.g. txh_space_towrite doesn't take into account * indirect blocks, and dd_space_towrite[] doesn't take into account changes * to the MOS). * * Note that due to this algorithm, it is possible to exceed the allowed * usage by one transaction. Also, as we approach the allowed usage, * we will allow a very limited amount of changes into each TXG, thus * decreasing performance. */ static int dmu_tx_try_assign(dmu_tx_t *tx, uint64_t txg_how) { spa_t *spa = tx->tx_pool->dp_spa; ASSERT0(tx->tx_txg); if (tx->tx_err) { DMU_TX_STAT_BUMP(dmu_tx_error); return (tx->tx_err); } if (spa_suspended(spa)) { DMU_TX_STAT_BUMP(dmu_tx_suspended); /* * If the user has indicated a blocking failure mode * then return ERESTART which will block in dmu_tx_wait(). * Otherwise, return EIO so that an error can get * propagated back to the VOP calls. * * Note that we always honor the txg_how flag regardless * of the failuremode setting. */ if (spa_get_failmode(spa) == ZIO_FAILURE_MODE_CONTINUE && !(txg_how & TXG_WAIT)) return (SET_ERROR(EIO)); return (SET_ERROR(ERESTART)); } if (!tx->tx_dirty_delayed && dsl_pool_need_dirty_delay(tx->tx_pool)) { tx->tx_wait_dirty = B_TRUE; DMU_TX_STAT_BUMP(dmu_tx_dirty_delay); return (SET_ERROR(ERESTART)); } tx->tx_txg = txg_hold_open(tx->tx_pool, &tx->tx_txgh); tx->tx_needassign_txh = NULL; /* * NB: No error returns are allowed after txg_hold_open, but * before processing the dnode holds, due to the * dmu_tx_unassign() logic. */ uint64_t towrite = 0; uint64_t tohold = 0; for (dmu_tx_hold_t *txh = list_head(&tx->tx_holds); txh != NULL; txh = list_next(&tx->tx_holds, txh)) { dnode_t *dn = txh->txh_dnode; if (dn != NULL) { /* * This thread can't hold the dn_struct_rwlock * while assigning the tx, because this can lead to * deadlock. Specifically, if this dnode is already * assigned to an earlier txg, this thread may need * to wait for that txg to sync (the ERESTART case * below). The other thread that has assigned this * dnode to an earlier txg prevents this txg from * syncing until its tx can complete (calling * dmu_tx_commit()), but it may need to acquire the * dn_struct_rwlock to do so (e.g. via * dmu_buf_hold*()). * * Note that this thread can't hold the lock for * read either, but the rwlock doesn't record * enough information to make that assertion. */ ASSERT(!RW_WRITE_HELD(&dn->dn_struct_rwlock)); mutex_enter(&dn->dn_mtx); if (dn->dn_assigned_txg == tx->tx_txg - 1) { mutex_exit(&dn->dn_mtx); tx->tx_needassign_txh = txh; DMU_TX_STAT_BUMP(dmu_tx_group); return (SET_ERROR(ERESTART)); } if (dn->dn_assigned_txg == 0) dn->dn_assigned_txg = tx->tx_txg; ASSERT3U(dn->dn_assigned_txg, ==, tx->tx_txg); (void) zfs_refcount_add(&dn->dn_tx_holds, tx); mutex_exit(&dn->dn_mtx); } towrite += zfs_refcount_count(&txh->txh_space_towrite); tohold += zfs_refcount_count(&txh->txh_memory_tohold); } /* needed allocation: worst-case estimate of write space */ uint64_t asize = spa_get_worst_case_asize(tx->tx_pool->dp_spa, towrite); /* calculate memory footprint estimate */ uint64_t memory = towrite + tohold; if (tx->tx_dir != NULL && asize != 0) { int err = dsl_dir_tempreserve_space(tx->tx_dir, memory, asize, tx->tx_netfree, &tx->tx_tempreserve_cookie, tx); if (err != 0) return (err); } DMU_TX_STAT_BUMP(dmu_tx_assigned); return (0); } static void dmu_tx_unassign(dmu_tx_t *tx) { if (tx->tx_txg == 0) return; txg_rele_to_quiesce(&tx->tx_txgh); /* * Walk the transaction's hold list, removing the hold on the * associated dnode, and notifying waiters if the refcount drops to 0. */ for (dmu_tx_hold_t *txh = list_head(&tx->tx_holds); txh && txh != tx->tx_needassign_txh; txh = list_next(&tx->tx_holds, txh)) { dnode_t *dn = txh->txh_dnode; if (dn == NULL) continue; mutex_enter(&dn->dn_mtx); ASSERT3U(dn->dn_assigned_txg, ==, tx->tx_txg); if (zfs_refcount_remove(&dn->dn_tx_holds, tx) == 0) { dn->dn_assigned_txg = 0; cv_broadcast(&dn->dn_notxholds); } mutex_exit(&dn->dn_mtx); } txg_rele_to_sync(&tx->tx_txgh); tx->tx_lasttried_txg = tx->tx_txg; tx->tx_txg = 0; } /* * Assign tx to a transaction group; txg_how is a bitmask: * * If TXG_WAIT is set and the currently open txg is full, this function * will wait until there's a new txg. This should be used when no locks * are being held. With this bit set, this function will only fail if * we're truly out of space (or over quota). * * If TXG_WAIT is *not* set and we can't assign into the currently open * txg without blocking, this function will return immediately with * ERESTART. This should be used whenever locks are being held. On an * ERESTART error, the caller should drop all locks, call dmu_tx_wait(), * and try again. * * If TXG_NOTHROTTLE is set, this indicates that this tx should not be * delayed due on the ZFS Write Throttle (see comments in dsl_pool.c for * details on the throttle). This is used by the VFS operations, after * they have already called dmu_tx_wait() (though most likely on a * different tx). */ int dmu_tx_assign(dmu_tx_t *tx, uint64_t txg_how) { int err; ASSERT(tx->tx_txg == 0); ASSERT0(txg_how & ~(TXG_WAIT | TXG_NOTHROTTLE)); ASSERT(!dsl_pool_sync_context(tx->tx_pool)); /* If we might wait, we must not hold the config lock. */ IMPLY((txg_how & TXG_WAIT), !dsl_pool_config_held(tx->tx_pool)); if ((txg_how & TXG_NOTHROTTLE)) tx->tx_dirty_delayed = B_TRUE; while ((err = dmu_tx_try_assign(tx, txg_how)) != 0) { dmu_tx_unassign(tx); if (err != ERESTART || !(txg_how & TXG_WAIT)) return (err); dmu_tx_wait(tx); } txg_rele_to_quiesce(&tx->tx_txgh); return (0); } void dmu_tx_wait(dmu_tx_t *tx) { spa_t *spa = tx->tx_pool->dp_spa; dsl_pool_t *dp = tx->tx_pool; hrtime_t before; ASSERT(tx->tx_txg == 0); ASSERT(!dsl_pool_config_held(tx->tx_pool)); before = gethrtime(); if (tx->tx_wait_dirty) { uint64_t dirty; /* * dmu_tx_try_assign() has determined that we need to wait * because we've consumed much or all of the dirty buffer * space. */ mutex_enter(&dp->dp_lock); if (dp->dp_dirty_total >= zfs_dirty_data_max) DMU_TX_STAT_BUMP(dmu_tx_dirty_over_max); while (dp->dp_dirty_total >= zfs_dirty_data_max) cv_wait(&dp->dp_spaceavail_cv, &dp->dp_lock); dirty = dp->dp_dirty_total; mutex_exit(&dp->dp_lock); dmu_tx_delay(tx, dirty); tx->tx_wait_dirty = B_FALSE; /* * Note: setting tx_dirty_delayed only has effect if the * caller used TX_WAIT. Otherwise they are going to * destroy this tx and try again. The common case, * zfs_write(), uses TX_WAIT. */ tx->tx_dirty_delayed = B_TRUE; } else if (spa_suspended(spa) || tx->tx_lasttried_txg == 0) { /* * If the pool is suspended we need to wait until it * is resumed. Note that it's possible that the pool * has become active after this thread has tried to * obtain a tx. If that's the case then tx_lasttried_txg * would not have been set. */ txg_wait_synced(dp, spa_last_synced_txg(spa) + 1); } else if (tx->tx_needassign_txh) { dnode_t *dn = tx->tx_needassign_txh->txh_dnode; mutex_enter(&dn->dn_mtx); while (dn->dn_assigned_txg == tx->tx_lasttried_txg - 1) cv_wait(&dn->dn_notxholds, &dn->dn_mtx); mutex_exit(&dn->dn_mtx); tx->tx_needassign_txh = NULL; } else { /* * If we have a lot of dirty data just wait until we sync * out a TXG at which point we'll hopefully have synced * a portion of the changes. */ txg_wait_synced(dp, spa_last_synced_txg(spa) + 1); } spa_tx_assign_add_nsecs(spa, gethrtime() - before); } static void dmu_tx_destroy(dmu_tx_t *tx) { dmu_tx_hold_t *txh; while ((txh = list_head(&tx->tx_holds)) != NULL) { dnode_t *dn = txh->txh_dnode; list_remove(&tx->tx_holds, txh); zfs_refcount_destroy_many(&txh->txh_space_towrite, zfs_refcount_count(&txh->txh_space_towrite)); zfs_refcount_destroy_many(&txh->txh_memory_tohold, zfs_refcount_count(&txh->txh_memory_tohold)); kmem_free(txh, sizeof (dmu_tx_hold_t)); if (dn != NULL) dnode_rele(dn, tx); } list_destroy(&tx->tx_callbacks); list_destroy(&tx->tx_holds); kmem_free(tx, sizeof (dmu_tx_t)); } void dmu_tx_commit(dmu_tx_t *tx) { ASSERT(tx->tx_txg != 0); /* * Go through the transaction's hold list and remove holds on * associated dnodes, notifying waiters if no holds remain. */ for (dmu_tx_hold_t *txh = list_head(&tx->tx_holds); txh != NULL; txh = list_next(&tx->tx_holds, txh)) { dnode_t *dn = txh->txh_dnode; if (dn == NULL) continue; mutex_enter(&dn->dn_mtx); ASSERT3U(dn->dn_assigned_txg, ==, tx->tx_txg); if (zfs_refcount_remove(&dn->dn_tx_holds, tx) == 0) { dn->dn_assigned_txg = 0; cv_broadcast(&dn->dn_notxholds); } mutex_exit(&dn->dn_mtx); } if (tx->tx_tempreserve_cookie) dsl_dir_tempreserve_clear(tx->tx_tempreserve_cookie, tx); if (!list_is_empty(&tx->tx_callbacks)) txg_register_callbacks(&tx->tx_txgh, &tx->tx_callbacks); if (tx->tx_anyobj == FALSE) txg_rele_to_sync(&tx->tx_txgh); dmu_tx_destroy(tx); } void dmu_tx_abort(dmu_tx_t *tx) { ASSERT(tx->tx_txg == 0); /* * Call any registered callbacks with an error code. */ if (!list_is_empty(&tx->tx_callbacks)) dmu_tx_do_callbacks(&tx->tx_callbacks, ECANCELED); dmu_tx_destroy(tx); } uint64_t dmu_tx_get_txg(dmu_tx_t *tx) { ASSERT(tx->tx_txg != 0); return (tx->tx_txg); } dsl_pool_t * dmu_tx_pool(dmu_tx_t *tx) { ASSERT(tx->tx_pool != NULL); return (tx->tx_pool); } void dmu_tx_callback_register(dmu_tx_t *tx, dmu_tx_callback_func_t *func, void *data) { dmu_tx_callback_t *dcb; dcb = kmem_alloc(sizeof (dmu_tx_callback_t), KM_SLEEP); dcb->dcb_func = func; dcb->dcb_data = data; list_insert_tail(&tx->tx_callbacks, dcb); } /* * Call all the commit callbacks on a list, with a given error code. */ void dmu_tx_do_callbacks(list_t *cb_list, int error) { dmu_tx_callback_t *dcb; while ((dcb = list_tail(cb_list)) != NULL) { list_remove(cb_list, dcb); dcb->dcb_func(dcb->dcb_data, error); kmem_free(dcb, sizeof (dmu_tx_callback_t)); } } /* * Interface to hold a bunch of attributes. * used for creating new files. * attrsize is the total size of all attributes * to be added during object creation * * For updating/adding a single attribute dmu_tx_hold_sa() should be used. */ /* * hold necessary attribute name for attribute registration. * should be a very rare case where this is needed. If it does * happen it would only happen on the first write to the file system. */ static void dmu_tx_sa_registration_hold(sa_os_t *sa, dmu_tx_t *tx) { if (!sa->sa_need_attr_registration) return; for (int i = 0; i != sa->sa_num_attrs; i++) { if (!sa->sa_attr_table[i].sa_registered) { if (sa->sa_reg_attr_obj) dmu_tx_hold_zap(tx, sa->sa_reg_attr_obj, B_TRUE, sa->sa_attr_table[i].sa_name); else dmu_tx_hold_zap(tx, DMU_NEW_OBJECT, B_TRUE, sa->sa_attr_table[i].sa_name); } } } void dmu_tx_hold_spill(dmu_tx_t *tx, uint64_t object) { dmu_tx_hold_t *txh; txh = dmu_tx_hold_object_impl(tx, tx->tx_objset, object, THT_SPILL, 0, 0); if (txh != NULL) (void) zfs_refcount_add_many(&txh->txh_space_towrite, SPA_OLD_MAXBLOCKSIZE, FTAG); } void dmu_tx_hold_sa_create(dmu_tx_t *tx, int attrsize) { sa_os_t *sa = tx->tx_objset->os_sa; dmu_tx_hold_bonus(tx, DMU_NEW_OBJECT); if (tx->tx_objset->os_sa->sa_master_obj == 0) return; if (tx->tx_objset->os_sa->sa_layout_attr_obj) { dmu_tx_hold_zap(tx, sa->sa_layout_attr_obj, B_TRUE, NULL); } else { dmu_tx_hold_zap(tx, sa->sa_master_obj, B_TRUE, SA_LAYOUTS); dmu_tx_hold_zap(tx, sa->sa_master_obj, B_TRUE, SA_REGISTRY); dmu_tx_hold_zap(tx, DMU_NEW_OBJECT, B_TRUE, NULL); dmu_tx_hold_zap(tx, DMU_NEW_OBJECT, B_TRUE, NULL); } dmu_tx_sa_registration_hold(sa, tx); if (attrsize <= DN_OLD_MAX_BONUSLEN && !sa->sa_force_spill) return; (void) dmu_tx_hold_object_impl(tx, tx->tx_objset, DMU_NEW_OBJECT, THT_SPILL, 0, 0); } /* * Hold SA attribute * * dmu_tx_hold_sa(dmu_tx_t *tx, sa_handle_t *, attribute, add, size) * * variable_size is the total size of all variable sized attributes * passed to this function. It is not the total size of all * variable size attributes that *may* exist on this object. */ void dmu_tx_hold_sa(dmu_tx_t *tx, sa_handle_t *hdl, boolean_t may_grow) { uint64_t object; sa_os_t *sa = tx->tx_objset->os_sa; ASSERT(hdl != NULL); object = sa_handle_object(hdl); dmu_buf_impl_t *db = (dmu_buf_impl_t *)hdl->sa_bonus; DB_DNODE_ENTER(db); dmu_tx_hold_bonus_by_dnode(tx, DB_DNODE(db)); DB_DNODE_EXIT(db); if (tx->tx_objset->os_sa->sa_master_obj == 0) return; if (tx->tx_objset->os_sa->sa_reg_attr_obj == 0 || tx->tx_objset->os_sa->sa_layout_attr_obj == 0) { dmu_tx_hold_zap(tx, sa->sa_master_obj, B_TRUE, SA_LAYOUTS); dmu_tx_hold_zap(tx, sa->sa_master_obj, B_TRUE, SA_REGISTRY); dmu_tx_hold_zap(tx, DMU_NEW_OBJECT, B_TRUE, NULL); dmu_tx_hold_zap(tx, DMU_NEW_OBJECT, B_TRUE, NULL); } dmu_tx_sa_registration_hold(sa, tx); if (may_grow && tx->tx_objset->os_sa->sa_layout_attr_obj) dmu_tx_hold_zap(tx, sa->sa_layout_attr_obj, B_TRUE, NULL); if (sa->sa_force_spill || may_grow || hdl->sa_spill) { ASSERT(tx->tx_txg == 0); dmu_tx_hold_spill(tx, object); } else { dnode_t *dn; DB_DNODE_ENTER(db); dn = DB_DNODE(db); if (dn->dn_have_spill) { ASSERT(tx->tx_txg == 0); dmu_tx_hold_spill(tx, object); } DB_DNODE_EXIT(db); } } void dmu_tx_init(void) { dmu_tx_ksp = kstat_create("zfs", 0, "dmu_tx", "misc", KSTAT_TYPE_NAMED, sizeof (dmu_tx_stats) / sizeof (kstat_named_t), KSTAT_FLAG_VIRTUAL); if (dmu_tx_ksp != NULL) { dmu_tx_ksp->ks_data = &dmu_tx_stats; kstat_install(dmu_tx_ksp); } } void dmu_tx_fini(void) { if (dmu_tx_ksp != NULL) { kstat_delete(dmu_tx_ksp); dmu_tx_ksp = NULL; } } #if defined(_KERNEL) EXPORT_SYMBOL(dmu_tx_create); EXPORT_SYMBOL(dmu_tx_hold_write); EXPORT_SYMBOL(dmu_tx_hold_write_by_dnode); EXPORT_SYMBOL(dmu_tx_hold_free); EXPORT_SYMBOL(dmu_tx_hold_free_by_dnode); EXPORT_SYMBOL(dmu_tx_hold_zap); EXPORT_SYMBOL(dmu_tx_hold_zap_by_dnode); EXPORT_SYMBOL(dmu_tx_hold_bonus); EXPORT_SYMBOL(dmu_tx_hold_bonus_by_dnode); EXPORT_SYMBOL(dmu_tx_abort); EXPORT_SYMBOL(dmu_tx_assign); EXPORT_SYMBOL(dmu_tx_wait); EXPORT_SYMBOL(dmu_tx_commit); EXPORT_SYMBOL(dmu_tx_mark_netfree); EXPORT_SYMBOL(dmu_tx_get_txg); EXPORT_SYMBOL(dmu_tx_callback_register); EXPORT_SYMBOL(dmu_tx_do_callbacks); EXPORT_SYMBOL(dmu_tx_hold_spill); EXPORT_SYMBOL(dmu_tx_hold_sa_create); EXPORT_SYMBOL(dmu_tx_hold_sa); #endif pan> static void zfs_init_vattr(vattr_t *vap, uint64_t mask, uint64_t mode, uint64_t uid, uint64_t gid, uint64_t rdev, uint64_t nodeid) { bzero(vap, sizeof (*vap)); vap->va_mask = (uint_t)mask; vap->va_type = IFTOVT(mode); vap->va_mode = mode; vap->va_uid = (uid_t)(IS_EPHEMERAL(uid)) ? -1 : uid; vap->va_gid = (gid_t)(IS_EPHEMERAL(gid)) ? -1 : gid; vap->va_rdev = rdev; vap->va_nodeid = nodeid; } /* ARGSUSED */ static int zfs_replay_error(void *arg1, void *arg2, boolean_t byteswap) { return (SET_ERROR(ENOTSUP)); } static void zfs_replay_xvattr(lr_attr_t *lrattr, xvattr_t *xvap) { xoptattr_t *xoap = NULL; uint64_t *attrs; uint64_t *crtime; uint32_t *bitmap; void *scanstamp; int i; xvap->xva_vattr.va_mask |= ATTR_XVATTR; if ((xoap = xva_getxoptattr(xvap)) == NULL) { xvap->xva_vattr.va_mask &= ~ATTR_XVATTR; /* shouldn't happen */ return; } ASSERT(lrattr->lr_attr_masksize == xvap->xva_mapsize); bitmap = &lrattr->lr_attr_bitmap; for (i = 0; i != lrattr->lr_attr_masksize; i++, bitmap++) xvap->xva_reqattrmap[i] = *bitmap; attrs = (uint64_t *)(lrattr + lrattr->lr_attr_masksize - 1); crtime = attrs + 1; scanstamp = (caddr_t)(crtime + 2); if (XVA_ISSET_REQ(xvap, XAT_HIDDEN)) xoap->xoa_hidden = ((*attrs & XAT0_HIDDEN) != 0); if (XVA_ISSET_REQ(xvap, XAT_SYSTEM)) xoap->xoa_system = ((*attrs & XAT0_SYSTEM) != 0); if (XVA_ISSET_REQ(xvap, XAT_ARCHIVE)) xoap->xoa_archive = ((*attrs & XAT0_ARCHIVE) != 0); if (XVA_ISSET_REQ(xvap, XAT_READONLY)) xoap->xoa_readonly = ((*attrs & XAT0_READONLY) != 0); if (XVA_ISSET_REQ(xvap, XAT_IMMUTABLE)) xoap->xoa_immutable = ((*attrs & XAT0_IMMUTABLE) != 0); if (XVA_ISSET_REQ(xvap, XAT_NOUNLINK)) xoap->xoa_nounlink = ((*attrs & XAT0_NOUNLINK) != 0); if (XVA_ISSET_REQ(xvap, XAT_APPENDONLY)) xoap->xoa_appendonly = ((*attrs & XAT0_APPENDONLY) != 0); if (XVA_ISSET_REQ(xvap, XAT_NODUMP)) xoap->xoa_nodump = ((*attrs & XAT0_NODUMP) != 0); if (XVA_ISSET_REQ(xvap, XAT_OPAQUE)) xoap->xoa_opaque = ((*attrs & XAT0_OPAQUE) != 0); if (XVA_ISSET_REQ(xvap, XAT_AV_MODIFIED)) xoap->xoa_av_modified = ((*attrs & XAT0_AV_MODIFIED) != 0); if (XVA_ISSET_REQ(xvap, XAT_AV_QUARANTINED)) xoap->xoa_av_quarantined = ((*attrs & XAT0_AV_QUARANTINED) != 0); if (XVA_ISSET_REQ(xvap, XAT_CREATETIME)) ZFS_TIME_DECODE(&xoap->xoa_createtime, crtime); if (XVA_ISSET_REQ(xvap, XAT_AV_SCANSTAMP)) { ASSERT(!XVA_ISSET_REQ(xvap, XAT_PROJID)); bcopy(scanstamp, xoap->xoa_av_scanstamp, AV_SCANSTAMP_SZ); } else if (XVA_ISSET_REQ(xvap, XAT_PROJID)) { /* * XAT_PROJID and XAT_AV_SCANSTAMP will never be valid * at the same time, so we can share the same space. */ bcopy(scanstamp, &xoap->xoa_projid, sizeof (uint64_t)); } if (XVA_ISSET_REQ(xvap, XAT_REPARSE)) xoap->xoa_reparse = ((*attrs & XAT0_REPARSE) != 0); if (XVA_ISSET_REQ(xvap, XAT_OFFLINE)) xoap->xoa_offline = ((*attrs & XAT0_OFFLINE) != 0); if (XVA_ISSET_REQ(xvap, XAT_SPARSE)) xoap->xoa_sparse = ((*attrs & XAT0_SPARSE) != 0); if (XVA_ISSET_REQ(xvap, XAT_PROJINHERIT)) xoap->xoa_projinherit = ((*attrs & XAT0_PROJINHERIT) != 0); } static int zfs_replay_domain_cnt(uint64_t uid, uint64_t gid) { uint64_t uid_idx; uint64_t gid_idx; int domcnt = 0; uid_idx = FUID_INDEX(uid); gid_idx = FUID_INDEX(gid); if (uid_idx) domcnt++; if (gid_idx > 0 && gid_idx != uid_idx) domcnt++; return (domcnt); } static void * zfs_replay_fuid_domain_common(zfs_fuid_info_t *fuid_infop, void *start, int domcnt) { int i; for (i = 0; i != domcnt; i++) { fuid_infop->z_domain_table[i] = start; start = (caddr_t)start + strlen(start) + 1; } return (start); } /* * Set the uid/gid in the fuid_info structure. */ static void zfs_replay_fuid_ugid(zfs_fuid_info_t *fuid_infop, uint64_t uid, uint64_t gid) { /* * If owner or group are log specific FUIDs then slurp up * domain information and build zfs_fuid_info_t */ if (IS_EPHEMERAL(uid)) fuid_infop->z_fuid_owner = uid; if (IS_EPHEMERAL(gid)) fuid_infop->z_fuid_group = gid; } /* * Load fuid domains into fuid_info_t */ static zfs_fuid_info_t * zfs_replay_fuid_domain(void *buf, void **end, uint64_t uid, uint64_t gid) { int domcnt; zfs_fuid_info_t *fuid_infop; fuid_infop = zfs_fuid_info_alloc(); domcnt = zfs_replay_domain_cnt(uid, gid); if (domcnt == 0) return (fuid_infop); fuid_infop->z_domain_table = kmem_zalloc(domcnt * sizeof (char *), KM_SLEEP); zfs_replay_fuid_ugid(fuid_infop, uid, gid); fuid_infop->z_domain_cnt = domcnt; *end = zfs_replay_fuid_domain_common(fuid_infop, buf, domcnt); return (fuid_infop); } /* * load zfs_fuid_t's and fuid_domains into fuid_info_t */ static zfs_fuid_info_t * zfs_replay_fuids(void *start, void **end, int idcnt, int domcnt, uint64_t uid, uint64_t gid) { uint64_t *log_fuid = (uint64_t *)start; zfs_fuid_info_t *fuid_infop; int i; fuid_infop = zfs_fuid_info_alloc(); fuid_infop->z_domain_cnt = domcnt; fuid_infop->z_domain_table = kmem_zalloc(domcnt * sizeof (char *), KM_SLEEP); for (i = 0; i != idcnt; i++) { zfs_fuid_t *zfuid; zfuid = kmem_alloc(sizeof (zfs_fuid_t), KM_SLEEP); zfuid->z_logfuid = *log_fuid; zfuid->z_id = -1; zfuid->z_domidx = 0; list_insert_tail(&fuid_infop->z_fuids, zfuid); log_fuid++; } zfs_replay_fuid_ugid(fuid_infop, uid, gid); *end = zfs_replay_fuid_domain_common(fuid_infop, log_fuid, domcnt); return (fuid_infop); } static void zfs_replay_swap_attrs(lr_attr_t *lrattr) { /* swap the lr_attr structure */ byteswap_uint32_array(lrattr, sizeof (*lrattr)); /* swap the bitmap */ byteswap_uint32_array(lrattr + 1, (lrattr->lr_attr_masksize - 1) * sizeof (uint32_t)); /* swap the attributes, create time + 64 bit word for attributes */ byteswap_uint64_array((caddr_t)(lrattr + 1) + (sizeof (uint32_t) * (lrattr->lr_attr_masksize - 1)), 3 * sizeof (uint64_t)); } /* * Replay file create with optional ACL, xvattr information as well * as option FUID information. */ static int zfs_replay_create_acl(void *arg1, void *arg2, boolean_t byteswap) { zfsvfs_t *zfsvfs = arg1; lr_acl_create_t *lracl = arg2; char *name = NULL; /* location determined later */ lr_create_t *lr = (lr_create_t *)lracl; znode_t *dzp; struct inode *ip = NULL; xvattr_t xva; int vflg = 0; vsecattr_t vsec = { 0 }; lr_attr_t *lrattr; void *aclstart; void *fuidstart; size_t xvatlen = 0; uint64_t txtype; uint64_t objid; uint64_t dnodesize; int error; txtype = (lr->lr_common.lrc_txtype & ~TX_CI); if (byteswap) { byteswap_uint64_array(lracl, sizeof (*lracl)); if (txtype == TX_CREATE_ACL_ATTR || txtype == TX_MKDIR_ACL_ATTR) { lrattr = (lr_attr_t *)(caddr_t)(lracl + 1); zfs_replay_swap_attrs(lrattr); xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize); } aclstart = (caddr_t)(lracl + 1) + xvatlen; zfs_ace_byteswap(aclstart, lracl->lr_acl_bytes, B_FALSE); /* swap fuids */ if (lracl->lr_fuidcnt) { byteswap_uint64_array((caddr_t)aclstart + ZIL_ACE_LENGTH(lracl->lr_acl_bytes), lracl->lr_fuidcnt * sizeof (uint64_t)); } } if ((error = zfs_zget(zfsvfs, lr->lr_doid, &dzp)) != 0) return (error); objid = LR_FOID_GET_OBJ(lr->lr_foid); dnodesize = LR_FOID_GET_SLOTS(lr->lr_foid) << DNODE_SHIFT; xva_init(&xva); zfs_init_vattr(&xva.xva_vattr, ATTR_MODE | ATTR_UID | ATTR_GID, lr->lr_mode, lr->lr_uid, lr->lr_gid, lr->lr_rdev, objid); /* * All forms of zfs create (create, mkdir, mkxattrdir, symlink) * eventually end up in zfs_mknode(), which assigns the object's * creation time, generation number, and dnode size. The generic * zfs_create() has no concept of these attributes, so we smuggle * the values inside the vattr's otherwise unused va_ctime, * va_nblocks, and va_fsid fields. */ ZFS_TIME_DECODE(&xva.xva_vattr.va_ctime, lr->lr_crtime); xva.xva_vattr.va_nblocks = lr->lr_gen; xva.xva_vattr.va_fsid = dnodesize; error = dnode_try_claim(zfsvfs->z_os, objid, dnodesize >> DNODE_SHIFT); if (error) goto bail; if (lr->lr_common.lrc_txtype & TX_CI) vflg |= FIGNORECASE; switch (txtype) { case TX_CREATE_ACL: aclstart = (caddr_t)(lracl + 1); fuidstart = (caddr_t)aclstart + ZIL_ACE_LENGTH(lracl->lr_acl_bytes); zfsvfs->z_fuid_replay = zfs_replay_fuids(fuidstart, (void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt, lr->lr_uid, lr->lr_gid); /*FALLTHROUGH*/ case TX_CREATE_ACL_ATTR: if (name == NULL) { lrattr = (lr_attr_t *)(caddr_t)(lracl + 1); xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize); xva.xva_vattr.va_mask |= ATTR_XVATTR; zfs_replay_xvattr(lrattr, &xva); } vsec.vsa_mask = VSA_ACE | VSA_ACE_ACLFLAGS; vsec.vsa_aclentp = (caddr_t)(lracl + 1) + xvatlen; vsec.vsa_aclcnt = lracl->lr_aclcnt; vsec.vsa_aclentsz = lracl->lr_acl_bytes; vsec.vsa_aclflags = lracl->lr_acl_flags; if (zfsvfs->z_fuid_replay == NULL) { fuidstart = (caddr_t)(lracl + 1) + xvatlen + ZIL_ACE_LENGTH(lracl->lr_acl_bytes); zfsvfs->z_fuid_replay = zfs_replay_fuids(fuidstart, (void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt, lr->lr_uid, lr->lr_gid); } error = zfs_create(ZTOI(dzp), name, &xva.xva_vattr, 0, 0, &ip, kcred, vflg, &vsec); break; case TX_MKDIR_ACL: aclstart = (caddr_t)(lracl + 1); fuidstart = (caddr_t)aclstart + ZIL_ACE_LENGTH(lracl->lr_acl_bytes); zfsvfs->z_fuid_replay = zfs_replay_fuids(fuidstart, (void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt, lr->lr_uid, lr->lr_gid); /*FALLTHROUGH*/ case TX_MKDIR_ACL_ATTR: if (name == NULL) { lrattr = (lr_attr_t *)(caddr_t)(lracl + 1); xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize); zfs_replay_xvattr(lrattr, &xva); } vsec.vsa_mask = VSA_ACE | VSA_ACE_ACLFLAGS; vsec.vsa_aclentp = (caddr_t)(lracl + 1) + xvatlen; vsec.vsa_aclcnt = lracl->lr_aclcnt; vsec.vsa_aclentsz = lracl->lr_acl_bytes; vsec.vsa_aclflags = lracl->lr_acl_flags; if (zfsvfs->z_fuid_replay == NULL) { fuidstart = (caddr_t)(lracl + 1) + xvatlen + ZIL_ACE_LENGTH(lracl->lr_acl_bytes); zfsvfs->z_fuid_replay = zfs_replay_fuids(fuidstart, (void *)&name, lracl->lr_fuidcnt, lracl->lr_domcnt, lr->lr_uid, lr->lr_gid); } error = zfs_mkdir(ZTOI(dzp), name, &xva.xva_vattr, &ip, kcred, vflg, &vsec); break; default: error = SET_ERROR(ENOTSUP); } bail: if (error == 0 && ip != NULL) iput(ip); iput(ZTOI(dzp)); if (zfsvfs->z_fuid_replay) zfs_fuid_info_free(zfsvfs->z_fuid_replay); zfsvfs->z_fuid_replay = NULL; return (error); } static int zfs_replay_create(void *arg1, void *arg2, boolean_t byteswap) { zfsvfs_t *zfsvfs = arg1; lr_create_t *lr = arg2; char *name = NULL; /* location determined later */ char *link; /* symlink content follows name */ znode_t *dzp; struct inode *ip = NULL; xvattr_t xva; int vflg = 0; size_t lrsize = sizeof (lr_create_t); lr_attr_t *lrattr; void *start; size_t xvatlen; uint64_t txtype; uint64_t objid; uint64_t dnodesize; int error; txtype = (lr->lr_common.lrc_txtype & ~TX_CI); if (byteswap) { byteswap_uint64_array(lr, sizeof (*lr)); if (txtype == TX_CREATE_ATTR || txtype == TX_MKDIR_ATTR) zfs_replay_swap_attrs((lr_attr_t *)(lr + 1)); } if ((error = zfs_zget(zfsvfs, lr->lr_doid, &dzp)) != 0) return (error); objid = LR_FOID_GET_OBJ(lr->lr_foid); dnodesize = LR_FOID_GET_SLOTS(lr->lr_foid) << DNODE_SHIFT; xva_init(&xva); zfs_init_vattr(&xva.xva_vattr, ATTR_MODE | ATTR_UID | ATTR_GID, lr->lr_mode, lr->lr_uid, lr->lr_gid, lr->lr_rdev, objid); /* * All forms of zfs create (create, mkdir, mkxattrdir, symlink) * eventually end up in zfs_mknode(), which assigns the object's * creation time, generation number, and dnode slot count. The * generic zfs_create() has no concept of these attributes, so * we smuggle the values inside the vattr's otherwise unused * va_ctime, va_nblocks, and va_fsid fields. */ ZFS_TIME_DECODE(&xva.xva_vattr.va_ctime, lr->lr_crtime); xva.xva_vattr.va_nblocks = lr->lr_gen; xva.xva_vattr.va_fsid = dnodesize; error = dnode_try_claim(zfsvfs->z_os, objid, dnodesize >> DNODE_SHIFT); if (error) goto out; if (lr->lr_common.lrc_txtype & TX_CI) vflg |= FIGNORECASE; /* * Symlinks don't have fuid info, and CIFS never creates * symlinks. * * The _ATTR versions will grab the fuid info in their subcases. */ if ((int)lr->lr_common.lrc_txtype != TX_SYMLINK && (int)lr->lr_common.lrc_txtype != TX_MKDIR_ATTR && (int)lr->lr_common.lrc_txtype != TX_CREATE_ATTR) { start = (lr + 1); zfsvfs->z_fuid_replay = zfs_replay_fuid_domain(start, &start, lr->lr_uid, lr->lr_gid); } switch (txtype) { case TX_CREATE_ATTR: lrattr = (lr_attr_t *)(caddr_t)(lr + 1); xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize); zfs_replay_xvattr((lr_attr_t *)((caddr_t)lr + lrsize), &xva); start = (caddr_t)(lr + 1) + xvatlen; zfsvfs->z_fuid_replay = zfs_replay_fuid_domain(start, &start, lr->lr_uid, lr->lr_gid); name = (char *)start; /*FALLTHROUGH*/ case TX_CREATE: if (name == NULL) name = (char *)start; error = zfs_create(ZTOI(dzp), name, &xva.xva_vattr, 0, 0, &ip, kcred, vflg, NULL); break; case TX_MKDIR_ATTR: lrattr = (lr_attr_t *)(caddr_t)(lr + 1); xvatlen = ZIL_XVAT_SIZE(lrattr->lr_attr_masksize); zfs_replay_xvattr((lr_attr_t *)((caddr_t)lr + lrsize), &xva); start = (caddr_t)(lr + 1) + xvatlen; zfsvfs->z_fuid_replay = zfs_replay_fuid_domain(start, &start, lr->lr_uid, lr->lr_gid); name = (char *)start; /*FALLTHROUGH*/ case TX_MKDIR: if (name == NULL) name = (char *)(lr + 1); error = zfs_mkdir(ZTOI(dzp), name, &xva.xva_vattr, &ip, kcred, vflg, NULL); break; case TX_MKXATTR: error = zfs_make_xattrdir(dzp, &xva.xva_vattr, &ip, kcred); break; case TX_SYMLINK: name = (char *)(lr + 1); link = name + strlen(name) + 1; error = zfs_symlink(ZTOI(dzp), name, &xva.xva_vattr, link, &ip, kcred, vflg); break; default: error = SET_ERROR(ENOTSUP); } out: if (error == 0 && ip != NULL) iput(ip); iput(ZTOI(dzp)); if (zfsvfs->z_fuid_replay) zfs_fuid_info_free(zfsvfs->z_fuid_replay); zfsvfs->z_fuid_replay = NULL; return (error); } static int zfs_replay_remove(void *arg1, void *arg2, boolean_t byteswap) { zfsvfs_t *zfsvfs = arg1; lr_remove_t *lr = arg2; char *name = (char *)(lr + 1); /* name follows lr_remove_t */ znode_t *dzp; int error; int vflg = 0; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); if ((error = zfs_zget(zfsvfs, lr->lr_doid, &dzp)) != 0) return (error); if (lr->lr_common.lrc_txtype & TX_CI) vflg |= FIGNORECASE; switch ((int)lr->lr_common.lrc_txtype) { case TX_REMOVE: error = zfs_remove(ZTOI(dzp), name, kcred, vflg); break; case TX_RMDIR: error = zfs_rmdir(ZTOI(dzp), name, NULL, kcred, vflg); break; default: error = SET_ERROR(ENOTSUP); } iput(ZTOI(dzp)); return (error); } static int zfs_replay_link(void *arg1, void *arg2, boolean_t byteswap) { zfsvfs_t *zfsvfs = arg1; lr_link_t *lr = arg2; char *name = (char *)(lr + 1); /* name follows lr_link_t */ znode_t *dzp, *zp; int error; int vflg = 0; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); if ((error = zfs_zget(zfsvfs, lr->lr_doid, &dzp)) != 0) return (error); if ((error = zfs_zget(zfsvfs, lr->lr_link_obj, &zp)) != 0) { iput(ZTOI(dzp)); return (error); } if (lr->lr_common.lrc_txtype & TX_CI) vflg |= FIGNORECASE; error = zfs_link(ZTOI(dzp), ZTOI(zp), name, kcred, vflg); iput(ZTOI(zp)); iput(ZTOI(dzp)); return (error); } static int zfs_replay_rename(void *arg1, void *arg2, boolean_t byteswap) { zfsvfs_t *zfsvfs = arg1; lr_rename_t *lr = arg2; char *sname = (char *)(lr + 1); /* sname and tname follow lr_rename_t */ char *tname = sname + strlen(sname) + 1; znode_t *sdzp, *tdzp; int error; int vflg = 0; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); if ((error = zfs_zget(zfsvfs, lr->lr_sdoid, &sdzp)) != 0) return (error); if ((error = zfs_zget(zfsvfs, lr->lr_tdoid, &tdzp)) != 0) { iput(ZTOI(sdzp)); return (error); } if (lr->lr_common.lrc_txtype & TX_CI) vflg |= FIGNORECASE; error = zfs_rename(ZTOI(sdzp), sname, ZTOI(tdzp), tname, kcred, vflg); iput(ZTOI(tdzp)); iput(ZTOI(sdzp)); return (error); } static int zfs_replay_write(void *arg1, void *arg2, boolean_t byteswap) { zfsvfs_t *zfsvfs = arg1; lr_write_t *lr = arg2; char *data = (char *)(lr + 1); /* data follows lr_write_t */ znode_t *zp; int error, written; uint64_t eod, offset, length; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) { /* * As we can log writes out of order, it's possible the * file has been removed. In this case just drop the write * and return success. */ if (error == ENOENT) error = 0; return (error); } offset = lr->lr_offset; length = lr->lr_length; eod = offset + length; /* end of data for this write */ /* * This may be a write from a dmu_sync() for a whole block, * and may extend beyond the current end of the file. * We can't just replay what was written for this TX_WRITE as * a future TX_WRITE2 may extend the eof and the data for that * write needs to be there. So we write the whole block and * reduce the eof. This needs to be done within the single dmu * transaction created within vn_rdwr -> zfs_write. So a possible * new end of file is passed through in zfsvfs->z_replay_eof */ zfsvfs->z_replay_eof = 0; /* 0 means don't change end of file */ /* If it's a dmu_sync() block, write the whole block */ if (lr->lr_common.lrc_reclen == sizeof (lr_write_t)) { uint64_t blocksize = BP_GET_LSIZE(&lr->lr_blkptr); if (length < blocksize) { offset -= offset % blocksize; length = blocksize; } if (zp->z_size < eod) zfsvfs->z_replay_eof = eod; } written = zpl_write_common(ZTOI(zp), data, length, &offset, UIO_SYSSPACE, 0, kcred); if (written < 0) error = -written; else if (written < length) error = SET_ERROR(EIO); /* short write */ iput(ZTOI(zp)); zfsvfs->z_replay_eof = 0; /* safety */ return (error); } /* * TX_WRITE2 are only generated when dmu_sync() returns EALREADY * meaning the pool block is already being synced. So now that we always write * out full blocks, all we have to do is expand the eof if * the file is grown. */ static int zfs_replay_write2(void *arg1, void *arg2, boolean_t byteswap) { zfsvfs_t *zfsvfs = arg1; lr_write_t *lr = arg2; znode_t *zp; int error; uint64_t end; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) return (error); top: end = lr->lr_offset + lr->lr_length; if (end > zp->z_size) { dmu_tx_t *tx = dmu_tx_create(zfsvfs->z_os); zp->z_size = end; dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_FALSE); error = dmu_tx_assign(tx, TXG_WAIT); if (error) { iput(ZTOI(zp)); if (error == ERESTART) { dmu_tx_wait(tx); dmu_tx_abort(tx); goto top; } dmu_tx_abort(tx); return (error); } (void) sa_update(zp->z_sa_hdl, SA_ZPL_SIZE(zfsvfs), (void *)&zp->z_size, sizeof (uint64_t), tx); /* Ensure the replayed seq is updated */ (void) zil_replaying(zfsvfs->z_log, tx); dmu_tx_commit(tx); } iput(ZTOI(zp)); return (error); } static int zfs_replay_truncate(void *arg1, void *arg2, boolean_t byteswap) { zfsvfs_t *zfsvfs = arg1; lr_truncate_t *lr = arg2; znode_t *zp; flock64_t fl; int error; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) return (error); bzero(&fl, sizeof (fl)); fl.l_type = F_WRLCK; fl.l_whence = SEEK_SET; fl.l_start = lr->lr_offset; fl.l_len = lr->lr_length; error = zfs_space(ZTOI(zp), F_FREESP, &fl, FWRITE | FOFFMAX, lr->lr_offset, kcred); iput(ZTOI(zp)); return (error); } static int zfs_replay_setattr(void *arg1, void *arg2, boolean_t byteswap) { zfsvfs_t *zfsvfs = arg1; lr_setattr_t *lr = arg2; znode_t *zp; xvattr_t xva; vattr_t *vap = &xva.xva_vattr; int error; void *start; xva_init(&xva); if (byteswap) { byteswap_uint64_array(lr, sizeof (*lr)); if ((lr->lr_mask & ATTR_XVATTR) && zfsvfs->z_version >= ZPL_VERSION_INITIAL) zfs_replay_swap_attrs((lr_attr_t *)(lr + 1)); } if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) return (error); zfs_init_vattr(vap, lr->lr_mask, lr->lr_mode, lr->lr_uid, lr->lr_gid, 0, lr->lr_foid); vap->va_size = lr->lr_size; ZFS_TIME_DECODE(&vap->va_atime, lr->lr_atime); ZFS_TIME_DECODE(&vap->va_mtime, lr->lr_mtime); gethrestime(&vap->va_ctime); vap->va_mask |= ATTR_CTIME; /* * Fill in xvattr_t portions if necessary. */ start = (lr_setattr_t *)(lr + 1); if (vap->va_mask & ATTR_XVATTR) { zfs_replay_xvattr((lr_attr_t *)start, &xva); start = (caddr_t)start + ZIL_XVAT_SIZE(((lr_attr_t *)start)->lr_attr_masksize); } else xva.xva_vattr.va_mask &= ~ATTR_XVATTR; zfsvfs->z_fuid_replay = zfs_replay_fuid_domain(start, &start, lr->lr_uid, lr->lr_gid); error = zfs_setattr(ZTOI(zp), vap, 0, kcred); zfs_fuid_info_free(zfsvfs->z_fuid_replay); zfsvfs->z_fuid_replay = NULL; iput(ZTOI(zp)); return (error); } static int zfs_replay_acl_v0(void *arg1, void *arg2, boolean_t byteswap) { zfsvfs_t *zfsvfs = arg1; lr_acl_v0_t *lr = arg2; ace_t *ace = (ace_t *)(lr + 1); /* ace array follows lr_acl_t */ vsecattr_t vsa; znode_t *zp; int error; if (byteswap) { byteswap_uint64_array(lr, sizeof (*lr)); zfs_oldace_byteswap(ace, lr->lr_aclcnt); } if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) return (error); bzero(&vsa, sizeof (vsa)); vsa.vsa_mask = VSA_ACE | VSA_ACECNT; vsa.vsa_aclcnt = lr->lr_aclcnt; vsa.vsa_aclentsz = sizeof (ace_t) * vsa.vsa_aclcnt; vsa.vsa_aclflags = 0; vsa.vsa_aclentp = ace; error = zfs_setsecattr(ZTOI(zp), &vsa, 0, kcred); iput(ZTOI(zp)); return (error); } /* * Replaying ACLs is complicated by FUID support. * The log record may contain some optional data * to be used for replaying FUID's. These pieces * are the actual FUIDs that were created initially. * The FUID table index may no longer be valid and * during zfs_create() a new index may be assigned. * Because of this the log will contain the original * domain+rid in order to create a new FUID. * * The individual ACEs may contain an ephemeral uid/gid which is no * longer valid and will need to be replaced with an actual FUID. * */ static int zfs_replay_acl(void *arg1, void *arg2, boolean_t byteswap) { zfsvfs_t *zfsvfs = arg1; lr_acl_t *lr = arg2; ace_t *ace = (ace_t *)(lr + 1); vsecattr_t vsa; znode_t *zp; int error; if (byteswap) { byteswap_uint64_array(lr, sizeof (*lr)); zfs_ace_byteswap(ace, lr->lr_acl_bytes, B_FALSE); if (lr->lr_fuidcnt) { byteswap_uint64_array((caddr_t)ace + ZIL_ACE_LENGTH(lr->lr_acl_bytes), lr->lr_fuidcnt * sizeof (uint64_t)); } } if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) return (error); bzero(&vsa, sizeof (vsa)); vsa.vsa_mask = VSA_ACE | VSA_ACECNT | VSA_ACE_ACLFLAGS; vsa.vsa_aclcnt = lr->lr_aclcnt; vsa.vsa_aclentp = ace; vsa.vsa_aclentsz = lr->lr_acl_bytes; vsa.vsa_aclflags = lr->lr_acl_flags; if (lr->lr_fuidcnt) { void *fuidstart = (caddr_t)ace + ZIL_ACE_LENGTH(lr->lr_acl_bytes); zfsvfs->z_fuid_replay = zfs_replay_fuids(fuidstart, &fuidstart, lr->lr_fuidcnt, lr->lr_domcnt, 0, 0); } error = zfs_setsecattr(ZTOI(zp), &vsa, 0, kcred); if (zfsvfs->z_fuid_replay) zfs_fuid_info_free(zfsvfs->z_fuid_replay); zfsvfs->z_fuid_replay = NULL; iput(ZTOI(zp)); return (error); } /* * Callback vectors for replaying records */ zil_replay_func_t *zfs_replay_vector[TX_MAX_TYPE] = { zfs_replay_error, /* no such type */ zfs_replay_create, /* TX_CREATE */ zfs_replay_create, /* TX_MKDIR */ zfs_replay_create, /* TX_MKXATTR */ zfs_replay_create, /* TX_SYMLINK */ zfs_replay_remove, /* TX_REMOVE */ zfs_replay_remove, /* TX_RMDIR */ zfs_replay_link, /* TX_LINK */ zfs_replay_rename, /* TX_RENAME */ zfs_replay_write, /* TX_WRITE */ zfs_replay_truncate, /* TX_TRUNCATE */ zfs_replay_setattr, /* TX_SETATTR */ zfs_replay_acl_v0, /* TX_ACL_V0 */ zfs_replay_acl, /* TX_ACL */ zfs_replay_create_acl, /* TX_CREATE_ACL */ zfs_replay_create, /* TX_CREATE_ATTR */ zfs_replay_create_acl, /* TX_CREATE_ACL_ATTR */ zfs_replay_create_acl, /* TX_MKDIR_ACL */ zfs_replay_create, /* TX_MKDIR_ATTR */ zfs_replay_create_acl, /* TX_MKDIR_ACL_ATTR */ zfs_replay_write2, /* TX_WRITE2 */ };
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-26 08:22:26 +0000