diff --git a/cmd/zdb/zdb_il.c b/cmd/zdb/zdb_il.c index d6f588d8316e..76b1d64d76dc 100644 --- a/cmd/zdb/zdb_il.c +++ b/cmd/zdb/zdb_il.c @@ -1,430 +1,455 @@ /* * 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 2009 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2012 Cyril Plisko. All rights reserved. * Use is subject to license terms. */ /* * Copyright (c) 2013, 2017 by Delphix. All rights reserved. */ /* * Print intent log header and statistics. */ #include #include #include #include #include #include #include #include #include #include #include #include #include "zdb.h" extern uint8_t dump_opt[256]; static char tab_prefix[4] = "\t\t\t"; static void print_log_bp(const blkptr_t *bp, const char *prefix) { char blkbuf[BP_SPRINTF_LEN]; snprintf_blkptr(blkbuf, sizeof (blkbuf), bp); (void) printf("%s%s\n", prefix, blkbuf); } static void zil_prt_rec_create(zilog_t *zilog, int txtype, const void *arg) { (void) zilog; const lr_create_t *lr = arg; time_t crtime = lr->lr_crtime[0]; char *name, *link; lr_attr_t *lrattr; name = (char *)(lr + 1); if (lr->lr_common.lrc_txtype == TX_CREATE_ATTR || lr->lr_common.lrc_txtype == TX_MKDIR_ATTR) { lrattr = (lr_attr_t *)(lr + 1); name += ZIL_XVAT_SIZE(lrattr->lr_attr_masksize); } if (txtype == TX_SYMLINK) { link = name + strlen(name) + 1; (void) printf("%s%s -> %s\n", tab_prefix, name, link); } else if (txtype != TX_MKXATTR) { (void) printf("%s%s\n", tab_prefix, name); } (void) printf("%s%s", tab_prefix, ctime(&crtime)); (void) printf("%sdoid %llu, foid %llu, slots %llu, mode %llo\n", tab_prefix, (u_longlong_t)lr->lr_doid, (u_longlong_t)LR_FOID_GET_OBJ(lr->lr_foid), (u_longlong_t)LR_FOID_GET_SLOTS(lr->lr_foid), (longlong_t)lr->lr_mode); (void) printf("%suid %llu, gid %llu, gen %llu, rdev 0x%llx\n", tab_prefix, (u_longlong_t)lr->lr_uid, (u_longlong_t)lr->lr_gid, (u_longlong_t)lr->lr_gen, (u_longlong_t)lr->lr_rdev); } static void zil_prt_rec_remove(zilog_t *zilog, int txtype, const void *arg) { (void) zilog, (void) txtype; const lr_remove_t *lr = arg; (void) printf("%sdoid %llu, name %s\n", tab_prefix, (u_longlong_t)lr->lr_doid, (char *)(lr + 1)); } static void zil_prt_rec_link(zilog_t *zilog, int txtype, const void *arg) { (void) zilog, (void) txtype; const lr_link_t *lr = arg; (void) printf("%sdoid %llu, link_obj %llu, name %s\n", tab_prefix, (u_longlong_t)lr->lr_doid, (u_longlong_t)lr->lr_link_obj, (char *)(lr + 1)); } static void zil_prt_rec_rename(zilog_t *zilog, int txtype, const void *arg) { (void) zilog, (void) txtype; const lr_rename_t *lr = arg; char *snm = (char *)(lr + 1); char *tnm = snm + strlen(snm) + 1; (void) printf("%ssdoid %llu, tdoid %llu\n", tab_prefix, (u_longlong_t)lr->lr_sdoid, (u_longlong_t)lr->lr_tdoid); (void) printf("%ssrc %s tgt %s\n", tab_prefix, snm, tnm); } static int zil_prt_rec_write_cb(void *data, size_t len, void *unused) { (void) unused; char *cdata = data; for (size_t i = 0; i < len; i++) { if (isprint(*cdata)) (void) printf("%c ", *cdata); else (void) printf("%2X", *cdata); cdata++; } return (0); } static void zil_prt_rec_write(zilog_t *zilog, int txtype, const void *arg) { const lr_write_t *lr = arg; abd_t *data; const blkptr_t *bp = &lr->lr_blkptr; zbookmark_phys_t zb; int verbose = MAX(dump_opt['d'], dump_opt['i']); int error; (void) printf("%sfoid %llu, offset %llx, length %llx\n", tab_prefix, (u_longlong_t)lr->lr_foid, (u_longlong_t)lr->lr_offset, (u_longlong_t)lr->lr_length); if (txtype == TX_WRITE2 || verbose < 5) return; if (lr->lr_common.lrc_reclen == sizeof (lr_write_t)) { (void) printf("%shas blkptr, %s\n", tab_prefix, !BP_IS_HOLE(bp) && bp->blk_birth >= spa_min_claim_txg(zilog->zl_spa) ? "will claim" : "won't claim"); print_log_bp(bp, tab_prefix); if (BP_IS_HOLE(bp)) { (void) printf("\t\t\tLSIZE 0x%llx\n", (u_longlong_t)BP_GET_LSIZE(bp)); (void) printf("%s\n", tab_prefix); return; } if (bp->blk_birth < zilog->zl_header->zh_claim_txg) { (void) printf("%s\n", tab_prefix); return; } SET_BOOKMARK(&zb, dmu_objset_id(zilog->zl_os), lr->lr_foid, ZB_ZIL_LEVEL, lr->lr_offset / BP_GET_LSIZE(bp)); data = abd_alloc(BP_GET_LSIZE(bp), B_FALSE); error = zio_wait(zio_read(NULL, zilog->zl_spa, bp, data, BP_GET_LSIZE(bp), NULL, NULL, ZIO_PRIORITY_SYNC_READ, ZIO_FLAG_CANFAIL, &zb)); if (error) goto out; } else { /* data is stored after the end of the lr_write record */ data = abd_alloc(lr->lr_length, B_FALSE); abd_copy_from_buf(data, lr + 1, lr->lr_length); } (void) printf("%s", tab_prefix); (void) abd_iterate_func(data, 0, MIN(lr->lr_length, (verbose < 6 ? 20 : SPA_MAXBLOCKSIZE)), zil_prt_rec_write_cb, NULL); (void) printf("\n"); out: abd_free(data); } static void zil_prt_rec_truncate(zilog_t *zilog, int txtype, const void *arg) { (void) zilog, (void) txtype; const lr_truncate_t *lr = arg; (void) printf("%sfoid %llu, offset 0x%llx, length 0x%llx\n", tab_prefix, (u_longlong_t)lr->lr_foid, (longlong_t)lr->lr_offset, (u_longlong_t)lr->lr_length); } static void zil_prt_rec_setattr(zilog_t *zilog, int txtype, const void *arg) { (void) zilog, (void) txtype; const lr_setattr_t *lr = arg; time_t atime = (time_t)lr->lr_atime[0]; time_t mtime = (time_t)lr->lr_mtime[0]; (void) printf("%sfoid %llu, mask 0x%llx\n", tab_prefix, (u_longlong_t)lr->lr_foid, (u_longlong_t)lr->lr_mask); if (lr->lr_mask & AT_MODE) { (void) printf("%sAT_MODE %llo\n", tab_prefix, (longlong_t)lr->lr_mode); } if (lr->lr_mask & AT_UID) { (void) printf("%sAT_UID %llu\n", tab_prefix, (u_longlong_t)lr->lr_uid); } if (lr->lr_mask & AT_GID) { (void) printf("%sAT_GID %llu\n", tab_prefix, (u_longlong_t)lr->lr_gid); } if (lr->lr_mask & AT_SIZE) { (void) printf("%sAT_SIZE %llu\n", tab_prefix, (u_longlong_t)lr->lr_size); } if (lr->lr_mask & AT_ATIME) { (void) printf("%sAT_ATIME %llu.%09llu %s", tab_prefix, (u_longlong_t)lr->lr_atime[0], (u_longlong_t)lr->lr_atime[1], ctime(&atime)); } if (lr->lr_mask & AT_MTIME) { (void) printf("%sAT_MTIME %llu.%09llu %s", tab_prefix, (u_longlong_t)lr->lr_mtime[0], (u_longlong_t)lr->lr_mtime[1], ctime(&mtime)); } } +static void +zil_prt_rec_setsaxattr(zilog_t *zilog, int txtype, const void *arg) +{ + (void) zilog, (void) txtype; + const lr_setsaxattr_t *lr = arg; + + char *name = (char *)(lr + 1); + (void) printf("%sfoid %llu\n", tab_prefix, + (u_longlong_t)lr->lr_foid); + + (void) printf("%sXAT_NAME %s\n", tab_prefix, name); + if (lr->lr_size == 0) { + (void) printf("%sXAT_VALUE NULL\n", tab_prefix); + } else { + (void) printf("%sXAT_VALUE ", tab_prefix); + char *val = name + (strlen(name) + 1); + for (int i = 0; i < lr->lr_size; i++) { + (void) printf("%c", *val); + val++; + } + } +} + static void zil_prt_rec_acl(zilog_t *zilog, int txtype, const void *arg) { (void) zilog, (void) txtype; const lr_acl_t *lr = arg; (void) printf("%sfoid %llu, aclcnt %llu\n", tab_prefix, (u_longlong_t)lr->lr_foid, (u_longlong_t)lr->lr_aclcnt); } typedef void (*zil_prt_rec_func_t)(zilog_t *, int, const void *); typedef struct zil_rec_info { zil_prt_rec_func_t zri_print; const char *zri_name; uint64_t zri_count; } zil_rec_info_t; static zil_rec_info_t zil_rec_info[TX_MAX_TYPE] = { {.zri_print = NULL, .zri_name = "Total "}, {.zri_print = zil_prt_rec_create, .zri_name = "TX_CREATE "}, {.zri_print = zil_prt_rec_create, .zri_name = "TX_MKDIR "}, {.zri_print = zil_prt_rec_create, .zri_name = "TX_MKXATTR "}, {.zri_print = zil_prt_rec_create, .zri_name = "TX_SYMLINK "}, {.zri_print = zil_prt_rec_remove, .zri_name = "TX_REMOVE "}, {.zri_print = zil_prt_rec_remove, .zri_name = "TX_RMDIR "}, {.zri_print = zil_prt_rec_link, .zri_name = "TX_LINK "}, {.zri_print = zil_prt_rec_rename, .zri_name = "TX_RENAME "}, {.zri_print = zil_prt_rec_write, .zri_name = "TX_WRITE "}, {.zri_print = zil_prt_rec_truncate, .zri_name = "TX_TRUNCATE "}, {.zri_print = zil_prt_rec_setattr, .zri_name = "TX_SETATTR "}, {.zri_print = zil_prt_rec_acl, .zri_name = "TX_ACL_V0 "}, {.zri_print = zil_prt_rec_acl, .zri_name = "TX_ACL_ACL "}, {.zri_print = zil_prt_rec_create, .zri_name = "TX_CREATE_ACL "}, {.zri_print = zil_prt_rec_create, .zri_name = "TX_CREATE_ATTR "}, {.zri_print = zil_prt_rec_create, .zri_name = "TX_CREATE_ACL_ATTR "}, {.zri_print = zil_prt_rec_create, .zri_name = "TX_MKDIR_ACL "}, {.zri_print = zil_prt_rec_create, .zri_name = "TX_MKDIR_ATTR "}, {.zri_print = zil_prt_rec_create, .zri_name = "TX_MKDIR_ACL_ATTR "}, {.zri_print = zil_prt_rec_write, .zri_name = "TX_WRITE2 "}, + {.zri_print = zil_prt_rec_setsaxattr, + .zri_name = "TX_SETSAXATTR "}, }; static int print_log_record(zilog_t *zilog, const lr_t *lr, void *arg, uint64_t claim_txg) { (void) arg, (void) claim_txg; int txtype; int verbose = MAX(dump_opt['d'], dump_opt['i']); /* reduce size of txtype to strip off TX_CI bit */ txtype = lr->lrc_txtype; ASSERT(txtype != 0 && (uint_t)txtype < TX_MAX_TYPE); ASSERT(lr->lrc_txg); (void) printf("\t\t%s%s len %6llu, txg %llu, seq %llu\n", (lr->lrc_txtype & TX_CI) ? "CI-" : "", zil_rec_info[txtype].zri_name, (u_longlong_t)lr->lrc_reclen, (u_longlong_t)lr->lrc_txg, (u_longlong_t)lr->lrc_seq); if (txtype && verbose >= 3) { if (!zilog->zl_os->os_encrypted) { zil_rec_info[txtype].zri_print(zilog, txtype, lr); } else { (void) printf("%s(encrypted)\n", tab_prefix); } } zil_rec_info[txtype].zri_count++; zil_rec_info[0].zri_count++; return (0); } static int print_log_block(zilog_t *zilog, const blkptr_t *bp, void *arg, uint64_t claim_txg) { (void) arg; char blkbuf[BP_SPRINTF_LEN + 10]; int verbose = MAX(dump_opt['d'], dump_opt['i']); const char *claim; if (verbose <= 3) return (0); if (verbose >= 5) { (void) strcpy(blkbuf, ", "); snprintf_blkptr(blkbuf + strlen(blkbuf), sizeof (blkbuf) - strlen(blkbuf), bp); } else { blkbuf[0] = '\0'; } if (claim_txg != 0) claim = "already claimed"; else if (bp->blk_birth >= spa_min_claim_txg(zilog->zl_spa)) claim = "will claim"; else claim = "won't claim"; (void) printf("\tBlock seqno %llu, %s%s\n", (u_longlong_t)bp->blk_cksum.zc_word[ZIL_ZC_SEQ], claim, blkbuf); return (0); } static void print_log_stats(int verbose) { unsigned i, w, p10; if (verbose > 3) (void) printf("\n"); if (zil_rec_info[0].zri_count == 0) return; for (w = 1, p10 = 10; zil_rec_info[0].zri_count >= p10; p10 *= 10) w++; for (i = 0; i < TX_MAX_TYPE; i++) if (zil_rec_info[i].zri_count || verbose >= 3) (void) printf("\t\t%s %*llu\n", zil_rec_info[i].zri_name, w, (u_longlong_t)zil_rec_info[i].zri_count); (void) printf("\n"); } void dump_intent_log(zilog_t *zilog) { const zil_header_t *zh = zilog->zl_header; int verbose = MAX(dump_opt['d'], dump_opt['i']); int i; if (BP_IS_HOLE(&zh->zh_log) || verbose < 1) return; (void) printf("\n ZIL header: claim_txg %llu, " "claim_blk_seq %llu, claim_lr_seq %llu", (u_longlong_t)zh->zh_claim_txg, (u_longlong_t)zh->zh_claim_blk_seq, (u_longlong_t)zh->zh_claim_lr_seq); (void) printf(" replay_seq %llu, flags 0x%llx\n", (u_longlong_t)zh->zh_replay_seq, (u_longlong_t)zh->zh_flags); for (i = 0; i < TX_MAX_TYPE; i++) zil_rec_info[i].zri_count = 0; /* see comment in zil_claim() or zil_check_log_chain() */ if (zilog->zl_spa->spa_uberblock.ub_checkpoint_txg != 0 && zh->zh_claim_txg == 0) return; if (verbose >= 2) { (void) printf("\n"); (void) zil_parse(zilog, print_log_block, print_log_record, NULL, zh->zh_claim_txg, B_FALSE); print_log_stats(verbose); } } diff --git a/cmd/ztest/ztest.c b/cmd/ztest/ztest.c index ed60d065c8a7..0daaab69c702 100644 --- a/cmd/ztest/ztest.c +++ b/cmd/ztest/ztest.c @@ -1,8211 +1,8212 @@ /* * 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 (c) 2011, 2018 by Delphix. All rights reserved. * Copyright 2011 Nexenta Systems, Inc. All rights reserved. * Copyright (c) 2013 Steven Hartland. All rights reserved. * Copyright (c) 2014 Integros [integros.com] * Copyright 2017 Joyent, Inc. * Copyright (c) 2017, Intel Corporation. */ /* * The objective of this program is to provide a DMU/ZAP/SPA stress test * that runs entirely in userland, is easy to use, and easy to extend. * * The overall design of the ztest program is as follows: * * (1) For each major functional area (e.g. adding vdevs to a pool, * creating and destroying datasets, reading and writing objects, etc) * we have a simple routine to test that functionality. These * individual routines do not have to do anything "stressful". * * (2) We turn these simple functionality tests into a stress test by * running them all in parallel, with as many threads as desired, * and spread across as many datasets, objects, and vdevs as desired. * * (3) While all this is happening, we inject faults into the pool to * verify that self-healing data really works. * * (4) Every time we open a dataset, we change its checksum and compression * functions. Thus even individual objects vary from block to block * in which checksum they use and whether they're compressed. * * (5) To verify that we never lose on-disk consistency after a crash, * we run the entire test in a child of the main process. * At random times, the child self-immolates with a SIGKILL. * This is the software equivalent of pulling the power cord. * The parent then runs the test again, using the existing * storage pool, as many times as desired. If backwards compatibility * testing is enabled ztest will sometimes run the "older" version * of ztest after a SIGKILL. * * (6) To verify that we don't have future leaks or temporal incursions, * many of the functional tests record the transaction group number * as part of their data. When reading old data, they verify that * the transaction group number is less than the current, open txg. * If you add a new test, please do this if applicable. * * (7) Threads are created with a reduced stack size, for sanity checking. * Therefore, it's important not to allocate huge buffers on the stack. * * When run with no arguments, ztest runs for about five minutes and * produces no output if successful. To get a little bit of information, * specify -V. To get more information, specify -VV, and so on. * * To turn this into an overnight stress test, use -T to specify run time. * * You can ask more vdevs [-v], datasets [-d], or threads [-t] * to increase the pool capacity, fanout, and overall stress level. * * Use the -k option to set the desired frequency of kills. * * When ztest invokes itself it passes all relevant information through a * temporary file which is mmap-ed in the child process. This allows shared * memory to survive the exec syscall. The ztest_shared_hdr_t struct is always * stored at offset 0 of this file and contains information on the size and * number of shared structures in the file. The information stored in this file * must remain backwards compatible with older versions of ztest so that * ztest can invoke them during backwards compatibility testing (-B). */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #if (__GLIBC__ && !__UCLIBC__) #include /* for backtrace() */ #endif static int ztest_fd_data = -1; static int ztest_fd_rand = -1; typedef struct ztest_shared_hdr { uint64_t zh_hdr_size; uint64_t zh_opts_size; uint64_t zh_size; uint64_t zh_stats_size; uint64_t zh_stats_count; uint64_t zh_ds_size; uint64_t zh_ds_count; } ztest_shared_hdr_t; static ztest_shared_hdr_t *ztest_shared_hdr; enum ztest_class_state { ZTEST_VDEV_CLASS_OFF, ZTEST_VDEV_CLASS_ON, ZTEST_VDEV_CLASS_RND }; #define ZO_GVARS_MAX_ARGLEN ((size_t)64) #define ZO_GVARS_MAX_COUNT ((size_t)10) typedef struct ztest_shared_opts { char zo_pool[ZFS_MAX_DATASET_NAME_LEN]; char zo_dir[ZFS_MAX_DATASET_NAME_LEN]; char zo_alt_ztest[MAXNAMELEN]; char zo_alt_libpath[MAXNAMELEN]; uint64_t zo_vdevs; uint64_t zo_vdevtime; size_t zo_vdev_size; int zo_ashift; int zo_mirrors; int zo_raid_children; int zo_raid_parity; char zo_raid_type[8]; int zo_draid_data; int zo_draid_spares; int zo_datasets; int zo_threads; uint64_t zo_passtime; uint64_t zo_killrate; int zo_verbose; int zo_init; uint64_t zo_time; uint64_t zo_maxloops; uint64_t zo_metaslab_force_ganging; int zo_mmp_test; int zo_special_vdevs; int zo_dump_dbgmsg; int zo_gvars_count; char zo_gvars[ZO_GVARS_MAX_COUNT][ZO_GVARS_MAX_ARGLEN]; } ztest_shared_opts_t; /* Default values for command line options. */ #define DEFAULT_POOL "ztest" #define DEFAULT_VDEV_DIR "/tmp" #define DEFAULT_VDEV_COUNT 5 #define DEFAULT_VDEV_SIZE (SPA_MINDEVSIZE * 4) /* 256m default size */ #define DEFAULT_VDEV_SIZE_STR "256M" #define DEFAULT_ASHIFT SPA_MINBLOCKSHIFT #define DEFAULT_MIRRORS 2 #define DEFAULT_RAID_CHILDREN 4 #define DEFAULT_RAID_PARITY 1 #define DEFAULT_DRAID_DATA 4 #define DEFAULT_DRAID_SPARES 1 #define DEFAULT_DATASETS_COUNT 7 #define DEFAULT_THREADS 23 #define DEFAULT_RUN_TIME 300 /* 300 seconds */ #define DEFAULT_RUN_TIME_STR "300 sec" #define DEFAULT_PASS_TIME 60 /* 60 seconds */ #define DEFAULT_PASS_TIME_STR "60 sec" #define DEFAULT_KILL_RATE 70 /* 70% kill rate */ #define DEFAULT_KILLRATE_STR "70%" #define DEFAULT_INITS 1 #define DEFAULT_MAX_LOOPS 50 /* 5 minutes */ #define DEFAULT_FORCE_GANGING (64 << 10) #define DEFAULT_FORCE_GANGING_STR "64K" /* Simplifying assumption: -1 is not a valid default. */ #define NO_DEFAULT -1 static const ztest_shared_opts_t ztest_opts_defaults = { .zo_pool = DEFAULT_POOL, .zo_dir = DEFAULT_VDEV_DIR, .zo_alt_ztest = { '\0' }, .zo_alt_libpath = { '\0' }, .zo_vdevs = DEFAULT_VDEV_COUNT, .zo_ashift = DEFAULT_ASHIFT, .zo_mirrors = DEFAULT_MIRRORS, .zo_raid_children = DEFAULT_RAID_CHILDREN, .zo_raid_parity = DEFAULT_RAID_PARITY, .zo_raid_type = VDEV_TYPE_RAIDZ, .zo_vdev_size = DEFAULT_VDEV_SIZE, .zo_draid_data = DEFAULT_DRAID_DATA, /* data drives */ .zo_draid_spares = DEFAULT_DRAID_SPARES, /* distributed spares */ .zo_datasets = DEFAULT_DATASETS_COUNT, .zo_threads = DEFAULT_THREADS, .zo_passtime = DEFAULT_PASS_TIME, .zo_killrate = DEFAULT_KILL_RATE, .zo_verbose = 0, .zo_mmp_test = 0, .zo_init = DEFAULT_INITS, .zo_time = DEFAULT_RUN_TIME, .zo_maxloops = DEFAULT_MAX_LOOPS, /* max loops during spa_freeze() */ .zo_metaslab_force_ganging = DEFAULT_FORCE_GANGING, .zo_special_vdevs = ZTEST_VDEV_CLASS_RND, .zo_gvars_count = 0, }; extern uint64_t metaslab_force_ganging; extern uint64_t metaslab_df_alloc_threshold; extern unsigned long zfs_deadman_synctime_ms; extern int metaslab_preload_limit; extern int zfs_compressed_arc_enabled; extern int zfs_abd_scatter_enabled; extern int dmu_object_alloc_chunk_shift; extern boolean_t zfs_force_some_double_word_sm_entries; extern unsigned long zio_decompress_fail_fraction; extern unsigned long zfs_reconstruct_indirect_damage_fraction; static ztest_shared_opts_t *ztest_shared_opts; static ztest_shared_opts_t ztest_opts; static char *ztest_wkeydata = "abcdefghijklmnopqrstuvwxyz012345"; typedef struct ztest_shared_ds { uint64_t zd_seq; } ztest_shared_ds_t; static ztest_shared_ds_t *ztest_shared_ds; #define ZTEST_GET_SHARED_DS(d) (&ztest_shared_ds[d]) #define BT_MAGIC 0x123456789abcdefULL #define MAXFAULTS(zs) \ (MAX((zs)->zs_mirrors, 1) * (ztest_opts.zo_raid_parity + 1) - 1) enum ztest_io_type { ZTEST_IO_WRITE_TAG, ZTEST_IO_WRITE_PATTERN, ZTEST_IO_WRITE_ZEROES, ZTEST_IO_TRUNCATE, ZTEST_IO_SETATTR, ZTEST_IO_REWRITE, ZTEST_IO_TYPES }; typedef struct ztest_block_tag { uint64_t bt_magic; uint64_t bt_objset; uint64_t bt_object; uint64_t bt_dnodesize; uint64_t bt_offset; uint64_t bt_gen; uint64_t bt_txg; uint64_t bt_crtxg; } ztest_block_tag_t; typedef struct bufwad { uint64_t bw_index; uint64_t bw_txg; uint64_t bw_data; } bufwad_t; /* * It would be better to use a rangelock_t per object. Unfortunately * the rangelock_t is not a drop-in replacement for rl_t, because we * still need to map from object ID to rangelock_t. */ typedef enum { RL_READER, RL_WRITER, RL_APPEND } rl_type_t; typedef struct rll { void *rll_writer; int rll_readers; kmutex_t rll_lock; kcondvar_t rll_cv; } rll_t; typedef struct rl { uint64_t rl_object; uint64_t rl_offset; uint64_t rl_size; rll_t *rl_lock; } rl_t; #define ZTEST_RANGE_LOCKS 64 #define ZTEST_OBJECT_LOCKS 64 /* * Object descriptor. Used as a template for object lookup/create/remove. */ typedef struct ztest_od { uint64_t od_dir; uint64_t od_object; dmu_object_type_t od_type; dmu_object_type_t od_crtype; uint64_t od_blocksize; uint64_t od_crblocksize; uint64_t od_crdnodesize; uint64_t od_gen; uint64_t od_crgen; char od_name[ZFS_MAX_DATASET_NAME_LEN]; } ztest_od_t; /* * Per-dataset state. */ typedef struct ztest_ds { ztest_shared_ds_t *zd_shared; objset_t *zd_os; pthread_rwlock_t zd_zilog_lock; zilog_t *zd_zilog; ztest_od_t *zd_od; /* debugging aid */ char zd_name[ZFS_MAX_DATASET_NAME_LEN]; kmutex_t zd_dirobj_lock; rll_t zd_object_lock[ZTEST_OBJECT_LOCKS]; rll_t zd_range_lock[ZTEST_RANGE_LOCKS]; } ztest_ds_t; /* * Per-iteration state. */ typedef void ztest_func_t(ztest_ds_t *zd, uint64_t id); typedef struct ztest_info { ztest_func_t *zi_func; /* test function */ uint64_t zi_iters; /* iterations per execution */ uint64_t *zi_interval; /* execute every seconds */ const char *zi_funcname; /* name of test function */ } ztest_info_t; typedef struct ztest_shared_callstate { uint64_t zc_count; /* per-pass count */ uint64_t zc_time; /* per-pass time */ uint64_t zc_next; /* next time to call this function */ } ztest_shared_callstate_t; static ztest_shared_callstate_t *ztest_shared_callstate; #define ZTEST_GET_SHARED_CALLSTATE(c) (&ztest_shared_callstate[c]) ztest_func_t ztest_dmu_read_write; ztest_func_t ztest_dmu_write_parallel; ztest_func_t ztest_dmu_object_alloc_free; ztest_func_t ztest_dmu_object_next_chunk; ztest_func_t ztest_dmu_commit_callbacks; ztest_func_t ztest_zap; ztest_func_t ztest_zap_parallel; ztest_func_t ztest_zil_commit; ztest_func_t ztest_zil_remount; ztest_func_t ztest_dmu_read_write_zcopy; ztest_func_t ztest_dmu_objset_create_destroy; ztest_func_t ztest_dmu_prealloc; ztest_func_t ztest_fzap; ztest_func_t ztest_dmu_snapshot_create_destroy; ztest_func_t ztest_dsl_prop_get_set; ztest_func_t ztest_spa_prop_get_set; ztest_func_t ztest_spa_create_destroy; ztest_func_t ztest_fault_inject; ztest_func_t ztest_dmu_snapshot_hold; ztest_func_t ztest_mmp_enable_disable; ztest_func_t ztest_scrub; ztest_func_t ztest_dsl_dataset_promote_busy; ztest_func_t ztest_vdev_attach_detach; ztest_func_t ztest_vdev_LUN_growth; ztest_func_t ztest_vdev_add_remove; ztest_func_t ztest_vdev_class_add; ztest_func_t ztest_vdev_aux_add_remove; ztest_func_t ztest_split_pool; ztest_func_t ztest_reguid; ztest_func_t ztest_spa_upgrade; ztest_func_t ztest_device_removal; ztest_func_t ztest_spa_checkpoint_create_discard; ztest_func_t ztest_initialize; ztest_func_t ztest_trim; ztest_func_t ztest_fletcher; ztest_func_t ztest_fletcher_incr; ztest_func_t ztest_verify_dnode_bt; uint64_t zopt_always = 0ULL * NANOSEC; /* all the time */ uint64_t zopt_incessant = 1ULL * NANOSEC / 10; /* every 1/10 second */ uint64_t zopt_often = 1ULL * NANOSEC; /* every second */ uint64_t zopt_sometimes = 10ULL * NANOSEC; /* every 10 seconds */ uint64_t zopt_rarely = 60ULL * NANOSEC; /* every 60 seconds */ #define ZTI_INIT(func, iters, interval) \ { .zi_func = (func), \ .zi_iters = (iters), \ .zi_interval = (interval), \ .zi_funcname = # func } ztest_info_t ztest_info[] = { ZTI_INIT(ztest_dmu_read_write, 1, &zopt_always), ZTI_INIT(ztest_dmu_write_parallel, 10, &zopt_always), ZTI_INIT(ztest_dmu_object_alloc_free, 1, &zopt_always), ZTI_INIT(ztest_dmu_object_next_chunk, 1, &zopt_sometimes), ZTI_INIT(ztest_dmu_commit_callbacks, 1, &zopt_always), ZTI_INIT(ztest_zap, 30, &zopt_always), ZTI_INIT(ztest_zap_parallel, 100, &zopt_always), ZTI_INIT(ztest_split_pool, 1, &zopt_always), ZTI_INIT(ztest_zil_commit, 1, &zopt_incessant), ZTI_INIT(ztest_zil_remount, 1, &zopt_sometimes), ZTI_INIT(ztest_dmu_read_write_zcopy, 1, &zopt_often), ZTI_INIT(ztest_dmu_objset_create_destroy, 1, &zopt_often), ZTI_INIT(ztest_dsl_prop_get_set, 1, &zopt_often), ZTI_INIT(ztest_spa_prop_get_set, 1, &zopt_sometimes), #if 0 ZTI_INIT(ztest_dmu_prealloc, 1, &zopt_sometimes), #endif ZTI_INIT(ztest_fzap, 1, &zopt_sometimes), ZTI_INIT(ztest_dmu_snapshot_create_destroy, 1, &zopt_sometimes), ZTI_INIT(ztest_spa_create_destroy, 1, &zopt_sometimes), ZTI_INIT(ztest_fault_inject, 1, &zopt_sometimes), ZTI_INIT(ztest_dmu_snapshot_hold, 1, &zopt_sometimes), ZTI_INIT(ztest_mmp_enable_disable, 1, &zopt_sometimes), ZTI_INIT(ztest_reguid, 1, &zopt_rarely), ZTI_INIT(ztest_scrub, 1, &zopt_rarely), ZTI_INIT(ztest_spa_upgrade, 1, &zopt_rarely), ZTI_INIT(ztest_dsl_dataset_promote_busy, 1, &zopt_rarely), ZTI_INIT(ztest_vdev_attach_detach, 1, &zopt_sometimes), ZTI_INIT(ztest_vdev_LUN_growth, 1, &zopt_rarely), ZTI_INIT(ztest_vdev_add_remove, 1, &ztest_opts.zo_vdevtime), ZTI_INIT(ztest_vdev_class_add, 1, &ztest_opts.zo_vdevtime), ZTI_INIT(ztest_vdev_aux_add_remove, 1, &ztest_opts.zo_vdevtime), ZTI_INIT(ztest_device_removal, 1, &zopt_sometimes), ZTI_INIT(ztest_spa_checkpoint_create_discard, 1, &zopt_rarely), ZTI_INIT(ztest_initialize, 1, &zopt_sometimes), ZTI_INIT(ztest_trim, 1, &zopt_sometimes), ZTI_INIT(ztest_fletcher, 1, &zopt_rarely), ZTI_INIT(ztest_fletcher_incr, 1, &zopt_rarely), ZTI_INIT(ztest_verify_dnode_bt, 1, &zopt_sometimes), }; #define ZTEST_FUNCS (sizeof (ztest_info) / sizeof (ztest_info_t)) /* * The following struct is used to hold a list of uncalled commit callbacks. * The callbacks are ordered by txg number. */ typedef struct ztest_cb_list { kmutex_t zcl_callbacks_lock; list_t zcl_callbacks; } ztest_cb_list_t; /* * Stuff we need to share writably between parent and child. */ typedef struct ztest_shared { boolean_t zs_do_init; hrtime_t zs_proc_start; hrtime_t zs_proc_stop; hrtime_t zs_thread_start; hrtime_t zs_thread_stop; hrtime_t zs_thread_kill; uint64_t zs_enospc_count; uint64_t zs_vdev_next_leaf; uint64_t zs_vdev_aux; uint64_t zs_alloc; uint64_t zs_space; uint64_t zs_splits; uint64_t zs_mirrors; uint64_t zs_metaslab_sz; uint64_t zs_metaslab_df_alloc_threshold; uint64_t zs_guid; } ztest_shared_t; #define ID_PARALLEL -1ULL static char ztest_dev_template[] = "%s/%s.%llua"; static char ztest_aux_template[] = "%s/%s.%s.%llu"; ztest_shared_t *ztest_shared; static spa_t *ztest_spa = NULL; static ztest_ds_t *ztest_ds; static kmutex_t ztest_vdev_lock; static boolean_t ztest_device_removal_active = B_FALSE; static boolean_t ztest_pool_scrubbed = B_FALSE; static kmutex_t ztest_checkpoint_lock; /* * The ztest_name_lock protects the pool and dataset namespace used by * the individual tests. To modify the namespace, consumers must grab * this lock as writer. Grabbing the lock as reader will ensure that the * namespace does not change while the lock is held. */ static pthread_rwlock_t ztest_name_lock; static boolean_t ztest_dump_core = B_TRUE; static boolean_t ztest_exiting; /* Global commit callback list */ static ztest_cb_list_t zcl; /* Commit cb delay */ static uint64_t zc_min_txg_delay = UINT64_MAX; static int zc_cb_counter = 0; /* * Minimum number of commit callbacks that need to be registered for us to check * whether the minimum txg delay is acceptable. */ #define ZTEST_COMMIT_CB_MIN_REG 100 /* * If a number of txgs equal to this threshold have been created after a commit * callback has been registered but not called, then we assume there is an * implementation bug. */ #define ZTEST_COMMIT_CB_THRESH (TXG_CONCURRENT_STATES + 1000) enum ztest_object { ZTEST_META_DNODE = 0, ZTEST_DIROBJ, ZTEST_OBJECTS }; static void usage(boolean_t) __NORETURN; static int ztest_scrub_impl(spa_t *spa); /* * These libumem hooks provide a reasonable set of defaults for the allocator's * debugging facilities. */ const char * _umem_debug_init(void) { return ("default,verbose"); /* $UMEM_DEBUG setting */ } const char * _umem_logging_init(void) { return ("fail,contents"); /* $UMEM_LOGGING setting */ } static void dump_debug_buffer(void) { ssize_t ret __attribute__((unused)); if (!ztest_opts.zo_dump_dbgmsg) return; /* * We use write() instead of printf() so that this function * is safe to call from a signal handler. */ ret = write(STDOUT_FILENO, "\n", 1); zfs_dbgmsg_print("ztest"); } #define BACKTRACE_SZ 100 static void sig_handler(int signo) { struct sigaction action; #if (__GLIBC__ && !__UCLIBC__) /* backtrace() is a GNU extension */ int nptrs; void *buffer[BACKTRACE_SZ]; nptrs = backtrace(buffer, BACKTRACE_SZ); backtrace_symbols_fd(buffer, nptrs, STDERR_FILENO); #endif dump_debug_buffer(); /* * Restore default action and re-raise signal so SIGSEGV and * SIGABRT can trigger a core dump. */ action.sa_handler = SIG_DFL; sigemptyset(&action.sa_mask); action.sa_flags = 0; (void) sigaction(signo, &action, NULL); raise(signo); } #define FATAL_MSG_SZ 1024 char *fatal_msg; static __attribute__((noreturn)) __attribute__((format(printf, 2, 3))) void fatal(int do_perror, char *message, ...) { va_list args; int save_errno = errno; char *buf; (void) fflush(stdout); buf = umem_alloc(FATAL_MSG_SZ, UMEM_NOFAIL); if (buf == NULL) goto out; va_start(args, message); (void) sprintf(buf, "ztest: "); /* LINTED */ (void) vsprintf(buf + strlen(buf), message, args); va_end(args); if (do_perror) { (void) snprintf(buf + strlen(buf), FATAL_MSG_SZ - strlen(buf), ": %s", strerror(save_errno)); } (void) fprintf(stderr, "%s\n", buf); fatal_msg = buf; /* to ease debugging */ out: if (ztest_dump_core) abort(); else dump_debug_buffer(); exit(3); } static int str2shift(const char *buf) { const char *ends = "BKMGTPEZ"; int i; if (buf[0] == '\0') return (0); for (i = 0; i < strlen(ends); i++) { if (toupper(buf[0]) == ends[i]) break; } if (i == strlen(ends)) { (void) fprintf(stderr, "ztest: invalid bytes suffix: %s\n", buf); usage(B_FALSE); } if (buf[1] == '\0' || (toupper(buf[1]) == 'B' && buf[2] == '\0')) { return (10*i); } (void) fprintf(stderr, "ztest: invalid bytes suffix: %s\n", buf); usage(B_FALSE); } static uint64_t nicenumtoull(const char *buf) { char *end; uint64_t val; val = strtoull(buf, &end, 0); if (end == buf) { (void) fprintf(stderr, "ztest: bad numeric value: %s\n", buf); usage(B_FALSE); } else if (end[0] == '.') { double fval = strtod(buf, &end); fval *= pow(2, str2shift(end)); /* * UINT64_MAX is not exactly representable as a double. * The closest representation is UINT64_MAX + 1, so we * use a >= comparison instead of > for the bounds check. */ if (fval >= (double)UINT64_MAX) { (void) fprintf(stderr, "ztest: value too large: %s\n", buf); usage(B_FALSE); } val = (uint64_t)fval; } else { int shift = str2shift(end); if (shift >= 64 || (val << shift) >> shift != val) { (void) fprintf(stderr, "ztest: value too large: %s\n", buf); usage(B_FALSE); } val <<= shift; } return (val); } typedef struct ztest_option { const char short_opt; const char *long_opt; const char *long_opt_param; const char *comment; unsigned int default_int; char *default_str; } ztest_option_t; /* * The following option_table is used for generating the usage info as well as * the long and short option information for calling getopt_long(). */ static ztest_option_t option_table[] = { { 'v', "vdevs", "INTEGER", "Number of vdevs", DEFAULT_VDEV_COUNT, NULL}, { 's', "vdev-size", "INTEGER", "Size of each vdev", NO_DEFAULT, DEFAULT_VDEV_SIZE_STR}, { 'a', "alignment-shift", "INTEGER", "Alignment shift; use 0 for random", DEFAULT_ASHIFT, NULL}, { 'm', "mirror-copies", "INTEGER", "Number of mirror copies", DEFAULT_MIRRORS, NULL}, { 'r', "raid-disks", "INTEGER", "Number of raidz/draid disks", DEFAULT_RAID_CHILDREN, NULL}, { 'R', "raid-parity", "INTEGER", "Raid parity", DEFAULT_RAID_PARITY, NULL}, { 'K', "raid-kind", "raidz|draid|random", "Raid kind", NO_DEFAULT, "random"}, { 'D', "draid-data", "INTEGER", "Number of draid data drives", DEFAULT_DRAID_DATA, NULL}, { 'S', "draid-spares", "INTEGER", "Number of draid spares", DEFAULT_DRAID_SPARES, NULL}, { 'd', "datasets", "INTEGER", "Number of datasets", DEFAULT_DATASETS_COUNT, NULL}, { 't', "threads", "INTEGER", "Number of ztest threads", DEFAULT_THREADS, NULL}, { 'g', "gang-block-threshold", "INTEGER", "Metaslab gang block threshold", NO_DEFAULT, DEFAULT_FORCE_GANGING_STR}, { 'i', "init-count", "INTEGER", "Number of times to initialize pool", DEFAULT_INITS, NULL}, { 'k', "kill-percentage", "INTEGER", "Kill percentage", NO_DEFAULT, DEFAULT_KILLRATE_STR}, { 'p', "pool-name", "STRING", "Pool name", NO_DEFAULT, DEFAULT_POOL}, { 'f', "vdev-file-directory", "PATH", "File directory for vdev files", NO_DEFAULT, DEFAULT_VDEV_DIR}, { 'M', "multi-host", NULL, "Multi-host; simulate pool imported on remote host", NO_DEFAULT, NULL}, { 'E', "use-existing-pool", NULL, "Use existing pool instead of creating new one", NO_DEFAULT, NULL}, { 'T', "run-time", "INTEGER", "Total run time", NO_DEFAULT, DEFAULT_RUN_TIME_STR}, { 'P', "pass-time", "INTEGER", "Time per pass", NO_DEFAULT, DEFAULT_PASS_TIME_STR}, { 'F', "freeze-loops", "INTEGER", "Max loops in spa_freeze()", DEFAULT_MAX_LOOPS, NULL}, { 'B', "alt-ztest", "PATH", "Alternate ztest path", NO_DEFAULT, NULL}, { 'C', "vdev-class-state", "on|off|random", "vdev class state", NO_DEFAULT, "random"}, { 'o', "option", "\"OPTION=INTEGER\"", "Set global variable to an unsigned 32-bit integer value", NO_DEFAULT, NULL}, { 'G', "dump-debug-msg", NULL, "Dump zfs_dbgmsg buffer before exiting due to an error", NO_DEFAULT, NULL}, { 'V', "verbose", NULL, "Verbose (use multiple times for ever more verbosity)", NO_DEFAULT, NULL}, { 'h', "help", NULL, "Show this help", NO_DEFAULT, NULL}, {0, 0, 0, 0, 0, 0} }; static struct option *long_opts = NULL; static char *short_opts = NULL; static void init_options(void) { ASSERT3P(long_opts, ==, NULL); ASSERT3P(short_opts, ==, NULL); int count = sizeof (option_table) / sizeof (option_table[0]); long_opts = umem_alloc(sizeof (struct option) * count, UMEM_NOFAIL); short_opts = umem_alloc(sizeof (char) * 2 * count, UMEM_NOFAIL); int short_opt_index = 0; for (int i = 0; i < count; i++) { long_opts[i].val = option_table[i].short_opt; long_opts[i].name = option_table[i].long_opt; long_opts[i].has_arg = option_table[i].long_opt_param != NULL ? required_argument : no_argument; long_opts[i].flag = NULL; short_opts[short_opt_index++] = option_table[i].short_opt; if (option_table[i].long_opt_param != NULL) { short_opts[short_opt_index++] = ':'; } } } static void fini_options(void) { int count = sizeof (option_table) / sizeof (option_table[0]); umem_free(long_opts, sizeof (struct option) * count); umem_free(short_opts, sizeof (char) * 2 * count); long_opts = NULL; short_opts = NULL; } static void usage(boolean_t requested) { char option[80]; FILE *fp = requested ? stdout : stderr; (void) fprintf(fp, "Usage: %s [OPTIONS...]\n", DEFAULT_POOL); for (int i = 0; option_table[i].short_opt != 0; i++) { if (option_table[i].long_opt_param != NULL) { (void) sprintf(option, " -%c --%s=%s", option_table[i].short_opt, option_table[i].long_opt, option_table[i].long_opt_param); } else { (void) sprintf(option, " -%c --%s", option_table[i].short_opt, option_table[i].long_opt); } (void) fprintf(fp, " %-40s%s", option, option_table[i].comment); if (option_table[i].long_opt_param != NULL) { if (option_table[i].default_str != NULL) { (void) fprintf(fp, " (default: %s)", option_table[i].default_str); } else if (option_table[i].default_int != NO_DEFAULT) { (void) fprintf(fp, " (default: %u)", option_table[i].default_int); } } (void) fprintf(fp, "\n"); } exit(requested ? 0 : 1); } static uint64_t ztest_random(uint64_t range) { uint64_t r; ASSERT3S(ztest_fd_rand, >=, 0); if (range == 0) return (0); if (read(ztest_fd_rand, &r, sizeof (r)) != sizeof (r)) fatal(B_TRUE, "short read from /dev/urandom"); return (r % range); } static void ztest_parse_name_value(const char *input, ztest_shared_opts_t *zo) { char name[32]; char *value; int state = ZTEST_VDEV_CLASS_RND; (void) strlcpy(name, input, sizeof (name)); value = strchr(name, '='); if (value == NULL) { (void) fprintf(stderr, "missing value in property=value " "'-C' argument (%s)\n", input); usage(B_FALSE); } *(value) = '\0'; value++; if (strcmp(value, "on") == 0) { state = ZTEST_VDEV_CLASS_ON; } else if (strcmp(value, "off") == 0) { state = ZTEST_VDEV_CLASS_OFF; } else if (strcmp(value, "random") == 0) { state = ZTEST_VDEV_CLASS_RND; } else { (void) fprintf(stderr, "invalid property value '%s'\n", value); usage(B_FALSE); } if (strcmp(name, "special") == 0) { zo->zo_special_vdevs = state; } else { (void) fprintf(stderr, "invalid property name '%s'\n", name); usage(B_FALSE); } if (zo->zo_verbose >= 3) (void) printf("%s vdev state is '%s'\n", name, value); } static void process_options(int argc, char **argv) { char *path; ztest_shared_opts_t *zo = &ztest_opts; int opt; uint64_t value; char altdir[MAXNAMELEN] = { 0 }; char raid_kind[8] = { "random" }; bcopy(&ztest_opts_defaults, zo, sizeof (*zo)); init_options(); while ((opt = getopt_long(argc, argv, short_opts, long_opts, NULL)) != EOF) { value = 0; switch (opt) { case 'v': case 's': case 'a': case 'm': case 'r': case 'R': case 'D': case 'S': case 'd': case 't': case 'g': case 'i': case 'k': case 'T': case 'P': case 'F': value = nicenumtoull(optarg); } switch (opt) { case 'v': zo->zo_vdevs = value; break; case 's': zo->zo_vdev_size = MAX(SPA_MINDEVSIZE, value); break; case 'a': zo->zo_ashift = value; break; case 'm': zo->zo_mirrors = value; break; case 'r': zo->zo_raid_children = MAX(1, value); break; case 'R': zo->zo_raid_parity = MIN(MAX(value, 1), 3); break; case 'K': (void) strlcpy(raid_kind, optarg, sizeof (raid_kind)); break; case 'D': zo->zo_draid_data = MAX(1, value); break; case 'S': zo->zo_draid_spares = MAX(1, value); break; case 'd': zo->zo_datasets = MAX(1, value); break; case 't': zo->zo_threads = MAX(1, value); break; case 'g': zo->zo_metaslab_force_ganging = MAX(SPA_MINBLOCKSIZE << 1, value); break; case 'i': zo->zo_init = value; break; case 'k': zo->zo_killrate = value; break; case 'p': (void) strlcpy(zo->zo_pool, optarg, sizeof (zo->zo_pool)); break; case 'f': path = realpath(optarg, NULL); if (path == NULL) { (void) fprintf(stderr, "error: %s: %s\n", optarg, strerror(errno)); usage(B_FALSE); } else { (void) strlcpy(zo->zo_dir, path, sizeof (zo->zo_dir)); free(path); } break; case 'M': zo->zo_mmp_test = 1; break; case 'V': zo->zo_verbose++; break; case 'E': zo->zo_init = 0; break; case 'T': zo->zo_time = value; break; case 'P': zo->zo_passtime = MAX(1, value); break; case 'F': zo->zo_maxloops = MAX(1, value); break; case 'B': (void) strlcpy(altdir, optarg, sizeof (altdir)); break; case 'C': ztest_parse_name_value(optarg, zo); break; case 'o': if (zo->zo_gvars_count >= ZO_GVARS_MAX_COUNT) { (void) fprintf(stderr, "max global var count (%zu) exceeded\n", ZO_GVARS_MAX_COUNT); usage(B_FALSE); } char *v = zo->zo_gvars[zo->zo_gvars_count]; if (strlcpy(v, optarg, ZO_GVARS_MAX_ARGLEN) >= ZO_GVARS_MAX_ARGLEN) { (void) fprintf(stderr, "global var option '%s' is too long\n", optarg); usage(B_FALSE); } zo->zo_gvars_count++; break; case 'G': zo->zo_dump_dbgmsg = 1; break; case 'h': usage(B_TRUE); break; case '?': default: usage(B_FALSE); break; } } fini_options(); /* When raid choice is 'random' add a draid pool 50% of the time */ if (strcmp(raid_kind, "random") == 0) { (void) strlcpy(raid_kind, (ztest_random(2) == 0) ? "draid" : "raidz", sizeof (raid_kind)); if (ztest_opts.zo_verbose >= 3) (void) printf("choosing RAID type '%s'\n", raid_kind); } if (strcmp(raid_kind, "draid") == 0) { uint64_t min_devsize; /* With fewer disk use 256M, otherwise 128M is OK */ min_devsize = (ztest_opts.zo_raid_children < 16) ? (256ULL << 20) : (128ULL << 20); /* No top-level mirrors with dRAID for now */ zo->zo_mirrors = 0; /* Use more appropriate defaults for dRAID */ if (zo->zo_vdevs == ztest_opts_defaults.zo_vdevs) zo->zo_vdevs = 1; if (zo->zo_raid_children == ztest_opts_defaults.zo_raid_children) zo->zo_raid_children = 16; if (zo->zo_ashift < 12) zo->zo_ashift = 12; if (zo->zo_vdev_size < min_devsize) zo->zo_vdev_size = min_devsize; if (zo->zo_draid_data + zo->zo_raid_parity > zo->zo_raid_children - zo->zo_draid_spares) { (void) fprintf(stderr, "error: too few draid " "children (%d) for stripe width (%d)\n", zo->zo_raid_children, zo->zo_draid_data + zo->zo_raid_parity); usage(B_FALSE); } (void) strlcpy(zo->zo_raid_type, VDEV_TYPE_DRAID, sizeof (zo->zo_raid_type)); } else /* using raidz */ { ASSERT0(strcmp(raid_kind, "raidz")); zo->zo_raid_parity = MIN(zo->zo_raid_parity, zo->zo_raid_children - 1); } zo->zo_vdevtime = (zo->zo_vdevs > 0 ? zo->zo_time * NANOSEC / zo->zo_vdevs : UINT64_MAX >> 2); if (strlen(altdir) > 0) { char *cmd; char *realaltdir; char *bin; char *ztest; char *isa; int isalen; cmd = umem_alloc(MAXPATHLEN, UMEM_NOFAIL); realaltdir = umem_alloc(MAXPATHLEN, UMEM_NOFAIL); VERIFY3P(NULL, !=, realpath(getexecname(), cmd)); if (0 != access(altdir, F_OK)) { ztest_dump_core = B_FALSE; fatal(B_TRUE, "invalid alternate ztest path: %s", altdir); } VERIFY3P(NULL, !=, realpath(altdir, realaltdir)); /* * 'cmd' should be of the form "/usr/bin//ztest". * We want to extract to determine if we should use * 32 or 64 bit binaries. */ bin = strstr(cmd, "/usr/bin/"); ztest = strstr(bin, "/ztest"); isa = bin + 9; isalen = ztest - isa; (void) snprintf(zo->zo_alt_ztest, sizeof (zo->zo_alt_ztest), "%s/usr/bin/%.*s/ztest", realaltdir, isalen, isa); (void) snprintf(zo->zo_alt_libpath, sizeof (zo->zo_alt_libpath), "%s/usr/lib/%.*s", realaltdir, isalen, isa); if (0 != access(zo->zo_alt_ztest, X_OK)) { ztest_dump_core = B_FALSE; fatal(B_TRUE, "invalid alternate ztest: %s", zo->zo_alt_ztest); } else if (0 != access(zo->zo_alt_libpath, X_OK)) { ztest_dump_core = B_FALSE; fatal(B_TRUE, "invalid alternate lib directory %s", zo->zo_alt_libpath); } umem_free(cmd, MAXPATHLEN); umem_free(realaltdir, MAXPATHLEN); } } static void ztest_kill(ztest_shared_t *zs) { zs->zs_alloc = metaslab_class_get_alloc(spa_normal_class(ztest_spa)); zs->zs_space = metaslab_class_get_space(spa_normal_class(ztest_spa)); /* * Before we kill off ztest, make sure that the config is updated. * See comment above spa_write_cachefile(). */ mutex_enter(&spa_namespace_lock); spa_write_cachefile(ztest_spa, B_FALSE, B_FALSE); mutex_exit(&spa_namespace_lock); (void) kill(getpid(), SIGKILL); } static void ztest_record_enospc(const char *s) { (void) s; ztest_shared->zs_enospc_count++; } static uint64_t ztest_get_ashift(void) { if (ztest_opts.zo_ashift == 0) return (SPA_MINBLOCKSHIFT + ztest_random(5)); return (ztest_opts.zo_ashift); } static boolean_t ztest_is_draid_spare(const char *name) { uint64_t spare_id = 0, parity = 0, vdev_id = 0; if (sscanf(name, VDEV_TYPE_DRAID "%"PRIu64"-%"PRIu64"-%"PRIu64"", &parity, &vdev_id, &spare_id) == 3) { return (B_TRUE); } return (B_FALSE); } static nvlist_t * make_vdev_file(char *path, char *aux, char *pool, size_t size, uint64_t ashift) { char *pathbuf; uint64_t vdev; nvlist_t *file; boolean_t draid_spare = B_FALSE; pathbuf = umem_alloc(MAXPATHLEN, UMEM_NOFAIL); if (ashift == 0) ashift = ztest_get_ashift(); if (path == NULL) { path = pathbuf; if (aux != NULL) { vdev = ztest_shared->zs_vdev_aux; (void) snprintf(path, MAXPATHLEN, ztest_aux_template, ztest_opts.zo_dir, pool == NULL ? ztest_opts.zo_pool : pool, aux, vdev); } else { vdev = ztest_shared->zs_vdev_next_leaf++; (void) snprintf(path, MAXPATHLEN, ztest_dev_template, ztest_opts.zo_dir, pool == NULL ? ztest_opts.zo_pool : pool, vdev); } } else { draid_spare = ztest_is_draid_spare(path); } if (size != 0 && !draid_spare) { int fd = open(path, O_RDWR | O_CREAT | O_TRUNC, 0666); if (fd == -1) fatal(B_TRUE, "can't open %s", path); if (ftruncate(fd, size) != 0) fatal(B_TRUE, "can't ftruncate %s", path); (void) close(fd); } file = fnvlist_alloc(); fnvlist_add_string(file, ZPOOL_CONFIG_TYPE, draid_spare ? VDEV_TYPE_DRAID_SPARE : VDEV_TYPE_FILE); fnvlist_add_string(file, ZPOOL_CONFIG_PATH, path); fnvlist_add_uint64(file, ZPOOL_CONFIG_ASHIFT, ashift); umem_free(pathbuf, MAXPATHLEN); return (file); } static nvlist_t * make_vdev_raid(char *path, char *aux, char *pool, size_t size, uint64_t ashift, int r) { nvlist_t *raid, **child; int c; if (r < 2) return (make_vdev_file(path, aux, pool, size, ashift)); child = umem_alloc(r * sizeof (nvlist_t *), UMEM_NOFAIL); for (c = 0; c < r; c++) child[c] = make_vdev_file(path, aux, pool, size, ashift); raid = fnvlist_alloc(); fnvlist_add_string(raid, ZPOOL_CONFIG_TYPE, ztest_opts.zo_raid_type); fnvlist_add_uint64(raid, ZPOOL_CONFIG_NPARITY, ztest_opts.zo_raid_parity); fnvlist_add_nvlist_array(raid, ZPOOL_CONFIG_CHILDREN, (const nvlist_t **)child, r); if (strcmp(ztest_opts.zo_raid_type, VDEV_TYPE_DRAID) == 0) { uint64_t ndata = ztest_opts.zo_draid_data; uint64_t nparity = ztest_opts.zo_raid_parity; uint64_t nspares = ztest_opts.zo_draid_spares; uint64_t children = ztest_opts.zo_raid_children; uint64_t ngroups = 1; /* * Calculate the minimum number of groups required to fill a * slice. This is the LCM of the stripe width (data + parity) * and the number of data drives (children - spares). */ while (ngroups * (ndata + nparity) % (children - nspares) != 0) ngroups++; /* Store the basic dRAID configuration. */ fnvlist_add_uint64(raid, ZPOOL_CONFIG_DRAID_NDATA, ndata); fnvlist_add_uint64(raid, ZPOOL_CONFIG_DRAID_NSPARES, nspares); fnvlist_add_uint64(raid, ZPOOL_CONFIG_DRAID_NGROUPS, ngroups); } for (c = 0; c < r; c++) fnvlist_free(child[c]); umem_free(child, r * sizeof (nvlist_t *)); return (raid); } static nvlist_t * make_vdev_mirror(char *path, char *aux, char *pool, size_t size, uint64_t ashift, int r, int m) { nvlist_t *mirror, **child; int c; if (m < 1) return (make_vdev_raid(path, aux, pool, size, ashift, r)); child = umem_alloc(m * sizeof (nvlist_t *), UMEM_NOFAIL); for (c = 0; c < m; c++) child[c] = make_vdev_raid(path, aux, pool, size, ashift, r); mirror = fnvlist_alloc(); fnvlist_add_string(mirror, ZPOOL_CONFIG_TYPE, VDEV_TYPE_MIRROR); fnvlist_add_nvlist_array(mirror, ZPOOL_CONFIG_CHILDREN, (const nvlist_t **)child, m); for (c = 0; c < m; c++) fnvlist_free(child[c]); umem_free(child, m * sizeof (nvlist_t *)); return (mirror); } static nvlist_t * make_vdev_root(char *path, char *aux, char *pool, size_t size, uint64_t ashift, const char *class, int r, int m, int t) { nvlist_t *root, **child; int c; boolean_t log; ASSERT3S(t, >, 0); log = (class != NULL && strcmp(class, "log") == 0); child = umem_alloc(t * sizeof (nvlist_t *), UMEM_NOFAIL); for (c = 0; c < t; c++) { child[c] = make_vdev_mirror(path, aux, pool, size, ashift, r, m); fnvlist_add_uint64(child[c], ZPOOL_CONFIG_IS_LOG, log); if (class != NULL && class[0] != '\0') { ASSERT(m > 1 || log); /* expecting a mirror */ fnvlist_add_string(child[c], ZPOOL_CONFIG_ALLOCATION_BIAS, class); } } root = fnvlist_alloc(); fnvlist_add_string(root, ZPOOL_CONFIG_TYPE, VDEV_TYPE_ROOT); fnvlist_add_nvlist_array(root, aux ? aux : ZPOOL_CONFIG_CHILDREN, (const nvlist_t **)child, t); for (c = 0; c < t; c++) fnvlist_free(child[c]); umem_free(child, t * sizeof (nvlist_t *)); return (root); } /* * Find a random spa version. Returns back a random spa version in the * range [initial_version, SPA_VERSION_FEATURES]. */ static uint64_t ztest_random_spa_version(uint64_t initial_version) { uint64_t version = initial_version; if (version <= SPA_VERSION_BEFORE_FEATURES) { version = version + ztest_random(SPA_VERSION_BEFORE_FEATURES - version + 1); } if (version > SPA_VERSION_BEFORE_FEATURES) version = SPA_VERSION_FEATURES; ASSERT(SPA_VERSION_IS_SUPPORTED(version)); return (version); } static int ztest_random_blocksize(void) { ASSERT3U(ztest_spa->spa_max_ashift, !=, 0); /* * Choose a block size >= the ashift. * If the SPA supports new MAXBLOCKSIZE, test up to 1MB blocks. */ int maxbs = SPA_OLD_MAXBLOCKSHIFT; if (spa_maxblocksize(ztest_spa) == SPA_MAXBLOCKSIZE) maxbs = 20; uint64_t block_shift = ztest_random(maxbs - ztest_spa->spa_max_ashift + 1); return (1 << (SPA_MINBLOCKSHIFT + block_shift)); } static int ztest_random_dnodesize(void) { int slots; int max_slots = spa_maxdnodesize(ztest_spa) >> DNODE_SHIFT; if (max_slots == DNODE_MIN_SLOTS) return (DNODE_MIN_SIZE); /* * Weight the random distribution more heavily toward smaller * dnode sizes since that is more likely to reflect real-world * usage. */ ASSERT3U(max_slots, >, 4); switch (ztest_random(10)) { case 0: slots = 5 + ztest_random(max_slots - 4); break; case 1 ... 4: slots = 2 + ztest_random(3); break; default: slots = 1; break; } return (slots << DNODE_SHIFT); } static int ztest_random_ibshift(void) { return (DN_MIN_INDBLKSHIFT + ztest_random(DN_MAX_INDBLKSHIFT - DN_MIN_INDBLKSHIFT + 1)); } static uint64_t ztest_random_vdev_top(spa_t *spa, boolean_t log_ok) { uint64_t top; vdev_t *rvd = spa->spa_root_vdev; vdev_t *tvd; ASSERT3U(spa_config_held(spa, SCL_ALL, RW_READER), !=, 0); do { top = ztest_random(rvd->vdev_children); tvd = rvd->vdev_child[top]; } while (!vdev_is_concrete(tvd) || (tvd->vdev_islog && !log_ok) || tvd->vdev_mg == NULL || tvd->vdev_mg->mg_class == NULL); return (top); } static uint64_t ztest_random_dsl_prop(zfs_prop_t prop) { uint64_t value; do { value = zfs_prop_random_value(prop, ztest_random(-1ULL)); } while (prop == ZFS_PROP_CHECKSUM && value == ZIO_CHECKSUM_OFF); return (value); } static int ztest_dsl_prop_set_uint64(char *osname, zfs_prop_t prop, uint64_t value, boolean_t inherit) { const char *propname = zfs_prop_to_name(prop); const char *valname; char *setpoint; uint64_t curval; int error; error = dsl_prop_set_int(osname, propname, (inherit ? ZPROP_SRC_NONE : ZPROP_SRC_LOCAL), value); if (error == ENOSPC) { ztest_record_enospc(FTAG); return (error); } ASSERT0(error); setpoint = umem_alloc(MAXPATHLEN, UMEM_NOFAIL); VERIFY0(dsl_prop_get_integer(osname, propname, &curval, setpoint)); if (ztest_opts.zo_verbose >= 6) { int err; err = zfs_prop_index_to_string(prop, curval, &valname); if (err) (void) printf("%s %s = %llu at '%s'\n", osname, propname, (unsigned long long)curval, setpoint); else (void) printf("%s %s = %s at '%s'\n", osname, propname, valname, setpoint); } umem_free(setpoint, MAXPATHLEN); return (error); } static int ztest_spa_prop_set_uint64(zpool_prop_t prop, uint64_t value) { spa_t *spa = ztest_spa; nvlist_t *props = NULL; int error; props = fnvlist_alloc(); fnvlist_add_uint64(props, zpool_prop_to_name(prop), value); error = spa_prop_set(spa, props); fnvlist_free(props); if (error == ENOSPC) { ztest_record_enospc(FTAG); return (error); } ASSERT0(error); return (error); } static int ztest_dmu_objset_own(const char *name, dmu_objset_type_t type, boolean_t readonly, boolean_t decrypt, void *tag, objset_t **osp) { int err; char *cp = NULL; char ddname[ZFS_MAX_DATASET_NAME_LEN]; strcpy(ddname, name); cp = strchr(ddname, '@'); if (cp != NULL) *cp = '\0'; err = dmu_objset_own(name, type, readonly, decrypt, tag, osp); while (decrypt && err == EACCES) { dsl_crypto_params_t *dcp; nvlist_t *crypto_args = fnvlist_alloc(); fnvlist_add_uint8_array(crypto_args, "wkeydata", (uint8_t *)ztest_wkeydata, WRAPPING_KEY_LEN); VERIFY0(dsl_crypto_params_create_nvlist(DCP_CMD_NONE, NULL, crypto_args, &dcp)); err = spa_keystore_load_wkey(ddname, dcp, B_FALSE); /* * Note: if there was an error loading, the wkey was not * consumed, and needs to be freed. */ dsl_crypto_params_free(dcp, (err != 0)); fnvlist_free(crypto_args); if (err == EINVAL) { /* * We couldn't load a key for this dataset so try * the parent. This loop will eventually hit the * encryption root since ztest only makes clones * as children of their origin datasets. */ cp = strrchr(ddname, '/'); if (cp == NULL) return (err); *cp = '\0'; err = EACCES; continue; } else if (err != 0) { break; } err = dmu_objset_own(name, type, readonly, decrypt, tag, osp); break; } return (err); } static void ztest_rll_init(rll_t *rll) { rll->rll_writer = NULL; rll->rll_readers = 0; mutex_init(&rll->rll_lock, NULL, MUTEX_DEFAULT, NULL); cv_init(&rll->rll_cv, NULL, CV_DEFAULT, NULL); } static void ztest_rll_destroy(rll_t *rll) { ASSERT3P(rll->rll_writer, ==, NULL); ASSERT0(rll->rll_readers); mutex_destroy(&rll->rll_lock); cv_destroy(&rll->rll_cv); } static void ztest_rll_lock(rll_t *rll, rl_type_t type) { mutex_enter(&rll->rll_lock); if (type == RL_READER) { while (rll->rll_writer != NULL) (void) cv_wait(&rll->rll_cv, &rll->rll_lock); rll->rll_readers++; } else { while (rll->rll_writer != NULL || rll->rll_readers) (void) cv_wait(&rll->rll_cv, &rll->rll_lock); rll->rll_writer = curthread; } mutex_exit(&rll->rll_lock); } static void ztest_rll_unlock(rll_t *rll) { mutex_enter(&rll->rll_lock); if (rll->rll_writer) { ASSERT0(rll->rll_readers); rll->rll_writer = NULL; } else { ASSERT3S(rll->rll_readers, >, 0); ASSERT3P(rll->rll_writer, ==, NULL); rll->rll_readers--; } if (rll->rll_writer == NULL && rll->rll_readers == 0) cv_broadcast(&rll->rll_cv); mutex_exit(&rll->rll_lock); } static void ztest_object_lock(ztest_ds_t *zd, uint64_t object, rl_type_t type) { rll_t *rll = &zd->zd_object_lock[object & (ZTEST_OBJECT_LOCKS - 1)]; ztest_rll_lock(rll, type); } static void ztest_object_unlock(ztest_ds_t *zd, uint64_t object) { rll_t *rll = &zd->zd_object_lock[object & (ZTEST_OBJECT_LOCKS - 1)]; ztest_rll_unlock(rll); } static rl_t * ztest_range_lock(ztest_ds_t *zd, uint64_t object, uint64_t offset, uint64_t size, rl_type_t type) { uint64_t hash = object ^ (offset % (ZTEST_RANGE_LOCKS + 1)); rll_t *rll = &zd->zd_range_lock[hash & (ZTEST_RANGE_LOCKS - 1)]; rl_t *rl; rl = umem_alloc(sizeof (*rl), UMEM_NOFAIL); rl->rl_object = object; rl->rl_offset = offset; rl->rl_size = size; rl->rl_lock = rll; ztest_rll_lock(rll, type); return (rl); } static void ztest_range_unlock(rl_t *rl) { rll_t *rll = rl->rl_lock; ztest_rll_unlock(rll); umem_free(rl, sizeof (*rl)); } static void ztest_zd_init(ztest_ds_t *zd, ztest_shared_ds_t *szd, objset_t *os) { zd->zd_os = os; zd->zd_zilog = dmu_objset_zil(os); zd->zd_shared = szd; dmu_objset_name(os, zd->zd_name); int l; if (zd->zd_shared != NULL) zd->zd_shared->zd_seq = 0; VERIFY0(pthread_rwlock_init(&zd->zd_zilog_lock, NULL)); mutex_init(&zd->zd_dirobj_lock, NULL, MUTEX_DEFAULT, NULL); for (l = 0; l < ZTEST_OBJECT_LOCKS; l++) ztest_rll_init(&zd->zd_object_lock[l]); for (l = 0; l < ZTEST_RANGE_LOCKS; l++) ztest_rll_init(&zd->zd_range_lock[l]); } static void ztest_zd_fini(ztest_ds_t *zd) { int l; mutex_destroy(&zd->zd_dirobj_lock); (void) pthread_rwlock_destroy(&zd->zd_zilog_lock); for (l = 0; l < ZTEST_OBJECT_LOCKS; l++) ztest_rll_destroy(&zd->zd_object_lock[l]); for (l = 0; l < ZTEST_RANGE_LOCKS; l++) ztest_rll_destroy(&zd->zd_range_lock[l]); } #define TXG_MIGHTWAIT (ztest_random(10) == 0 ? TXG_NOWAIT : TXG_WAIT) static uint64_t ztest_tx_assign(dmu_tx_t *tx, uint64_t txg_how, const char *tag) { uint64_t txg; int error; /* * Attempt to assign tx to some transaction group. */ error = dmu_tx_assign(tx, txg_how); if (error) { if (error == ERESTART) { ASSERT3U(txg_how, ==, TXG_NOWAIT); dmu_tx_wait(tx); } else { ASSERT3U(error, ==, ENOSPC); ztest_record_enospc(tag); } dmu_tx_abort(tx); return (0); } txg = dmu_tx_get_txg(tx); ASSERT3U(txg, !=, 0); return (txg); } static void ztest_bt_generate(ztest_block_tag_t *bt, objset_t *os, uint64_t object, uint64_t dnodesize, uint64_t offset, uint64_t gen, uint64_t txg, uint64_t crtxg) { bt->bt_magic = BT_MAGIC; bt->bt_objset = dmu_objset_id(os); bt->bt_object = object; bt->bt_dnodesize = dnodesize; bt->bt_offset = offset; bt->bt_gen = gen; bt->bt_txg = txg; bt->bt_crtxg = crtxg; } static void ztest_bt_verify(ztest_block_tag_t *bt, objset_t *os, uint64_t object, uint64_t dnodesize, uint64_t offset, uint64_t gen, uint64_t txg, uint64_t crtxg) { ASSERT3U(bt->bt_magic, ==, BT_MAGIC); ASSERT3U(bt->bt_objset, ==, dmu_objset_id(os)); ASSERT3U(bt->bt_object, ==, object); ASSERT3U(bt->bt_dnodesize, ==, dnodesize); ASSERT3U(bt->bt_offset, ==, offset); ASSERT3U(bt->bt_gen, <=, gen); ASSERT3U(bt->bt_txg, <=, txg); ASSERT3U(bt->bt_crtxg, ==, crtxg); } static ztest_block_tag_t * ztest_bt_bonus(dmu_buf_t *db) { dmu_object_info_t doi; ztest_block_tag_t *bt; dmu_object_info_from_db(db, &doi); ASSERT3U(doi.doi_bonus_size, <=, db->db_size); ASSERT3U(doi.doi_bonus_size, >=, sizeof (*bt)); bt = (void *)((char *)db->db_data + doi.doi_bonus_size - sizeof (*bt)); return (bt); } /* * Generate a token to fill up unused bonus buffer space. Try to make * it unique to the object, generation, and offset to verify that data * is not getting overwritten by data from other dnodes. */ #define ZTEST_BONUS_FILL_TOKEN(obj, ds, gen, offset) \ (((ds) << 48) | ((gen) << 32) | ((obj) << 8) | (offset)) /* * Fill up the unused bonus buffer region before the block tag with a * verifiable pattern. Filling the whole bonus area with non-zero data * helps ensure that all dnode traversal code properly skips the * interior regions of large dnodes. */ static void ztest_fill_unused_bonus(dmu_buf_t *db, void *end, uint64_t obj, objset_t *os, uint64_t gen) { uint64_t *bonusp; ASSERT(IS_P2ALIGNED((char *)end - (char *)db->db_data, 8)); for (bonusp = db->db_data; bonusp < (uint64_t *)end; bonusp++) { uint64_t token = ZTEST_BONUS_FILL_TOKEN(obj, dmu_objset_id(os), gen, bonusp - (uint64_t *)db->db_data); *bonusp = token; } } /* * Verify that the unused area of a bonus buffer is filled with the * expected tokens. */ static void ztest_verify_unused_bonus(dmu_buf_t *db, void *end, uint64_t obj, objset_t *os, uint64_t gen) { uint64_t *bonusp; for (bonusp = db->db_data; bonusp < (uint64_t *)end; bonusp++) { uint64_t token = ZTEST_BONUS_FILL_TOKEN(obj, dmu_objset_id(os), gen, bonusp - (uint64_t *)db->db_data); VERIFY3U(*bonusp, ==, token); } } /* * ZIL logging ops */ #define lrz_type lr_mode #define lrz_blocksize lr_uid #define lrz_ibshift lr_gid #define lrz_bonustype lr_rdev #define lrz_dnodesize lr_crtime[1] static void ztest_log_create(ztest_ds_t *zd, dmu_tx_t *tx, lr_create_t *lr) { char *name = (void *)(lr + 1); /* name follows lr */ size_t namesize = strlen(name) + 1; itx_t *itx; if (zil_replaying(zd->zd_zilog, tx)) return; itx = zil_itx_create(TX_CREATE, sizeof (*lr) + namesize); bcopy(&lr->lr_common + 1, &itx->itx_lr + 1, sizeof (*lr) + namesize - sizeof (lr_t)); zil_itx_assign(zd->zd_zilog, itx, tx); } static void ztest_log_remove(ztest_ds_t *zd, dmu_tx_t *tx, lr_remove_t *lr, uint64_t object) { char *name = (void *)(lr + 1); /* name follows lr */ size_t namesize = strlen(name) + 1; itx_t *itx; if (zil_replaying(zd->zd_zilog, tx)) return; itx = zil_itx_create(TX_REMOVE, sizeof (*lr) + namesize); bcopy(&lr->lr_common + 1, &itx->itx_lr + 1, sizeof (*lr) + namesize - sizeof (lr_t)); itx->itx_oid = object; zil_itx_assign(zd->zd_zilog, itx, tx); } static void ztest_log_write(ztest_ds_t *zd, dmu_tx_t *tx, lr_write_t *lr) { itx_t *itx; itx_wr_state_t write_state = ztest_random(WR_NUM_STATES); if (zil_replaying(zd->zd_zilog, tx)) return; if (lr->lr_length > zil_max_log_data(zd->zd_zilog)) write_state = WR_INDIRECT; itx = zil_itx_create(TX_WRITE, sizeof (*lr) + (write_state == WR_COPIED ? lr->lr_length : 0)); if (write_state == WR_COPIED && dmu_read(zd->zd_os, lr->lr_foid, lr->lr_offset, lr->lr_length, ((lr_write_t *)&itx->itx_lr) + 1, DMU_READ_NO_PREFETCH) != 0) { zil_itx_destroy(itx); itx = zil_itx_create(TX_WRITE, sizeof (*lr)); write_state = WR_NEED_COPY; } itx->itx_private = zd; itx->itx_wr_state = write_state; itx->itx_sync = (ztest_random(8) == 0); bcopy(&lr->lr_common + 1, &itx->itx_lr + 1, sizeof (*lr) - sizeof (lr_t)); zil_itx_assign(zd->zd_zilog, itx, tx); } static void ztest_log_truncate(ztest_ds_t *zd, dmu_tx_t *tx, lr_truncate_t *lr) { itx_t *itx; if (zil_replaying(zd->zd_zilog, tx)) return; itx = zil_itx_create(TX_TRUNCATE, sizeof (*lr)); bcopy(&lr->lr_common + 1, &itx->itx_lr + 1, sizeof (*lr) - sizeof (lr_t)); itx->itx_sync = B_FALSE; zil_itx_assign(zd->zd_zilog, itx, tx); } static void ztest_log_setattr(ztest_ds_t *zd, dmu_tx_t *tx, lr_setattr_t *lr) { itx_t *itx; if (zil_replaying(zd->zd_zilog, tx)) return; itx = zil_itx_create(TX_SETATTR, sizeof (*lr)); bcopy(&lr->lr_common + 1, &itx->itx_lr + 1, sizeof (*lr) - sizeof (lr_t)); itx->itx_sync = B_FALSE; zil_itx_assign(zd->zd_zilog, itx, tx); } /* * ZIL replay ops */ static int ztest_replay_create(void *arg1, void *arg2, boolean_t byteswap) { ztest_ds_t *zd = arg1; lr_create_t *lr = arg2; char *name = (void *)(lr + 1); /* name follows lr */ objset_t *os = zd->zd_os; ztest_block_tag_t *bbt; dmu_buf_t *db; dmu_tx_t *tx; uint64_t txg; int error = 0; int bonuslen; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); ASSERT3U(lr->lr_doid, ==, ZTEST_DIROBJ); ASSERT3S(name[0], !=, '\0'); tx = dmu_tx_create(os); dmu_tx_hold_zap(tx, lr->lr_doid, B_TRUE, name); if (lr->lrz_type == DMU_OT_ZAP_OTHER) { dmu_tx_hold_zap(tx, DMU_NEW_OBJECT, B_TRUE, NULL); } else { dmu_tx_hold_bonus(tx, DMU_NEW_OBJECT); } txg = ztest_tx_assign(tx, TXG_WAIT, FTAG); if (txg == 0) return (ENOSPC); ASSERT3U(dmu_objset_zil(os)->zl_replay, ==, !!lr->lr_foid); bonuslen = DN_BONUS_SIZE(lr->lrz_dnodesize); if (lr->lrz_type == DMU_OT_ZAP_OTHER) { if (lr->lr_foid == 0) { lr->lr_foid = zap_create_dnsize(os, lr->lrz_type, lr->lrz_bonustype, bonuslen, lr->lrz_dnodesize, tx); } else { error = zap_create_claim_dnsize(os, lr->lr_foid, lr->lrz_type, lr->lrz_bonustype, bonuslen, lr->lrz_dnodesize, tx); } } else { if (lr->lr_foid == 0) { lr->lr_foid = dmu_object_alloc_dnsize(os, lr->lrz_type, 0, lr->lrz_bonustype, bonuslen, lr->lrz_dnodesize, tx); } else { error = dmu_object_claim_dnsize(os, lr->lr_foid, lr->lrz_type, 0, lr->lrz_bonustype, bonuslen, lr->lrz_dnodesize, tx); } } if (error) { ASSERT3U(error, ==, EEXIST); ASSERT(zd->zd_zilog->zl_replay); dmu_tx_commit(tx); return (error); } ASSERT3U(lr->lr_foid, !=, 0); if (lr->lrz_type != DMU_OT_ZAP_OTHER) VERIFY0(dmu_object_set_blocksize(os, lr->lr_foid, lr->lrz_blocksize, lr->lrz_ibshift, tx)); VERIFY0(dmu_bonus_hold(os, lr->lr_foid, FTAG, &db)); bbt = ztest_bt_bonus(db); dmu_buf_will_dirty(db, tx); ztest_bt_generate(bbt, os, lr->lr_foid, lr->lrz_dnodesize, -1ULL, lr->lr_gen, txg, txg); ztest_fill_unused_bonus(db, bbt, lr->lr_foid, os, lr->lr_gen); dmu_buf_rele(db, FTAG); VERIFY0(zap_add(os, lr->lr_doid, name, sizeof (uint64_t), 1, &lr->lr_foid, tx)); (void) ztest_log_create(zd, tx, lr); dmu_tx_commit(tx); return (0); } static int ztest_replay_remove(void *arg1, void *arg2, boolean_t byteswap) { ztest_ds_t *zd = arg1; lr_remove_t *lr = arg2; char *name = (void *)(lr + 1); /* name follows lr */ objset_t *os = zd->zd_os; dmu_object_info_t doi; dmu_tx_t *tx; uint64_t object, txg; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); ASSERT3U(lr->lr_doid, ==, ZTEST_DIROBJ); ASSERT3S(name[0], !=, '\0'); VERIFY0( zap_lookup(os, lr->lr_doid, name, sizeof (object), 1, &object)); ASSERT3U(object, !=, 0); ztest_object_lock(zd, object, RL_WRITER); VERIFY0(dmu_object_info(os, object, &doi)); tx = dmu_tx_create(os); dmu_tx_hold_zap(tx, lr->lr_doid, B_FALSE, name); dmu_tx_hold_free(tx, object, 0, DMU_OBJECT_END); txg = ztest_tx_assign(tx, TXG_WAIT, FTAG); if (txg == 0) { ztest_object_unlock(zd, object); return (ENOSPC); } if (doi.doi_type == DMU_OT_ZAP_OTHER) { VERIFY0(zap_destroy(os, object, tx)); } else { VERIFY0(dmu_object_free(os, object, tx)); } VERIFY0(zap_remove(os, lr->lr_doid, name, tx)); (void) ztest_log_remove(zd, tx, lr, object); dmu_tx_commit(tx); ztest_object_unlock(zd, object); return (0); } static int ztest_replay_write(void *arg1, void *arg2, boolean_t byteswap) { ztest_ds_t *zd = arg1; lr_write_t *lr = arg2; objset_t *os = zd->zd_os; void *data = lr + 1; /* data follows lr */ uint64_t offset, length; ztest_block_tag_t *bt = data; ztest_block_tag_t *bbt; uint64_t gen, txg, lrtxg, crtxg; dmu_object_info_t doi; dmu_tx_t *tx; dmu_buf_t *db; arc_buf_t *abuf = NULL; rl_t *rl; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); offset = lr->lr_offset; length = lr->lr_length; /* 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 (bt->bt_magic == BSWAP_64(BT_MAGIC)) byteswap_uint64_array(bt, sizeof (*bt)); if (bt->bt_magic != BT_MAGIC) bt = NULL; ztest_object_lock(zd, lr->lr_foid, RL_READER); rl = ztest_range_lock(zd, lr->lr_foid, offset, length, RL_WRITER); VERIFY0(dmu_bonus_hold(os, lr->lr_foid, FTAG, &db)); dmu_object_info_from_db(db, &doi); bbt = ztest_bt_bonus(db); ASSERT3U(bbt->bt_magic, ==, BT_MAGIC); gen = bbt->bt_gen; crtxg = bbt->bt_crtxg; lrtxg = lr->lr_common.lrc_txg; tx = dmu_tx_create(os); dmu_tx_hold_write(tx, lr->lr_foid, offset, length); if (ztest_random(8) == 0 && length == doi.doi_data_block_size && P2PHASE(offset, length) == 0) abuf = dmu_request_arcbuf(db, length); txg = ztest_tx_assign(tx, TXG_WAIT, FTAG); if (txg == 0) { if (abuf != NULL) dmu_return_arcbuf(abuf); dmu_buf_rele(db, FTAG); ztest_range_unlock(rl); ztest_object_unlock(zd, lr->lr_foid); return (ENOSPC); } if (bt != NULL) { /* * Usually, verify the old data before writing new data -- * but not always, because we also want to verify correct * behavior when the data was not recently read into cache. */ ASSERT0(offset % doi.doi_data_block_size); if (ztest_random(4) != 0) { int prefetch = ztest_random(2) ? DMU_READ_PREFETCH : DMU_READ_NO_PREFETCH; ztest_block_tag_t rbt; VERIFY(dmu_read(os, lr->lr_foid, offset, sizeof (rbt), &rbt, prefetch) == 0); if (rbt.bt_magic == BT_MAGIC) { ztest_bt_verify(&rbt, os, lr->lr_foid, 0, offset, gen, txg, crtxg); } } /* * Writes can appear to be newer than the bonus buffer because * the ztest_get_data() callback does a dmu_read() of the * open-context data, which may be different than the data * as it was when the write was generated. */ if (zd->zd_zilog->zl_replay) { ztest_bt_verify(bt, os, lr->lr_foid, 0, offset, MAX(gen, bt->bt_gen), MAX(txg, lrtxg), bt->bt_crtxg); } /* * Set the bt's gen/txg to the bonus buffer's gen/txg * so that all of the usual ASSERTs will work. */ ztest_bt_generate(bt, os, lr->lr_foid, 0, offset, gen, txg, crtxg); } if (abuf == NULL) { dmu_write(os, lr->lr_foid, offset, length, data, tx); } else { bcopy(data, abuf->b_data, length); dmu_assign_arcbuf_by_dbuf(db, offset, abuf, tx); } (void) ztest_log_write(zd, tx, lr); dmu_buf_rele(db, FTAG); dmu_tx_commit(tx); ztest_range_unlock(rl); ztest_object_unlock(zd, lr->lr_foid); return (0); } static int ztest_replay_truncate(void *arg1, void *arg2, boolean_t byteswap) { ztest_ds_t *zd = arg1; lr_truncate_t *lr = arg2; objset_t *os = zd->zd_os; dmu_tx_t *tx; uint64_t txg; rl_t *rl; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); ztest_object_lock(zd, lr->lr_foid, RL_READER); rl = ztest_range_lock(zd, lr->lr_foid, lr->lr_offset, lr->lr_length, RL_WRITER); tx = dmu_tx_create(os); dmu_tx_hold_free(tx, lr->lr_foid, lr->lr_offset, lr->lr_length); txg = ztest_tx_assign(tx, TXG_WAIT, FTAG); if (txg == 0) { ztest_range_unlock(rl); ztest_object_unlock(zd, lr->lr_foid); return (ENOSPC); } VERIFY0(dmu_free_range(os, lr->lr_foid, lr->lr_offset, lr->lr_length, tx)); (void) ztest_log_truncate(zd, tx, lr); dmu_tx_commit(tx); ztest_range_unlock(rl); ztest_object_unlock(zd, lr->lr_foid); return (0); } static int ztest_replay_setattr(void *arg1, void *arg2, boolean_t byteswap) { ztest_ds_t *zd = arg1; lr_setattr_t *lr = arg2; objset_t *os = zd->zd_os; dmu_tx_t *tx; dmu_buf_t *db; ztest_block_tag_t *bbt; uint64_t txg, lrtxg, crtxg, dnodesize; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); ztest_object_lock(zd, lr->lr_foid, RL_WRITER); VERIFY0(dmu_bonus_hold(os, lr->lr_foid, FTAG, &db)); tx = dmu_tx_create(os); dmu_tx_hold_bonus(tx, lr->lr_foid); txg = ztest_tx_assign(tx, TXG_WAIT, FTAG); if (txg == 0) { dmu_buf_rele(db, FTAG); ztest_object_unlock(zd, lr->lr_foid); return (ENOSPC); } bbt = ztest_bt_bonus(db); ASSERT3U(bbt->bt_magic, ==, BT_MAGIC); crtxg = bbt->bt_crtxg; lrtxg = lr->lr_common.lrc_txg; dnodesize = bbt->bt_dnodesize; if (zd->zd_zilog->zl_replay) { ASSERT3U(lr->lr_size, !=, 0); ASSERT3U(lr->lr_mode, !=, 0); ASSERT3U(lrtxg, !=, 0); } else { /* * Randomly change the size and increment the generation. */ lr->lr_size = (ztest_random(db->db_size / sizeof (*bbt)) + 1) * sizeof (*bbt); lr->lr_mode = bbt->bt_gen + 1; ASSERT0(lrtxg); } /* * Verify that the current bonus buffer is not newer than our txg. */ ztest_bt_verify(bbt, os, lr->lr_foid, dnodesize, -1ULL, lr->lr_mode, MAX(txg, lrtxg), crtxg); dmu_buf_will_dirty(db, tx); ASSERT3U(lr->lr_size, >=, sizeof (*bbt)); ASSERT3U(lr->lr_size, <=, db->db_size); VERIFY0(dmu_set_bonus(db, lr->lr_size, tx)); bbt = ztest_bt_bonus(db); ztest_bt_generate(bbt, os, lr->lr_foid, dnodesize, -1ULL, lr->lr_mode, txg, crtxg); ztest_fill_unused_bonus(db, bbt, lr->lr_foid, os, bbt->bt_gen); dmu_buf_rele(db, FTAG); (void) ztest_log_setattr(zd, tx, lr); dmu_tx_commit(tx); ztest_object_unlock(zd, lr->lr_foid); return (0); } zil_replay_func_t *ztest_replay_vector[TX_MAX_TYPE] = { NULL, /* 0 no such transaction type */ ztest_replay_create, /* TX_CREATE */ NULL, /* TX_MKDIR */ NULL, /* TX_MKXATTR */ NULL, /* TX_SYMLINK */ ztest_replay_remove, /* TX_REMOVE */ NULL, /* TX_RMDIR */ NULL, /* TX_LINK */ NULL, /* TX_RENAME */ ztest_replay_write, /* TX_WRITE */ ztest_replay_truncate, /* TX_TRUNCATE */ ztest_replay_setattr, /* TX_SETATTR */ NULL, /* TX_ACL */ NULL, /* TX_CREATE_ACL */ NULL, /* TX_CREATE_ATTR */ NULL, /* TX_CREATE_ACL_ATTR */ NULL, /* TX_MKDIR_ACL */ NULL, /* TX_MKDIR_ATTR */ NULL, /* TX_MKDIR_ACL_ATTR */ NULL, /* TX_WRITE2 */ + NULL, /* TX_SETSAXATTR */ }; /* * ZIL get_data callbacks */ static void ztest_get_done(zgd_t *zgd, int error) { (void) error; ztest_ds_t *zd = zgd->zgd_private; uint64_t object = ((rl_t *)zgd->zgd_lr)->rl_object; if (zgd->zgd_db) dmu_buf_rele(zgd->zgd_db, zgd); ztest_range_unlock((rl_t *)zgd->zgd_lr); ztest_object_unlock(zd, object); umem_free(zgd, sizeof (*zgd)); } static int ztest_get_data(void *arg, uint64_t arg2, lr_write_t *lr, char *buf, struct lwb *lwb, zio_t *zio) { (void) arg2; ztest_ds_t *zd = arg; objset_t *os = zd->zd_os; uint64_t object = lr->lr_foid; uint64_t offset = lr->lr_offset; uint64_t size = lr->lr_length; uint64_t txg = lr->lr_common.lrc_txg; uint64_t crtxg; dmu_object_info_t doi; dmu_buf_t *db; zgd_t *zgd; int error; ASSERT3P(lwb, !=, NULL); ASSERT3P(zio, !=, NULL); ASSERT3U(size, !=, 0); ztest_object_lock(zd, object, RL_READER); error = dmu_bonus_hold(os, object, FTAG, &db); if (error) { ztest_object_unlock(zd, object); return (error); } crtxg = ztest_bt_bonus(db)->bt_crtxg; if (crtxg == 0 || crtxg > txg) { dmu_buf_rele(db, FTAG); ztest_object_unlock(zd, object); return (ENOENT); } dmu_object_info_from_db(db, &doi); dmu_buf_rele(db, FTAG); db = NULL; zgd = umem_zalloc(sizeof (*zgd), UMEM_NOFAIL); zgd->zgd_lwb = lwb; zgd->zgd_private = zd; if (buf != NULL) { /* immediate write */ zgd->zgd_lr = (struct zfs_locked_range *)ztest_range_lock(zd, object, offset, size, RL_READER); error = dmu_read(os, object, offset, size, buf, DMU_READ_NO_PREFETCH); ASSERT0(error); } else { size = doi.doi_data_block_size; if (ISP2(size)) { offset = P2ALIGN(offset, size); } else { ASSERT3U(offset, <, size); offset = 0; } zgd->zgd_lr = (struct zfs_locked_range *)ztest_range_lock(zd, object, offset, size, RL_READER); error = dmu_buf_hold(os, object, offset, zgd, &db, DMU_READ_NO_PREFETCH); if (error == 0) { blkptr_t *bp = &lr->lr_blkptr; zgd->zgd_db = db; zgd->zgd_bp = bp; ASSERT3U(db->db_offset, ==, offset); ASSERT3U(db->db_size, ==, size); error = dmu_sync(zio, lr->lr_common.lrc_txg, ztest_get_done, zgd); if (error == 0) return (0); } } ztest_get_done(zgd, error); return (error); } static void * ztest_lr_alloc(size_t lrsize, char *name) { char *lr; size_t namesize = name ? strlen(name) + 1 : 0; lr = umem_zalloc(lrsize + namesize, UMEM_NOFAIL); if (name) bcopy(name, lr + lrsize, namesize); return (lr); } static void ztest_lr_free(void *lr, size_t lrsize, char *name) { size_t namesize = name ? strlen(name) + 1 : 0; umem_free(lr, lrsize + namesize); } /* * Lookup a bunch of objects. Returns the number of objects not found. */ static int ztest_lookup(ztest_ds_t *zd, ztest_od_t *od, int count) { int missing = 0; int error; int i; ASSERT(MUTEX_HELD(&zd->zd_dirobj_lock)); for (i = 0; i < count; i++, od++) { od->od_object = 0; error = zap_lookup(zd->zd_os, od->od_dir, od->od_name, sizeof (uint64_t), 1, &od->od_object); if (error) { ASSERT3S(error, ==, ENOENT); ASSERT0(od->od_object); missing++; } else { dmu_buf_t *db; ztest_block_tag_t *bbt; dmu_object_info_t doi; ASSERT3U(od->od_object, !=, 0); ASSERT0(missing); /* there should be no gaps */ ztest_object_lock(zd, od->od_object, RL_READER); VERIFY0(dmu_bonus_hold(zd->zd_os, od->od_object, FTAG, &db)); dmu_object_info_from_db(db, &doi); bbt = ztest_bt_bonus(db); ASSERT3U(bbt->bt_magic, ==, BT_MAGIC); od->od_type = doi.doi_type; od->od_blocksize = doi.doi_data_block_size; od->od_gen = bbt->bt_gen; dmu_buf_rele(db, FTAG); ztest_object_unlock(zd, od->od_object); } } return (missing); } static int ztest_create(ztest_ds_t *zd, ztest_od_t *od, int count) { int missing = 0; int i; ASSERT(MUTEX_HELD(&zd->zd_dirobj_lock)); for (i = 0; i < count; i++, od++) { if (missing) { od->od_object = 0; missing++; continue; } lr_create_t *lr = ztest_lr_alloc(sizeof (*lr), od->od_name); lr->lr_doid = od->od_dir; lr->lr_foid = 0; /* 0 to allocate, > 0 to claim */ lr->lrz_type = od->od_crtype; lr->lrz_blocksize = od->od_crblocksize; lr->lrz_ibshift = ztest_random_ibshift(); lr->lrz_bonustype = DMU_OT_UINT64_OTHER; lr->lrz_dnodesize = od->od_crdnodesize; lr->lr_gen = od->od_crgen; lr->lr_crtime[0] = time(NULL); if (ztest_replay_create(zd, lr, B_FALSE) != 0) { ASSERT0(missing); od->od_object = 0; missing++; } else { od->od_object = lr->lr_foid; od->od_type = od->od_crtype; od->od_blocksize = od->od_crblocksize; od->od_gen = od->od_crgen; ASSERT3U(od->od_object, !=, 0); } ztest_lr_free(lr, sizeof (*lr), od->od_name); } return (missing); } static int ztest_remove(ztest_ds_t *zd, ztest_od_t *od, int count) { int missing = 0; int error; int i; ASSERT(MUTEX_HELD(&zd->zd_dirobj_lock)); od += count - 1; for (i = count - 1; i >= 0; i--, od--) { if (missing) { missing++; continue; } /* * No object was found. */ if (od->od_object == 0) continue; lr_remove_t *lr = ztest_lr_alloc(sizeof (*lr), od->od_name); lr->lr_doid = od->od_dir; if ((error = ztest_replay_remove(zd, lr, B_FALSE)) != 0) { ASSERT3U(error, ==, ENOSPC); missing++; } else { od->od_object = 0; } ztest_lr_free(lr, sizeof (*lr), od->od_name); } return (missing); } static int ztest_write(ztest_ds_t *zd, uint64_t object, uint64_t offset, uint64_t size, void *data) { lr_write_t *lr; int error; lr = ztest_lr_alloc(sizeof (*lr) + size, NULL); lr->lr_foid = object; lr->lr_offset = offset; lr->lr_length = size; lr->lr_blkoff = 0; BP_ZERO(&lr->lr_blkptr); bcopy(data, lr + 1, size); error = ztest_replay_write(zd, lr, B_FALSE); ztest_lr_free(lr, sizeof (*lr) + size, NULL); return (error); } static int ztest_truncate(ztest_ds_t *zd, uint64_t object, uint64_t offset, uint64_t size) { lr_truncate_t *lr; int error; lr = ztest_lr_alloc(sizeof (*lr), NULL); lr->lr_foid = object; lr->lr_offset = offset; lr->lr_length = size; error = ztest_replay_truncate(zd, lr, B_FALSE); ztest_lr_free(lr, sizeof (*lr), NULL); return (error); } static int ztest_setattr(ztest_ds_t *zd, uint64_t object) { lr_setattr_t *lr; int error; lr = ztest_lr_alloc(sizeof (*lr), NULL); lr->lr_foid = object; lr->lr_size = 0; lr->lr_mode = 0; error = ztest_replay_setattr(zd, lr, B_FALSE); ztest_lr_free(lr, sizeof (*lr), NULL); return (error); } static void ztest_prealloc(ztest_ds_t *zd, uint64_t object, uint64_t offset, uint64_t size) { objset_t *os = zd->zd_os; dmu_tx_t *tx; uint64_t txg; rl_t *rl; txg_wait_synced(dmu_objset_pool(os), 0); ztest_object_lock(zd, object, RL_READER); rl = ztest_range_lock(zd, object, offset, size, RL_WRITER); tx = dmu_tx_create(os); dmu_tx_hold_write(tx, object, offset, size); txg = ztest_tx_assign(tx, TXG_WAIT, FTAG); if (txg != 0) { dmu_prealloc(os, object, offset, size, tx); dmu_tx_commit(tx); txg_wait_synced(dmu_objset_pool(os), txg); } else { (void) dmu_free_long_range(os, object, offset, size); } ztest_range_unlock(rl); ztest_object_unlock(zd, object); } static void ztest_io(ztest_ds_t *zd, uint64_t object, uint64_t offset) { int err; ztest_block_tag_t wbt; dmu_object_info_t doi; enum ztest_io_type io_type; uint64_t blocksize; void *data; VERIFY0(dmu_object_info(zd->zd_os, object, &doi)); blocksize = doi.doi_data_block_size; data = umem_alloc(blocksize, UMEM_NOFAIL); /* * Pick an i/o type at random, biased toward writing block tags. */ io_type = ztest_random(ZTEST_IO_TYPES); if (ztest_random(2) == 0) io_type = ZTEST_IO_WRITE_TAG; (void) pthread_rwlock_rdlock(&zd->zd_zilog_lock); switch (io_type) { case ZTEST_IO_WRITE_TAG: ztest_bt_generate(&wbt, zd->zd_os, object, doi.doi_dnodesize, offset, 0, 0, 0); (void) ztest_write(zd, object, offset, sizeof (wbt), &wbt); break; case ZTEST_IO_WRITE_PATTERN: (void) memset(data, 'a' + (object + offset) % 5, blocksize); if (ztest_random(2) == 0) { /* * Induce fletcher2 collisions to ensure that * zio_ddt_collision() detects and resolves them * when using fletcher2-verify for deduplication. */ ((uint64_t *)data)[0] ^= 1ULL << 63; ((uint64_t *)data)[4] ^= 1ULL << 63; } (void) ztest_write(zd, object, offset, blocksize, data); break; case ZTEST_IO_WRITE_ZEROES: bzero(data, blocksize); (void) ztest_write(zd, object, offset, blocksize, data); break; case ZTEST_IO_TRUNCATE: (void) ztest_truncate(zd, object, offset, blocksize); break; case ZTEST_IO_SETATTR: (void) ztest_setattr(zd, object); break; default: break; case ZTEST_IO_REWRITE: (void) pthread_rwlock_rdlock(&ztest_name_lock); err = ztest_dsl_prop_set_uint64(zd->zd_name, ZFS_PROP_CHECKSUM, spa_dedup_checksum(ztest_spa), B_FALSE); VERIFY(err == 0 || err == ENOSPC); err = ztest_dsl_prop_set_uint64(zd->zd_name, ZFS_PROP_COMPRESSION, ztest_random_dsl_prop(ZFS_PROP_COMPRESSION), B_FALSE); VERIFY(err == 0 || err == ENOSPC); (void) pthread_rwlock_unlock(&ztest_name_lock); VERIFY0(dmu_read(zd->zd_os, object, offset, blocksize, data, DMU_READ_NO_PREFETCH)); (void) ztest_write(zd, object, offset, blocksize, data); break; } (void) pthread_rwlock_unlock(&zd->zd_zilog_lock); umem_free(data, blocksize); } /* * Initialize an object description template. */ static void ztest_od_init(ztest_od_t *od, uint64_t id, char *tag, uint64_t index, dmu_object_type_t type, uint64_t blocksize, uint64_t dnodesize, uint64_t gen) { od->od_dir = ZTEST_DIROBJ; od->od_object = 0; od->od_crtype = type; od->od_crblocksize = blocksize ? blocksize : ztest_random_blocksize(); od->od_crdnodesize = dnodesize ? dnodesize : ztest_random_dnodesize(); od->od_crgen = gen; od->od_type = DMU_OT_NONE; od->od_blocksize = 0; od->od_gen = 0; (void) snprintf(od->od_name, sizeof (od->od_name), "%s(%"PRId64")[%"PRIu64"]", tag, id, index); } /* * Lookup or create the objects for a test using the od template. * If the objects do not all exist, or if 'remove' is specified, * remove any existing objects and create new ones. Otherwise, * use the existing objects. */ static int ztest_object_init(ztest_ds_t *zd, ztest_od_t *od, size_t size, boolean_t remove) { int count = size / sizeof (*od); int rv = 0; mutex_enter(&zd->zd_dirobj_lock); if ((ztest_lookup(zd, od, count) != 0 || remove) && (ztest_remove(zd, od, count) != 0 || ztest_create(zd, od, count) != 0)) rv = -1; zd->zd_od = od; mutex_exit(&zd->zd_dirobj_lock); return (rv); } void ztest_zil_commit(ztest_ds_t *zd, uint64_t id) { (void) id; zilog_t *zilog = zd->zd_zilog; (void) pthread_rwlock_rdlock(&zd->zd_zilog_lock); zil_commit(zilog, ztest_random(ZTEST_OBJECTS)); /* * Remember the committed values in zd, which is in parent/child * shared memory. If we die, the next iteration of ztest_run() * will verify that the log really does contain this record. */ mutex_enter(&zilog->zl_lock); ASSERT3P(zd->zd_shared, !=, NULL); ASSERT3U(zd->zd_shared->zd_seq, <=, zilog->zl_commit_lr_seq); zd->zd_shared->zd_seq = zilog->zl_commit_lr_seq; mutex_exit(&zilog->zl_lock); (void) pthread_rwlock_unlock(&zd->zd_zilog_lock); } /* * This function is designed to simulate the operations that occur during a * mount/unmount operation. We hold the dataset across these operations in an * attempt to expose any implicit assumptions about ZIL management. */ void ztest_zil_remount(ztest_ds_t *zd, uint64_t id) { (void) id; objset_t *os = zd->zd_os; /* * We hold the ztest_vdev_lock so we don't cause problems with * other threads that wish to remove a log device, such as * ztest_device_removal(). */ mutex_enter(&ztest_vdev_lock); /* * We grab the zd_dirobj_lock to ensure that no other thread is * updating the zil (i.e. adding in-memory log records) and the * zd_zilog_lock to block any I/O. */ mutex_enter(&zd->zd_dirobj_lock); (void) pthread_rwlock_wrlock(&zd->zd_zilog_lock); /* zfsvfs_teardown() */ zil_close(zd->zd_zilog); /* zfsvfs_setup() */ VERIFY3P(zil_open(os, ztest_get_data), ==, zd->zd_zilog); zil_replay(os, zd, ztest_replay_vector); (void) pthread_rwlock_unlock(&zd->zd_zilog_lock); mutex_exit(&zd->zd_dirobj_lock); mutex_exit(&ztest_vdev_lock); } /* * Verify that we can't destroy an active pool, create an existing pool, * or create a pool with a bad vdev spec. */ void ztest_spa_create_destroy(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; ztest_shared_opts_t *zo = &ztest_opts; spa_t *spa; nvlist_t *nvroot; if (zo->zo_mmp_test) return; /* * Attempt to create using a bad file. */ nvroot = make_vdev_root("/dev/bogus", NULL, NULL, 0, 0, NULL, 0, 0, 1); VERIFY3U(ENOENT, ==, spa_create("ztest_bad_file", nvroot, NULL, NULL, NULL)); fnvlist_free(nvroot); /* * Attempt to create using a bad mirror. */ nvroot = make_vdev_root("/dev/bogus", NULL, NULL, 0, 0, NULL, 0, 2, 1); VERIFY3U(ENOENT, ==, spa_create("ztest_bad_mirror", nvroot, NULL, NULL, NULL)); fnvlist_free(nvroot); /* * Attempt to create an existing pool. It shouldn't matter * what's in the nvroot; we should fail with EEXIST. */ (void) pthread_rwlock_rdlock(&ztest_name_lock); nvroot = make_vdev_root("/dev/bogus", NULL, NULL, 0, 0, NULL, 0, 0, 1); VERIFY3U(EEXIST, ==, spa_create(zo->zo_pool, nvroot, NULL, NULL, NULL)); fnvlist_free(nvroot); /* * We open a reference to the spa and then we try to export it * expecting one of the following errors: * * EBUSY * Because of the reference we just opened. * * ZFS_ERR_EXPORT_IN_PROGRESS * For the case that there is another ztest thread doing * an export concurrently. */ VERIFY0(spa_open(zo->zo_pool, &spa, FTAG)); int error = spa_destroy(zo->zo_pool); if (error != EBUSY && error != ZFS_ERR_EXPORT_IN_PROGRESS) { fatal(B_FALSE, "spa_destroy(%s) returned unexpected value %d", spa->spa_name, error); } spa_close(spa, FTAG); (void) pthread_rwlock_unlock(&ztest_name_lock); } /* * Start and then stop the MMP threads to ensure the startup and shutdown code * works properly. Actual protection and property-related code tested via ZTS. */ void ztest_mmp_enable_disable(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; ztest_shared_opts_t *zo = &ztest_opts; spa_t *spa = ztest_spa; if (zo->zo_mmp_test) return; /* * Since enabling MMP involves setting a property, it could not be done * while the pool is suspended. */ if (spa_suspended(spa)) return; spa_config_enter(spa, SCL_CONFIG, FTAG, RW_READER); mutex_enter(&spa->spa_props_lock); zfs_multihost_fail_intervals = 0; if (!spa_multihost(spa)) { spa->spa_multihost = B_TRUE; mmp_thread_start(spa); } mutex_exit(&spa->spa_props_lock); spa_config_exit(spa, SCL_CONFIG, FTAG); txg_wait_synced(spa_get_dsl(spa), 0); mmp_signal_all_threads(); txg_wait_synced(spa_get_dsl(spa), 0); spa_config_enter(spa, SCL_CONFIG, FTAG, RW_READER); mutex_enter(&spa->spa_props_lock); if (spa_multihost(spa)) { mmp_thread_stop(spa); spa->spa_multihost = B_FALSE; } mutex_exit(&spa->spa_props_lock); spa_config_exit(spa, SCL_CONFIG, FTAG); } void ztest_spa_upgrade(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; spa_t *spa; uint64_t initial_version = SPA_VERSION_INITIAL; uint64_t version, newversion; nvlist_t *nvroot, *props; char *name; if (ztest_opts.zo_mmp_test) return; /* dRAID added after feature flags, skip upgrade test. */ if (strcmp(ztest_opts.zo_raid_type, VDEV_TYPE_DRAID) == 0) return; mutex_enter(&ztest_vdev_lock); name = kmem_asprintf("%s_upgrade", ztest_opts.zo_pool); /* * Clean up from previous runs. */ (void) spa_destroy(name); nvroot = make_vdev_root(NULL, NULL, name, ztest_opts.zo_vdev_size, 0, NULL, ztest_opts.zo_raid_children, ztest_opts.zo_mirrors, 1); /* * If we're configuring a RAIDZ device then make sure that the * initial version is capable of supporting that feature. */ switch (ztest_opts.zo_raid_parity) { case 0: case 1: initial_version = SPA_VERSION_INITIAL; break; case 2: initial_version = SPA_VERSION_RAIDZ2; break; case 3: initial_version = SPA_VERSION_RAIDZ3; break; } /* * Create a pool with a spa version that can be upgraded. Pick * a value between initial_version and SPA_VERSION_BEFORE_FEATURES. */ do { version = ztest_random_spa_version(initial_version); } while (version > SPA_VERSION_BEFORE_FEATURES); props = fnvlist_alloc(); fnvlist_add_uint64(props, zpool_prop_to_name(ZPOOL_PROP_VERSION), version); VERIFY0(spa_create(name, nvroot, props, NULL, NULL)); fnvlist_free(nvroot); fnvlist_free(props); VERIFY0(spa_open(name, &spa, FTAG)); VERIFY3U(spa_version(spa), ==, version); newversion = ztest_random_spa_version(version + 1); if (ztest_opts.zo_verbose >= 4) { (void) printf("upgrading spa version from " "%"PRIu64" to %"PRIu64"\n", version, newversion); } spa_upgrade(spa, newversion); VERIFY3U(spa_version(spa), >, version); VERIFY3U(spa_version(spa), ==, fnvlist_lookup_uint64(spa->spa_config, zpool_prop_to_name(ZPOOL_PROP_VERSION))); spa_close(spa, FTAG); kmem_strfree(name); mutex_exit(&ztest_vdev_lock); } static void ztest_spa_checkpoint(spa_t *spa) { ASSERT(MUTEX_HELD(&ztest_checkpoint_lock)); int error = spa_checkpoint(spa->spa_name); switch (error) { case 0: case ZFS_ERR_DEVRM_IN_PROGRESS: case ZFS_ERR_DISCARDING_CHECKPOINT: case ZFS_ERR_CHECKPOINT_EXISTS: break; case ENOSPC: ztest_record_enospc(FTAG); break; default: fatal(B_FALSE, "spa_checkpoint(%s) = %d", spa->spa_name, error); } } static void ztest_spa_discard_checkpoint(spa_t *spa) { ASSERT(MUTEX_HELD(&ztest_checkpoint_lock)); int error = spa_checkpoint_discard(spa->spa_name); switch (error) { case 0: case ZFS_ERR_DISCARDING_CHECKPOINT: case ZFS_ERR_NO_CHECKPOINT: break; default: fatal(B_FALSE, "spa_discard_checkpoint(%s) = %d", spa->spa_name, error); } } void ztest_spa_checkpoint_create_discard(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; spa_t *spa = ztest_spa; mutex_enter(&ztest_checkpoint_lock); if (ztest_random(2) == 0) { ztest_spa_checkpoint(spa); } else { ztest_spa_discard_checkpoint(spa); } mutex_exit(&ztest_checkpoint_lock); } static vdev_t * vdev_lookup_by_path(vdev_t *vd, const char *path) { vdev_t *mvd; int c; if (vd->vdev_path != NULL && strcmp(path, vd->vdev_path) == 0) return (vd); for (c = 0; c < vd->vdev_children; c++) if ((mvd = vdev_lookup_by_path(vd->vdev_child[c], path)) != NULL) return (mvd); return (NULL); } static int spa_num_top_vdevs(spa_t *spa) { vdev_t *rvd = spa->spa_root_vdev; ASSERT3U(spa_config_held(spa, SCL_VDEV, RW_READER), ==, SCL_VDEV); return (rvd->vdev_children); } /* * Verify that vdev_add() works as expected. */ void ztest_vdev_add_remove(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; ztest_shared_t *zs = ztest_shared; spa_t *spa = ztest_spa; uint64_t leaves; uint64_t guid; nvlist_t *nvroot; int error; if (ztest_opts.zo_mmp_test) return; mutex_enter(&ztest_vdev_lock); leaves = MAX(zs->zs_mirrors + zs->zs_splits, 1) * ztest_opts.zo_raid_children; spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER); ztest_shared->zs_vdev_next_leaf = spa_num_top_vdevs(spa) * leaves; /* * If we have slogs then remove them 1/4 of the time. */ if (spa_has_slogs(spa) && ztest_random(4) == 0) { metaslab_group_t *mg; /* * find the first real slog in log allocation class */ mg = spa_log_class(spa)->mc_allocator[0].mca_rotor; while (!mg->mg_vd->vdev_islog) mg = mg->mg_next; guid = mg->mg_vd->vdev_guid; spa_config_exit(spa, SCL_VDEV, FTAG); /* * We have to grab the zs_name_lock as writer to * prevent a race between removing a slog (dmu_objset_find) * and destroying a dataset. Removing the slog will * grab a reference on the dataset which may cause * dsl_destroy_head() to fail with EBUSY thus * leaving the dataset in an inconsistent state. */ pthread_rwlock_wrlock(&ztest_name_lock); error = spa_vdev_remove(spa, guid, B_FALSE); pthread_rwlock_unlock(&ztest_name_lock); switch (error) { case 0: case EEXIST: /* Generic zil_reset() error */ case EBUSY: /* Replay required */ case EACCES: /* Crypto key not loaded */ case ZFS_ERR_CHECKPOINT_EXISTS: case ZFS_ERR_DISCARDING_CHECKPOINT: break; default: fatal(B_FALSE, "spa_vdev_remove() = %d", error); } } else { spa_config_exit(spa, SCL_VDEV, FTAG); /* * Make 1/4 of the devices be log devices */ nvroot = make_vdev_root(NULL, NULL, NULL, ztest_opts.zo_vdev_size, 0, (ztest_random(4) == 0) ? "log" : NULL, ztest_opts.zo_raid_children, zs->zs_mirrors, 1); error = spa_vdev_add(spa, nvroot); fnvlist_free(nvroot); switch (error) { case 0: break; case ENOSPC: ztest_record_enospc("spa_vdev_add"); break; default: fatal(B_FALSE, "spa_vdev_add() = %d", error); } } mutex_exit(&ztest_vdev_lock); } void ztest_vdev_class_add(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; ztest_shared_t *zs = ztest_shared; spa_t *spa = ztest_spa; uint64_t leaves; nvlist_t *nvroot; const char *class = (ztest_random(2) == 0) ? VDEV_ALLOC_BIAS_SPECIAL : VDEV_ALLOC_BIAS_DEDUP; int error; /* * By default add a special vdev 50% of the time */ if ((ztest_opts.zo_special_vdevs == ZTEST_VDEV_CLASS_OFF) || (ztest_opts.zo_special_vdevs == ZTEST_VDEV_CLASS_RND && ztest_random(2) == 0)) { return; } mutex_enter(&ztest_vdev_lock); /* Only test with mirrors */ if (zs->zs_mirrors < 2) { mutex_exit(&ztest_vdev_lock); return; } /* requires feature@allocation_classes */ if (!spa_feature_is_enabled(spa, SPA_FEATURE_ALLOCATION_CLASSES)) { mutex_exit(&ztest_vdev_lock); return; } leaves = MAX(zs->zs_mirrors + zs->zs_splits, 1) * ztest_opts.zo_raid_children; spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER); ztest_shared->zs_vdev_next_leaf = spa_num_top_vdevs(spa) * leaves; spa_config_exit(spa, SCL_VDEV, FTAG); nvroot = make_vdev_root(NULL, NULL, NULL, ztest_opts.zo_vdev_size, 0, class, ztest_opts.zo_raid_children, zs->zs_mirrors, 1); error = spa_vdev_add(spa, nvroot); fnvlist_free(nvroot); if (error == ENOSPC) ztest_record_enospc("spa_vdev_add"); else if (error != 0) fatal(B_FALSE, "spa_vdev_add() = %d", error); /* * 50% of the time allow small blocks in the special class */ if (error == 0 && spa_special_class(spa)->mc_groups == 1 && ztest_random(2) == 0) { if (ztest_opts.zo_verbose >= 3) (void) printf("Enabling special VDEV small blocks\n"); (void) ztest_dsl_prop_set_uint64(zd->zd_name, ZFS_PROP_SPECIAL_SMALL_BLOCKS, 32768, B_FALSE); } mutex_exit(&ztest_vdev_lock); if (ztest_opts.zo_verbose >= 3) { metaslab_class_t *mc; if (strcmp(class, VDEV_ALLOC_BIAS_SPECIAL) == 0) mc = spa_special_class(spa); else mc = spa_dedup_class(spa); (void) printf("Added a %s mirrored vdev (of %d)\n", class, (int)mc->mc_groups); } } /* * Verify that adding/removing aux devices (l2arc, hot spare) works as expected. */ void ztest_vdev_aux_add_remove(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; ztest_shared_t *zs = ztest_shared; spa_t *spa = ztest_spa; vdev_t *rvd = spa->spa_root_vdev; spa_aux_vdev_t *sav; char *aux; char *path; uint64_t guid = 0; int error, ignore_err = 0; if (ztest_opts.zo_mmp_test) return; path = umem_alloc(MAXPATHLEN, UMEM_NOFAIL); if (ztest_random(2) == 0) { sav = &spa->spa_spares; aux = ZPOOL_CONFIG_SPARES; } else { sav = &spa->spa_l2cache; aux = ZPOOL_CONFIG_L2CACHE; } mutex_enter(&ztest_vdev_lock); spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER); if (sav->sav_count != 0 && ztest_random(4) == 0) { /* * Pick a random device to remove. */ vdev_t *svd = sav->sav_vdevs[ztest_random(sav->sav_count)]; /* dRAID spares cannot be removed; try anyways to see ENOTSUP */ if (strstr(svd->vdev_path, VDEV_TYPE_DRAID) != NULL) ignore_err = ENOTSUP; guid = svd->vdev_guid; } else { /* * Find an unused device we can add. */ zs->zs_vdev_aux = 0; for (;;) { int c; (void) snprintf(path, MAXPATHLEN, ztest_aux_template, ztest_opts.zo_dir, ztest_opts.zo_pool, aux, zs->zs_vdev_aux); for (c = 0; c < sav->sav_count; c++) if (strcmp(sav->sav_vdevs[c]->vdev_path, path) == 0) break; if (c == sav->sav_count && vdev_lookup_by_path(rvd, path) == NULL) break; zs->zs_vdev_aux++; } } spa_config_exit(spa, SCL_VDEV, FTAG); if (guid == 0) { /* * Add a new device. */ nvlist_t *nvroot = make_vdev_root(NULL, aux, NULL, (ztest_opts.zo_vdev_size * 5) / 4, 0, NULL, 0, 0, 1); error = spa_vdev_add(spa, nvroot); switch (error) { case 0: break; default: fatal(B_FALSE, "spa_vdev_add(%p) = %d", nvroot, error); } fnvlist_free(nvroot); } else { /* * Remove an existing device. Sometimes, dirty its * vdev state first to make sure we handle removal * of devices that have pending state changes. */ if (ztest_random(2) == 0) (void) vdev_online(spa, guid, 0, NULL); error = spa_vdev_remove(spa, guid, B_FALSE); switch (error) { case 0: case EBUSY: case ZFS_ERR_CHECKPOINT_EXISTS: case ZFS_ERR_DISCARDING_CHECKPOINT: break; default: if (error != ignore_err) fatal(B_FALSE, "spa_vdev_remove(%"PRIu64") = %d", guid, error); } } mutex_exit(&ztest_vdev_lock); umem_free(path, MAXPATHLEN); } /* * split a pool if it has mirror tlvdevs */ void ztest_split_pool(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; ztest_shared_t *zs = ztest_shared; spa_t *spa = ztest_spa; vdev_t *rvd = spa->spa_root_vdev; nvlist_t *tree, **child, *config, *split, **schild; uint_t c, children, schildren = 0, lastlogid = 0; int error = 0; if (ztest_opts.zo_mmp_test) return; mutex_enter(&ztest_vdev_lock); /* ensure we have a usable config; mirrors of raidz aren't supported */ if (zs->zs_mirrors < 3 || ztest_opts.zo_raid_children > 1) { mutex_exit(&ztest_vdev_lock); return; } /* clean up the old pool, if any */ (void) spa_destroy("splitp"); spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER); /* generate a config from the existing config */ mutex_enter(&spa->spa_props_lock); tree = fnvlist_lookup_nvlist(spa->spa_config, ZPOOL_CONFIG_VDEV_TREE); mutex_exit(&spa->spa_props_lock); VERIFY0(nvlist_lookup_nvlist_array(tree, ZPOOL_CONFIG_CHILDREN, &child, &children)); schild = malloc(rvd->vdev_children * sizeof (nvlist_t *)); for (c = 0; c < children; c++) { vdev_t *tvd = rvd->vdev_child[c]; nvlist_t **mchild; uint_t mchildren; if (tvd->vdev_islog || tvd->vdev_ops == &vdev_hole_ops) { schild[schildren] = fnvlist_alloc(); fnvlist_add_string(schild[schildren], ZPOOL_CONFIG_TYPE, VDEV_TYPE_HOLE); fnvlist_add_uint64(schild[schildren], ZPOOL_CONFIG_IS_HOLE, 1); if (lastlogid == 0) lastlogid = schildren; ++schildren; continue; } lastlogid = 0; VERIFY0(nvlist_lookup_nvlist_array(child[c], ZPOOL_CONFIG_CHILDREN, &mchild, &mchildren)); schild[schildren++] = fnvlist_dup(mchild[0]); } /* OK, create a config that can be used to split */ split = fnvlist_alloc(); fnvlist_add_string(split, ZPOOL_CONFIG_TYPE, VDEV_TYPE_ROOT); fnvlist_add_nvlist_array(split, ZPOOL_CONFIG_CHILDREN, (const nvlist_t **)schild, lastlogid != 0 ? lastlogid : schildren); config = fnvlist_alloc(); fnvlist_add_nvlist(config, ZPOOL_CONFIG_VDEV_TREE, split); for (c = 0; c < schildren; c++) fnvlist_free(schild[c]); free(schild); fnvlist_free(split); spa_config_exit(spa, SCL_VDEV, FTAG); (void) pthread_rwlock_wrlock(&ztest_name_lock); error = spa_vdev_split_mirror(spa, "splitp", config, NULL, B_FALSE); (void) pthread_rwlock_unlock(&ztest_name_lock); fnvlist_free(config); if (error == 0) { (void) printf("successful split - results:\n"); mutex_enter(&spa_namespace_lock); show_pool_stats(spa); show_pool_stats(spa_lookup("splitp")); mutex_exit(&spa_namespace_lock); ++zs->zs_splits; --zs->zs_mirrors; } mutex_exit(&ztest_vdev_lock); } /* * Verify that we can attach and detach devices. */ void ztest_vdev_attach_detach(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; ztest_shared_t *zs = ztest_shared; spa_t *spa = ztest_spa; spa_aux_vdev_t *sav = &spa->spa_spares; vdev_t *rvd = spa->spa_root_vdev; vdev_t *oldvd, *newvd, *pvd; nvlist_t *root; uint64_t leaves; uint64_t leaf, top; uint64_t ashift = ztest_get_ashift(); uint64_t oldguid, pguid; uint64_t oldsize, newsize; char *oldpath, *newpath; int replacing; int oldvd_has_siblings = B_FALSE; int newvd_is_spare = B_FALSE; int newvd_is_dspare = B_FALSE; int oldvd_is_log; int error, expected_error; if (ztest_opts.zo_mmp_test) return; oldpath = umem_alloc(MAXPATHLEN, UMEM_NOFAIL); newpath = umem_alloc(MAXPATHLEN, UMEM_NOFAIL); mutex_enter(&ztest_vdev_lock); leaves = MAX(zs->zs_mirrors, 1) * ztest_opts.zo_raid_children; spa_config_enter(spa, SCL_ALL, FTAG, RW_WRITER); /* * If a vdev is in the process of being removed, its removal may * finish while we are in progress, leading to an unexpected error * value. Don't bother trying to attach while we are in the middle * of removal. */ if (ztest_device_removal_active) { spa_config_exit(spa, SCL_ALL, FTAG); goto out; } /* * Decide whether to do an attach or a replace. */ replacing = ztest_random(2); /* * Pick a random top-level vdev. */ top = ztest_random_vdev_top(spa, B_TRUE); /* * Pick a random leaf within it. */ leaf = ztest_random(leaves); /* * Locate this vdev. */ oldvd = rvd->vdev_child[top]; /* pick a child from the mirror */ if (zs->zs_mirrors >= 1) { ASSERT3P(oldvd->vdev_ops, ==, &vdev_mirror_ops); ASSERT3U(oldvd->vdev_children, >=, zs->zs_mirrors); oldvd = oldvd->vdev_child[leaf / ztest_opts.zo_raid_children]; } /* pick a child out of the raidz group */ if (ztest_opts.zo_raid_children > 1) { if (strcmp(oldvd->vdev_ops->vdev_op_type, "raidz") == 0) ASSERT3P(oldvd->vdev_ops, ==, &vdev_raidz_ops); else ASSERT3P(oldvd->vdev_ops, ==, &vdev_draid_ops); ASSERT3U(oldvd->vdev_children, ==, ztest_opts.zo_raid_children); oldvd = oldvd->vdev_child[leaf % ztest_opts.zo_raid_children]; } /* * If we're already doing an attach or replace, oldvd may be a * mirror vdev -- in which case, pick a random child. */ while (oldvd->vdev_children != 0) { oldvd_has_siblings = B_TRUE; ASSERT3U(oldvd->vdev_children, >=, 2); oldvd = oldvd->vdev_child[ztest_random(oldvd->vdev_children)]; } oldguid = oldvd->vdev_guid; oldsize = vdev_get_min_asize(oldvd); oldvd_is_log = oldvd->vdev_top->vdev_islog; (void) strcpy(oldpath, oldvd->vdev_path); pvd = oldvd->vdev_parent; pguid = pvd->vdev_guid; /* * If oldvd has siblings, then half of the time, detach it. Prior * to the detach the pool is scrubbed in order to prevent creating * unrepairable blocks as a result of the data corruption injection. */ if (oldvd_has_siblings && ztest_random(2) == 0) { spa_config_exit(spa, SCL_ALL, FTAG); error = ztest_scrub_impl(spa); if (error) goto out; error = spa_vdev_detach(spa, oldguid, pguid, B_FALSE); if (error != 0 && error != ENODEV && error != EBUSY && error != ENOTSUP && error != ZFS_ERR_CHECKPOINT_EXISTS && error != ZFS_ERR_DISCARDING_CHECKPOINT) fatal(B_FALSE, "detach (%s) returned %d", oldpath, error); goto out; } /* * For the new vdev, choose with equal probability between the two * standard paths (ending in either 'a' or 'b') or a random hot spare. */ if (sav->sav_count != 0 && ztest_random(3) == 0) { newvd = sav->sav_vdevs[ztest_random(sav->sav_count)]; newvd_is_spare = B_TRUE; if (newvd->vdev_ops == &vdev_draid_spare_ops) newvd_is_dspare = B_TRUE; (void) strcpy(newpath, newvd->vdev_path); } else { (void) snprintf(newpath, MAXPATHLEN, ztest_dev_template, ztest_opts.zo_dir, ztest_opts.zo_pool, top * leaves + leaf); if (ztest_random(2) == 0) newpath[strlen(newpath) - 1] = 'b'; newvd = vdev_lookup_by_path(rvd, newpath); } if (newvd) { /* * Reopen to ensure the vdev's asize field isn't stale. */ vdev_reopen(newvd); newsize = vdev_get_min_asize(newvd); } else { /* * Make newsize a little bigger or smaller than oldsize. * If it's smaller, the attach should fail. * If it's larger, and we're doing a replace, * we should get dynamic LUN growth when we're done. */ newsize = 10 * oldsize / (9 + ztest_random(3)); } /* * If pvd is not a mirror or root, the attach should fail with ENOTSUP, * unless it's a replace; in that case any non-replacing parent is OK. * * If newvd is already part of the pool, it should fail with EBUSY. * * If newvd is too small, it should fail with EOVERFLOW. * * If newvd is a distributed spare and it's being attached to a * dRAID which is not its parent it should fail with EINVAL. */ if (pvd->vdev_ops != &vdev_mirror_ops && pvd->vdev_ops != &vdev_root_ops && (!replacing || pvd->vdev_ops == &vdev_replacing_ops || pvd->vdev_ops == &vdev_spare_ops)) expected_error = ENOTSUP; else if (newvd_is_spare && (!replacing || oldvd_is_log)) expected_error = ENOTSUP; else if (newvd == oldvd) expected_error = replacing ? 0 : EBUSY; else if (vdev_lookup_by_path(rvd, newpath) != NULL) expected_error = EBUSY; else if (!newvd_is_dspare && newsize < oldsize) expected_error = EOVERFLOW; else if (ashift > oldvd->vdev_top->vdev_ashift) expected_error = EDOM; else if (newvd_is_dspare && pvd != vdev_draid_spare_get_parent(newvd)) expected_error = ENOTSUP; else expected_error = 0; spa_config_exit(spa, SCL_ALL, FTAG); /* * Build the nvlist describing newpath. */ root = make_vdev_root(newpath, NULL, NULL, newvd == NULL ? newsize : 0, ashift, NULL, 0, 0, 1); /* * When supported select either a healing or sequential resilver. */ boolean_t rebuilding = B_FALSE; if (pvd->vdev_ops == &vdev_mirror_ops || pvd->vdev_ops == &vdev_root_ops) { rebuilding = !!ztest_random(2); } error = spa_vdev_attach(spa, oldguid, root, replacing, rebuilding); fnvlist_free(root); /* * If our parent was the replacing vdev, but the replace completed, * then instead of failing with ENOTSUP we may either succeed, * fail with ENODEV, or fail with EOVERFLOW. */ if (expected_error == ENOTSUP && (error == 0 || error == ENODEV || error == EOVERFLOW)) expected_error = error; /* * If someone grew the LUN, the replacement may be too small. */ if (error == EOVERFLOW || error == EBUSY) expected_error = error; if (error == ZFS_ERR_CHECKPOINT_EXISTS || error == ZFS_ERR_DISCARDING_CHECKPOINT || error == ZFS_ERR_RESILVER_IN_PROGRESS || error == ZFS_ERR_REBUILD_IN_PROGRESS) expected_error = error; if (error != expected_error && expected_error != EBUSY) { fatal(B_FALSE, "attach (%s %"PRIu64", %s %"PRIu64", %d) " "returned %d, expected %d", oldpath, oldsize, newpath, newsize, replacing, error, expected_error); } out: mutex_exit(&ztest_vdev_lock); umem_free(oldpath, MAXPATHLEN); umem_free(newpath, MAXPATHLEN); } void ztest_device_removal(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; spa_t *spa = ztest_spa; vdev_t *vd; uint64_t guid; int error; mutex_enter(&ztest_vdev_lock); if (ztest_device_removal_active) { mutex_exit(&ztest_vdev_lock); return; } /* * Remove a random top-level vdev and wait for removal to finish. */ spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER); vd = vdev_lookup_top(spa, ztest_random_vdev_top(spa, B_FALSE)); guid = vd->vdev_guid; spa_config_exit(spa, SCL_VDEV, FTAG); error = spa_vdev_remove(spa, guid, B_FALSE); if (error == 0) { ztest_device_removal_active = B_TRUE; mutex_exit(&ztest_vdev_lock); /* * spa->spa_vdev_removal is created in a sync task that * is initiated via dsl_sync_task_nowait(). Since the * task may not run before spa_vdev_remove() returns, we * must wait at least 1 txg to ensure that the removal * struct has been created. */ txg_wait_synced(spa_get_dsl(spa), 0); while (spa->spa_removing_phys.sr_state == DSS_SCANNING) txg_wait_synced(spa_get_dsl(spa), 0); } else { mutex_exit(&ztest_vdev_lock); return; } /* * The pool needs to be scrubbed after completing device removal. * Failure to do so may result in checksum errors due to the * strategy employed by ztest_fault_inject() when selecting which * offset are redundant and can be damaged. */ error = spa_scan(spa, POOL_SCAN_SCRUB); if (error == 0) { while (dsl_scan_scrubbing(spa_get_dsl(spa))) txg_wait_synced(spa_get_dsl(spa), 0); } mutex_enter(&ztest_vdev_lock); ztest_device_removal_active = B_FALSE; mutex_exit(&ztest_vdev_lock); } /* * Callback function which expands the physical size of the vdev. */ static vdev_t * grow_vdev(vdev_t *vd, void *arg) { spa_t *spa __maybe_unused = vd->vdev_spa; size_t *newsize = arg; size_t fsize; int fd; ASSERT3S(spa_config_held(spa, SCL_STATE, RW_READER), ==, SCL_STATE); ASSERT(vd->vdev_ops->vdev_op_leaf); if ((fd = open(vd->vdev_path, O_RDWR)) == -1) return (vd); fsize = lseek(fd, 0, SEEK_END); VERIFY0(ftruncate(fd, *newsize)); if (ztest_opts.zo_verbose >= 6) { (void) printf("%s grew from %lu to %lu bytes\n", vd->vdev_path, (ulong_t)fsize, (ulong_t)*newsize); } (void) close(fd); return (NULL); } /* * Callback function which expands a given vdev by calling vdev_online(). */ static vdev_t * online_vdev(vdev_t *vd, void *arg) { (void) arg; spa_t *spa = vd->vdev_spa; vdev_t *tvd = vd->vdev_top; uint64_t guid = vd->vdev_guid; uint64_t generation = spa->spa_config_generation + 1; vdev_state_t newstate = VDEV_STATE_UNKNOWN; int error; ASSERT3S(spa_config_held(spa, SCL_STATE, RW_READER), ==, SCL_STATE); ASSERT(vd->vdev_ops->vdev_op_leaf); /* Calling vdev_online will initialize the new metaslabs */ spa_config_exit(spa, SCL_STATE, spa); error = vdev_online(spa, guid, ZFS_ONLINE_EXPAND, &newstate); spa_config_enter(spa, SCL_STATE, spa, RW_READER); /* * If vdev_online returned an error or the underlying vdev_open * failed then we abort the expand. The only way to know that * vdev_open fails is by checking the returned newstate. */ if (error || newstate != VDEV_STATE_HEALTHY) { if (ztest_opts.zo_verbose >= 5) { (void) printf("Unable to expand vdev, state %u, " "error %d\n", newstate, error); } return (vd); } ASSERT3U(newstate, ==, VDEV_STATE_HEALTHY); /* * Since we dropped the lock we need to ensure that we're * still talking to the original vdev. It's possible this * vdev may have been detached/replaced while we were * trying to online it. */ if (generation != spa->spa_config_generation) { if (ztest_opts.zo_verbose >= 5) { (void) printf("vdev configuration has changed, " "guid %"PRIu64", state %"PRIu64", " "expected gen %"PRIu64", got gen %"PRIu64"\n", guid, tvd->vdev_state, generation, spa->spa_config_generation); } return (vd); } return (NULL); } /* * Traverse the vdev tree calling the supplied function. * We continue to walk the tree until we either have walked all * children or we receive a non-NULL return from the callback. * If a NULL callback is passed, then we just return back the first * leaf vdev we encounter. */ static vdev_t * vdev_walk_tree(vdev_t *vd, vdev_t *(*func)(vdev_t *, void *), void *arg) { uint_t c; if (vd->vdev_ops->vdev_op_leaf) { if (func == NULL) return (vd); else return (func(vd, arg)); } for (c = 0; c < vd->vdev_children; c++) { vdev_t *cvd = vd->vdev_child[c]; if ((cvd = vdev_walk_tree(cvd, func, arg)) != NULL) return (cvd); } return (NULL); } /* * Verify that dynamic LUN growth works as expected. */ void ztest_vdev_LUN_growth(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; spa_t *spa = ztest_spa; vdev_t *vd, *tvd; metaslab_class_t *mc; metaslab_group_t *mg; size_t psize, newsize; uint64_t top; uint64_t old_class_space, new_class_space, old_ms_count, new_ms_count; mutex_enter(&ztest_checkpoint_lock); mutex_enter(&ztest_vdev_lock); spa_config_enter(spa, SCL_STATE, spa, RW_READER); /* * If there is a vdev removal in progress, it could complete while * we are running, in which case we would not be able to verify * that the metaslab_class space increased (because it decreases * when the device removal completes). */ if (ztest_device_removal_active) { spa_config_exit(spa, SCL_STATE, spa); mutex_exit(&ztest_vdev_lock); mutex_exit(&ztest_checkpoint_lock); return; } top = ztest_random_vdev_top(spa, B_TRUE); tvd = spa->spa_root_vdev->vdev_child[top]; mg = tvd->vdev_mg; mc = mg->mg_class; old_ms_count = tvd->vdev_ms_count; old_class_space = metaslab_class_get_space(mc); /* * Determine the size of the first leaf vdev associated with * our top-level device. */ vd = vdev_walk_tree(tvd, NULL, NULL); ASSERT3P(vd, !=, NULL); ASSERT(vd->vdev_ops->vdev_op_leaf); psize = vd->vdev_psize; /* * We only try to expand the vdev if it's healthy, less than 4x its * original size, and it has a valid psize. */ if (tvd->vdev_state != VDEV_STATE_HEALTHY || psize == 0 || psize >= 4 * ztest_opts.zo_vdev_size) { spa_config_exit(spa, SCL_STATE, spa); mutex_exit(&ztest_vdev_lock); mutex_exit(&ztest_checkpoint_lock); return; } ASSERT3U(psize, >, 0); newsize = psize + MAX(psize / 8, SPA_MAXBLOCKSIZE); ASSERT3U(newsize, >, psize); if (ztest_opts.zo_verbose >= 6) { (void) printf("Expanding LUN %s from %lu to %lu\n", vd->vdev_path, (ulong_t)psize, (ulong_t)newsize); } /* * Growing the vdev is a two step process: * 1). expand the physical size (i.e. relabel) * 2). online the vdev to create the new metaslabs */ if (vdev_walk_tree(tvd, grow_vdev, &newsize) != NULL || vdev_walk_tree(tvd, online_vdev, NULL) != NULL || tvd->vdev_state != VDEV_STATE_HEALTHY) { if (ztest_opts.zo_verbose >= 5) { (void) printf("Could not expand LUN because " "the vdev configuration changed.\n"); } spa_config_exit(spa, SCL_STATE, spa); mutex_exit(&ztest_vdev_lock); mutex_exit(&ztest_checkpoint_lock); return; } spa_config_exit(spa, SCL_STATE, spa); /* * Expanding the LUN will update the config asynchronously, * thus we must wait for the async thread to complete any * pending tasks before proceeding. */ for (;;) { boolean_t done; mutex_enter(&spa->spa_async_lock); done = (spa->spa_async_thread == NULL && !spa->spa_async_tasks); mutex_exit(&spa->spa_async_lock); if (done) break; txg_wait_synced(spa_get_dsl(spa), 0); (void) poll(NULL, 0, 100); } spa_config_enter(spa, SCL_STATE, spa, RW_READER); tvd = spa->spa_root_vdev->vdev_child[top]; new_ms_count = tvd->vdev_ms_count; new_class_space = metaslab_class_get_space(mc); if (tvd->vdev_mg != mg || mg->mg_class != mc) { if (ztest_opts.zo_verbose >= 5) { (void) printf("Could not verify LUN expansion due to " "intervening vdev offline or remove.\n"); } spa_config_exit(spa, SCL_STATE, spa); mutex_exit(&ztest_vdev_lock); mutex_exit(&ztest_checkpoint_lock); return; } /* * Make sure we were able to grow the vdev. */ if (new_ms_count <= old_ms_count) { fatal(B_FALSE, "LUN expansion failed: ms_count %"PRIu64" < %"PRIu64"\n", old_ms_count, new_ms_count); } /* * Make sure we were able to grow the pool. */ if (new_class_space <= old_class_space) { fatal(B_FALSE, "LUN expansion failed: class_space %"PRIu64" < %"PRIu64"\n", old_class_space, new_class_space); } if (ztest_opts.zo_verbose >= 5) { char oldnumbuf[NN_NUMBUF_SZ], newnumbuf[NN_NUMBUF_SZ]; nicenum(old_class_space, oldnumbuf, sizeof (oldnumbuf)); nicenum(new_class_space, newnumbuf, sizeof (newnumbuf)); (void) printf("%s grew from %s to %s\n", spa->spa_name, oldnumbuf, newnumbuf); } spa_config_exit(spa, SCL_STATE, spa); mutex_exit(&ztest_vdev_lock); mutex_exit(&ztest_checkpoint_lock); } /* * Verify that dmu_objset_{create,destroy,open,close} work as expected. */ static void ztest_objset_create_cb(objset_t *os, void *arg, cred_t *cr, dmu_tx_t *tx) { (void) arg, (void) cr; /* * Create the objects common to all ztest datasets. */ VERIFY0(zap_create_claim(os, ZTEST_DIROBJ, DMU_OT_ZAP_OTHER, DMU_OT_NONE, 0, tx)); } static int ztest_dataset_create(char *dsname) { int err; uint64_t rand; dsl_crypto_params_t *dcp = NULL; /* * 50% of the time, we create encrypted datasets * using a random cipher suite and a hard-coded * wrapping key. */ rand = ztest_random(2); if (rand != 0) { nvlist_t *crypto_args = fnvlist_alloc(); nvlist_t *props = fnvlist_alloc(); /* slight bias towards the default cipher suite */ rand = ztest_random(ZIO_CRYPT_FUNCTIONS); if (rand < ZIO_CRYPT_AES_128_CCM) rand = ZIO_CRYPT_ON; fnvlist_add_uint64(props, zfs_prop_to_name(ZFS_PROP_ENCRYPTION), rand); fnvlist_add_uint8_array(crypto_args, "wkeydata", (uint8_t *)ztest_wkeydata, WRAPPING_KEY_LEN); /* * These parameters aren't really used by the kernel. They * are simply stored so that userspace knows how to load * the wrapping key. */ fnvlist_add_uint64(props, zfs_prop_to_name(ZFS_PROP_KEYFORMAT), ZFS_KEYFORMAT_RAW); fnvlist_add_string(props, zfs_prop_to_name(ZFS_PROP_KEYLOCATION), "prompt"); fnvlist_add_uint64(props, zfs_prop_to_name(ZFS_PROP_PBKDF2_SALT), 0ULL); fnvlist_add_uint64(props, zfs_prop_to_name(ZFS_PROP_PBKDF2_ITERS), 0ULL); VERIFY0(dsl_crypto_params_create_nvlist(DCP_CMD_NONE, props, crypto_args, &dcp)); /* * Cycle through all available encryption implementations * to verify interoperability. */ VERIFY0(gcm_impl_set("cycle")); VERIFY0(aes_impl_set("cycle")); fnvlist_free(crypto_args); fnvlist_free(props); } err = dmu_objset_create(dsname, DMU_OST_OTHER, 0, dcp, ztest_objset_create_cb, NULL); dsl_crypto_params_free(dcp, !!err); rand = ztest_random(100); if (err || rand < 80) return (err); if (ztest_opts.zo_verbose >= 5) (void) printf("Setting dataset %s to sync always\n", dsname); return (ztest_dsl_prop_set_uint64(dsname, ZFS_PROP_SYNC, ZFS_SYNC_ALWAYS, B_FALSE)); } static int ztest_objset_destroy_cb(const char *name, void *arg) { (void) arg; objset_t *os; dmu_object_info_t doi; int error; /* * Verify that the dataset contains a directory object. */ VERIFY0(ztest_dmu_objset_own(name, DMU_OST_OTHER, B_TRUE, B_TRUE, FTAG, &os)); error = dmu_object_info(os, ZTEST_DIROBJ, &doi); if (error != ENOENT) { /* We could have crashed in the middle of destroying it */ ASSERT0(error); ASSERT3U(doi.doi_type, ==, DMU_OT_ZAP_OTHER); ASSERT3S(doi.doi_physical_blocks_512, >=, 0); } dmu_objset_disown(os, B_TRUE, FTAG); /* * Destroy the dataset. */ if (strchr(name, '@') != NULL) { VERIFY0(dsl_destroy_snapshot(name, B_TRUE)); } else { error = dsl_destroy_head(name); if (error == ENOSPC) { /* There could be checkpoint or insufficient slop */ ztest_record_enospc(FTAG); } else if (error != EBUSY) { /* There could be a hold on this dataset */ ASSERT0(error); } } return (0); } static boolean_t ztest_snapshot_create(char *osname, uint64_t id) { char snapname[ZFS_MAX_DATASET_NAME_LEN]; int error; (void) snprintf(snapname, sizeof (snapname), "%"PRIu64"", id); error = dmu_objset_snapshot_one(osname, snapname); if (error == ENOSPC) { ztest_record_enospc(FTAG); return (B_FALSE); } if (error != 0 && error != EEXIST) { fatal(B_FALSE, "ztest_snapshot_create(%s@%s) = %d", osname, snapname, error); } return (B_TRUE); } static boolean_t ztest_snapshot_destroy(char *osname, uint64_t id) { char snapname[ZFS_MAX_DATASET_NAME_LEN]; int error; (void) snprintf(snapname, sizeof (snapname), "%s@%"PRIu64"", osname, id); error = dsl_destroy_snapshot(snapname, B_FALSE); if (error != 0 && error != ENOENT) fatal(B_FALSE, "ztest_snapshot_destroy(%s) = %d", snapname, error); return (B_TRUE); } void ztest_dmu_objset_create_destroy(ztest_ds_t *zd, uint64_t id) { (void) zd; ztest_ds_t *zdtmp; int iters; int error; objset_t *os, *os2; char name[ZFS_MAX_DATASET_NAME_LEN]; zilog_t *zilog; int i; zdtmp = umem_alloc(sizeof (ztest_ds_t), UMEM_NOFAIL); (void) pthread_rwlock_rdlock(&ztest_name_lock); (void) snprintf(name, sizeof (name), "%s/temp_%"PRIu64"", ztest_opts.zo_pool, id); /* * If this dataset exists from a previous run, process its replay log * half of the time. If we don't replay it, then dsl_destroy_head() * (invoked from ztest_objset_destroy_cb()) should just throw it away. */ if (ztest_random(2) == 0 && ztest_dmu_objset_own(name, DMU_OST_OTHER, B_FALSE, B_TRUE, FTAG, &os) == 0) { ztest_zd_init(zdtmp, NULL, os); zil_replay(os, zdtmp, ztest_replay_vector); ztest_zd_fini(zdtmp); dmu_objset_disown(os, B_TRUE, FTAG); } /* * There may be an old instance of the dataset we're about to * create lying around from a previous run. If so, destroy it * and all of its snapshots. */ (void) dmu_objset_find(name, ztest_objset_destroy_cb, NULL, DS_FIND_CHILDREN | DS_FIND_SNAPSHOTS); /* * Verify that the destroyed dataset is no longer in the namespace. */ VERIFY3U(ENOENT, ==, ztest_dmu_objset_own(name, DMU_OST_OTHER, B_TRUE, B_TRUE, FTAG, &os)); /* * Verify that we can create a new dataset. */ error = ztest_dataset_create(name); if (error) { if (error == ENOSPC) { ztest_record_enospc(FTAG); goto out; } fatal(B_FALSE, "dmu_objset_create(%s) = %d", name, error); } VERIFY0(ztest_dmu_objset_own(name, DMU_OST_OTHER, B_FALSE, B_TRUE, FTAG, &os)); ztest_zd_init(zdtmp, NULL, os); /* * Open the intent log for it. */ zilog = zil_open(os, ztest_get_data); /* * Put some objects in there, do a little I/O to them, * and randomly take a couple of snapshots along the way. */ iters = ztest_random(5); for (i = 0; i < iters; i++) { ztest_dmu_object_alloc_free(zdtmp, id); if (ztest_random(iters) == 0) (void) ztest_snapshot_create(name, i); } /* * Verify that we cannot create an existing dataset. */ VERIFY3U(EEXIST, ==, dmu_objset_create(name, DMU_OST_OTHER, 0, NULL, NULL, NULL)); /* * Verify that we can hold an objset that is also owned. */ VERIFY0(dmu_objset_hold(name, FTAG, &os2)); dmu_objset_rele(os2, FTAG); /* * Verify that we cannot own an objset that is already owned. */ VERIFY3U(EBUSY, ==, ztest_dmu_objset_own(name, DMU_OST_OTHER, B_FALSE, B_TRUE, FTAG, &os2)); zil_close(zilog); dmu_objset_disown(os, B_TRUE, FTAG); ztest_zd_fini(zdtmp); out: (void) pthread_rwlock_unlock(&ztest_name_lock); umem_free(zdtmp, sizeof (ztest_ds_t)); } /* * Verify that dmu_snapshot_{create,destroy,open,close} work as expected. */ void ztest_dmu_snapshot_create_destroy(ztest_ds_t *zd, uint64_t id) { (void) pthread_rwlock_rdlock(&ztest_name_lock); (void) ztest_snapshot_destroy(zd->zd_name, id); (void) ztest_snapshot_create(zd->zd_name, id); (void) pthread_rwlock_unlock(&ztest_name_lock); } /* * Cleanup non-standard snapshots and clones. */ static void ztest_dsl_dataset_cleanup(char *osname, uint64_t id) { char *snap1name; char *clone1name; char *snap2name; char *clone2name; char *snap3name; int error; snap1name = umem_alloc(ZFS_MAX_DATASET_NAME_LEN, UMEM_NOFAIL); clone1name = umem_alloc(ZFS_MAX_DATASET_NAME_LEN, UMEM_NOFAIL); snap2name = umem_alloc(ZFS_MAX_DATASET_NAME_LEN, UMEM_NOFAIL); clone2name = umem_alloc(ZFS_MAX_DATASET_NAME_LEN, UMEM_NOFAIL); snap3name = umem_alloc(ZFS_MAX_DATASET_NAME_LEN, UMEM_NOFAIL); (void) snprintf(snap1name, ZFS_MAX_DATASET_NAME_LEN, "%s@s1_%"PRIu64"", osname, id); (void) snprintf(clone1name, ZFS_MAX_DATASET_NAME_LEN, "%s/c1_%"PRIu64"", osname, id); (void) snprintf(snap2name, ZFS_MAX_DATASET_NAME_LEN, "%s@s2_%"PRIu64"", clone1name, id); (void) snprintf(clone2name, ZFS_MAX_DATASET_NAME_LEN, "%s/c2_%"PRIu64"", osname, id); (void) snprintf(snap3name, ZFS_MAX_DATASET_NAME_LEN, "%s@s3_%"PRIu64"", clone1name, id); error = dsl_destroy_head(clone2name); if (error && error != ENOENT) fatal(B_FALSE, "dsl_destroy_head(%s) = %d", clone2name, error); error = dsl_destroy_snapshot(snap3name, B_FALSE); if (error && error != ENOENT) fatal(B_FALSE, "dsl_destroy_snapshot(%s) = %d", snap3name, error); error = dsl_destroy_snapshot(snap2name, B_FALSE); if (error && error != ENOENT) fatal(B_FALSE, "dsl_destroy_snapshot(%s) = %d", snap2name, error); error = dsl_destroy_head(clone1name); if (error && error != ENOENT) fatal(B_FALSE, "dsl_destroy_head(%s) = %d", clone1name, error); error = dsl_destroy_snapshot(snap1name, B_FALSE); if (error && error != ENOENT) fatal(B_FALSE, "dsl_destroy_snapshot(%s) = %d", snap1name, error); umem_free(snap1name, ZFS_MAX_DATASET_NAME_LEN); umem_free(clone1name, ZFS_MAX_DATASET_NAME_LEN); umem_free(snap2name, ZFS_MAX_DATASET_NAME_LEN); umem_free(clone2name, ZFS_MAX_DATASET_NAME_LEN); umem_free(snap3name, ZFS_MAX_DATASET_NAME_LEN); } /* * Verify dsl_dataset_promote handles EBUSY */ void ztest_dsl_dataset_promote_busy(ztest_ds_t *zd, uint64_t id) { objset_t *os; char *snap1name; char *clone1name; char *snap2name; char *clone2name; char *snap3name; char *osname = zd->zd_name; int error; snap1name = umem_alloc(ZFS_MAX_DATASET_NAME_LEN, UMEM_NOFAIL); clone1name = umem_alloc(ZFS_MAX_DATASET_NAME_LEN, UMEM_NOFAIL); snap2name = umem_alloc(ZFS_MAX_DATASET_NAME_LEN, UMEM_NOFAIL); clone2name = umem_alloc(ZFS_MAX_DATASET_NAME_LEN, UMEM_NOFAIL); snap3name = umem_alloc(ZFS_MAX_DATASET_NAME_LEN, UMEM_NOFAIL); (void) pthread_rwlock_rdlock(&ztest_name_lock); ztest_dsl_dataset_cleanup(osname, id); (void) snprintf(snap1name, ZFS_MAX_DATASET_NAME_LEN, "%s@s1_%"PRIu64"", osname, id); (void) snprintf(clone1name, ZFS_MAX_DATASET_NAME_LEN, "%s/c1_%"PRIu64"", osname, id); (void) snprintf(snap2name, ZFS_MAX_DATASET_NAME_LEN, "%s@s2_%"PRIu64"", clone1name, id); (void) snprintf(clone2name, ZFS_MAX_DATASET_NAME_LEN, "%s/c2_%"PRIu64"", osname, id); (void) snprintf(snap3name, ZFS_MAX_DATASET_NAME_LEN, "%s@s3_%"PRIu64"", clone1name, id); error = dmu_objset_snapshot_one(osname, strchr(snap1name, '@') + 1); if (error && error != EEXIST) { if (error == ENOSPC) { ztest_record_enospc(FTAG); goto out; } fatal(B_FALSE, "dmu_take_snapshot(%s) = %d", snap1name, error); } error = dmu_objset_clone(clone1name, snap1name); if (error) { if (error == ENOSPC) { ztest_record_enospc(FTAG); goto out; } fatal(B_FALSE, "dmu_objset_create(%s) = %d", clone1name, error); } error = dmu_objset_snapshot_one(clone1name, strchr(snap2name, '@') + 1); if (error && error != EEXIST) { if (error == ENOSPC) { ztest_record_enospc(FTAG); goto out; } fatal(B_FALSE, "dmu_open_snapshot(%s) = %d", snap2name, error); } error = dmu_objset_snapshot_one(clone1name, strchr(snap3name, '@') + 1); if (error && error != EEXIST) { if (error == ENOSPC) { ztest_record_enospc(FTAG); goto out; } fatal(B_FALSE, "dmu_open_snapshot(%s) = %d", snap3name, error); } error = dmu_objset_clone(clone2name, snap3name); if (error) { if (error == ENOSPC) { ztest_record_enospc(FTAG); goto out; } fatal(B_FALSE, "dmu_objset_create(%s) = %d", clone2name, error); } error = ztest_dmu_objset_own(snap2name, DMU_OST_ANY, B_TRUE, B_TRUE, FTAG, &os); if (error) fatal(B_FALSE, "dmu_objset_own(%s) = %d", snap2name, error); error = dsl_dataset_promote(clone2name, NULL); if (error == ENOSPC) { dmu_objset_disown(os, B_TRUE, FTAG); ztest_record_enospc(FTAG); goto out; } if (error != EBUSY) fatal(B_FALSE, "dsl_dataset_promote(%s), %d, not EBUSY", clone2name, error); dmu_objset_disown(os, B_TRUE, FTAG); out: ztest_dsl_dataset_cleanup(osname, id); (void) pthread_rwlock_unlock(&ztest_name_lock); umem_free(snap1name, ZFS_MAX_DATASET_NAME_LEN); umem_free(clone1name, ZFS_MAX_DATASET_NAME_LEN); umem_free(snap2name, ZFS_MAX_DATASET_NAME_LEN); umem_free(clone2name, ZFS_MAX_DATASET_NAME_LEN); umem_free(snap3name, ZFS_MAX_DATASET_NAME_LEN); } #undef OD_ARRAY_SIZE #define OD_ARRAY_SIZE 4 /* * Verify that dmu_object_{alloc,free} work as expected. */ void ztest_dmu_object_alloc_free(ztest_ds_t *zd, uint64_t id) { ztest_od_t *od; int batchsize; int size; int b; size = sizeof (ztest_od_t) * OD_ARRAY_SIZE; od = umem_alloc(size, UMEM_NOFAIL); batchsize = OD_ARRAY_SIZE; for (b = 0; b < batchsize; b++) ztest_od_init(od + b, id, FTAG, b, DMU_OT_UINT64_OTHER, 0, 0, 0); /* * Destroy the previous batch of objects, create a new batch, * and do some I/O on the new objects. */ if (ztest_object_init(zd, od, size, B_TRUE) != 0) return; while (ztest_random(4 * batchsize) != 0) ztest_io(zd, od[ztest_random(batchsize)].od_object, ztest_random(ZTEST_RANGE_LOCKS) << SPA_MAXBLOCKSHIFT); umem_free(od, size); } /* * Rewind the global allocator to verify object allocation backfilling. */ void ztest_dmu_object_next_chunk(ztest_ds_t *zd, uint64_t id) { (void) id; objset_t *os = zd->zd_os; int dnodes_per_chunk = 1 << dmu_object_alloc_chunk_shift; uint64_t object; /* * Rewind the global allocator randomly back to a lower object number * to force backfilling and reclamation of recently freed dnodes. */ mutex_enter(&os->os_obj_lock); object = ztest_random(os->os_obj_next_chunk); os->os_obj_next_chunk = P2ALIGN(object, dnodes_per_chunk); mutex_exit(&os->os_obj_lock); } #undef OD_ARRAY_SIZE #define OD_ARRAY_SIZE 2 /* * Verify that dmu_{read,write} work as expected. */ void ztest_dmu_read_write(ztest_ds_t *zd, uint64_t id) { int size; ztest_od_t *od; objset_t *os = zd->zd_os; size = sizeof (ztest_od_t) * OD_ARRAY_SIZE; od = umem_alloc(size, UMEM_NOFAIL); dmu_tx_t *tx; int freeit, error; uint64_t i, n, s, txg; bufwad_t *packbuf, *bigbuf, *pack, *bigH, *bigT; uint64_t packobj, packoff, packsize, bigobj, bigoff, bigsize; uint64_t chunksize = (1000 + ztest_random(1000)) * sizeof (uint64_t); uint64_t regions = 997; uint64_t stride = 123456789ULL; uint64_t width = 40; int free_percent = 5; /* * This test uses two objects, packobj and bigobj, that are always * updated together (i.e. in the same tx) so that their contents are * in sync and can be compared. Their contents relate to each other * in a simple way: packobj is a dense array of 'bufwad' structures, * while bigobj is a sparse array of the same bufwads. Specifically, * for any index n, there are three bufwads that should be identical: * * packobj, at offset n * sizeof (bufwad_t) * bigobj, at the head of the nth chunk * bigobj, at the tail of the nth chunk * * The chunk size is arbitrary. It doesn't have to be a power of two, * and it doesn't have any relation to the object blocksize. * The only requirement is that it can hold at least two bufwads. * * Normally, we write the bufwad to each of these locations. * However, free_percent of the time we instead write zeroes to * packobj and perform a dmu_free_range() on bigobj. By comparing * bigobj to packobj, we can verify that the DMU is correctly * tracking which parts of an object are allocated and free, * and that the contents of the allocated blocks are correct. */ /* * Read the directory info. If it's the first time, set things up. */ ztest_od_init(od, id, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0, chunksize); ztest_od_init(od + 1, id, FTAG, 1, DMU_OT_UINT64_OTHER, 0, 0, chunksize); if (ztest_object_init(zd, od, size, B_FALSE) != 0) { umem_free(od, size); return; } bigobj = od[0].od_object; packobj = od[1].od_object; chunksize = od[0].od_gen; ASSERT3U(chunksize, ==, od[1].od_gen); /* * Prefetch a random chunk of the big object. * Our aim here is to get some async reads in flight * for blocks that we may free below; the DMU should * handle this race correctly. */ n = ztest_random(regions) * stride + ztest_random(width); s = 1 + ztest_random(2 * width - 1); dmu_prefetch(os, bigobj, 0, n * chunksize, s * chunksize, ZIO_PRIORITY_SYNC_READ); /* * Pick a random index and compute the offsets into packobj and bigobj. */ n = ztest_random(regions) * stride + ztest_random(width); s = 1 + ztest_random(width - 1); packoff = n * sizeof (bufwad_t); packsize = s * sizeof (bufwad_t); bigoff = n * chunksize; bigsize = s * chunksize; packbuf = umem_alloc(packsize, UMEM_NOFAIL); bigbuf = umem_alloc(bigsize, UMEM_NOFAIL); /* * free_percent of the time, free a range of bigobj rather than * overwriting it. */ freeit = (ztest_random(100) < free_percent); /* * Read the current contents of our objects. */ error = dmu_read(os, packobj, packoff, packsize, packbuf, DMU_READ_PREFETCH); ASSERT0(error); error = dmu_read(os, bigobj, bigoff, bigsize, bigbuf, DMU_READ_PREFETCH); ASSERT0(error); /* * Get a tx for the mods to both packobj and bigobj. */ tx = dmu_tx_create(os); dmu_tx_hold_write(tx, packobj, packoff, packsize); if (freeit) dmu_tx_hold_free(tx, bigobj, bigoff, bigsize); else dmu_tx_hold_write(tx, bigobj, bigoff, bigsize); /* This accounts for setting the checksum/compression. */ dmu_tx_hold_bonus(tx, bigobj); txg = ztest_tx_assign(tx, TXG_MIGHTWAIT, FTAG); if (txg == 0) { umem_free(packbuf, packsize); umem_free(bigbuf, bigsize); umem_free(od, size); return; } enum zio_checksum cksum; do { cksum = (enum zio_checksum) ztest_random_dsl_prop(ZFS_PROP_CHECKSUM); } while (cksum >= ZIO_CHECKSUM_LEGACY_FUNCTIONS); dmu_object_set_checksum(os, bigobj, cksum, tx); enum zio_compress comp; do { comp = (enum zio_compress) ztest_random_dsl_prop(ZFS_PROP_COMPRESSION); } while (comp >= ZIO_COMPRESS_LEGACY_FUNCTIONS); dmu_object_set_compress(os, bigobj, comp, tx); /* * For each index from n to n + s, verify that the existing bufwad * in packobj matches the bufwads at the head and tail of the * corresponding chunk in bigobj. Then update all three bufwads * with the new values we want to write out. */ for (i = 0; i < s; i++) { /* LINTED */ pack = (bufwad_t *)((char *)packbuf + i * sizeof (bufwad_t)); /* LINTED */ bigH = (bufwad_t *)((char *)bigbuf + i * chunksize); /* LINTED */ bigT = (bufwad_t *)((char *)bigH + chunksize) - 1; ASSERT3U((uintptr_t)bigH - (uintptr_t)bigbuf, <, bigsize); ASSERT3U((uintptr_t)bigT - (uintptr_t)bigbuf, <, bigsize); if (pack->bw_txg > txg) fatal(B_FALSE, "future leak: got %"PRIx64", open txg is %"PRIx64"", pack->bw_txg, txg); if (pack->bw_data != 0 && pack->bw_index != n + i) fatal(B_FALSE, "wrong index: " "got %"PRIx64", wanted %"PRIx64"+%"PRIx64"", pack->bw_index, n, i); if (bcmp(pack, bigH, sizeof (bufwad_t)) != 0) fatal(B_FALSE, "pack/bigH mismatch in %p/%p", pack, bigH); if (bcmp(pack, bigT, sizeof (bufwad_t)) != 0) fatal(B_FALSE, "pack/bigT mismatch in %p/%p", pack, bigT); if (freeit) { bzero(pack, sizeof (bufwad_t)); } else { pack->bw_index = n + i; pack->bw_txg = txg; pack->bw_data = 1 + ztest_random(-2ULL); } *bigH = *pack; *bigT = *pack; } /* * We've verified all the old bufwads, and made new ones. * Now write them out. */ dmu_write(os, packobj, packoff, packsize, packbuf, tx); if (freeit) { if (ztest_opts.zo_verbose >= 7) { (void) printf("freeing offset %"PRIx64" size %"PRIx64"" " txg %"PRIx64"\n", bigoff, bigsize, txg); } VERIFY0(dmu_free_range(os, bigobj, bigoff, bigsize, tx)); } else { if (ztest_opts.zo_verbose >= 7) { (void) printf("writing offset %"PRIx64" size %"PRIx64"" " txg %"PRIx64"\n", bigoff, bigsize, txg); } dmu_write(os, bigobj, bigoff, bigsize, bigbuf, tx); } dmu_tx_commit(tx); /* * Sanity check the stuff we just wrote. */ { void *packcheck = umem_alloc(packsize, UMEM_NOFAIL); void *bigcheck = umem_alloc(bigsize, UMEM_NOFAIL); VERIFY0(dmu_read(os, packobj, packoff, packsize, packcheck, DMU_READ_PREFETCH)); VERIFY0(dmu_read(os, bigobj, bigoff, bigsize, bigcheck, DMU_READ_PREFETCH)); ASSERT0(bcmp(packbuf, packcheck, packsize)); ASSERT0(bcmp(bigbuf, bigcheck, bigsize)); umem_free(packcheck, packsize); umem_free(bigcheck, bigsize); } umem_free(packbuf, packsize); umem_free(bigbuf, bigsize); umem_free(od, size); } static void compare_and_update_pbbufs(uint64_t s, bufwad_t *packbuf, bufwad_t *bigbuf, uint64_t bigsize, uint64_t n, uint64_t chunksize, uint64_t txg) { uint64_t i; bufwad_t *pack; bufwad_t *bigH; bufwad_t *bigT; /* * For each index from n to n + s, verify that the existing bufwad * in packobj matches the bufwads at the head and tail of the * corresponding chunk in bigobj. Then update all three bufwads * with the new values we want to write out. */ for (i = 0; i < s; i++) { /* LINTED */ pack = (bufwad_t *)((char *)packbuf + i * sizeof (bufwad_t)); /* LINTED */ bigH = (bufwad_t *)((char *)bigbuf + i * chunksize); /* LINTED */ bigT = (bufwad_t *)((char *)bigH + chunksize) - 1; ASSERT3U((uintptr_t)bigH - (uintptr_t)bigbuf, <, bigsize); ASSERT3U((uintptr_t)bigT - (uintptr_t)bigbuf, <, bigsize); if (pack->bw_txg > txg) fatal(B_FALSE, "future leak: got %"PRIx64", open txg is %"PRIx64"", pack->bw_txg, txg); if (pack->bw_data != 0 && pack->bw_index != n + i) fatal(B_FALSE, "wrong index: " "got %"PRIx64", wanted %"PRIx64"+%"PRIx64"", pack->bw_index, n, i); if (bcmp(pack, bigH, sizeof (bufwad_t)) != 0) fatal(B_FALSE, "pack/bigH mismatch in %p/%p", pack, bigH); if (bcmp(pack, bigT, sizeof (bufwad_t)) != 0) fatal(B_FALSE, "pack/bigT mismatch in %p/%p", pack, bigT); pack->bw_index = n + i; pack->bw_txg = txg; pack->bw_data = 1 + ztest_random(-2ULL); *bigH = *pack; *bigT = *pack; } } #undef OD_ARRAY_SIZE #define OD_ARRAY_SIZE 2 void ztest_dmu_read_write_zcopy(ztest_ds_t *zd, uint64_t id) { objset_t *os = zd->zd_os; ztest_od_t *od; dmu_tx_t *tx; uint64_t i; int error; int size; uint64_t n, s, txg; bufwad_t *packbuf, *bigbuf; uint64_t packobj, packoff, packsize, bigobj, bigoff, bigsize; uint64_t blocksize = ztest_random_blocksize(); uint64_t chunksize = blocksize; uint64_t regions = 997; uint64_t stride = 123456789ULL; uint64_t width = 9; dmu_buf_t *bonus_db; arc_buf_t **bigbuf_arcbufs; dmu_object_info_t doi; size = sizeof (ztest_od_t) * OD_ARRAY_SIZE; od = umem_alloc(size, UMEM_NOFAIL); /* * This test uses two objects, packobj and bigobj, that are always * updated together (i.e. in the same tx) so that their contents are * in sync and can be compared. Their contents relate to each other * in a simple way: packobj is a dense array of 'bufwad' structures, * while bigobj is a sparse array of the same bufwads. Specifically, * for any index n, there are three bufwads that should be identical: * * packobj, at offset n * sizeof (bufwad_t) * bigobj, at the head of the nth chunk * bigobj, at the tail of the nth chunk * * The chunk size is set equal to bigobj block size so that * dmu_assign_arcbuf_by_dbuf() can be tested for object updates. */ /* * Read the directory info. If it's the first time, set things up. */ ztest_od_init(od, id, FTAG, 0, DMU_OT_UINT64_OTHER, blocksize, 0, 0); ztest_od_init(od + 1, id, FTAG, 1, DMU_OT_UINT64_OTHER, 0, 0, chunksize); if (ztest_object_init(zd, od, size, B_FALSE) != 0) { umem_free(od, size); return; } bigobj = od[0].od_object; packobj = od[1].od_object; blocksize = od[0].od_blocksize; chunksize = blocksize; ASSERT3U(chunksize, ==, od[1].od_gen); VERIFY0(dmu_object_info(os, bigobj, &doi)); VERIFY(ISP2(doi.doi_data_block_size)); VERIFY3U(chunksize, ==, doi.doi_data_block_size); VERIFY3U(chunksize, >=, 2 * sizeof (bufwad_t)); /* * Pick a random index and compute the offsets into packobj and bigobj. */ n = ztest_random(regions) * stride + ztest_random(width); s = 1 + ztest_random(width - 1); packoff = n * sizeof (bufwad_t); packsize = s * sizeof (bufwad_t); bigoff = n * chunksize; bigsize = s * chunksize; packbuf = umem_zalloc(packsize, UMEM_NOFAIL); bigbuf = umem_zalloc(bigsize, UMEM_NOFAIL); VERIFY0(dmu_bonus_hold(os, bigobj, FTAG, &bonus_db)); bigbuf_arcbufs = umem_zalloc(2 * s * sizeof (arc_buf_t *), UMEM_NOFAIL); /* * Iteration 0 test zcopy for DB_UNCACHED dbufs. * Iteration 1 test zcopy to already referenced dbufs. * Iteration 2 test zcopy to dirty dbuf in the same txg. * Iteration 3 test zcopy to dbuf dirty in previous txg. * Iteration 4 test zcopy when dbuf is no longer dirty. * Iteration 5 test zcopy when it can't be done. * Iteration 6 one more zcopy write. */ for (i = 0; i < 7; i++) { uint64_t j; uint64_t off; /* * In iteration 5 (i == 5) use arcbufs * that don't match bigobj blksz to test * dmu_assign_arcbuf_by_dbuf() when it can't directly * assign an arcbuf to a dbuf. */ for (j = 0; j < s; j++) { if (i != 5 || chunksize < (SPA_MINBLOCKSIZE * 2)) { bigbuf_arcbufs[j] = dmu_request_arcbuf(bonus_db, chunksize); } else { bigbuf_arcbufs[2 * j] = dmu_request_arcbuf(bonus_db, chunksize / 2); bigbuf_arcbufs[2 * j + 1] = dmu_request_arcbuf(bonus_db, chunksize / 2); } } /* * Get a tx for the mods to both packobj and bigobj. */ tx = dmu_tx_create(os); dmu_tx_hold_write(tx, packobj, packoff, packsize); dmu_tx_hold_write(tx, bigobj, bigoff, bigsize); txg = ztest_tx_assign(tx, TXG_MIGHTWAIT, FTAG); if (txg == 0) { umem_free(packbuf, packsize); umem_free(bigbuf, bigsize); for (j = 0; j < s; j++) { if (i != 5 || chunksize < (SPA_MINBLOCKSIZE * 2)) { dmu_return_arcbuf(bigbuf_arcbufs[j]); } else { dmu_return_arcbuf( bigbuf_arcbufs[2 * j]); dmu_return_arcbuf( bigbuf_arcbufs[2 * j + 1]); } } umem_free(bigbuf_arcbufs, 2 * s * sizeof (arc_buf_t *)); umem_free(od, size); dmu_buf_rele(bonus_db, FTAG); return; } /* * 50% of the time don't read objects in the 1st iteration to * test dmu_assign_arcbuf_by_dbuf() for the case when there are * no existing dbufs for the specified offsets. */ if (i != 0 || ztest_random(2) != 0) { error = dmu_read(os, packobj, packoff, packsize, packbuf, DMU_READ_PREFETCH); ASSERT0(error); error = dmu_read(os, bigobj, bigoff, bigsize, bigbuf, DMU_READ_PREFETCH); ASSERT0(error); } compare_and_update_pbbufs(s, packbuf, bigbuf, bigsize, n, chunksize, txg); /* * We've verified all the old bufwads, and made new ones. * Now write them out. */ dmu_write(os, packobj, packoff, packsize, packbuf, tx); if (ztest_opts.zo_verbose >= 7) { (void) printf("writing offset %"PRIx64" size %"PRIx64"" " txg %"PRIx64"\n", bigoff, bigsize, txg); } for (off = bigoff, j = 0; j < s; j++, off += chunksize) { dmu_buf_t *dbt; if (i != 5 || chunksize < (SPA_MINBLOCKSIZE * 2)) { bcopy((caddr_t)bigbuf + (off - bigoff), bigbuf_arcbufs[j]->b_data, chunksize); } else { bcopy((caddr_t)bigbuf + (off - bigoff), bigbuf_arcbufs[2 * j]->b_data, chunksize / 2); bcopy((caddr_t)bigbuf + (off - bigoff) + chunksize / 2, bigbuf_arcbufs[2 * j + 1]->b_data, chunksize / 2); } if (i == 1) { VERIFY(dmu_buf_hold(os, bigobj, off, FTAG, &dbt, DMU_READ_NO_PREFETCH) == 0); } if (i != 5 || chunksize < (SPA_MINBLOCKSIZE * 2)) { VERIFY0(dmu_assign_arcbuf_by_dbuf(bonus_db, off, bigbuf_arcbufs[j], tx)); } else { VERIFY0(dmu_assign_arcbuf_by_dbuf(bonus_db, off, bigbuf_arcbufs[2 * j], tx)); VERIFY0(dmu_assign_arcbuf_by_dbuf(bonus_db, off + chunksize / 2, bigbuf_arcbufs[2 * j + 1], tx)); } if (i == 1) { dmu_buf_rele(dbt, FTAG); } } dmu_tx_commit(tx); /* * Sanity check the stuff we just wrote. */ { void *packcheck = umem_alloc(packsize, UMEM_NOFAIL); void *bigcheck = umem_alloc(bigsize, UMEM_NOFAIL); VERIFY0(dmu_read(os, packobj, packoff, packsize, packcheck, DMU_READ_PREFETCH)); VERIFY0(dmu_read(os, bigobj, bigoff, bigsize, bigcheck, DMU_READ_PREFETCH)); ASSERT0(bcmp(packbuf, packcheck, packsize)); ASSERT0(bcmp(bigbuf, bigcheck, bigsize)); umem_free(packcheck, packsize); umem_free(bigcheck, bigsize); } if (i == 2) { txg_wait_open(dmu_objset_pool(os), 0, B_TRUE); } else if (i == 3) { txg_wait_synced(dmu_objset_pool(os), 0); } } dmu_buf_rele(bonus_db, FTAG); umem_free(packbuf, packsize); umem_free(bigbuf, bigsize); umem_free(bigbuf_arcbufs, 2 * s * sizeof (arc_buf_t *)); umem_free(od, size); } void ztest_dmu_write_parallel(ztest_ds_t *zd, uint64_t id) { (void) id; ztest_od_t *od; od = umem_alloc(sizeof (ztest_od_t), UMEM_NOFAIL); uint64_t offset = (1ULL << (ztest_random(20) + 43)) + (ztest_random(ZTEST_RANGE_LOCKS) << SPA_MAXBLOCKSHIFT); /* * Have multiple threads write to large offsets in an object * to verify that parallel writes to an object -- even to the * same blocks within the object -- doesn't cause any trouble. */ ztest_od_init(od, ID_PARALLEL, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), B_FALSE) != 0) return; while (ztest_random(10) != 0) ztest_io(zd, od->od_object, offset); umem_free(od, sizeof (ztest_od_t)); } void ztest_dmu_prealloc(ztest_ds_t *zd, uint64_t id) { ztest_od_t *od; uint64_t offset = (1ULL << (ztest_random(4) + SPA_MAXBLOCKSHIFT)) + (ztest_random(ZTEST_RANGE_LOCKS) << SPA_MAXBLOCKSHIFT); uint64_t count = ztest_random(20) + 1; uint64_t blocksize = ztest_random_blocksize(); void *data; od = umem_alloc(sizeof (ztest_od_t), UMEM_NOFAIL); ztest_od_init(od, id, FTAG, 0, DMU_OT_UINT64_OTHER, blocksize, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), !ztest_random(2)) != 0) { umem_free(od, sizeof (ztest_od_t)); return; } if (ztest_truncate(zd, od->od_object, offset, count * blocksize) != 0) { umem_free(od, sizeof (ztest_od_t)); return; } ztest_prealloc(zd, od->od_object, offset, count * blocksize); data = umem_zalloc(blocksize, UMEM_NOFAIL); while (ztest_random(count) != 0) { uint64_t randoff = offset + (ztest_random(count) * blocksize); if (ztest_write(zd, od->od_object, randoff, blocksize, data) != 0) break; while (ztest_random(4) != 0) ztest_io(zd, od->od_object, randoff); } umem_free(data, blocksize); umem_free(od, sizeof (ztest_od_t)); } /* * Verify that zap_{create,destroy,add,remove,update} work as expected. */ #define ZTEST_ZAP_MIN_INTS 1 #define ZTEST_ZAP_MAX_INTS 4 #define ZTEST_ZAP_MAX_PROPS 1000 void ztest_zap(ztest_ds_t *zd, uint64_t id) { objset_t *os = zd->zd_os; ztest_od_t *od; uint64_t object; uint64_t txg, last_txg; uint64_t value[ZTEST_ZAP_MAX_INTS]; uint64_t zl_ints, zl_intsize, prop; int i, ints; dmu_tx_t *tx; char propname[100], txgname[100]; int error; char *hc[2] = { "s.acl.h", ".s.open.h.hyLZlg" }; od = umem_alloc(sizeof (ztest_od_t), UMEM_NOFAIL); ztest_od_init(od, id, FTAG, 0, DMU_OT_ZAP_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), !ztest_random(2)) != 0) goto out; object = od->od_object; /* * Generate a known hash collision, and verify that * we can lookup and remove both entries. */ tx = dmu_tx_create(os); dmu_tx_hold_zap(tx, object, B_TRUE, NULL); txg = ztest_tx_assign(tx, TXG_MIGHTWAIT, FTAG); if (txg == 0) goto out; for (i = 0; i < 2; i++) { value[i] = i; VERIFY0(zap_add(os, object, hc[i], sizeof (uint64_t), 1, &value[i], tx)); } for (i = 0; i < 2; i++) { VERIFY3U(EEXIST, ==, zap_add(os, object, hc[i], sizeof (uint64_t), 1, &value[i], tx)); VERIFY0( zap_length(os, object, hc[i], &zl_intsize, &zl_ints)); ASSERT3U(zl_intsize, ==, sizeof (uint64_t)); ASSERT3U(zl_ints, ==, 1); } for (i = 0; i < 2; i++) { VERIFY0(zap_remove(os, object, hc[i], tx)); } dmu_tx_commit(tx); /* * Generate a bunch of random entries. */ ints = MAX(ZTEST_ZAP_MIN_INTS, object % ZTEST_ZAP_MAX_INTS); prop = ztest_random(ZTEST_ZAP_MAX_PROPS); (void) sprintf(propname, "prop_%"PRIu64"", prop); (void) sprintf(txgname, "txg_%"PRIu64"", prop); bzero(value, sizeof (value)); last_txg = 0; /* * If these zap entries already exist, validate their contents. */ error = zap_length(os, object, txgname, &zl_intsize, &zl_ints); if (error == 0) { ASSERT3U(zl_intsize, ==, sizeof (uint64_t)); ASSERT3U(zl_ints, ==, 1); VERIFY0(zap_lookup(os, object, txgname, zl_intsize, zl_ints, &last_txg)); VERIFY0(zap_length(os, object, propname, &zl_intsize, &zl_ints)); ASSERT3U(zl_intsize, ==, sizeof (uint64_t)); ASSERT3U(zl_ints, ==, ints); VERIFY0(zap_lookup(os, object, propname, zl_intsize, zl_ints, value)); for (i = 0; i < ints; i++) { ASSERT3U(value[i], ==, last_txg + object + i); } } else { ASSERT3U(error, ==, ENOENT); } /* * Atomically update two entries in our zap object. * The first is named txg_%llu, and contains the txg * in which the property was last updated. The second * is named prop_%llu, and the nth element of its value * should be txg + object + n. */ tx = dmu_tx_create(os); dmu_tx_hold_zap(tx, object, B_TRUE, NULL); txg = ztest_tx_assign(tx, TXG_MIGHTWAIT, FTAG); if (txg == 0) goto out; if (last_txg > txg) fatal(B_FALSE, "zap future leak: old %"PRIu64" new %"PRIu64"", last_txg, txg); for (i = 0; i < ints; i++) value[i] = txg + object + i; VERIFY0(zap_update(os, object, txgname, sizeof (uint64_t), 1, &txg, tx)); VERIFY0(zap_update(os, object, propname, sizeof (uint64_t), ints, value, tx)); dmu_tx_commit(tx); /* * Remove a random pair of entries. */ prop = ztest_random(ZTEST_ZAP_MAX_PROPS); (void) sprintf(propname, "prop_%"PRIu64"", prop); (void) sprintf(txgname, "txg_%"PRIu64"", prop); error = zap_length(os, object, txgname, &zl_intsize, &zl_ints); if (error == ENOENT) goto out; ASSERT0(error); tx = dmu_tx_create(os); dmu_tx_hold_zap(tx, object, B_TRUE, NULL); txg = ztest_tx_assign(tx, TXG_MIGHTWAIT, FTAG); if (txg == 0) goto out; VERIFY0(zap_remove(os, object, txgname, tx)); VERIFY0(zap_remove(os, object, propname, tx)); dmu_tx_commit(tx); out: umem_free(od, sizeof (ztest_od_t)); } /* * Test case to test the upgrading of a microzap to fatzap. */ void ztest_fzap(ztest_ds_t *zd, uint64_t id) { objset_t *os = zd->zd_os; ztest_od_t *od; uint64_t object, txg, value; od = umem_alloc(sizeof (ztest_od_t), UMEM_NOFAIL); ztest_od_init(od, id, FTAG, 0, DMU_OT_ZAP_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), !ztest_random(2)) != 0) goto out; object = od->od_object; /* * Add entries to this ZAP and make sure it spills over * and gets upgraded to a fatzap. Also, since we are adding * 2050 entries we should see ptrtbl growth and leaf-block split. */ for (value = 0; value < 2050; value++) { char name[ZFS_MAX_DATASET_NAME_LEN]; dmu_tx_t *tx; int error; (void) snprintf(name, sizeof (name), "fzap-%"PRIu64"-%"PRIu64"", id, value); tx = dmu_tx_create(os); dmu_tx_hold_zap(tx, object, B_TRUE, name); txg = ztest_tx_assign(tx, TXG_MIGHTWAIT, FTAG); if (txg == 0) goto out; error = zap_add(os, object, name, sizeof (uint64_t), 1, &value, tx); ASSERT(error == 0 || error == EEXIST); dmu_tx_commit(tx); } out: umem_free(od, sizeof (ztest_od_t)); } void ztest_zap_parallel(ztest_ds_t *zd, uint64_t id) { (void) id; objset_t *os = zd->zd_os; ztest_od_t *od; uint64_t txg, object, count, wsize, wc, zl_wsize, zl_wc; dmu_tx_t *tx; int i, namelen, error; int micro = ztest_random(2); char name[20], string_value[20]; void *data; od = umem_alloc(sizeof (ztest_od_t), UMEM_NOFAIL); ztest_od_init(od, ID_PARALLEL, FTAG, micro, DMU_OT_ZAP_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), B_FALSE) != 0) { umem_free(od, sizeof (ztest_od_t)); return; } object = od->od_object; /* * Generate a random name of the form 'xxx.....' where each * x is a random printable character and the dots are dots. * There are 94 such characters, and the name length goes from * 6 to 20, so there are 94^3 * 15 = 12,458,760 possible names. */ namelen = ztest_random(sizeof (name) - 5) + 5 + 1; for (i = 0; i < 3; i++) name[i] = '!' + ztest_random('~' - '!' + 1); for (; i < namelen - 1; i++) name[i] = '.'; name[i] = '\0'; if ((namelen & 1) || micro) { wsize = sizeof (txg); wc = 1; data = &txg; } else { wsize = 1; wc = namelen; data = string_value; } count = -1ULL; VERIFY0(zap_count(os, object, &count)); ASSERT3S(count, !=, -1ULL); /* * Select an operation: length, lookup, add, update, remove. */ i = ztest_random(5); if (i >= 2) { tx = dmu_tx_create(os); dmu_tx_hold_zap(tx, object, B_TRUE, NULL); txg = ztest_tx_assign(tx, TXG_MIGHTWAIT, FTAG); if (txg == 0) { umem_free(od, sizeof (ztest_od_t)); return; } bcopy(name, string_value, namelen); } else { tx = NULL; txg = 0; bzero(string_value, namelen); } switch (i) { case 0: error = zap_length(os, object, name, &zl_wsize, &zl_wc); if (error == 0) { ASSERT3U(wsize, ==, zl_wsize); ASSERT3U(wc, ==, zl_wc); } else { ASSERT3U(error, ==, ENOENT); } break; case 1: error = zap_lookup(os, object, name, wsize, wc, data); if (error == 0) { if (data == string_value && bcmp(name, data, namelen) != 0) fatal(B_FALSE, "name '%s' != val '%s' len %d", name, (char *)data, namelen); } else { ASSERT3U(error, ==, ENOENT); } break; case 2: error = zap_add(os, object, name, wsize, wc, data, tx); ASSERT(error == 0 || error == EEXIST); break; case 3: VERIFY0(zap_update(os, object, name, wsize, wc, data, tx)); break; case 4: error = zap_remove(os, object, name, tx); ASSERT(error == 0 || error == ENOENT); break; } if (tx != NULL) dmu_tx_commit(tx); umem_free(od, sizeof (ztest_od_t)); } /* * Commit callback data. */ typedef struct ztest_cb_data { list_node_t zcd_node; uint64_t zcd_txg; int zcd_expected_err; boolean_t zcd_added; boolean_t zcd_called; spa_t *zcd_spa; } ztest_cb_data_t; /* This is the actual commit callback function */ static void ztest_commit_callback(void *arg, int error) { ztest_cb_data_t *data = arg; uint64_t synced_txg; VERIFY3P(data, !=, NULL); VERIFY3S(data->zcd_expected_err, ==, error); VERIFY(!data->zcd_called); synced_txg = spa_last_synced_txg(data->zcd_spa); if (data->zcd_txg > synced_txg) fatal(B_FALSE, "commit callback of txg %"PRIu64" called prematurely, " "last synced txg = %"PRIu64"\n", data->zcd_txg, synced_txg); data->zcd_called = B_TRUE; if (error == ECANCELED) { ASSERT0(data->zcd_txg); ASSERT(!data->zcd_added); /* * The private callback data should be destroyed here, but * since we are going to check the zcd_called field after * dmu_tx_abort(), we will destroy it there. */ return; } ASSERT(data->zcd_added); ASSERT3U(data->zcd_txg, !=, 0); (void) mutex_enter(&zcl.zcl_callbacks_lock); /* See if this cb was called more quickly */ if ((synced_txg - data->zcd_txg) < zc_min_txg_delay) zc_min_txg_delay = synced_txg - data->zcd_txg; /* Remove our callback from the list */ list_remove(&zcl.zcl_callbacks, data); (void) mutex_exit(&zcl.zcl_callbacks_lock); umem_free(data, sizeof (ztest_cb_data_t)); } /* Allocate and initialize callback data structure */ static ztest_cb_data_t * ztest_create_cb_data(objset_t *os, uint64_t txg) { ztest_cb_data_t *cb_data; cb_data = umem_zalloc(sizeof (ztest_cb_data_t), UMEM_NOFAIL); cb_data->zcd_txg = txg; cb_data->zcd_spa = dmu_objset_spa(os); list_link_init(&cb_data->zcd_node); return (cb_data); } /* * Commit callback test. */ void ztest_dmu_commit_callbacks(ztest_ds_t *zd, uint64_t id) { objset_t *os = zd->zd_os; ztest_od_t *od; dmu_tx_t *tx; ztest_cb_data_t *cb_data[3], *tmp_cb; uint64_t old_txg, txg; int i, error = 0; od = umem_alloc(sizeof (ztest_od_t), UMEM_NOFAIL); ztest_od_init(od, id, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), B_FALSE) != 0) { umem_free(od, sizeof (ztest_od_t)); return; } tx = dmu_tx_create(os); cb_data[0] = ztest_create_cb_data(os, 0); dmu_tx_callback_register(tx, ztest_commit_callback, cb_data[0]); dmu_tx_hold_write(tx, od->od_object, 0, sizeof (uint64_t)); /* Every once in a while, abort the transaction on purpose */ if (ztest_random(100) == 0) error = -1; if (!error) error = dmu_tx_assign(tx, TXG_NOWAIT); txg = error ? 0 : dmu_tx_get_txg(tx); cb_data[0]->zcd_txg = txg; cb_data[1] = ztest_create_cb_data(os, txg); dmu_tx_callback_register(tx, ztest_commit_callback, cb_data[1]); if (error) { /* * It's not a strict requirement to call the registered * callbacks from inside dmu_tx_abort(), but that's what * it's supposed to happen in the current implementation * so we will check for that. */ for (i = 0; i < 2; i++) { cb_data[i]->zcd_expected_err = ECANCELED; VERIFY(!cb_data[i]->zcd_called); } dmu_tx_abort(tx); for (i = 0; i < 2; i++) { VERIFY(cb_data[i]->zcd_called); umem_free(cb_data[i], sizeof (ztest_cb_data_t)); } umem_free(od, sizeof (ztest_od_t)); return; } cb_data[2] = ztest_create_cb_data(os, txg); dmu_tx_callback_register(tx, ztest_commit_callback, cb_data[2]); /* * Read existing data to make sure there isn't a future leak. */ VERIFY0(dmu_read(os, od->od_object, 0, sizeof (uint64_t), &old_txg, DMU_READ_PREFETCH)); if (old_txg > txg) fatal(B_FALSE, "future leak: got %"PRIu64", open txg is %"PRIu64"", old_txg, txg); dmu_write(os, od->od_object, 0, sizeof (uint64_t), &txg, tx); (void) mutex_enter(&zcl.zcl_callbacks_lock); /* * Since commit callbacks don't have any ordering requirement and since * it is theoretically possible for a commit callback to be called * after an arbitrary amount of time has elapsed since its txg has been * synced, it is difficult to reliably determine whether a commit * callback hasn't been called due to high load or due to a flawed * implementation. * * In practice, we will assume that if after a certain number of txgs a * commit callback hasn't been called, then most likely there's an * implementation bug.. */ tmp_cb = list_head(&zcl.zcl_callbacks); if (tmp_cb != NULL && tmp_cb->zcd_txg + ZTEST_COMMIT_CB_THRESH < txg) { fatal(B_FALSE, "Commit callback threshold exceeded, " "oldest txg: %"PRIu64", open txg: %"PRIu64"\n", tmp_cb->zcd_txg, txg); } /* * Let's find the place to insert our callbacks. * * Even though the list is ordered by txg, it is possible for the * insertion point to not be the end because our txg may already be * quiescing at this point and other callbacks in the open txg * (from other objsets) may have sneaked in. */ tmp_cb = list_tail(&zcl.zcl_callbacks); while (tmp_cb != NULL && tmp_cb->zcd_txg > txg) tmp_cb = list_prev(&zcl.zcl_callbacks, tmp_cb); /* Add the 3 callbacks to the list */ for (i = 0; i < 3; i++) { if (tmp_cb == NULL) list_insert_head(&zcl.zcl_callbacks, cb_data[i]); else list_insert_after(&zcl.zcl_callbacks, tmp_cb, cb_data[i]); cb_data[i]->zcd_added = B_TRUE; VERIFY(!cb_data[i]->zcd_called); tmp_cb = cb_data[i]; } zc_cb_counter += 3; (void) mutex_exit(&zcl.zcl_callbacks_lock); dmu_tx_commit(tx); umem_free(od, sizeof (ztest_od_t)); } /* * Visit each object in the dataset. Verify that its properties * are consistent what was stored in the block tag when it was created, * and that its unused bonus buffer space has not been overwritten. */ void ztest_verify_dnode_bt(ztest_ds_t *zd, uint64_t id) { (void) id; objset_t *os = zd->zd_os; uint64_t obj; int err = 0; for (obj = 0; err == 0; err = dmu_object_next(os, &obj, FALSE, 0)) { ztest_block_tag_t *bt = NULL; dmu_object_info_t doi; dmu_buf_t *db; ztest_object_lock(zd, obj, RL_READER); if (dmu_bonus_hold(os, obj, FTAG, &db) != 0) { ztest_object_unlock(zd, obj); continue; } dmu_object_info_from_db(db, &doi); if (doi.doi_bonus_size >= sizeof (*bt)) bt = ztest_bt_bonus(db); if (bt && bt->bt_magic == BT_MAGIC) { ztest_bt_verify(bt, os, obj, doi.doi_dnodesize, bt->bt_offset, bt->bt_gen, bt->bt_txg, bt->bt_crtxg); ztest_verify_unused_bonus(db, bt, obj, os, bt->bt_gen); } dmu_buf_rele(db, FTAG); ztest_object_unlock(zd, obj); } } void ztest_dsl_prop_get_set(ztest_ds_t *zd, uint64_t id) { (void) id; zfs_prop_t proplist[] = { ZFS_PROP_CHECKSUM, ZFS_PROP_COMPRESSION, ZFS_PROP_COPIES, ZFS_PROP_DEDUP }; (void) pthread_rwlock_rdlock(&ztest_name_lock); for (int p = 0; p < sizeof (proplist) / sizeof (proplist[0]); p++) (void) ztest_dsl_prop_set_uint64(zd->zd_name, proplist[p], ztest_random_dsl_prop(proplist[p]), (int)ztest_random(2)); VERIFY0(ztest_dsl_prop_set_uint64(zd->zd_name, ZFS_PROP_RECORDSIZE, ztest_random_blocksize(), (int)ztest_random(2))); (void) pthread_rwlock_unlock(&ztest_name_lock); } void ztest_spa_prop_get_set(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; nvlist_t *props = NULL; (void) pthread_rwlock_rdlock(&ztest_name_lock); (void) ztest_spa_prop_set_uint64(ZPOOL_PROP_AUTOTRIM, ztest_random(2)); VERIFY0(spa_prop_get(ztest_spa, &props)); if (ztest_opts.zo_verbose >= 6) dump_nvlist(props, 4); fnvlist_free(props); (void) pthread_rwlock_unlock(&ztest_name_lock); } static int user_release_one(const char *snapname, const char *holdname) { nvlist_t *snaps, *holds; int error; snaps = fnvlist_alloc(); holds = fnvlist_alloc(); fnvlist_add_boolean(holds, holdname); fnvlist_add_nvlist(snaps, snapname, holds); fnvlist_free(holds); error = dsl_dataset_user_release(snaps, NULL); fnvlist_free(snaps); return (error); } /* * Test snapshot hold/release and deferred destroy. */ void ztest_dmu_snapshot_hold(ztest_ds_t *zd, uint64_t id) { int error; objset_t *os = zd->zd_os; objset_t *origin; char snapname[100]; char fullname[100]; char clonename[100]; char tag[100]; char osname[ZFS_MAX_DATASET_NAME_LEN]; nvlist_t *holds; (void) pthread_rwlock_rdlock(&ztest_name_lock); dmu_objset_name(os, osname); (void) snprintf(snapname, sizeof (snapname), "sh1_%"PRIu64"", id); (void) snprintf(fullname, sizeof (fullname), "%s@%s", osname, snapname); (void) snprintf(clonename, sizeof (clonename), "%s/ch1_%"PRIu64"", osname, id); (void) snprintf(tag, sizeof (tag), "tag_%"PRIu64"", id); /* * Clean up from any previous run. */ error = dsl_destroy_head(clonename); if (error != ENOENT) ASSERT0(error); error = user_release_one(fullname, tag); if (error != ESRCH && error != ENOENT) ASSERT0(error); error = dsl_destroy_snapshot(fullname, B_FALSE); if (error != ENOENT) ASSERT0(error); /* * Create snapshot, clone it, mark snap for deferred destroy, * destroy clone, verify snap was also destroyed. */ error = dmu_objset_snapshot_one(osname, snapname); if (error) { if (error == ENOSPC) { ztest_record_enospc("dmu_objset_snapshot"); goto out; } fatal(B_FALSE, "dmu_objset_snapshot(%s) = %d", fullname, error); } error = dmu_objset_clone(clonename, fullname); if (error) { if (error == ENOSPC) { ztest_record_enospc("dmu_objset_clone"); goto out; } fatal(B_FALSE, "dmu_objset_clone(%s) = %d", clonename, error); } error = dsl_destroy_snapshot(fullname, B_TRUE); if (error) { fatal(B_FALSE, "dsl_destroy_snapshot(%s, B_TRUE) = %d", fullname, error); } error = dsl_destroy_head(clonename); if (error) fatal(B_FALSE, "dsl_destroy_head(%s) = %d", clonename, error); error = dmu_objset_hold(fullname, FTAG, &origin); if (error != ENOENT) fatal(B_FALSE, "dmu_objset_hold(%s) = %d", fullname, error); /* * Create snapshot, add temporary hold, verify that we can't * destroy a held snapshot, mark for deferred destroy, * release hold, verify snapshot was destroyed. */ error = dmu_objset_snapshot_one(osname, snapname); if (error) { if (error == ENOSPC) { ztest_record_enospc("dmu_objset_snapshot"); goto out; } fatal(B_FALSE, "dmu_objset_snapshot(%s) = %d", fullname, error); } holds = fnvlist_alloc(); fnvlist_add_string(holds, fullname, tag); error = dsl_dataset_user_hold(holds, 0, NULL); fnvlist_free(holds); if (error == ENOSPC) { ztest_record_enospc("dsl_dataset_user_hold"); goto out; } else if (error) { fatal(B_FALSE, "dsl_dataset_user_hold(%s, %s) = %u", fullname, tag, error); } error = dsl_destroy_snapshot(fullname, B_FALSE); if (error != EBUSY) { fatal(B_FALSE, "dsl_destroy_snapshot(%s, B_FALSE) = %d", fullname, error); } error = dsl_destroy_snapshot(fullname, B_TRUE); if (error) { fatal(B_FALSE, "dsl_destroy_snapshot(%s, B_TRUE) = %d", fullname, error); } error = user_release_one(fullname, tag); if (error) fatal(B_FALSE, "user_release_one(%s, %s) = %d", fullname, tag, error); VERIFY3U(dmu_objset_hold(fullname, FTAG, &origin), ==, ENOENT); out: (void) pthread_rwlock_unlock(&ztest_name_lock); } /* * Inject random faults into the on-disk data. */ void ztest_fault_inject(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; ztest_shared_t *zs = ztest_shared; spa_t *spa = ztest_spa; int fd; uint64_t offset; uint64_t leaves; uint64_t bad = 0x1990c0ffeedecadeull; uint64_t top, leaf; char *path0; char *pathrand; size_t fsize; int bshift = SPA_MAXBLOCKSHIFT + 2; int iters = 1000; int maxfaults; int mirror_save; vdev_t *vd0 = NULL; uint64_t guid0 = 0; boolean_t islog = B_FALSE; path0 = umem_alloc(MAXPATHLEN, UMEM_NOFAIL); pathrand = umem_alloc(MAXPATHLEN, UMEM_NOFAIL); mutex_enter(&ztest_vdev_lock); /* * Device removal is in progress, fault injection must be disabled * until it completes and the pool is scrubbed. The fault injection * strategy for damaging blocks does not take in to account evacuated * blocks which may have already been damaged. */ if (ztest_device_removal_active) { mutex_exit(&ztest_vdev_lock); goto out; } maxfaults = MAXFAULTS(zs); leaves = MAX(zs->zs_mirrors, 1) * ztest_opts.zo_raid_children; mirror_save = zs->zs_mirrors; mutex_exit(&ztest_vdev_lock); ASSERT3U(leaves, >=, 1); /* * While ztest is running the number of leaves will not change. This * is critical for the fault injection logic as it determines where * errors can be safely injected such that they are always repairable. * * When restarting ztest a different number of leaves may be requested * which will shift the regions to be damaged. This is fine as long * as the pool has been scrubbed prior to using the new mapping. * Failure to do can result in non-repairable damage being injected. */ if (ztest_pool_scrubbed == B_FALSE) goto out; /* * Grab the name lock as reader. There are some operations * which don't like to have their vdevs changed while * they are in progress (i.e. spa_change_guid). Those * operations will have grabbed the name lock as writer. */ (void) pthread_rwlock_rdlock(&ztest_name_lock); /* * We need SCL_STATE here because we're going to look at vd0->vdev_tsd. */ spa_config_enter(spa, SCL_STATE, FTAG, RW_READER); if (ztest_random(2) == 0) { /* * Inject errors on a normal data device or slog device. */ top = ztest_random_vdev_top(spa, B_TRUE); leaf = ztest_random(leaves) + zs->zs_splits; /* * Generate paths to the first leaf in this top-level vdev, * and to the random leaf we selected. We'll induce transient * write failures and random online/offline activity on leaf 0, * and we'll write random garbage to the randomly chosen leaf. */ (void) snprintf(path0, MAXPATHLEN, ztest_dev_template, ztest_opts.zo_dir, ztest_opts.zo_pool, top * leaves + zs->zs_splits); (void) snprintf(pathrand, MAXPATHLEN, ztest_dev_template, ztest_opts.zo_dir, ztest_opts.zo_pool, top * leaves + leaf); vd0 = vdev_lookup_by_path(spa->spa_root_vdev, path0); if (vd0 != NULL && vd0->vdev_top->vdev_islog) islog = B_TRUE; /* * If the top-level vdev needs to be resilvered * then we only allow faults on the device that is * resilvering. */ if (vd0 != NULL && maxfaults != 1 && (!vdev_resilver_needed(vd0->vdev_top, NULL, NULL) || vd0->vdev_resilver_txg != 0)) { /* * Make vd0 explicitly claim to be unreadable, * or unwritable, or reach behind its back * and close the underlying fd. We can do this if * maxfaults == 0 because we'll fail and reexecute, * and we can do it if maxfaults >= 2 because we'll * have enough redundancy. If maxfaults == 1, the * combination of this with injection of random data * corruption below exceeds the pool's fault tolerance. */ vdev_file_t *vf = vd0->vdev_tsd; zfs_dbgmsg("injecting fault to vdev %llu; maxfaults=%d", (long long)vd0->vdev_id, (int)maxfaults); if (vf != NULL && ztest_random(3) == 0) { (void) close(vf->vf_file->f_fd); vf->vf_file->f_fd = -1; } else if (ztest_random(2) == 0) { vd0->vdev_cant_read = B_TRUE; } else { vd0->vdev_cant_write = B_TRUE; } guid0 = vd0->vdev_guid; } } else { /* * Inject errors on an l2cache device. */ spa_aux_vdev_t *sav = &spa->spa_l2cache; if (sav->sav_count == 0) { spa_config_exit(spa, SCL_STATE, FTAG); (void) pthread_rwlock_unlock(&ztest_name_lock); goto out; } vd0 = sav->sav_vdevs[ztest_random(sav->sav_count)]; guid0 = vd0->vdev_guid; (void) strcpy(path0, vd0->vdev_path); (void) strcpy(pathrand, vd0->vdev_path); leaf = 0; leaves = 1; maxfaults = INT_MAX; /* no limit on cache devices */ } spa_config_exit(spa, SCL_STATE, FTAG); (void) pthread_rwlock_unlock(&ztest_name_lock); /* * If we can tolerate two or more faults, or we're dealing * with a slog, randomly online/offline vd0. */ if ((maxfaults >= 2 || islog) && guid0 != 0) { if (ztest_random(10) < 6) { int flags = (ztest_random(2) == 0 ? ZFS_OFFLINE_TEMPORARY : 0); /* * We have to grab the zs_name_lock as writer to * prevent a race between offlining a slog and * destroying a dataset. Offlining the slog will * grab a reference on the dataset which may cause * dsl_destroy_head() to fail with EBUSY thus * leaving the dataset in an inconsistent state. */ if (islog) (void) pthread_rwlock_wrlock(&ztest_name_lock); VERIFY3U(vdev_offline(spa, guid0, flags), !=, EBUSY); if (islog) (void) pthread_rwlock_unlock(&ztest_name_lock); } else { /* * Ideally we would like to be able to randomly * call vdev_[on|off]line without holding locks * to force unpredictable failures but the side * effects of vdev_[on|off]line prevent us from * doing so. We grab the ztest_vdev_lock here to * prevent a race between injection testing and * aux_vdev removal. */ mutex_enter(&ztest_vdev_lock); (void) vdev_online(spa, guid0, 0, NULL); mutex_exit(&ztest_vdev_lock); } } if (maxfaults == 0) goto out; /* * We have at least single-fault tolerance, so inject data corruption. */ fd = open(pathrand, O_RDWR); if (fd == -1) /* we hit a gap in the device namespace */ goto out; fsize = lseek(fd, 0, SEEK_END); while (--iters != 0) { /* * The offset must be chosen carefully to ensure that * we do not inject a given logical block with errors * on two different leaf devices, because ZFS can not * tolerate that (if maxfaults==1). * * To achieve this we divide each leaf device into * chunks of size (# leaves * SPA_MAXBLOCKSIZE * 4). * Each chunk is further divided into error-injection * ranges (can accept errors) and clear ranges (we do * not inject errors in those). Each error-injection * range can accept errors only for a single leaf vdev. * Error-injection ranges are separated by clear ranges. * * For example, with 3 leaves, each chunk looks like: * 0 to 32M: injection range for leaf 0 * 32M to 64M: clear range - no injection allowed * 64M to 96M: injection range for leaf 1 * 96M to 128M: clear range - no injection allowed * 128M to 160M: injection range for leaf 2 * 160M to 192M: clear range - no injection allowed * * Each clear range must be large enough such that a * single block cannot straddle it. This way a block * can't be a target in two different injection ranges * (on different leaf vdevs). */ offset = ztest_random(fsize / (leaves << bshift)) * (leaves << bshift) + (leaf << bshift) + (ztest_random(1ULL << (bshift - 1)) & -8ULL); /* * Only allow damage to the labels at one end of the vdev. * * If all labels are damaged, the device will be totally * inaccessible, which will result in loss of data, * because we also damage (parts of) the other side of * the mirror/raidz. * * Additionally, we will always have both an even and an * odd label, so that we can handle crashes in the * middle of vdev_config_sync(). */ if ((leaf & 1) == 0 && offset < VDEV_LABEL_START_SIZE) continue; /* * The two end labels are stored at the "end" of the disk, but * the end of the disk (vdev_psize) is aligned to * sizeof (vdev_label_t). */ uint64_t psize = P2ALIGN(fsize, sizeof (vdev_label_t)); if ((leaf & 1) == 1 && offset + sizeof (bad) > psize - VDEV_LABEL_END_SIZE) continue; mutex_enter(&ztest_vdev_lock); if (mirror_save != zs->zs_mirrors) { mutex_exit(&ztest_vdev_lock); (void) close(fd); goto out; } if (pwrite(fd, &bad, sizeof (bad), offset) != sizeof (bad)) fatal(B_TRUE, "can't inject bad word at 0x%"PRIx64" in %s", offset, pathrand); mutex_exit(&ztest_vdev_lock); if (ztest_opts.zo_verbose >= 7) (void) printf("injected bad word into %s," " offset 0x%"PRIx64"\n", pathrand, offset); } (void) close(fd); out: umem_free(path0, MAXPATHLEN); umem_free(pathrand, MAXPATHLEN); } /* * By design ztest will never inject uncorrectable damage in to the pool. * Issue a scrub, wait for it to complete, and verify there is never any * persistent damage. * * Only after a full scrub has been completed is it safe to start injecting * data corruption. See the comment in zfs_fault_inject(). */ static int ztest_scrub_impl(spa_t *spa) { int error = spa_scan(spa, POOL_SCAN_SCRUB); if (error) return (error); while (dsl_scan_scrubbing(spa_get_dsl(spa))) txg_wait_synced(spa_get_dsl(spa), 0); if (spa_get_errlog_size(spa) > 0) return (ECKSUM); ztest_pool_scrubbed = B_TRUE; return (0); } /* * Scrub the pool. */ void ztest_scrub(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; spa_t *spa = ztest_spa; int error; /* * Scrub in progress by device removal. */ if (ztest_device_removal_active) return; /* * Start a scrub, wait a moment, then force a restart. */ (void) spa_scan(spa, POOL_SCAN_SCRUB); (void) poll(NULL, 0, 100); error = ztest_scrub_impl(spa); if (error == EBUSY) error = 0; ASSERT0(error); } /* * Change the guid for the pool. */ void ztest_reguid(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; spa_t *spa = ztest_spa; uint64_t orig, load; int error; if (ztest_opts.zo_mmp_test) return; orig = spa_guid(spa); load = spa_load_guid(spa); (void) pthread_rwlock_wrlock(&ztest_name_lock); error = spa_change_guid(spa); (void) pthread_rwlock_unlock(&ztest_name_lock); if (error != 0) return; if (ztest_opts.zo_verbose >= 4) { (void) printf("Changed guid old %"PRIu64" -> %"PRIu64"\n", orig, spa_guid(spa)); } VERIFY3U(orig, !=, spa_guid(spa)); VERIFY3U(load, ==, spa_load_guid(spa)); } void ztest_fletcher(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; hrtime_t end = gethrtime() + NANOSEC; while (gethrtime() <= end) { int run_count = 100; void *buf; struct abd *abd_data, *abd_meta; uint32_t size; int *ptr; int i; zio_cksum_t zc_ref; zio_cksum_t zc_ref_byteswap; size = ztest_random_blocksize(); buf = umem_alloc(size, UMEM_NOFAIL); abd_data = abd_alloc(size, B_FALSE); abd_meta = abd_alloc(size, B_TRUE); for (i = 0, ptr = buf; i < size / sizeof (*ptr); i++, ptr++) *ptr = ztest_random(UINT_MAX); abd_copy_from_buf_off(abd_data, buf, 0, size); abd_copy_from_buf_off(abd_meta, buf, 0, size); VERIFY0(fletcher_4_impl_set("scalar")); fletcher_4_native(buf, size, NULL, &zc_ref); fletcher_4_byteswap(buf, size, NULL, &zc_ref_byteswap); VERIFY0(fletcher_4_impl_set("cycle")); while (run_count-- > 0) { zio_cksum_t zc; zio_cksum_t zc_byteswap; fletcher_4_byteswap(buf, size, NULL, &zc_byteswap); fletcher_4_native(buf, size, NULL, &zc); VERIFY0(bcmp(&zc, &zc_ref, sizeof (zc))); VERIFY0(bcmp(&zc_byteswap, &zc_ref_byteswap, sizeof (zc_byteswap))); /* Test ABD - data */ abd_fletcher_4_byteswap(abd_data, size, NULL, &zc_byteswap); abd_fletcher_4_native(abd_data, size, NULL, &zc); VERIFY0(bcmp(&zc, &zc_ref, sizeof (zc))); VERIFY0(bcmp(&zc_byteswap, &zc_ref_byteswap, sizeof (zc_byteswap))); /* Test ABD - metadata */ abd_fletcher_4_byteswap(abd_meta, size, NULL, &zc_byteswap); abd_fletcher_4_native(abd_meta, size, NULL, &zc); VERIFY0(bcmp(&zc, &zc_ref, sizeof (zc))); VERIFY0(bcmp(&zc_byteswap, &zc_ref_byteswap, sizeof (zc_byteswap))); } umem_free(buf, size); abd_free(abd_data); abd_free(abd_meta); } } void ztest_fletcher_incr(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; void *buf; size_t size; int *ptr; int i; zio_cksum_t zc_ref; zio_cksum_t zc_ref_bswap; hrtime_t end = gethrtime() + NANOSEC; while (gethrtime() <= end) { int run_count = 100; size = ztest_random_blocksize(); buf = umem_alloc(size, UMEM_NOFAIL); for (i = 0, ptr = buf; i < size / sizeof (*ptr); i++, ptr++) *ptr = ztest_random(UINT_MAX); VERIFY0(fletcher_4_impl_set("scalar")); fletcher_4_native(buf, size, NULL, &zc_ref); fletcher_4_byteswap(buf, size, NULL, &zc_ref_bswap); VERIFY0(fletcher_4_impl_set("cycle")); while (run_count-- > 0) { zio_cksum_t zc; zio_cksum_t zc_bswap; size_t pos = 0; ZIO_SET_CHECKSUM(&zc, 0, 0, 0, 0); ZIO_SET_CHECKSUM(&zc_bswap, 0, 0, 0, 0); while (pos < size) { size_t inc = 64 * ztest_random(size / 67); /* sometimes add few bytes to test non-simd */ if (ztest_random(100) < 10) inc += P2ALIGN(ztest_random(64), sizeof (uint32_t)); if (inc > (size - pos)) inc = size - pos; fletcher_4_incremental_native(buf + pos, inc, &zc); fletcher_4_incremental_byteswap(buf + pos, inc, &zc_bswap); pos += inc; } VERIFY3U(pos, ==, size); VERIFY(ZIO_CHECKSUM_EQUAL(zc, zc_ref)); VERIFY(ZIO_CHECKSUM_EQUAL(zc_bswap, zc_ref_bswap)); /* * verify if incremental on the whole buffer is * equivalent to non-incremental version */ ZIO_SET_CHECKSUM(&zc, 0, 0, 0, 0); ZIO_SET_CHECKSUM(&zc_bswap, 0, 0, 0, 0); fletcher_4_incremental_native(buf, size, &zc); fletcher_4_incremental_byteswap(buf, size, &zc_bswap); VERIFY(ZIO_CHECKSUM_EQUAL(zc, zc_ref)); VERIFY(ZIO_CHECKSUM_EQUAL(zc_bswap, zc_ref_bswap)); } umem_free(buf, size); } } static int ztest_set_global_vars(void) { for (size_t i = 0; i < ztest_opts.zo_gvars_count; i++) { char *kv = ztest_opts.zo_gvars[i]; VERIFY3U(strlen(kv), <=, ZO_GVARS_MAX_ARGLEN); VERIFY3U(strlen(kv), >, 0); int err = set_global_var(kv); if (ztest_opts.zo_verbose > 0) { (void) printf("setting global var %s ... %s\n", kv, err ? "failed" : "ok"); } if (err != 0) { (void) fprintf(stderr, "failed to set global var '%s'\n", kv); return (err); } } return (0); } static char ** ztest_global_vars_to_zdb_args(void) { char **args = calloc(2*ztest_opts.zo_gvars_count + 1, sizeof (char *)); char **cur = args; for (size_t i = 0; i < ztest_opts.zo_gvars_count; i++) { char *kv = ztest_opts.zo_gvars[i]; *cur = "-o"; cur++; *cur = strdup(kv); cur++; } ASSERT3P(cur, ==, &args[2*ztest_opts.zo_gvars_count]); *cur = NULL; return (args); } /* The end of strings is indicated by a NULL element */ static char * join_strings(char **strings, const char *sep) { size_t totallen = 0; for (char **sp = strings; *sp != NULL; sp++) { totallen += strlen(*sp); totallen += strlen(sep); } if (totallen > 0) { ASSERT(totallen >= strlen(sep)); totallen -= strlen(sep); } size_t buflen = totallen + 1; char *o = malloc(buflen); /* trailing 0 byte */ o[0] = '\0'; for (char **sp = strings; *sp != NULL; sp++) { size_t would; would = strlcat(o, *sp, buflen); VERIFY3U(would, <, buflen); if (*(sp+1) == NULL) { break; } would = strlcat(o, sep, buflen); VERIFY3U(would, <, buflen); } ASSERT3S(strlen(o), ==, totallen); return (o); } static int ztest_check_path(char *path) { struct stat s; /* return true on success */ return (!stat(path, &s)); } static void ztest_get_zdb_bin(char *bin, int len) { char *zdb_path; /* * Try to use ZDB_PATH and in-tree zdb path. If not successful, just * let popen to search through PATH. */ if ((zdb_path = getenv("ZDB_PATH"))) { strlcpy(bin, zdb_path, len); /* In env */ if (!ztest_check_path(bin)) { ztest_dump_core = 0; fatal(B_TRUE, "invalid ZDB_PATH '%s'", bin); } return; } VERIFY3P(realpath(getexecname(), bin), !=, NULL); if (strstr(bin, "/ztest/")) { strstr(bin, "/ztest/")[0] = '\0'; /* In-tree */ strcat(bin, "/zdb/zdb"); if (ztest_check_path(bin)) return; } strcpy(bin, "zdb"); } static vdev_t * ztest_random_concrete_vdev_leaf(vdev_t *vd) { if (vd == NULL) return (NULL); if (vd->vdev_children == 0) return (vd); vdev_t *eligible[vd->vdev_children]; int eligible_idx = 0, i; for (i = 0; i < vd->vdev_children; i++) { vdev_t *cvd = vd->vdev_child[i]; if (cvd->vdev_top->vdev_removing) continue; if (cvd->vdev_children > 0 || (vdev_is_concrete(cvd) && !cvd->vdev_detached)) { eligible[eligible_idx++] = cvd; } } VERIFY3S(eligible_idx, >, 0); uint64_t child_no = ztest_random(eligible_idx); return (ztest_random_concrete_vdev_leaf(eligible[child_no])); } void ztest_initialize(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; spa_t *spa = ztest_spa; int error = 0; mutex_enter(&ztest_vdev_lock); spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER); /* Random leaf vdev */ vdev_t *rand_vd = ztest_random_concrete_vdev_leaf(spa->spa_root_vdev); if (rand_vd == NULL) { spa_config_exit(spa, SCL_VDEV, FTAG); mutex_exit(&ztest_vdev_lock); return; } /* * The random vdev we've selected may change as soon as we * drop the spa_config_lock. We create local copies of things * we're interested in. */ uint64_t guid = rand_vd->vdev_guid; char *path = strdup(rand_vd->vdev_path); boolean_t active = rand_vd->vdev_initialize_thread != NULL; zfs_dbgmsg("vd %px, guid %llu", rand_vd, (u_longlong_t)guid); spa_config_exit(spa, SCL_VDEV, FTAG); uint64_t cmd = ztest_random(POOL_INITIALIZE_FUNCS); nvlist_t *vdev_guids = fnvlist_alloc(); nvlist_t *vdev_errlist = fnvlist_alloc(); fnvlist_add_uint64(vdev_guids, path, guid); error = spa_vdev_initialize(spa, vdev_guids, cmd, vdev_errlist); fnvlist_free(vdev_guids); fnvlist_free(vdev_errlist); switch (cmd) { case POOL_INITIALIZE_CANCEL: if (ztest_opts.zo_verbose >= 4) { (void) printf("Cancel initialize %s", path); if (!active) (void) printf(" failed (no initialize active)"); (void) printf("\n"); } break; case POOL_INITIALIZE_START: if (ztest_opts.zo_verbose >= 4) { (void) printf("Start initialize %s", path); if (active && error == 0) (void) printf(" failed (already active)"); else if (error != 0) (void) printf(" failed (error %d)", error); (void) printf("\n"); } break; case POOL_INITIALIZE_SUSPEND: if (ztest_opts.zo_verbose >= 4) { (void) printf("Suspend initialize %s", path); if (!active) (void) printf(" failed (no initialize active)"); (void) printf("\n"); } break; } free(path); mutex_exit(&ztest_vdev_lock); } void ztest_trim(ztest_ds_t *zd, uint64_t id) { (void) zd, (void) id; spa_t *spa = ztest_spa; int error = 0; mutex_enter(&ztest_vdev_lock); spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER); /* Random leaf vdev */ vdev_t *rand_vd = ztest_random_concrete_vdev_leaf(spa->spa_root_vdev); if (rand_vd == NULL) { spa_config_exit(spa, SCL_VDEV, FTAG); mutex_exit(&ztest_vdev_lock); return; } /* * The random vdev we've selected may change as soon as we * drop the spa_config_lock. We create local copies of things * we're interested in. */ uint64_t guid = rand_vd->vdev_guid; char *path = strdup(rand_vd->vdev_path); boolean_t active = rand_vd->vdev_trim_thread != NULL; zfs_dbgmsg("vd %p, guid %llu", rand_vd, (u_longlong_t)guid); spa_config_exit(spa, SCL_VDEV, FTAG); uint64_t cmd = ztest_random(POOL_TRIM_FUNCS); uint64_t rate = 1 << ztest_random(30); boolean_t partial = (ztest_random(5) > 0); boolean_t secure = (ztest_random(5) > 0); nvlist_t *vdev_guids = fnvlist_alloc(); nvlist_t *vdev_errlist = fnvlist_alloc(); fnvlist_add_uint64(vdev_guids, path, guid); error = spa_vdev_trim(spa, vdev_guids, cmd, rate, partial, secure, vdev_errlist); fnvlist_free(vdev_guids); fnvlist_free(vdev_errlist); switch (cmd) { case POOL_TRIM_CANCEL: if (ztest_opts.zo_verbose >= 4) { (void) printf("Cancel TRIM %s", path); if (!active) (void) printf(" failed (no TRIM active)"); (void) printf("\n"); } break; case POOL_TRIM_START: if (ztest_opts.zo_verbose >= 4) { (void) printf("Start TRIM %s", path); if (active && error == 0) (void) printf(" failed (already active)"); else if (error != 0) (void) printf(" failed (error %d)", error); (void) printf("\n"); } break; case POOL_TRIM_SUSPEND: if (ztest_opts.zo_verbose >= 4) { (void) printf("Suspend TRIM %s", path); if (!active) (void) printf(" failed (no TRIM active)"); (void) printf("\n"); } break; } free(path); mutex_exit(&ztest_vdev_lock); } /* * Verify pool integrity by running zdb. */ static void ztest_run_zdb(char *pool) { int status; char *bin; char *zdb; char *zbuf; const int len = MAXPATHLEN + MAXNAMELEN + 20; FILE *fp; bin = umem_alloc(len, UMEM_NOFAIL); zdb = umem_alloc(len, UMEM_NOFAIL); zbuf = umem_alloc(1024, UMEM_NOFAIL); ztest_get_zdb_bin(bin, len); char **set_gvars_args = ztest_global_vars_to_zdb_args(); char *set_gvars_args_joined = join_strings(set_gvars_args, " "); free(set_gvars_args); size_t would = snprintf(zdb, len, "%s -bcc%s%s -G -d -Y -e -y %s -p %s %s", bin, ztest_opts.zo_verbose >= 3 ? "s" : "", ztest_opts.zo_verbose >= 4 ? "v" : "", set_gvars_args_joined, ztest_opts.zo_dir, pool); ASSERT3U(would, <, len); free(set_gvars_args_joined); if (ztest_opts.zo_verbose >= 5) (void) printf("Executing %s\n", strstr(zdb, "zdb ")); fp = popen(zdb, "r"); while (fgets(zbuf, 1024, fp) != NULL) if (ztest_opts.zo_verbose >= 3) (void) printf("%s", zbuf); status = pclose(fp); if (status == 0) goto out; ztest_dump_core = 0; if (WIFEXITED(status)) fatal(B_FALSE, "'%s' exit code %d", zdb, WEXITSTATUS(status)); else fatal(B_FALSE, "'%s' died with signal %d", zdb, WTERMSIG(status)); out: umem_free(bin, len); umem_free(zdb, len); umem_free(zbuf, 1024); } static void ztest_walk_pool_directory(char *header) { spa_t *spa = NULL; if (ztest_opts.zo_verbose >= 6) (void) printf("%s\n", header); mutex_enter(&spa_namespace_lock); while ((spa = spa_next(spa)) != NULL) if (ztest_opts.zo_verbose >= 6) (void) printf("\t%s\n", spa_name(spa)); mutex_exit(&spa_namespace_lock); } static void ztest_spa_import_export(char *oldname, char *newname) { nvlist_t *config, *newconfig; uint64_t pool_guid; spa_t *spa; int error; if (ztest_opts.zo_verbose >= 4) { (void) printf("import/export: old = %s, new = %s\n", oldname, newname); } /* * Clean up from previous runs. */ (void) spa_destroy(newname); /* * Get the pool's configuration and guid. */ VERIFY0(spa_open(oldname, &spa, FTAG)); /* * Kick off a scrub to tickle scrub/export races. */ if (ztest_random(2) == 0) (void) spa_scan(spa, POOL_SCAN_SCRUB); pool_guid = spa_guid(spa); spa_close(spa, FTAG); ztest_walk_pool_directory("pools before export"); /* * Export it. */ VERIFY0(spa_export(oldname, &config, B_FALSE, B_FALSE)); ztest_walk_pool_directory("pools after export"); /* * Try to import it. */ newconfig = spa_tryimport(config); ASSERT3P(newconfig, !=, NULL); fnvlist_free(newconfig); /* * Import it under the new name. */ error = spa_import(newname, config, NULL, 0); if (error != 0) { dump_nvlist(config, 0); fatal(B_FALSE, "couldn't import pool %s as %s: error %u", oldname, newname, error); } ztest_walk_pool_directory("pools after import"); /* * Try to import it again -- should fail with EEXIST. */ VERIFY3U(EEXIST, ==, spa_import(newname, config, NULL, 0)); /* * Try to import it under a different name -- should fail with EEXIST. */ VERIFY3U(EEXIST, ==, spa_import(oldname, config, NULL, 0)); /* * Verify that the pool is no longer visible under the old name. */ VERIFY3U(ENOENT, ==, spa_open(oldname, &spa, FTAG)); /* * Verify that we can open and close the pool using the new name. */ VERIFY0(spa_open(newname, &spa, FTAG)); ASSERT3U(pool_guid, ==, spa_guid(spa)); spa_close(spa, FTAG); fnvlist_free(config); } static void ztest_resume(spa_t *spa) { if (spa_suspended(spa) && ztest_opts.zo_verbose >= 6) (void) printf("resuming from suspended state\n"); spa_vdev_state_enter(spa, SCL_NONE); vdev_clear(spa, NULL); (void) spa_vdev_state_exit(spa, NULL, 0); (void) zio_resume(spa); } static void ztest_resume_thread(void *arg) { spa_t *spa = arg; while (!ztest_exiting) { if (spa_suspended(spa)) ztest_resume(spa); (void) poll(NULL, 0, 100); /* * Periodically change the zfs_compressed_arc_enabled setting. */ if (ztest_random(10) == 0) zfs_compressed_arc_enabled = ztest_random(2); /* * Periodically change the zfs_abd_scatter_enabled setting. */ if (ztest_random(10) == 0) zfs_abd_scatter_enabled = ztest_random(2); } thread_exit(); } static void ztest_deadman_thread(void *arg) { ztest_shared_t *zs = arg; spa_t *spa = ztest_spa; hrtime_t delay, overdue, last_run = gethrtime(); delay = (zs->zs_thread_stop - zs->zs_thread_start) + MSEC2NSEC(zfs_deadman_synctime_ms); while (!ztest_exiting) { /* * Wait for the delay timer while checking occasionally * if we should stop. */ if (gethrtime() < last_run + delay) { (void) poll(NULL, 0, 1000); continue; } /* * If the pool is suspended then fail immediately. Otherwise, * check to see if the pool is making any progress. If * vdev_deadman() discovers that there hasn't been any recent * I/Os then it will end up aborting the tests. */ if (spa_suspended(spa) || spa->spa_root_vdev == NULL) { fatal(B_FALSE, "aborting test after %lu seconds because " "pool has transitioned to a suspended state.", zfs_deadman_synctime_ms / 1000); } vdev_deadman(spa->spa_root_vdev, FTAG); /* * If the process doesn't complete within a grace period of * zfs_deadman_synctime_ms over the expected finish time, * then it may be hung and is terminated. */ overdue = zs->zs_proc_stop + MSEC2NSEC(zfs_deadman_synctime_ms); if (gethrtime() > overdue) { fatal(B_FALSE, "aborting test after %llu seconds because " "the process is overdue for termination.", (gethrtime() - zs->zs_proc_start) / NANOSEC); } (void) printf("ztest has been running for %lld seconds\n", (gethrtime() - zs->zs_proc_start) / NANOSEC); last_run = gethrtime(); delay = MSEC2NSEC(zfs_deadman_checktime_ms); } thread_exit(); } static void ztest_execute(int test, ztest_info_t *zi, uint64_t id) { ztest_ds_t *zd = &ztest_ds[id % ztest_opts.zo_datasets]; ztest_shared_callstate_t *zc = ZTEST_GET_SHARED_CALLSTATE(test); hrtime_t functime = gethrtime(); int i; for (i = 0; i < zi->zi_iters; i++) zi->zi_func(zd, id); functime = gethrtime() - functime; atomic_add_64(&zc->zc_count, 1); atomic_add_64(&zc->zc_time, functime); if (ztest_opts.zo_verbose >= 4) (void) printf("%6.2f sec in %s\n", (double)functime / NANOSEC, zi->zi_funcname); } static void ztest_thread(void *arg) { int rand; uint64_t id = (uintptr_t)arg; ztest_shared_t *zs = ztest_shared; uint64_t call_next; hrtime_t now; ztest_info_t *zi; ztest_shared_callstate_t *zc; while ((now = gethrtime()) < zs->zs_thread_stop) { /* * See if it's time to force a crash. */ if (now > zs->zs_thread_kill) ztest_kill(zs); /* * If we're getting ENOSPC with some regularity, stop. */ if (zs->zs_enospc_count > 10) break; /* * Pick a random function to execute. */ rand = ztest_random(ZTEST_FUNCS); zi = &ztest_info[rand]; zc = ZTEST_GET_SHARED_CALLSTATE(rand); call_next = zc->zc_next; if (now >= call_next && atomic_cas_64(&zc->zc_next, call_next, call_next + ztest_random(2 * zi->zi_interval[0] + 1)) == call_next) { ztest_execute(rand, zi, id); } } thread_exit(); } static void ztest_dataset_name(char *dsname, char *pool, int d) { (void) snprintf(dsname, ZFS_MAX_DATASET_NAME_LEN, "%s/ds_%d", pool, d); } static void ztest_dataset_destroy(int d) { char name[ZFS_MAX_DATASET_NAME_LEN]; int t; ztest_dataset_name(name, ztest_opts.zo_pool, d); if (ztest_opts.zo_verbose >= 3) (void) printf("Destroying %s to free up space\n", name); /* * Cleanup any non-standard clones and snapshots. In general, * ztest thread t operates on dataset (t % zopt_datasets), * so there may be more than one thing to clean up. */ for (t = d; t < ztest_opts.zo_threads; t += ztest_opts.zo_datasets) ztest_dsl_dataset_cleanup(name, t); (void) dmu_objset_find(name, ztest_objset_destroy_cb, NULL, DS_FIND_SNAPSHOTS | DS_FIND_CHILDREN); } static void ztest_dataset_dirobj_verify(ztest_ds_t *zd) { uint64_t usedobjs, dirobjs, scratch; /* * ZTEST_DIROBJ is the object directory for the entire dataset. * Therefore, the number of objects in use should equal the * number of ZTEST_DIROBJ entries, +1 for ZTEST_DIROBJ itself. * If not, we have an object leak. * * Note that we can only check this in ztest_dataset_open(), * when the open-context and syncing-context values agree. * That's because zap_count() returns the open-context value, * while dmu_objset_space() returns the rootbp fill count. */ VERIFY0(zap_count(zd->zd_os, ZTEST_DIROBJ, &dirobjs)); dmu_objset_space(zd->zd_os, &scratch, &scratch, &usedobjs, &scratch); ASSERT3U(dirobjs + 1, ==, usedobjs); } static int ztest_dataset_open(int d) { ztest_ds_t *zd = &ztest_ds[d]; uint64_t committed_seq = ZTEST_GET_SHARED_DS(d)->zd_seq; objset_t *os; zilog_t *zilog; char name[ZFS_MAX_DATASET_NAME_LEN]; int error; ztest_dataset_name(name, ztest_opts.zo_pool, d); (void) pthread_rwlock_rdlock(&ztest_name_lock); error = ztest_dataset_create(name); if (error == ENOSPC) { (void) pthread_rwlock_unlock(&ztest_name_lock); ztest_record_enospc(FTAG); return (error); } ASSERT(error == 0 || error == EEXIST); VERIFY0(ztest_dmu_objset_own(name, DMU_OST_OTHER, B_FALSE, B_TRUE, zd, &os)); (void) pthread_rwlock_unlock(&ztest_name_lock); ztest_zd_init(zd, ZTEST_GET_SHARED_DS(d), os); zilog = zd->zd_zilog; if (zilog->zl_header->zh_claim_lr_seq != 0 && zilog->zl_header->zh_claim_lr_seq < committed_seq) fatal(B_FALSE, "missing log records: " "claimed %"PRIu64" < committed %"PRIu64"", zilog->zl_header->zh_claim_lr_seq, committed_seq); ztest_dataset_dirobj_verify(zd); zil_replay(os, zd, ztest_replay_vector); ztest_dataset_dirobj_verify(zd); if (ztest_opts.zo_verbose >= 6) (void) printf("%s replay %"PRIu64" blocks, " "%"PRIu64" records, seq %"PRIu64"\n", zd->zd_name, zilog->zl_parse_blk_count, zilog->zl_parse_lr_count, zilog->zl_replaying_seq); zilog = zil_open(os, ztest_get_data); if (zilog->zl_replaying_seq != 0 && zilog->zl_replaying_seq < committed_seq) fatal(B_FALSE, "missing log records: " "replayed %"PRIu64" < committed %"PRIu64"", zilog->zl_replaying_seq, committed_seq); return (0); } static void ztest_dataset_close(int d) { ztest_ds_t *zd = &ztest_ds[d]; zil_close(zd->zd_zilog); dmu_objset_disown(zd->zd_os, B_TRUE, zd); ztest_zd_fini(zd); } static int ztest_replay_zil_cb(const char *name, void *arg) { (void) arg; objset_t *os; ztest_ds_t *zdtmp; VERIFY0(ztest_dmu_objset_own(name, DMU_OST_ANY, B_TRUE, B_TRUE, FTAG, &os)); zdtmp = umem_alloc(sizeof (ztest_ds_t), UMEM_NOFAIL); ztest_zd_init(zdtmp, NULL, os); zil_replay(os, zdtmp, ztest_replay_vector); ztest_zd_fini(zdtmp); if (dmu_objset_zil(os)->zl_parse_lr_count != 0 && ztest_opts.zo_verbose >= 6) { zilog_t *zilog = dmu_objset_zil(os); (void) printf("%s replay %"PRIu64" blocks, " "%"PRIu64" records, seq %"PRIu64"\n", name, zilog->zl_parse_blk_count, zilog->zl_parse_lr_count, zilog->zl_replaying_seq); } umem_free(zdtmp, sizeof (ztest_ds_t)); dmu_objset_disown(os, B_TRUE, FTAG); return (0); } static void ztest_freeze(void) { ztest_ds_t *zd = &ztest_ds[0]; spa_t *spa; int numloops = 0; if (ztest_opts.zo_verbose >= 3) (void) printf("testing spa_freeze()...\n"); kernel_init(SPA_MODE_READ | SPA_MODE_WRITE); VERIFY0(spa_open(ztest_opts.zo_pool, &spa, FTAG)); VERIFY0(ztest_dataset_open(0)); ztest_spa = spa; /* * Force the first log block to be transactionally allocated. * We have to do this before we freeze the pool -- otherwise * the log chain won't be anchored. */ while (BP_IS_HOLE(&zd->zd_zilog->zl_header->zh_log)) { ztest_dmu_object_alloc_free(zd, 0); zil_commit(zd->zd_zilog, 0); } txg_wait_synced(spa_get_dsl(spa), 0); /* * Freeze the pool. This stops spa_sync() from doing anything, * so that the only way to record changes from now on is the ZIL. */ spa_freeze(spa); /* * Because it is hard to predict how much space a write will actually * require beforehand, we leave ourselves some fudge space to write over * capacity. */ uint64_t capacity = metaslab_class_get_space(spa_normal_class(spa)) / 2; /* * Run tests that generate log records but don't alter the pool config * or depend on DSL sync tasks (snapshots, objset create/destroy, etc). * We do a txg_wait_synced() after each iteration to force the txg * to increase well beyond the last synced value in the uberblock. * The ZIL should be OK with that. * * Run a random number of times less than zo_maxloops and ensure we do * not run out of space on the pool. */ while (ztest_random(10) != 0 && numloops++ < ztest_opts.zo_maxloops && metaslab_class_get_alloc(spa_normal_class(spa)) < capacity) { ztest_od_t od; ztest_od_init(&od, 0, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0, 0); VERIFY0(ztest_object_init(zd, &od, sizeof (od), B_FALSE)); ztest_io(zd, od.od_object, ztest_random(ZTEST_RANGE_LOCKS) << SPA_MAXBLOCKSHIFT); txg_wait_synced(spa_get_dsl(spa), 0); } /* * Commit all of the changes we just generated. */ zil_commit(zd->zd_zilog, 0); txg_wait_synced(spa_get_dsl(spa), 0); /* * Close our dataset and close the pool. */ ztest_dataset_close(0); spa_close(spa, FTAG); kernel_fini(); /* * Open and close the pool and dataset to induce log replay. */ kernel_init(SPA_MODE_READ | SPA_MODE_WRITE); VERIFY0(spa_open(ztest_opts.zo_pool, &spa, FTAG)); ASSERT3U(spa_freeze_txg(spa), ==, UINT64_MAX); VERIFY0(ztest_dataset_open(0)); ztest_spa = spa; txg_wait_synced(spa_get_dsl(spa), 0); ztest_dataset_close(0); ztest_reguid(NULL, 0); spa_close(spa, FTAG); kernel_fini(); } static void ztest_import_impl(void) { importargs_t args = { 0 }; nvlist_t *cfg = NULL; int nsearch = 1; char *searchdirs[nsearch]; int flags = ZFS_IMPORT_MISSING_LOG; searchdirs[0] = ztest_opts.zo_dir; args.paths = nsearch; args.path = searchdirs; args.can_be_active = B_FALSE; VERIFY0(zpool_find_config(NULL, ztest_opts.zo_pool, &cfg, &args, &libzpool_config_ops)); VERIFY0(spa_import(ztest_opts.zo_pool, cfg, NULL, flags)); fnvlist_free(cfg); } /* * Import a storage pool with the given name. */ static void ztest_import(ztest_shared_t *zs) { spa_t *spa; mutex_init(&ztest_vdev_lock, NULL, MUTEX_DEFAULT, NULL); mutex_init(&ztest_checkpoint_lock, NULL, MUTEX_DEFAULT, NULL); VERIFY0(pthread_rwlock_init(&ztest_name_lock, NULL)); kernel_init(SPA_MODE_READ | SPA_MODE_WRITE); ztest_import_impl(); VERIFY0(spa_open(ztest_opts.zo_pool, &spa, FTAG)); zs->zs_metaslab_sz = 1ULL << spa->spa_root_vdev->vdev_child[0]->vdev_ms_shift; spa_close(spa, FTAG); kernel_fini(); if (!ztest_opts.zo_mmp_test) { ztest_run_zdb(ztest_opts.zo_pool); ztest_freeze(); ztest_run_zdb(ztest_opts.zo_pool); } (void) pthread_rwlock_destroy(&ztest_name_lock); mutex_destroy(&ztest_vdev_lock); mutex_destroy(&ztest_checkpoint_lock); } /* * Kick off threads to run tests on all datasets in parallel. */ static void ztest_run(ztest_shared_t *zs) { spa_t *spa; objset_t *os; kthread_t *resume_thread, *deadman_thread; kthread_t **run_threads; uint64_t object; int error; int t, d; ztest_exiting = B_FALSE; /* * Initialize parent/child shared state. */ mutex_init(&ztest_vdev_lock, NULL, MUTEX_DEFAULT, NULL); mutex_init(&ztest_checkpoint_lock, NULL, MUTEX_DEFAULT, NULL); VERIFY0(pthread_rwlock_init(&ztest_name_lock, NULL)); zs->zs_thread_start = gethrtime(); zs->zs_thread_stop = zs->zs_thread_start + ztest_opts.zo_passtime * NANOSEC; zs->zs_thread_stop = MIN(zs->zs_thread_stop, zs->zs_proc_stop); zs->zs_thread_kill = zs->zs_thread_stop; if (ztest_random(100) < ztest_opts.zo_killrate) { zs->zs_thread_kill -= ztest_random(ztest_opts.zo_passtime * NANOSEC); } mutex_init(&zcl.zcl_callbacks_lock, NULL, MUTEX_DEFAULT, NULL); list_create(&zcl.zcl_callbacks, sizeof (ztest_cb_data_t), offsetof(ztest_cb_data_t, zcd_node)); /* * Open our pool. It may need to be imported first depending on * what tests were running when the previous pass was terminated. */ kernel_init(SPA_MODE_READ | SPA_MODE_WRITE); error = spa_open(ztest_opts.zo_pool, &spa, FTAG); if (error) { VERIFY3S(error, ==, ENOENT); ztest_import_impl(); VERIFY0(spa_open(ztest_opts.zo_pool, &spa, FTAG)); zs->zs_metaslab_sz = 1ULL << spa->spa_root_vdev->vdev_child[0]->vdev_ms_shift; } metaslab_preload_limit = ztest_random(20) + 1; ztest_spa = spa; VERIFY0(vdev_raidz_impl_set("cycle")); dmu_objset_stats_t dds; VERIFY0(ztest_dmu_objset_own(ztest_opts.zo_pool, DMU_OST_ANY, B_TRUE, B_TRUE, FTAG, &os)); dsl_pool_config_enter(dmu_objset_pool(os), FTAG); dmu_objset_fast_stat(os, &dds); dsl_pool_config_exit(dmu_objset_pool(os), FTAG); zs->zs_guid = dds.dds_guid; dmu_objset_disown(os, B_TRUE, FTAG); /* * Create a thread to periodically resume suspended I/O. */ resume_thread = thread_create(NULL, 0, ztest_resume_thread, spa, 0, NULL, TS_RUN | TS_JOINABLE, defclsyspri); /* * Create a deadman thread and set to panic if we hang. */ deadman_thread = thread_create(NULL, 0, ztest_deadman_thread, zs, 0, NULL, TS_RUN | TS_JOINABLE, defclsyspri); spa->spa_deadman_failmode = ZIO_FAILURE_MODE_PANIC; /* * Verify that we can safely inquire about any object, * whether it's allocated or not. To make it interesting, * we probe a 5-wide window around each power of two. * This hits all edge cases, including zero and the max. */ for (t = 0; t < 64; t++) { for (d = -5; d <= 5; d++) { error = dmu_object_info(spa->spa_meta_objset, (1ULL << t) + d, NULL); ASSERT(error == 0 || error == ENOENT || error == EINVAL); } } /* * If we got any ENOSPC errors on the previous run, destroy something. */ if (zs->zs_enospc_count != 0) { int d = ztest_random(ztest_opts.zo_datasets); ztest_dataset_destroy(d); } zs->zs_enospc_count = 0; /* * If we were in the middle of ztest_device_removal() and were killed * we need to ensure the removal and scrub complete before running * any tests that check ztest_device_removal_active. The removal will * be restarted automatically when the spa is opened, but we need to * initiate the scrub manually if it is not already in progress. Note * that we always run the scrub whenever an indirect vdev exists * because we have no way of knowing for sure if ztest_device_removal() * fully completed its scrub before the pool was reimported. */ if (spa->spa_removing_phys.sr_state == DSS_SCANNING || spa->spa_removing_phys.sr_prev_indirect_vdev != -1) { while (spa->spa_removing_phys.sr_state == DSS_SCANNING) txg_wait_synced(spa_get_dsl(spa), 0); error = ztest_scrub_impl(spa); if (error == EBUSY) error = 0; ASSERT0(error); } run_threads = umem_zalloc(ztest_opts.zo_threads * sizeof (kthread_t *), UMEM_NOFAIL); if (ztest_opts.zo_verbose >= 4) (void) printf("starting main threads...\n"); /* * Replay all logs of all datasets in the pool. This is primarily for * temporary datasets which wouldn't otherwise get replayed, which * can trigger failures when attempting to offline a SLOG in * ztest_fault_inject(). */ (void) dmu_objset_find(ztest_opts.zo_pool, ztest_replay_zil_cb, NULL, DS_FIND_CHILDREN); /* * Kick off all the tests that run in parallel. */ for (t = 0; t < ztest_opts.zo_threads; t++) { if (t < ztest_opts.zo_datasets && ztest_dataset_open(t) != 0) { umem_free(run_threads, ztest_opts.zo_threads * sizeof (kthread_t *)); return; } run_threads[t] = thread_create(NULL, 0, ztest_thread, (void *)(uintptr_t)t, 0, NULL, TS_RUN | TS_JOINABLE, defclsyspri); } /* * Wait for all of the tests to complete. */ for (t = 0; t < ztest_opts.zo_threads; t++) VERIFY0(thread_join(run_threads[t])); /* * Close all datasets. This must be done after all the threads * are joined so we can be sure none of the datasets are in-use * by any of the threads. */ for (t = 0; t < ztest_opts.zo_threads; t++) { if (t < ztest_opts.zo_datasets) ztest_dataset_close(t); } txg_wait_synced(spa_get_dsl(spa), 0); zs->zs_alloc = metaslab_class_get_alloc(spa_normal_class(spa)); zs->zs_space = metaslab_class_get_space(spa_normal_class(spa)); umem_free(run_threads, ztest_opts.zo_threads * sizeof (kthread_t *)); /* Kill the resume and deadman threads */ ztest_exiting = B_TRUE; VERIFY0(thread_join(resume_thread)); VERIFY0(thread_join(deadman_thread)); ztest_resume(spa); /* * Right before closing the pool, kick off a bunch of async I/O; * spa_close() should wait for it to complete. */ for (object = 1; object < 50; object++) { dmu_prefetch(spa->spa_meta_objset, object, 0, 0, 1ULL << 20, ZIO_PRIORITY_SYNC_READ); } /* Verify that at least one commit cb was called in a timely fashion */ if (zc_cb_counter >= ZTEST_COMMIT_CB_MIN_REG) VERIFY0(zc_min_txg_delay); spa_close(spa, FTAG); /* * Verify that we can loop over all pools. */ mutex_enter(&spa_namespace_lock); for (spa = spa_next(NULL); spa != NULL; spa = spa_next(spa)) if (ztest_opts.zo_verbose > 3) (void) printf("spa_next: found %s\n", spa_name(spa)); mutex_exit(&spa_namespace_lock); /* * Verify that we can export the pool and reimport it under a * different name. */ if ((ztest_random(2) == 0) && !ztest_opts.zo_mmp_test) { char name[ZFS_MAX_DATASET_NAME_LEN]; (void) snprintf(name, sizeof (name), "%s_import", ztest_opts.zo_pool); ztest_spa_import_export(ztest_opts.zo_pool, name); ztest_spa_import_export(name, ztest_opts.zo_pool); } kernel_fini(); list_destroy(&zcl.zcl_callbacks); mutex_destroy(&zcl.zcl_callbacks_lock); (void) pthread_rwlock_destroy(&ztest_name_lock); mutex_destroy(&ztest_vdev_lock); mutex_destroy(&ztest_checkpoint_lock); } static void print_time(hrtime_t t, char *timebuf) { hrtime_t s = t / NANOSEC; hrtime_t m = s / 60; hrtime_t h = m / 60; hrtime_t d = h / 24; s -= m * 60; m -= h * 60; h -= d * 24; timebuf[0] = '\0'; if (d) (void) sprintf(timebuf, "%llud%02lluh%02llum%02llus", d, h, m, s); else if (h) (void) sprintf(timebuf, "%lluh%02llum%02llus", h, m, s); else if (m) (void) sprintf(timebuf, "%llum%02llus", m, s); else (void) sprintf(timebuf, "%llus", s); } static nvlist_t * make_random_props(void) { nvlist_t *props; props = fnvlist_alloc(); if (ztest_random(2) == 0) return (props); fnvlist_add_uint64(props, zpool_prop_to_name(ZPOOL_PROP_AUTOREPLACE), 1); return (props); } /* * Create a storage pool with the given name and initial vdev size. * Then test spa_freeze() functionality. */ static void ztest_init(ztest_shared_t *zs) { spa_t *spa; nvlist_t *nvroot, *props; int i; mutex_init(&ztest_vdev_lock, NULL, MUTEX_DEFAULT, NULL); mutex_init(&ztest_checkpoint_lock, NULL, MUTEX_DEFAULT, NULL); VERIFY0(pthread_rwlock_init(&ztest_name_lock, NULL)); kernel_init(SPA_MODE_READ | SPA_MODE_WRITE); /* * Create the storage pool. */ (void) spa_destroy(ztest_opts.zo_pool); ztest_shared->zs_vdev_next_leaf = 0; zs->zs_splits = 0; zs->zs_mirrors = ztest_opts.zo_mirrors; nvroot = make_vdev_root(NULL, NULL, NULL, ztest_opts.zo_vdev_size, 0, NULL, ztest_opts.zo_raid_children, zs->zs_mirrors, 1); props = make_random_props(); /* * We don't expect the pool to suspend unless maxfaults == 0, * in which case ztest_fault_inject() temporarily takes away * the only valid replica. */ fnvlist_add_uint64(props, zpool_prop_to_name(ZPOOL_PROP_FAILUREMODE), MAXFAULTS(zs) ? ZIO_FAILURE_MODE_PANIC : ZIO_FAILURE_MODE_WAIT); for (i = 0; i < SPA_FEATURES; i++) { char *buf; if (!spa_feature_table[i].fi_zfs_mod_supported) continue; /* * 75% chance of using the log space map feature. We want ztest * to exercise both the code paths that use the log space map * feature and the ones that don't. */ if (i == SPA_FEATURE_LOG_SPACEMAP && ztest_random(4) == 0) continue; VERIFY3S(-1, !=, asprintf(&buf, "feature@%s", spa_feature_table[i].fi_uname)); fnvlist_add_uint64(props, buf, 0); free(buf); } VERIFY0(spa_create(ztest_opts.zo_pool, nvroot, props, NULL, NULL)); fnvlist_free(nvroot); fnvlist_free(props); VERIFY0(spa_open(ztest_opts.zo_pool, &spa, FTAG)); zs->zs_metaslab_sz = 1ULL << spa->spa_root_vdev->vdev_child[0]->vdev_ms_shift; spa_close(spa, FTAG); kernel_fini(); if (!ztest_opts.zo_mmp_test) { ztest_run_zdb(ztest_opts.zo_pool); ztest_freeze(); ztest_run_zdb(ztest_opts.zo_pool); } (void) pthread_rwlock_destroy(&ztest_name_lock); mutex_destroy(&ztest_vdev_lock); mutex_destroy(&ztest_checkpoint_lock); } static void setup_data_fd(void) { static char ztest_name_data[] = "/tmp/ztest.data.XXXXXX"; ztest_fd_data = mkstemp(ztest_name_data); ASSERT3S(ztest_fd_data, >=, 0); (void) unlink(ztest_name_data); } static int shared_data_size(ztest_shared_hdr_t *hdr) { int size; size = hdr->zh_hdr_size; size += hdr->zh_opts_size; size += hdr->zh_size; size += hdr->zh_stats_size * hdr->zh_stats_count; size += hdr->zh_ds_size * hdr->zh_ds_count; return (size); } static void setup_hdr(void) { int size; ztest_shared_hdr_t *hdr; hdr = (void *)mmap(0, P2ROUNDUP(sizeof (*hdr), getpagesize()), PROT_READ | PROT_WRITE, MAP_SHARED, ztest_fd_data, 0); ASSERT3P(hdr, !=, MAP_FAILED); VERIFY0(ftruncate(ztest_fd_data, sizeof (ztest_shared_hdr_t))); hdr->zh_hdr_size = sizeof (ztest_shared_hdr_t); hdr->zh_opts_size = sizeof (ztest_shared_opts_t); hdr->zh_size = sizeof (ztest_shared_t); hdr->zh_stats_size = sizeof (ztest_shared_callstate_t); hdr->zh_stats_count = ZTEST_FUNCS; hdr->zh_ds_size = sizeof (ztest_shared_ds_t); hdr->zh_ds_count = ztest_opts.zo_datasets; size = shared_data_size(hdr); VERIFY0(ftruncate(ztest_fd_data, size)); (void) munmap((caddr_t)hdr, P2ROUNDUP(sizeof (*hdr), getpagesize())); } static void setup_data(void) { int size, offset; ztest_shared_hdr_t *hdr; uint8_t *buf; hdr = (void *)mmap(0, P2ROUNDUP(sizeof (*hdr), getpagesize()), PROT_READ, MAP_SHARED, ztest_fd_data, 0); ASSERT3P(hdr, !=, MAP_FAILED); size = shared_data_size(hdr); (void) munmap((caddr_t)hdr, P2ROUNDUP(sizeof (*hdr), getpagesize())); hdr = ztest_shared_hdr = (void *)mmap(0, P2ROUNDUP(size, getpagesize()), PROT_READ | PROT_WRITE, MAP_SHARED, ztest_fd_data, 0); ASSERT3P(hdr, !=, MAP_FAILED); buf = (uint8_t *)hdr; offset = hdr->zh_hdr_size; ztest_shared_opts = (void *)&buf[offset]; offset += hdr->zh_opts_size; ztest_shared = (void *)&buf[offset]; offset += hdr->zh_size; ztest_shared_callstate = (void *)&buf[offset]; offset += hdr->zh_stats_size * hdr->zh_stats_count; ztest_shared_ds = (void *)&buf[offset]; } static boolean_t exec_child(char *cmd, char *libpath, boolean_t ignorekill, int *statusp) { pid_t pid; int status; char *cmdbuf = NULL; pid = fork(); if (cmd == NULL) { cmdbuf = umem_alloc(MAXPATHLEN, UMEM_NOFAIL); (void) strlcpy(cmdbuf, getexecname(), MAXPATHLEN); cmd = cmdbuf; } if (pid == -1) fatal(B_TRUE, "fork failed"); if (pid == 0) { /* child */ char *emptyargv[2] = { cmd, NULL }; char fd_data_str[12]; struct rlimit rl = { 1024, 1024 }; (void) setrlimit(RLIMIT_NOFILE, &rl); (void) close(ztest_fd_rand); VERIFY3S(11, >=, snprintf(fd_data_str, 12, "%d", ztest_fd_data)); VERIFY0(setenv("ZTEST_FD_DATA", fd_data_str, 1)); (void) enable_extended_FILE_stdio(-1, -1); if (libpath != NULL) VERIFY0(setenv("LD_LIBRARY_PATH", libpath, 1)); (void) execv(cmd, emptyargv); ztest_dump_core = B_FALSE; fatal(B_TRUE, "exec failed: %s", cmd); } if (cmdbuf != NULL) { umem_free(cmdbuf, MAXPATHLEN); cmd = NULL; } while (waitpid(pid, &status, 0) != pid) continue; if (statusp != NULL) *statusp = status; if (WIFEXITED(status)) { if (WEXITSTATUS(status) != 0) { (void) fprintf(stderr, "child exited with code %d\n", WEXITSTATUS(status)); exit(2); } return (B_FALSE); } else if (WIFSIGNALED(status)) { if (!ignorekill || WTERMSIG(status) != SIGKILL) { (void) fprintf(stderr, "child died with signal %d\n", WTERMSIG(status)); exit(3); } return (B_TRUE); } else { (void) fprintf(stderr, "something strange happened to child\n"); exit(4); } } static void ztest_run_init(void) { int i; ztest_shared_t *zs = ztest_shared; /* * Blow away any existing copy of zpool.cache */ (void) remove(spa_config_path); if (ztest_opts.zo_init == 0) { if (ztest_opts.zo_verbose >= 1) (void) printf("Importing pool %s\n", ztest_opts.zo_pool); ztest_import(zs); return; } /* * Create and initialize our storage pool. */ for (i = 1; i <= ztest_opts.zo_init; i++) { bzero(zs, sizeof (ztest_shared_t)); if (ztest_opts.zo_verbose >= 3 && ztest_opts.zo_init != 1) { (void) printf("ztest_init(), pass %d\n", i); } ztest_init(zs); } } int main(int argc, char **argv) { int kills = 0; int iters = 0; int older = 0; int newer = 0; ztest_shared_t *zs; ztest_info_t *zi; ztest_shared_callstate_t *zc; char timebuf[100]; char numbuf[NN_NUMBUF_SZ]; char *cmd; boolean_t hasalt; int f, err; char *fd_data_str = getenv("ZTEST_FD_DATA"); struct sigaction action; (void) setvbuf(stdout, NULL, _IOLBF, 0); dprintf_setup(&argc, argv); zfs_deadman_synctime_ms = 300000; zfs_deadman_checktime_ms = 30000; /* * As two-word space map entries may not come up often (especially * if pool and vdev sizes are small) we want to force at least some * of them so the feature get tested. */ zfs_force_some_double_word_sm_entries = B_TRUE; /* * Verify that even extensively damaged split blocks with many * segments can be reconstructed in a reasonable amount of time * when reconstruction is known to be possible. * * Note: the lower this value is, the more damage we inflict, and * the more time ztest spends in recovering that damage. We chose * to induce damage 1/100th of the time so recovery is tested but * not so frequently that ztest doesn't get to test other code paths. */ zfs_reconstruct_indirect_damage_fraction = 100; action.sa_handler = sig_handler; sigemptyset(&action.sa_mask); action.sa_flags = 0; if (sigaction(SIGSEGV, &action, NULL) < 0) { (void) fprintf(stderr, "ztest: cannot catch SIGSEGV: %s.\n", strerror(errno)); exit(EXIT_FAILURE); } if (sigaction(SIGABRT, &action, NULL) < 0) { (void) fprintf(stderr, "ztest: cannot catch SIGABRT: %s.\n", strerror(errno)); exit(EXIT_FAILURE); } /* * Force random_get_bytes() to use /dev/urandom in order to prevent * ztest from needlessly depleting the system entropy pool. */ random_path = "/dev/urandom"; ztest_fd_rand = open(random_path, O_RDONLY); ASSERT3S(ztest_fd_rand, >=, 0); if (!fd_data_str) { process_options(argc, argv); setup_data_fd(); setup_hdr(); setup_data(); bcopy(&ztest_opts, ztest_shared_opts, sizeof (*ztest_shared_opts)); } else { ztest_fd_data = atoi(fd_data_str); setup_data(); bcopy(ztest_shared_opts, &ztest_opts, sizeof (ztest_opts)); } ASSERT3U(ztest_opts.zo_datasets, ==, ztest_shared_hdr->zh_ds_count); err = ztest_set_global_vars(); if (err != 0 && !fd_data_str) { /* error message done by ztest_set_global_vars */ exit(EXIT_FAILURE); } else { /* children should not be spawned if setting gvars fails */ VERIFY3S(err, ==, 0); } /* Override location of zpool.cache */ VERIFY3S(asprintf((char **)&spa_config_path, "%s/zpool.cache", ztest_opts.zo_dir), !=, -1); ztest_ds = umem_alloc(ztest_opts.zo_datasets * sizeof (ztest_ds_t), UMEM_NOFAIL); zs = ztest_shared; if (fd_data_str) { metaslab_force_ganging = ztest_opts.zo_metaslab_force_ganging; metaslab_df_alloc_threshold = zs->zs_metaslab_df_alloc_threshold; if (zs->zs_do_init) ztest_run_init(); else ztest_run(zs); exit(0); } hasalt = (strlen(ztest_opts.zo_alt_ztest) != 0); if (ztest_opts.zo_verbose >= 1) { (void) printf("%"PRIu64" vdevs, %d datasets, %d threads," "%d %s disks, %"PRIu64" seconds...\n\n", ztest_opts.zo_vdevs, ztest_opts.zo_datasets, ztest_opts.zo_threads, ztest_opts.zo_raid_children, ztest_opts.zo_raid_type, ztest_opts.zo_time); } cmd = umem_alloc(MAXNAMELEN, UMEM_NOFAIL); (void) strlcpy(cmd, getexecname(), MAXNAMELEN); zs->zs_do_init = B_TRUE; if (strlen(ztest_opts.zo_alt_ztest) != 0) { if (ztest_opts.zo_verbose >= 1) { (void) printf("Executing older ztest for " "initialization: %s\n", ztest_opts.zo_alt_ztest); } VERIFY(!exec_child(ztest_opts.zo_alt_ztest, ztest_opts.zo_alt_libpath, B_FALSE, NULL)); } else { VERIFY(!exec_child(NULL, NULL, B_FALSE, NULL)); } zs->zs_do_init = B_FALSE; zs->zs_proc_start = gethrtime(); zs->zs_proc_stop = zs->zs_proc_start + ztest_opts.zo_time * NANOSEC; for (f = 0; f < ZTEST_FUNCS; f++) { zi = &ztest_info[f]; zc = ZTEST_GET_SHARED_CALLSTATE(f); if (zs->zs_proc_start + zi->zi_interval[0] > zs->zs_proc_stop) zc->zc_next = UINT64_MAX; else zc->zc_next = zs->zs_proc_start + ztest_random(2 * zi->zi_interval[0] + 1); } /* * Run the tests in a loop. These tests include fault injection * to verify that self-healing data works, and forced crashes * to verify that we never lose on-disk consistency. */ while (gethrtime() < zs->zs_proc_stop) { int status; boolean_t killed; /* * Initialize the workload counters for each function. */ for (f = 0; f < ZTEST_FUNCS; f++) { zc = ZTEST_GET_SHARED_CALLSTATE(f); zc->zc_count = 0; zc->zc_time = 0; } /* Set the allocation switch size */ zs->zs_metaslab_df_alloc_threshold = ztest_random(zs->zs_metaslab_sz / 4) + 1; if (!hasalt || ztest_random(2) == 0) { if (hasalt && ztest_opts.zo_verbose >= 1) { (void) printf("Executing newer ztest: %s\n", cmd); } newer++; killed = exec_child(cmd, NULL, B_TRUE, &status); } else { if (hasalt && ztest_opts.zo_verbose >= 1) { (void) printf("Executing older ztest: %s\n", ztest_opts.zo_alt_ztest); } older++; killed = exec_child(ztest_opts.zo_alt_ztest, ztest_opts.zo_alt_libpath, B_TRUE, &status); } if (killed) kills++; iters++; if (ztest_opts.zo_verbose >= 1) { hrtime_t now = gethrtime(); now = MIN(now, zs->zs_proc_stop); print_time(zs->zs_proc_stop - now, timebuf); nicenum(zs->zs_space, numbuf, sizeof (numbuf)); (void) printf("Pass %3d, %8s, %3"PRIu64" ENOSPC, " "%4.1f%% of %5s used, %3.0f%% done, %8s to go\n", iters, WIFEXITED(status) ? "Complete" : "SIGKILL", zs->zs_enospc_count, 100.0 * zs->zs_alloc / zs->zs_space, numbuf, 100.0 * (now - zs->zs_proc_start) / (ztest_opts.zo_time * NANOSEC), timebuf); } if (ztest_opts.zo_verbose >= 2) { (void) printf("\nWorkload summary:\n\n"); (void) printf("%7s %9s %s\n", "Calls", "Time", "Function"); (void) printf("%7s %9s %s\n", "-----", "----", "--------"); for (f = 0; f < ZTEST_FUNCS; f++) { zi = &ztest_info[f]; zc = ZTEST_GET_SHARED_CALLSTATE(f); print_time(zc->zc_time, timebuf); (void) printf("%7"PRIu64" %9s %s\n", zc->zc_count, timebuf, zi->zi_funcname); } (void) printf("\n"); } if (!ztest_opts.zo_mmp_test) ztest_run_zdb(ztest_opts.zo_pool); } if (ztest_opts.zo_verbose >= 1) { if (hasalt) { (void) printf("%d runs of older ztest: %s\n", older, ztest_opts.zo_alt_ztest); (void) printf("%d runs of newer ztest: %s\n", newer, cmd); } (void) printf("%d killed, %d completed, %.0f%% kill rate\n", kills, iters - kills, (100.0 * kills) / MAX(1, iters)); } umem_free(cmd, MAXNAMELEN); return (0); } diff --git a/include/sys/zfs_sa.h b/include/sys/zfs_sa.h index a0c383807aa4..6b0336997c20 100644 --- a/include/sys/zfs_sa.h +++ b/include/sys/zfs_sa.h @@ -1,152 +1,152 @@ /* * 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 2010 Sun Microsystems, Inc. All rights reserved. * Use is subject to license terms. */ #ifndef _SYS_ZFS_SA_H #define _SYS_ZFS_SA_H #ifdef _KERNEL #include #include #include #include #include #include #include #endif #ifdef __cplusplus extern "C" { #endif /* * This is the list of known attributes * to the ZPL. The values of the actual * attributes are not defined by the order * the enums. It is controlled by the attribute * registration mechanism. Two different file system * could have different numeric values for the same * attributes. this list is only used for dereferencing * into the table that will hold the actual numeric value. */ typedef enum zpl_attr { ZPL_ATIME, ZPL_MTIME, ZPL_CTIME, ZPL_CRTIME, ZPL_GEN, ZPL_MODE, ZPL_SIZE, ZPL_PARENT, ZPL_LINKS, ZPL_XATTR, ZPL_RDEV, ZPL_FLAGS, ZPL_UID, ZPL_GID, ZPL_PAD, ZPL_ZNODE_ACL, ZPL_DACL_COUNT, ZPL_SYMLINK, ZPL_SCANSTAMP, ZPL_DACL_ACES, ZPL_DXATTR, ZPL_PROJID, ZPL_END } zpl_attr_t; #define ZFS_OLD_ZNODE_PHYS_SIZE 0x108 #define ZFS_SA_BASE_ATTR_SIZE (ZFS_OLD_ZNODE_PHYS_SIZE - \ sizeof (zfs_acl_phys_t)) #define SA_MODE_OFFSET 0 #define SA_SIZE_OFFSET 8 #define SA_GEN_OFFSET 16 #define SA_UID_OFFSET 24 #define SA_GID_OFFSET 32 #define SA_PARENT_OFFSET 40 #define SA_FLAGS_OFFSET 48 #define SA_PROJID_OFFSET 128 extern const sa_attr_reg_t zfs_attr_table[ZPL_END + 1]; /* * This is a deprecated data structure that only exists for * dealing with file systems create prior to ZPL version 5. */ typedef struct znode_phys { uint64_t zp_atime[2]; /* 0 - last file access time */ uint64_t zp_mtime[2]; /* 16 - last file modification time */ uint64_t zp_ctime[2]; /* 32 - last file change time */ uint64_t zp_crtime[2]; /* 48 - creation time */ uint64_t zp_gen; /* 64 - generation (txg of creation) */ uint64_t zp_mode; /* 72 - file mode bits */ uint64_t zp_size; /* 80 - size of file */ uint64_t zp_parent; /* 88 - directory parent (`..') */ uint64_t zp_links; /* 96 - number of links to file */ uint64_t zp_xattr; /* 104 - DMU object for xattrs */ uint64_t zp_rdev; /* 112 - dev_t for VBLK & VCHR files */ uint64_t zp_flags; /* 120 - persistent flags */ uint64_t zp_uid; /* 128 - file owner */ uint64_t zp_gid; /* 136 - owning group */ uint64_t zp_zap; /* 144 - extra attributes */ uint64_t zp_pad[3]; /* 152 - future */ zfs_acl_phys_t zp_acl; /* 176 - 263 ACL */ /* * Data may pad out any remaining bytes in the znode buffer, eg: * * |<---------------------- dnode_phys (512) ------------------------>| * |<-- dnode (192) --->|<----------- "bonus" buffer (320) ---------->| * |<---- znode (264) ---->|<---- data (56) ---->| * * At present, we use this space for the following: * - symbolic links * - 32-byte anti-virus scanstamp (regular files only) */ } znode_phys_t; #ifdef _KERNEL #define DXATTR_MAX_ENTRY_SIZE (32768) #define DXATTR_MAX_SA_SIZE (SPA_OLD_MAXBLOCKSIZE >> 1) int zfs_sa_readlink(struct znode *, zfs_uio_t *); void zfs_sa_symlink(struct znode *, char *link, int len, dmu_tx_t *); void zfs_sa_get_scanstamp(struct znode *, xvattr_t *); void zfs_sa_set_scanstamp(struct znode *, xvattr_t *, dmu_tx_t *); int zfs_sa_get_xattr(struct znode *); -int zfs_sa_set_xattr(struct znode *); +int zfs_sa_set_xattr(struct znode *, const char *, const void *, size_t); void zfs_sa_upgrade(struct sa_handle *, dmu_tx_t *); void zfs_sa_upgrade_txholds(dmu_tx_t *, struct znode *); void zfs_sa_init(void); void zfs_sa_fini(void); #endif #ifdef __cplusplus } #endif #endif /* _SYS_ZFS_SA_H */ diff --git a/include/sys/zfs_znode.h b/include/sys/zfs_znode.h index 1bf25a77d3a0..e20c18cc2b62 100644 --- a/include/sys/zfs_znode.h +++ b/include/sys/zfs_znode.h @@ -1,297 +1,299 @@ /* * 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 (c) 2012, 2018 by Delphix. All rights reserved. * Copyright 2016 Nexenta Systems, Inc. All rights reserved. */ #ifndef _SYS_FS_ZFS_ZNODE_H #define _SYS_FS_ZFS_ZNODE_H #include #include #include #ifdef __cplusplus extern "C" { #endif /* * Additional file level attributes, that are stored * in the upper half of zp_flags */ #define ZFS_READONLY 0x0000000100000000ull #define ZFS_HIDDEN 0x0000000200000000ull #define ZFS_SYSTEM 0x0000000400000000ull #define ZFS_ARCHIVE 0x0000000800000000ull #define ZFS_IMMUTABLE 0x0000001000000000ull #define ZFS_NOUNLINK 0x0000002000000000ull #define ZFS_APPENDONLY 0x0000004000000000ull #define ZFS_NODUMP 0x0000008000000000ull #define ZFS_OPAQUE 0x0000010000000000ull #define ZFS_AV_QUARANTINED 0x0000020000000000ull #define ZFS_AV_MODIFIED 0x0000040000000000ull #define ZFS_REPARSE 0x0000080000000000ull #define ZFS_OFFLINE 0x0000100000000000ull #define ZFS_SPARSE 0x0000200000000000ull /* * PROJINHERIT attribute is used to indicate that the child object under the * directory which has the PROJINHERIT attribute needs to inherit its parent * project ID that is used by project quota. */ #define ZFS_PROJINHERIT 0x0000400000000000ull /* * PROJID attr is used internally to indicate that the object has project ID. */ #define ZFS_PROJID 0x0000800000000000ull #define ZFS_ATTR_SET(zp, attr, value, pflags, tx) \ { \ if (value) \ pflags |= attr; \ else \ pflags &= ~attr; \ VERIFY(0 == sa_update(zp->z_sa_hdl, SA_ZPL_FLAGS(ZTOZSB(zp)), \ &pflags, sizeof (pflags), tx)); \ } /* * Define special zfs pflags */ #define ZFS_XATTR 0x1 /* is an extended attribute */ #define ZFS_INHERIT_ACE 0x2 /* ace has inheritable ACEs */ #define ZFS_ACL_TRIVIAL 0x4 /* files ACL is trivial */ #define ZFS_ACL_OBJ_ACE 0x8 /* ACL has CMPLX Object ACE */ #define ZFS_ACL_PROTECTED 0x10 /* ACL protected */ #define ZFS_ACL_DEFAULTED 0x20 /* ACL should be defaulted */ #define ZFS_ACL_AUTO_INHERIT 0x40 /* ACL should be inherited */ #define ZFS_BONUS_SCANSTAMP 0x80 /* Scanstamp in bonus area */ #define ZFS_NO_EXECS_DENIED 0x100 /* exec was given to everyone */ #define SA_ZPL_ATIME(z) z->z_attr_table[ZPL_ATIME] #define SA_ZPL_MTIME(z) z->z_attr_table[ZPL_MTIME] #define SA_ZPL_CTIME(z) z->z_attr_table[ZPL_CTIME] #define SA_ZPL_CRTIME(z) z->z_attr_table[ZPL_CRTIME] #define SA_ZPL_GEN(z) z->z_attr_table[ZPL_GEN] #define SA_ZPL_DACL_ACES(z) z->z_attr_table[ZPL_DACL_ACES] #define SA_ZPL_XATTR(z) z->z_attr_table[ZPL_XATTR] #define SA_ZPL_SYMLINK(z) z->z_attr_table[ZPL_SYMLINK] #define SA_ZPL_RDEV(z) z->z_attr_table[ZPL_RDEV] #define SA_ZPL_SCANSTAMP(z) z->z_attr_table[ZPL_SCANSTAMP] #define SA_ZPL_UID(z) z->z_attr_table[ZPL_UID] #define SA_ZPL_GID(z) z->z_attr_table[ZPL_GID] #define SA_ZPL_PARENT(z) z->z_attr_table[ZPL_PARENT] #define SA_ZPL_LINKS(z) z->z_attr_table[ZPL_LINKS] #define SA_ZPL_MODE(z) z->z_attr_table[ZPL_MODE] #define SA_ZPL_DACL_COUNT(z) z->z_attr_table[ZPL_DACL_COUNT] #define SA_ZPL_FLAGS(z) z->z_attr_table[ZPL_FLAGS] #define SA_ZPL_SIZE(z) z->z_attr_table[ZPL_SIZE] #define SA_ZPL_ZNODE_ACL(z) z->z_attr_table[ZPL_ZNODE_ACL] #define SA_ZPL_DXATTR(z) z->z_attr_table[ZPL_DXATTR] #define SA_ZPL_PAD(z) z->z_attr_table[ZPL_PAD] #define SA_ZPL_PROJID(z) z->z_attr_table[ZPL_PROJID] /* * Is ID ephemeral? */ #define IS_EPHEMERAL(x) (x > MAXUID) /* * Should we use FUIDs? */ #define USE_FUIDS(version, os) (version >= ZPL_VERSION_FUID && \ spa_version(dmu_objset_spa(os)) >= SPA_VERSION_FUID) #define USE_SA(version, os) (version >= ZPL_VERSION_SA && \ spa_version(dmu_objset_spa(os)) >= SPA_VERSION_SA) #define MASTER_NODE_OBJ 1 /* * Special attributes for master node. * "userquota@", "groupquota@" and "projectquota@" are also valid (from * zfs_userquota_prop_prefixes[]). */ #define ZFS_FSID "FSID" #define ZFS_UNLINKED_SET "DELETE_QUEUE" #define ZFS_ROOT_OBJ "ROOT" #define ZPL_VERSION_STR "VERSION" #define ZFS_FUID_TABLES "FUID" #define ZFS_SHARES_DIR "SHARES" #define ZFS_SA_ATTRS "SA_ATTRS" /* * Convert mode bits (zp_mode) to BSD-style DT_* values for storing in * the directory entries. On Linux systems this value is already * defined correctly as part of the /usr/include/dirent.h header file. */ #ifndef IFTODT #define IFTODT(mode) (((mode) & S_IFMT) >> 12) #endif /* * The directory entry has the type (currently unused on Solaris) in the * top 4 bits, and the object number in the low 48 bits. The "middle" * 12 bits are unused. */ #define ZFS_DIRENT_TYPE(de) BF64_GET(de, 60, 4) #define ZFS_DIRENT_OBJ(de) BF64_GET(de, 0, 48) extern int zfs_obj_to_path(objset_t *osp, uint64_t obj, char *buf, int len); #ifdef _KERNEL #include /* * Directory entry locks control access to directory entries. * They are used to protect creates, deletes, and renames. * Each directory znode has a mutex and a list of locked names. */ typedef struct zfs_dirlock { char *dl_name; /* directory entry being locked */ uint32_t dl_sharecnt; /* 0 if exclusive, > 0 if shared */ uint8_t dl_namelock; /* 1 if z_name_lock is NOT held */ uint16_t dl_namesize; /* set if dl_name was allocated */ kcondvar_t dl_cv; /* wait for entry to be unlocked */ struct znode *dl_dzp; /* directory znode */ struct zfs_dirlock *dl_next; /* next in z_dirlocks list */ } zfs_dirlock_t; typedef struct znode { uint64_t z_id; /* object ID for this znode */ kmutex_t z_lock; /* znode modification lock */ krwlock_t z_parent_lock; /* parent lock for directories */ krwlock_t z_name_lock; /* "master" lock for dirent locks */ zfs_dirlock_t *z_dirlocks; /* directory entry lock list */ zfs_rangelock_t z_rangelock; /* file range locks */ boolean_t z_unlinked; /* file has been unlinked */ boolean_t z_atime_dirty; /* atime needs to be synced */ boolean_t z_zn_prefetch; /* Prefetch znodes? */ boolean_t z_is_sa; /* are we native sa? */ boolean_t z_is_mapped; /* are we mmap'ed */ boolean_t z_is_ctldir; /* are we .zfs entry */ boolean_t z_is_stale; /* are we stale due to rollback? */ boolean_t z_suspended; /* extra ref from a suspend? */ uint_t z_blksz; /* block size in bytes */ uint_t z_seq; /* modification sequence number */ uint64_t z_mapcnt; /* number of pages mapped to file */ uint64_t z_dnodesize; /* dnode size */ uint64_t z_size; /* file size (cached) */ uint64_t z_pflags; /* pflags (cached) */ uint32_t z_sync_cnt; /* synchronous open count */ mode_t z_mode; /* mode (cached) */ kmutex_t z_acl_lock; /* acl data lock */ zfs_acl_t *z_acl_cached; /* cached acl */ krwlock_t z_xattr_lock; /* xattr data lock */ nvlist_t *z_xattr_cached; /* cached xattrs */ uint64_t z_xattr_parent; /* parent obj for this xattr */ uint64_t z_projid; /* project ID */ list_node_t z_link_node; /* all znodes in fs link */ sa_handle_t *z_sa_hdl; /* handle to sa data */ /* * Platform specific field, defined by each platform and only * accessible from platform specific code. */ ZNODE_OS_FIELDS; } znode_t; typedef struct znode_hold { uint64_t zh_obj; /* object id */ kmutex_t zh_lock; /* lock serializing object access */ avl_node_t zh_node; /* avl tree linkage */ zfs_refcount_t zh_refcount; /* active consumer reference count */ } znode_hold_t; static inline uint64_t zfs_inherit_projid(znode_t *dzp) { return ((dzp->z_pflags & ZFS_PROJINHERIT) ? dzp->z_projid : ZFS_DEFAULT_PROJID); } /* * Timestamp defines */ #define ACCESSED (ATTR_ATIME) #define STATE_CHANGED (ATTR_CTIME) #define CONTENT_MODIFIED (ATTR_MTIME | ATTR_CTIME) extern int zfs_init_fs(zfsvfs_t *, znode_t **); extern void zfs_set_dataprop(objset_t *); extern void zfs_create_fs(objset_t *os, cred_t *cr, nvlist_t *, dmu_tx_t *tx); extern void zfs_tstamp_update_setup(znode_t *, uint_t, uint64_t [2], uint64_t [2]); extern void zfs_grow_blocksize(znode_t *, uint64_t, dmu_tx_t *); extern int zfs_freesp(znode_t *, uint64_t, uint64_t, int, boolean_t); extern void zfs_znode_init(void); extern void zfs_znode_fini(void); extern int zfs_znode_hold_compare(const void *, const void *); extern int zfs_zget(zfsvfs_t *, uint64_t, znode_t **); extern int zfs_rezget(znode_t *); extern void zfs_zinactive(znode_t *); extern void zfs_znode_delete(znode_t *, dmu_tx_t *); extern void zfs_remove_op_tables(void); extern int zfs_create_op_tables(void); extern dev_t zfs_cmpldev(uint64_t); extern int zfs_get_zplprop(objset_t *os, zfs_prop_t prop, uint64_t *value); extern int zfs_get_stats(objset_t *os, nvlist_t *nv); extern boolean_t zfs_get_vfs_flag_unmounted(objset_t *os); extern void zfs_znode_dmu_fini(znode_t *); extern void zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, znode_t *dzp, znode_t *zp, const char *name, vsecattr_t *, zfs_fuid_info_t *, vattr_t *vap); extern int zfs_log_create_txtype(zil_create_t, vsecattr_t *vsecp, vattr_t *vap); extern void zfs_log_remove(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, znode_t *dzp, const char *name, uint64_t foid, boolean_t unlinked); #define ZFS_NO_OBJECT 0 /* no object id */ extern void zfs_log_link(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, znode_t *dzp, znode_t *zp, const char *name); extern void zfs_log_symlink(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, znode_t *dzp, znode_t *zp, const char *name, const char *link); extern void zfs_log_rename(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, znode_t *sdzp, const char *sname, znode_t *tdzp, const char *dname, znode_t *szp); extern void zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype, znode_t *zp, offset_t off, ssize_t len, int ioflag, zil_callback_t callback, void *callback_data); extern void zfs_log_truncate(zilog_t *zilog, dmu_tx_t *tx, int txtype, znode_t *zp, uint64_t off, uint64_t len); extern void zfs_log_setattr(zilog_t *zilog, dmu_tx_t *tx, int txtype, znode_t *zp, vattr_t *vap, uint_t mask_applied, zfs_fuid_info_t *fuidp); extern void zfs_log_acl(zilog_t *zilog, dmu_tx_t *tx, znode_t *zp, vsecattr_t *vsecp, zfs_fuid_info_t *fuidp); extern void zfs_xvattr_set(znode_t *zp, xvattr_t *xvap, dmu_tx_t *tx); extern void zfs_upgrade(zfsvfs_t *zfsvfs, dmu_tx_t *tx); +extern void zfs_log_setsaxattr(zilog_t *zilog, dmu_tx_t *tx, int txtype, + znode_t *zp, const char *name, const void *value, size_t size); extern void zfs_znode_update_vfs(struct znode *); #endif #ifdef __cplusplus } #endif #endif /* _SYS_FS_ZFS_ZNODE_H */ diff --git a/include/sys/zil.h b/include/sys/zil.h index 8e5a49da2929..05e3647e698a 100644 --- a/include/sys/zil.h +++ b/include/sys/zil.h @@ -1,528 +1,537 @@ /* * 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 (c) 2012, 2018 by Delphix. All rights reserved. */ /* Portions Copyright 2010 Robert Milkowski */ #ifndef _SYS_ZIL_H #define _SYS_ZIL_H #include #include #include #include #include #ifdef __cplusplus extern "C" { #endif struct dsl_pool; struct dsl_dataset; struct lwb; /* * Intent log format: * * Each objset has its own intent log. The log header (zil_header_t) * for objset N's intent log is kept in the Nth object of the SPA's * intent_log objset. The log header points to a chain of log blocks, * each of which contains log records (i.e., transactions) followed by * a log block trailer (zil_trailer_t). The format of a log record * depends on the record (or transaction) type, but all records begin * with a common structure that defines the type, length, and txg. */ /* * Intent log header - this on disk structure holds fields to manage * the log. All fields are 64 bit to easily handle cross architectures. */ typedef struct zil_header { uint64_t zh_claim_txg; /* txg in which log blocks were claimed */ uint64_t zh_replay_seq; /* highest replayed sequence number */ blkptr_t zh_log; /* log chain */ uint64_t zh_claim_blk_seq; /* highest claimed block sequence number */ uint64_t zh_flags; /* header flags */ uint64_t zh_claim_lr_seq; /* highest claimed lr sequence number */ uint64_t zh_pad[3]; } zil_header_t; /* * zh_flags bit settings */ #define ZIL_REPLAY_NEEDED 0x1 /* replay needed - internal only */ #define ZIL_CLAIM_LR_SEQ_VALID 0x2 /* zh_claim_lr_seq field is valid */ /* * Log block chaining. * * Log blocks are chained together. Originally they were chained at the * end of the block. For performance reasons the chain was moved to the * beginning of the block which allows writes for only the data being used. * The older position is supported for backwards compatibility. * * The zio_eck_t contains a zec_cksum which for the intent log is * the sequence number of this log block. A seq of 0 is invalid. * The zec_cksum is checked by the SPA against the sequence * number passed in the blk_cksum field of the blkptr_t */ typedef struct zil_chain { uint64_t zc_pad; blkptr_t zc_next_blk; /* next block in chain */ uint64_t zc_nused; /* bytes in log block used */ zio_eck_t zc_eck; /* block trailer */ } zil_chain_t; #define ZIL_MIN_BLKSZ 4096ULL /* * ziltest is by and large an ugly hack, but very useful in * checking replay without tedious work. * When running ziltest we want to keep all itx's and so maintain * a single list in the zl_itxg[] that uses a high txg: ZILTEST_TXG * We subtract TXG_CONCURRENT_STATES to allow for common code. */ #define ZILTEST_TXG (UINT64_MAX - TXG_CONCURRENT_STATES) /* * The words of a log block checksum. */ #define ZIL_ZC_GUID_0 0 #define ZIL_ZC_GUID_1 1 #define ZIL_ZC_OBJSET 2 #define ZIL_ZC_SEQ 3 typedef enum zil_create { Z_FILE, Z_DIR, Z_XATTRDIR, } zil_create_t; /* * size of xvattr log section. * its composed of lr_attr_t + xvattr bitmap + 2 64 bit timestamps * for create time and a single 64 bit integer for all of the attributes, * and 4 64 bit integers (32 bytes) for the scanstamp. * */ #define ZIL_XVAT_SIZE(mapsize) \ sizeof (lr_attr_t) + (sizeof (uint32_t) * (mapsize - 1)) + \ (sizeof (uint64_t) * 7) /* * Size of ACL in log. The ACE data is padded out to properly align * on 8 byte boundary. */ #define ZIL_ACE_LENGTH(x) (roundup(x, sizeof (uint64_t))) /* * Intent log transaction types and record structures */ #define TX_COMMIT 0 /* Commit marker (no on-disk state) */ #define TX_CREATE 1 /* Create file */ #define TX_MKDIR 2 /* Make directory */ #define TX_MKXATTR 3 /* Make XATTR directory */ #define TX_SYMLINK 4 /* Create symbolic link to a file */ #define TX_REMOVE 5 /* Remove file */ #define TX_RMDIR 6 /* Remove directory */ #define TX_LINK 7 /* Create hard link to a file */ #define TX_RENAME 8 /* Rename a file */ #define TX_WRITE 9 /* File write */ #define TX_TRUNCATE 10 /* Truncate a file */ #define TX_SETATTR 11 /* Set file attributes */ #define TX_ACL_V0 12 /* Set old formatted ACL */ #define TX_ACL 13 /* Set ACL */ #define TX_CREATE_ACL 14 /* create with ACL */ #define TX_CREATE_ATTR 15 /* create + attrs */ #define TX_CREATE_ACL_ATTR 16 /* create with ACL + attrs */ #define TX_MKDIR_ACL 17 /* mkdir with ACL */ #define TX_MKDIR_ATTR 18 /* mkdir with attr */ #define TX_MKDIR_ACL_ATTR 19 /* mkdir with ACL + attrs */ #define TX_WRITE2 20 /* dmu_sync EALREADY write */ -#define TX_MAX_TYPE 21 /* Max transaction type */ +#define TX_SETSAXATTR 21 /* Set sa xattrs on file */ +#define TX_MAX_TYPE 22 /* Max transaction type */ /* * The transactions for mkdir, symlink, remove, rmdir, link, and rename * may have the following bit set, indicating the original request * specified case-insensitive handling of names. */ #define TX_CI ((uint64_t)0x1 << 63) /* case-insensitive behavior requested */ /* * Transactions for write, truncate, setattr, acl_v0, and acl can be logged * out of order. For convenience in the code, all such records must have * lr_foid at the same offset. */ #define TX_OOO(txtype) \ ((txtype) == TX_WRITE || \ (txtype) == TX_TRUNCATE || \ (txtype) == TX_SETATTR || \ (txtype) == TX_ACL_V0 || \ (txtype) == TX_ACL || \ - (txtype) == TX_WRITE2) + (txtype) == TX_WRITE2 || \ + (txtype) == TX_SETSAXATTR) /* * The number of dnode slots consumed by the object is stored in the 8 * unused upper bits of the object ID. We subtract 1 from the value * stored on disk for compatibility with implementations that don't * support large dnodes. The slot count for a single-slot dnode will * contain 0 for those bits to preserve the log record format for * "small" dnodes. */ #define LR_FOID_GET_SLOTS(oid) (BF64_GET((oid), 56, 8) + 1) #define LR_FOID_SET_SLOTS(oid, x) BF64_SET((oid), 56, 8, (x) - 1) #define LR_FOID_GET_OBJ(oid) BF64_GET((oid), 0, DN_MAX_OBJECT_SHIFT) #define LR_FOID_SET_OBJ(oid, x) BF64_SET((oid), 0, DN_MAX_OBJECT_SHIFT, (x)) /* * Format of log records. * The fields are carefully defined to allow them to be aligned * and sized the same on sparc & intel architectures. * Each log record has a common structure at the beginning. * * The log record on disk (lrc_seq) holds the sequence number of all log * records which is used to ensure we don't replay the same record. */ typedef struct { /* common log record header */ uint64_t lrc_txtype; /* intent log transaction type */ uint64_t lrc_reclen; /* transaction record length */ uint64_t lrc_txg; /* dmu transaction group number */ uint64_t lrc_seq; /* see comment above */ } lr_t; /* * Common start of all out-of-order record types (TX_OOO() above). */ typedef struct { lr_t lr_common; /* common portion of log record */ uint64_t lr_foid; /* object id */ } lr_ooo_t; /* * Handle option extended vattr attributes. * * Whenever new attributes are added the version number * will need to be updated as will code in * zfs_log.c and zfs_replay.c */ typedef struct { uint32_t lr_attr_masksize; /* number of elements in array */ uint32_t lr_attr_bitmap; /* First entry of array */ /* remainder of array and any additional fields */ } lr_attr_t; /* * log record for creates without optional ACL. * This log record does support optional xvattr_t attributes. */ typedef struct { lr_t lr_common; /* common portion of log record */ uint64_t lr_doid; /* object id of directory */ uint64_t lr_foid; /* object id of created file object */ uint64_t lr_mode; /* mode of object */ uint64_t lr_uid; /* uid of object */ uint64_t lr_gid; /* gid of object */ uint64_t lr_gen; /* generation (txg of creation) */ uint64_t lr_crtime[2]; /* creation time */ uint64_t lr_rdev; /* rdev of object to create */ /* name of object to create follows this */ /* for symlinks, link content follows name */ /* for creates with xvattr data, the name follows the xvattr info */ } lr_create_t; /* * FUID ACL record will be an array of ACEs from the original ACL. * If this array includes ephemeral IDs, the record will also include * an array of log-specific FUIDs to replace the ephemeral IDs. * Only one copy of each unique domain will be present, so the log-specific * FUIDs will use an index into a compressed domain table. On replay this * information will be used to construct real FUIDs (and bypass idmap, * since it may not be available). */ /* * Log record for creates with optional ACL * This log record is also used for recording any FUID * information needed for replaying the create. If the * file doesn't have any actual ACEs then the lr_aclcnt * would be zero. * * After lr_acl_flags, there are a lr_acl_bytes number of variable sized ace's. * If create is also setting xvattr's, then acl data follows xvattr. * If ACE FUIDs are needed then they will follow the xvattr_t. Following * the FUIDs will be the domain table information. The FUIDs for the owner * and group will be in lr_create. Name follows ACL data. */ typedef struct { lr_create_t lr_create; /* common create portion */ uint64_t lr_aclcnt; /* number of ACEs in ACL */ uint64_t lr_domcnt; /* number of unique domains */ uint64_t lr_fuidcnt; /* number of real fuids */ uint64_t lr_acl_bytes; /* number of bytes in ACL */ uint64_t lr_acl_flags; /* ACL flags */ } lr_acl_create_t; typedef struct { lr_t lr_common; /* common portion of log record */ uint64_t lr_doid; /* obj id of directory */ /* name of object to remove follows this */ } lr_remove_t; typedef struct { lr_t lr_common; /* common portion of log record */ uint64_t lr_doid; /* obj id of directory */ uint64_t lr_link_obj; /* obj id of link */ /* name of object to link follows this */ } lr_link_t; typedef struct { lr_t lr_common; /* common portion of log record */ uint64_t lr_sdoid; /* obj id of source directory */ uint64_t lr_tdoid; /* obj id of target directory */ /* 2 strings: names of source and destination follow this */ } lr_rename_t; typedef struct { lr_t lr_common; /* common portion of log record */ uint64_t lr_foid; /* file object to write */ uint64_t lr_offset; /* offset to write to */ uint64_t lr_length; /* user data length to write */ uint64_t lr_blkoff; /* no longer used */ blkptr_t lr_blkptr; /* spa block pointer for replay */ /* write data will follow for small writes */ } lr_write_t; typedef struct { lr_t lr_common; /* common portion of log record */ uint64_t lr_foid; /* object id of file to truncate */ uint64_t lr_offset; /* offset to truncate from */ uint64_t lr_length; /* length to truncate */ } lr_truncate_t; typedef struct { lr_t lr_common; /* common portion of log record */ uint64_t lr_foid; /* file object to change attributes */ uint64_t lr_mask; /* mask of attributes to set */ uint64_t lr_mode; /* mode to set */ uint64_t lr_uid; /* uid to set */ uint64_t lr_gid; /* gid to set */ uint64_t lr_size; /* size to set */ uint64_t lr_atime[2]; /* access time */ uint64_t lr_mtime[2]; /* modification time */ /* optional attribute lr_attr_t may be here */ } lr_setattr_t; +typedef struct { + lr_t lr_common; /* common portion of log record */ + uint64_t lr_foid; /* file object to change attributes */ + uint64_t lr_size; + /* xattr name and value follows */ +} lr_setsaxattr_t; + typedef struct { lr_t lr_common; /* common portion of log record */ uint64_t lr_foid; /* obj id of file */ uint64_t lr_aclcnt; /* number of acl entries */ /* lr_aclcnt number of ace_t entries follow this */ } lr_acl_v0_t; typedef struct { lr_t lr_common; /* common portion of log record */ uint64_t lr_foid; /* obj id of file */ uint64_t lr_aclcnt; /* number of ACEs in ACL */ uint64_t lr_domcnt; /* number of unique domains */ uint64_t lr_fuidcnt; /* number of real fuids */ uint64_t lr_acl_bytes; /* number of bytes in ACL */ uint64_t lr_acl_flags; /* ACL flags */ /* lr_acl_bytes number of variable sized ace's follows */ } lr_acl_t; /* * ZIL structure definitions, interface function prototype and globals. */ /* * Writes are handled in three different ways: * * WR_INDIRECT: * In this mode, if we need to commit the write later, then the block * is immediately written into the file system (using dmu_sync), * and a pointer to the block is put into the log record. * When the txg commits the block is linked in. * This saves additionally writing the data into the log record. * There are a few requirements for this to occur: * - write is greater than zfs/zvol_immediate_write_sz * - not using slogs (as slogs are assumed to always be faster * than writing into the main pool) * - the write occupies only one block * WR_COPIED: * If we know we'll immediately be committing the * transaction (O_SYNC or O_DSYNC), then we allocate a larger * log record here for the data and copy the data in. * WR_NEED_COPY: * Otherwise we don't allocate a buffer, and *if* we need to * flush the write later then a buffer is allocated and * we retrieve the data using the dmu. */ typedef enum { WR_INDIRECT, /* indirect - a large write (dmu_sync() data */ /* and put blkptr in log, rather than actual data) */ WR_COPIED, /* immediate - data is copied into lr_write_t */ WR_NEED_COPY, /* immediate - data needs to be copied if pushed */ WR_NUM_STATES /* number of states */ } itx_wr_state_t; typedef void (*zil_callback_t)(void *data); typedef struct itx { list_node_t itx_node; /* linkage on zl_itx_list */ void *itx_private; /* type-specific opaque data */ itx_wr_state_t itx_wr_state; /* write state */ uint8_t itx_sync; /* synchronous transaction */ zil_callback_t itx_callback; /* Called when the itx is persistent */ void *itx_callback_data; /* User data for the callback */ size_t itx_size; /* allocated itx structure size */ uint64_t itx_oid; /* object id */ uint64_t itx_gen; /* gen number for zfs_get_data */ lr_t itx_lr; /* common part of log record */ /* followed by type-specific part of lr_xx_t and its immediate data */ } itx_t; /* * Used for zil kstat. */ typedef struct zil_stats { /* * Number of times a ZIL commit (e.g. fsync) has been requested. */ kstat_named_t zil_commit_count; /* * Number of times the ZIL has been flushed to stable storage. * This is less than zil_commit_count when commits are "merged" * (see the documentation above zil_commit()). */ kstat_named_t zil_commit_writer_count; /* * Number of transactions (reads, writes, renames, etc.) * that have been committed. */ kstat_named_t zil_itx_count; /* * See the documentation for itx_wr_state_t above. * Note that "bytes" accumulates the length of the transactions * (i.e. data), not the actual log record sizes. */ kstat_named_t zil_itx_indirect_count; kstat_named_t zil_itx_indirect_bytes; kstat_named_t zil_itx_copied_count; kstat_named_t zil_itx_copied_bytes; kstat_named_t zil_itx_needcopy_count; kstat_named_t zil_itx_needcopy_bytes; /* * Transactions which have been allocated to the "normal" * (i.e. not slog) storage pool. Note that "bytes" accumulate * the actual log record sizes - which do not include the actual * data in case of indirect writes. */ kstat_named_t zil_itx_metaslab_normal_count; kstat_named_t zil_itx_metaslab_normal_bytes; /* * Transactions which have been allocated to the "slog" storage pool. * If there are no separate log devices, this is the same as the * "normal" pool. */ kstat_named_t zil_itx_metaslab_slog_count; kstat_named_t zil_itx_metaslab_slog_bytes; } zil_stats_t; #define ZIL_STAT_INCR(stat, val) \ atomic_add_64(&zil_stats.stat.value.ui64, (val)); #define ZIL_STAT_BUMP(stat) \ ZIL_STAT_INCR(stat, 1); typedef int zil_parse_blk_func_t(zilog_t *zilog, const blkptr_t *bp, void *arg, uint64_t txg); typedef int zil_parse_lr_func_t(zilog_t *zilog, const lr_t *lr, void *arg, uint64_t txg); typedef int zil_replay_func_t(void *arg1, void *arg2, boolean_t byteswap); typedef int zil_get_data_t(void *arg, uint64_t arg2, lr_write_t *lr, char *dbuf, struct lwb *lwb, zio_t *zio); extern int zil_parse(zilog_t *zilog, zil_parse_blk_func_t *parse_blk_func, zil_parse_lr_func_t *parse_lr_func, void *arg, uint64_t txg, boolean_t decrypt); extern void zil_init(void); extern void zil_fini(void); extern zilog_t *zil_alloc(objset_t *os, zil_header_t *zh_phys); extern void zil_free(zilog_t *zilog); extern zilog_t *zil_open(objset_t *os, zil_get_data_t *get_data); extern void zil_close(zilog_t *zilog); extern void zil_replay(objset_t *os, void *arg, zil_replay_func_t *const replay_func[TX_MAX_TYPE]); extern boolean_t zil_replaying(zilog_t *zilog, dmu_tx_t *tx); extern void zil_destroy(zilog_t *zilog, boolean_t keep_first); extern void zil_destroy_sync(zilog_t *zilog, dmu_tx_t *tx); extern itx_t *zil_itx_create(uint64_t txtype, size_t lrsize); extern void zil_itx_destroy(itx_t *itx); extern void zil_itx_assign(zilog_t *zilog, itx_t *itx, dmu_tx_t *tx); extern void zil_async_to_sync(zilog_t *zilog, uint64_t oid); extern void zil_commit(zilog_t *zilog, uint64_t oid); extern void zil_commit_impl(zilog_t *zilog, uint64_t oid); extern void zil_remove_async(zilog_t *zilog, uint64_t oid); extern int zil_reset(const char *osname, void *txarg); extern int zil_claim(struct dsl_pool *dp, struct dsl_dataset *ds, void *txarg); extern int zil_check_log_chain(struct dsl_pool *dp, struct dsl_dataset *ds, void *tx); extern void zil_sync(zilog_t *zilog, dmu_tx_t *tx); extern void zil_clean(zilog_t *zilog, uint64_t synced_txg); extern int zil_suspend(const char *osname, void **cookiep); extern void zil_resume(void *cookie); extern void zil_lwb_add_block(struct lwb *lwb, const blkptr_t *bp); extern void zil_lwb_add_txg(struct lwb *lwb, uint64_t txg); extern int zil_bp_tree_add(zilog_t *zilog, const blkptr_t *bp); extern void zil_set_sync(zilog_t *zilog, uint64_t syncval); extern void zil_set_logbias(zilog_t *zilog, uint64_t slogval); extern uint64_t zil_max_copied_data(zilog_t *zilog); extern uint64_t zil_max_log_data(zilog_t *zilog); extern int zil_replay_disable; #ifdef __cplusplus } #endif #endif /* _SYS_ZIL_H */ diff --git a/include/zfeature_common.h b/include/zfeature_common.h index 874cbd9ff714..580f5ff3e0ee 100644 --- a/include/zfeature_common.h +++ b/include/zfeature_common.h @@ -1,135 +1,136 @@ /* * 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) 2011, 2018 by Delphix. All rights reserved. * Copyright (c) 2013 by Saso Kiselkov. All rights reserved. * Copyright (c) 2013, Joyent, Inc. All rights reserved. * Copyright (c) 2017, Intel Corporation. */ #ifndef _ZFEATURE_COMMON_H #define _ZFEATURE_COMMON_H extern __attribute__((visibility("default"))) #include #include #include #ifdef __cplusplus extern "C" { #endif struct zfeature_info; typedef enum spa_feature { SPA_FEATURE_NONE = -1, SPA_FEATURE_ASYNC_DESTROY, SPA_FEATURE_EMPTY_BPOBJ, SPA_FEATURE_LZ4_COMPRESS, SPA_FEATURE_MULTI_VDEV_CRASH_DUMP, SPA_FEATURE_SPACEMAP_HISTOGRAM, SPA_FEATURE_ENABLED_TXG, SPA_FEATURE_HOLE_BIRTH, SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_EMBEDDED_DATA, SPA_FEATURE_BOOKMARKS, SPA_FEATURE_FS_SS_LIMIT, SPA_FEATURE_LARGE_BLOCKS, SPA_FEATURE_LARGE_DNODE, SPA_FEATURE_SHA512, SPA_FEATURE_SKEIN, SPA_FEATURE_EDONR, SPA_FEATURE_USEROBJ_ACCOUNTING, SPA_FEATURE_ENCRYPTION, SPA_FEATURE_PROJECT_QUOTA, SPA_FEATURE_DEVICE_REMOVAL, SPA_FEATURE_OBSOLETE_COUNTS, SPA_FEATURE_POOL_CHECKPOINT, SPA_FEATURE_SPACEMAP_V2, SPA_FEATURE_ALLOCATION_CLASSES, SPA_FEATURE_RESILVER_DEFER, SPA_FEATURE_BOOKMARK_V2, SPA_FEATURE_REDACTION_BOOKMARKS, SPA_FEATURE_REDACTED_DATASETS, SPA_FEATURE_BOOKMARK_WRITTEN, SPA_FEATURE_LOG_SPACEMAP, SPA_FEATURE_LIVELIST, SPA_FEATURE_DEVICE_REBUILD, SPA_FEATURE_ZSTD_COMPRESS, SPA_FEATURE_DRAID, + SPA_FEATURE_ZILSAXATTR, SPA_FEATURES } spa_feature_t; #define SPA_FEATURE_DISABLED (-1ULL) typedef enum zfeature_flags { /* Can open pool readonly even if this feature is not supported. */ ZFEATURE_FLAG_READONLY_COMPAT = (1 << 0), /* * Is this feature necessary to load the pool? i.e. do we need this * feature to read the full feature list out of the MOS? */ ZFEATURE_FLAG_MOS = (1 << 1), /* Activate this feature at the same time it is enabled. */ ZFEATURE_FLAG_ACTIVATE_ON_ENABLE = (1 << 2), /* Each dataset has a field set if it has ever used this feature. */ ZFEATURE_FLAG_PER_DATASET = (1 << 3) } zfeature_flags_t; typedef enum zfeature_type { ZFEATURE_TYPE_BOOLEAN, ZFEATURE_TYPE_UINT64_ARRAY, ZFEATURE_NUM_TYPES } zfeature_type_t; typedef struct zfeature_info { spa_feature_t fi_feature; const char *fi_uname; /* User-facing feature name */ const char *fi_guid; /* On-disk feature identifier */ const char *fi_desc; /* Feature description */ zfeature_flags_t fi_flags; boolean_t fi_zfs_mod_supported; /* supported by running zfs module */ zfeature_type_t fi_type; /* Only relevant for PER_DATASET features */ /* array of dependencies, terminated by SPA_FEATURE_NONE */ const spa_feature_t *fi_depends; } zfeature_info_t; typedef int (zfeature_func_t)(zfeature_info_t *, void *); #define ZFS_FEATURE_DEBUG _ZFEATURE_COMMON_H zfeature_info_t spa_feature_table[SPA_FEATURES]; _ZFEATURE_COMMON_H boolean_t zfeature_checks_disable; _ZFEATURE_COMMON_H boolean_t zfeature_is_valid_guid(const char *); _ZFEATURE_COMMON_H boolean_t zfeature_is_supported(const char *); _ZFEATURE_COMMON_H int zfeature_lookup_guid(const char *, spa_feature_t *); _ZFEATURE_COMMON_H int zfeature_lookup_name(const char *, spa_feature_t *); _ZFEATURE_COMMON_H boolean_t zfeature_depends_on(spa_feature_t, spa_feature_t); _ZFEATURE_COMMON_H void zpool_feature_init(void); #ifdef __cplusplus } #endif #endif /* _ZFEATURE_COMMON_H */ diff --git a/lib/libzfs/libzfs.abi b/lib/libzfs/libzfs.abi index 8f586804c9dd..a34811b58042 100644 --- a/lib/libzfs/libzfs.abi +++ b/lib/libzfs/libzfs.abi @@ -1,5849 +1,5850 @@ - + - - + + - + + diff --git a/man/man4/zfs.4 b/man/man4/zfs.4 index 2f7a18ea62c7..01e9c5de445d 100644 --- a/man/man4/zfs.4 +++ b/man/man4/zfs.4 @@ -1,2430 +1,2440 @@ .\" .\" Copyright (c) 2013 by Turbo Fredriksson . All rights reserved. .\" Copyright (c) 2019, 2021 by Delphix. All rights reserved. .\" Copyright (c) 2019 Datto Inc. .\" 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] .\" .Dd June 1, 2021 .Dt ZFS 4 .Os . .Sh NAME .Nm zfs .Nd tuning of the ZFS kernel module . .Sh DESCRIPTION The ZFS module supports these parameters: .Bl -tag -width Ds .It Sy dbuf_cache_max_bytes Ns = Ns Sy ULONG_MAX Ns B Pq ulong Maximum size in bytes of the dbuf cache. The target size is determined by the MIN versus .No 1/2^ Ns Sy dbuf_cache_shift Pq 1/32nd of the target ARC size. The behavior of the dbuf cache and its associated settings can be observed via the .Pa /proc/spl/kstat/zfs/dbufstats kstat. . .It Sy dbuf_metadata_cache_max_bytes Ns = Ns Sy ULONG_MAX Ns B Pq ulong Maximum size in bytes of the metadata dbuf cache. The target size is determined by the MIN versus .No 1/2^ Ns Sy dbuf_metadata_cache_shift Pq 1/64th of the target ARC size. The behavior of the metadata dbuf cache and its associated settings can be observed via the .Pa /proc/spl/kstat/zfs/dbufstats kstat. . .It Sy dbuf_cache_hiwater_pct Ns = Ns Sy 10 Ns % Pq uint The percentage over .Sy dbuf_cache_max_bytes when dbufs must be evicted directly. . .It Sy dbuf_cache_lowater_pct Ns = Ns Sy 10 Ns % Pq uint The percentage below .Sy dbuf_cache_max_bytes when the evict thread stops evicting dbufs. . .It Sy dbuf_cache_shift Ns = Ns Sy 5 Pq int Set the size of the dbuf cache .Pq Sy dbuf_cache_max_bytes to a log2 fraction of the target ARC size. . .It Sy dbuf_metadata_cache_shift Ns = Ns Sy 6 Pq int Set the size of the dbuf metadata cache .Pq Sy dbuf_metadata_cache_max_bytes to a log2 fraction of the target ARC size. . .It Sy dmu_object_alloc_chunk_shift Ns = Ns Sy 7 Po 128 Pc Pq int dnode slots allocated in a single operation as a power of 2. The default value minimizes lock contention for the bulk operation performed. . .It Sy dmu_prefetch_max Ns = Ns Sy 134217728 Ns B Po 128MB Pc Pq int Limit the amount we can prefetch with one call to this amount in bytes. This helps to limit the amount of memory that can be used by prefetching. . .It Sy ignore_hole_birth Pq int Alias for .Sy send_holes_without_birth_time . . .It Sy l2arc_feed_again Ns = Ns Sy 1 Ns | Ns 0 Pq int Turbo L2ARC warm-up. When the L2ARC is cold the fill interval will be set as fast as possible. . .It Sy l2arc_feed_min_ms Ns = Ns Sy 200 Pq ulong Min feed interval in milliseconds. Requires .Sy l2arc_feed_again Ns = Ns Ar 1 and only applicable in related situations. . .It Sy l2arc_feed_secs Ns = Ns Sy 1 Pq ulong Seconds between L2ARC writing. . .It Sy l2arc_headroom Ns = Ns Sy 2 Pq ulong How far through the ARC lists to search for L2ARC cacheable content, expressed as a multiplier of .Sy l2arc_write_max . ARC persistence across reboots can be achieved with persistent L2ARC by setting this parameter to .Sy 0 , allowing the full length of ARC lists to be searched for cacheable content. . .It Sy l2arc_headroom_boost Ns = Ns Sy 200 Ns % Pq ulong Scales .Sy l2arc_headroom by this percentage when L2ARC contents are being successfully compressed before writing. A value of .Sy 100 disables this feature. . .It Sy l2arc_exclude_special Ns = Ns Sy 0 Ns | Ns 1 Pq int Controls whether buffers present on special vdevs are eligible for caching into L2ARC. If set to 1, exclude dbufs on special vdevs from being cached to L2ARC. . .It Sy l2arc_mfuonly Ns = Ns Sy 0 Ns | Ns 1 Pq int Controls whether only MFU metadata and data are cached from ARC into L2ARC. This may be desired to avoid wasting space on L2ARC when reading/writing large amounts of data that are not expected to be accessed more than once. .Pp The default is off, meaning both MRU and MFU data and metadata are cached. When turning off this feature, some MRU buffers will still be present in ARC and eventually cached on L2ARC. .No If Sy l2arc_noprefetch Ns = Ns Sy 0 , some prefetched buffers will be cached to L2ARC, and those might later transition to MRU, in which case the .Sy l2arc_mru_asize No arcstat will not be Sy 0 . .Pp Regardless of .Sy l2arc_noprefetch , some MFU buffers might be evicted from ARC, accessed later on as prefetches and transition to MRU as prefetches. If accessed again they are counted as MRU and the .Sy l2arc_mru_asize No arcstat will not be Sy 0 . .Pp The ARC status of L2ARC buffers when they were first cached in L2ARC can be seen in the .Sy l2arc_mru_asize , Sy l2arc_mfu_asize , No and Sy l2arc_prefetch_asize arcstats when importing the pool or onlining a cache device if persistent L2ARC is enabled. .Pp The .Sy evict_l2_eligible_mru arcstat does not take into account if this option is enabled as the information provided by the .Sy evict_l2_eligible_m[rf]u arcstats can be used to decide if toggling this option is appropriate for the current workload. . .It Sy l2arc_meta_percent Ns = Ns Sy 33 Ns % Pq int Percent of ARC size allowed for L2ARC-only headers. Since L2ARC buffers are not evicted on memory pressure, too many headers on a system with an irrationally large L2ARC can render it slow or unusable. This parameter limits L2ARC writes and rebuilds to achieve the target. . .It Sy l2arc_trim_ahead Ns = Ns Sy 0 Ns % Pq ulong Trims ahead of the current write size .Pq Sy l2arc_write_max on L2ARC devices by this percentage of write size if we have filled the device. If set to .Sy 100 we TRIM twice the space required to accommodate upcoming writes. A minimum of .Sy 64MB will be trimmed. It also enables TRIM of the whole L2ARC device upon creation or addition to an existing pool or if the header of the device is invalid upon importing a pool or onlining a cache device. A value of .Sy 0 disables TRIM on L2ARC altogether and is the default as it can put significant stress on the underlying storage devices. This will vary depending of how well the specific device handles these commands. . .It Sy l2arc_noprefetch Ns = Ns Sy 1 Ns | Ns 0 Pq int Do not write buffers to L2ARC if they were prefetched but not used by applications. In case there are prefetched buffers in L2ARC and this option is later set, we do not read the prefetched buffers from L2ARC. Unsetting this option is useful for caching sequential reads from the disks to L2ARC and serve those reads from L2ARC later on. This may be beneficial in case the L2ARC device is significantly faster in sequential reads than the disks of the pool. .Pp Use .Sy 1 to disable and .Sy 0 to enable caching/reading prefetches to/from L2ARC. . .It Sy l2arc_norw Ns = Ns Sy 0 Ns | Ns 1 Pq int No reads during writes. . .It Sy l2arc_write_boost Ns = Ns Sy 8388608 Ns B Po 8MB Pc Pq ulong Cold L2ARC devices will have .Sy l2arc_write_max increased by this amount while they remain cold. . .It Sy l2arc_write_max Ns = Ns Sy 8388608 Ns B Po 8MB Pc Pq ulong Max write bytes per interval. . .It Sy l2arc_rebuild_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int Rebuild the L2ARC when importing a pool (persistent L2ARC). This can be disabled if there are problems importing a pool or attaching an L2ARC device (e.g. the L2ARC device is slow in reading stored log metadata, or the metadata has become somehow fragmented/unusable). . .It Sy l2arc_rebuild_blocks_min_l2size Ns = Ns Sy 1073741824 Ns B Po 1GB Pc Pq ulong Mininum size of an L2ARC device required in order to write log blocks in it. The log blocks are used upon importing the pool to rebuild the persistent L2ARC. .Pp For L2ARC devices less than 1GB, the amount of data .Fn l2arc_evict evicts is significant compared to the amount of restored L2ARC data. In this case, do not write log blocks in L2ARC in order not to waste space. . .It Sy metaslab_aliquot Ns = Ns Sy 524288 Ns B Po 512kB Pc Pq ulong Metaslab granularity, in bytes. This is roughly similar to what would be referred to as the "stripe size" in traditional RAID arrays. In normal operation, ZFS will try to write this amount of data to a top-level vdev before moving on to the next one. . .It Sy metaslab_bias_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int Enable metaslab group biasing based on their vdevs' over- or under-utilization relative to the pool. . .It Sy metaslab_force_ganging Ns = Ns Sy 16777217 Ns B Ns B Po 16MB + 1B Pc Pq ulong Make some blocks above a certain size be gang blocks. This option is used by the test suite to facilitate testing. . .It Sy zfs_history_output_max Ns = Ns Sy 1048576 Ns B Ns B Po 1MB Pc Pq int When attempting to log an output nvlist of an ioctl in the on-disk history, the output will not be stored if it is larger than this size (in bytes). This must be less than .Sy DMU_MAX_ACCESS Pq 64MB . This applies primarily to .Fn zfs_ioc_channel_program Pq cf. Xr zfs-program 8 . . .It Sy zfs_keep_log_spacemaps_at_export Ns = Ns Sy 0 Ns | Ns 1 Pq int Prevent log spacemaps from being destroyed during pool exports and destroys. . .It Sy zfs_metaslab_segment_weight_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int Enable/disable segment-based metaslab selection. . .It Sy zfs_metaslab_switch_threshold Ns = Ns Sy 2 Pq int When using segment-based metaslab selection, continue allocating from the active metaslab until this option's worth of buckets have been exhausted. . .It Sy metaslab_debug_load Ns = Ns Sy 0 Ns | Ns 1 Pq int Load all metaslabs during pool import. . .It Sy metaslab_debug_unload Ns = Ns Sy 0 Ns | Ns 1 Pq int Prevent metaslabs from being unloaded. . .It Sy metaslab_fragmentation_factor_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int Enable use of the fragmentation metric in computing metaslab weights. . .It Sy metaslab_df_max_search Ns = Ns Sy 16777216 Ns B Po 16MB Pc Pq int Maximum distance to search forward from the last offset. Without this limit, fragmented pools can see .Em >100`000 iterations and .Fn metaslab_block_picker becomes the performance limiting factor on high-performance storage. .Pp With the default setting of .Sy 16MB , we typically see less than .Em 500 iterations, even with very fragmented .Sy ashift Ns = Ns Sy 9 pools. The maximum number of iterations possible is .Sy metaslab_df_max_search / 2^(ashift+1) . With the default setting of .Sy 16MB this is .Em 16*1024 Pq with Sy ashift Ns = Ns Sy 9 or .Em 2*1024 Pq with Sy ashift Ns = Ns Sy 12 . . .It Sy metaslab_df_use_largest_segment Ns = Ns Sy 0 Ns | Ns 1 Pq int If not searching forward (due to .Sy metaslab_df_max_search , metaslab_df_free_pct , .No or Sy metaslab_df_alloc_threshold ) , this tunable controls which segment is used. If set, we will use the largest free segment. If unset, we will use a segment of at least the requested size. . .It Sy zfs_metaslab_max_size_cache_sec Ns = Ns Sy 3600 Ns s Po 1h Pc Pq ulong When we unload a metaslab, we cache the size of the largest free chunk. We use that cached size to determine whether or not to load a metaslab for a given allocation. As more frees accumulate in that metaslab while it's unloaded, the cached max size becomes less and less accurate. After a number of seconds controlled by this tunable, we stop considering the cached max size and start considering only the histogram instead. . .It Sy zfs_metaslab_mem_limit Ns = Ns Sy 25 Ns % Pq int When we are loading a new metaslab, we check the amount of memory being used to store metaslab range trees. If it is over a threshold, we attempt to unload the least recently used metaslab to prevent the system from clogging all of its memory with range trees. This tunable sets the percentage of total system memory that is the threshold. . .It Sy zfs_metaslab_try_hard_before_gang Ns = Ns Sy 0 Ns | Ns 1 Pq int .Bl -item -compact .It If unset, we will first try normal allocation. .It If that fails then we will do a gang allocation. .It If that fails then we will do a "try hard" gang allocation. .It If that fails then we will have a multi-layer gang block. .El .Pp .Bl -item -compact .It If set, we will first try normal allocation. .It If that fails then we will do a "try hard" allocation. .It If that fails we will do a gang allocation. .It If that fails we will do a "try hard" gang allocation. .It If that fails then we will have a multi-layer gang block. .El . .It Sy zfs_metaslab_find_max_tries Ns = Ns Sy 100 Pq int When not trying hard, we only consider this number of the best metaslabs. This improves performance, especially when there are many metaslabs per vdev and the allocation can't actually be satisfied (so we would otherwise iterate all metaslabs). . .It Sy zfs_vdev_default_ms_count Ns = Ns Sy 200 Pq int When a vdev is added, target this number of metaslabs per top-level vdev. . .It Sy zfs_vdev_default_ms_shift Ns = Ns Sy 29 Po 512MB Pc Pq int Default limit for metaslab size. . .It Sy zfs_vdev_max_auto_ashift Ns = Ns Sy ASHIFT_MAX Po 16 Pc Pq ulong Maximum ashift used when optimizing for logical \[->] physical sector size on new top-level vdevs. . .It Sy zfs_vdev_min_auto_ashift Ns = Ns Sy ASHIFT_MIN Po 9 Pc Pq ulong Minimum ashift used when creating new top-level vdevs. . .It Sy zfs_vdev_min_ms_count Ns = Ns Sy 16 Pq int Minimum number of metaslabs to create in a top-level vdev. . .It Sy vdev_validate_skip Ns = Ns Sy 0 Ns | Ns 1 Pq int Skip label validation steps during pool import. Changing is not recommended unless you know what you're doing and are recovering a damaged label. . .It Sy zfs_vdev_ms_count_limit Ns = Ns Sy 131072 Po 128k Pc Pq int Practical upper limit of total metaslabs per top-level vdev. . .It Sy metaslab_preload_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int Enable metaslab group preloading. . .It Sy metaslab_lba_weighting_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int Give more weight to metaslabs with lower LBAs, assuming they have greater bandwidth, as is typically the case on a modern constant angular velocity disk drive. . .It Sy metaslab_unload_delay Ns = Ns Sy 32 Pq int After a metaslab is used, we keep it loaded for this many TXGs, to attempt to reduce unnecessary reloading. Note that both this many TXGs and .Sy metaslab_unload_delay_ms milliseconds must pass before unloading will occur. . .It Sy metaslab_unload_delay_ms Ns = Ns Sy 600000 Ns ms Po 10min Pc Pq int After a metaslab is used, we keep it loaded for this many milliseconds, to attempt to reduce unnecessary reloading. Note, that both this many milliseconds and .Sy metaslab_unload_delay TXGs must pass before unloading will occur. . .It Sy reference_history Ns = Ns Sy 3 Pq int Maximum reference holders being tracked when reference_tracking_enable is active. . .It Sy reference_tracking_enable Ns = Ns Sy 0 Ns | Ns 1 Pq int Track reference holders to .Sy refcount_t objects (debug builds only). . .It Sy send_holes_without_birth_time Ns = Ns Sy 1 Ns | Ns 0 Pq int When set, the .Sy hole_birth optimization will not be used, and all holes will always be sent during a .Nm zfs Cm send . This is useful if you suspect your datasets are affected by a bug in .Sy hole_birth . . .It Sy spa_config_path Ns = Ns Pa /etc/zfs/zpool.cache Pq charp SPA config file. . .It Sy spa_asize_inflation Ns = Ns Sy 24 Pq int Multiplication factor used to estimate actual disk consumption from the size of data being written. The default value is a worst case estimate, but lower values may be valid for a given pool depending on its configuration. Pool administrators who understand the factors involved may wish to specify a more realistic inflation factor, particularly if they operate close to quota or capacity limits. . .It Sy spa_load_print_vdev_tree Ns = Ns Sy 0 Ns | Ns 1 Pq int Whether to print the vdev tree in the debugging message buffer during pool import. . .It Sy spa_load_verify_data Ns = Ns Sy 1 Ns | Ns 0 Pq int Whether to traverse data blocks during an "extreme rewind" .Pq Fl X import. .Pp An extreme rewind import normally performs a full traversal of all blocks in the pool for verification. If this parameter is unset, the traversal skips non-metadata blocks. It can be toggled once the import has started to stop or start the traversal of non-metadata blocks. . .It Sy spa_load_verify_metadata Ns = Ns Sy 1 Ns | Ns 0 Pq int Whether to traverse blocks during an "extreme rewind" .Pq Fl X pool import. .Pp An extreme rewind import normally performs a full traversal of all blocks in the pool for verification. If this parameter is unset, the traversal is not performed. It can be toggled once the import has started to stop or start the traversal. . .It Sy spa_load_verify_shift Ns = Ns Sy 4 Po 1/16th Pc Pq int Sets the maximum number of bytes to consume during pool import to the log2 fraction of the target ARC size. . .It Sy spa_slop_shift Ns = Ns Sy 5 Po 1/32nd Pc Pq int Normally, we don't allow the last .Sy 3.2% Pq Sy 1/2^spa_slop_shift of space in the pool to be consumed. This ensures that we don't run the pool completely out of space, due to unaccounted changes (e.g. to the MOS). It also limits the worst-case time to allocate space. If we have less than this amount of free space, most ZPL operations (e.g. write, create) will return .Sy ENOSPC . . .It Sy vdev_removal_max_span Ns = Ns Sy 32768 Ns B Po 32kB Pc Pq int During top-level vdev removal, chunks of data are copied from the vdev which may include free space in order to trade bandwidth for IOPS. This parameter determines the maximum span of free space, in bytes, which will be included as "unnecessary" data in a chunk of copied data. .Pp The default value here was chosen to align with .Sy zfs_vdev_read_gap_limit , which is a similar concept when doing regular reads (but there's no reason it has to be the same). . .It Sy vdev_file_logical_ashift Ns = Ns Sy 9 Po 512B Pc Pq ulong Logical ashift for file-based devices. . .It Sy vdev_file_physical_ashift Ns = Ns Sy 9 Po 512B Pc Pq ulong Physical ashift for file-based devices. . .It Sy zap_iterate_prefetch Ns = Ns Sy 1 Ns | Ns 0 Pq int If set, when we start iterating over a ZAP object, prefetch the entire object (all leaf blocks). However, this is limited by .Sy dmu_prefetch_max . . .It Sy zfetch_array_rd_sz Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq ulong If prefetching is enabled, disable prefetching for reads larger than this size. . .It Sy zfetch_max_distance Ns = Ns Sy 8388608 Ns B Po 8MB Pc Pq uint Max bytes to prefetch per stream. . .It Sy zfetch_max_idistance Ns = Ns Sy 67108864 Ns B Po 64MB Pc Pq uint Max bytes to prefetch indirects for per stream. . .It Sy zfetch_max_streams Ns = Ns Sy 8 Pq uint Max number of streams per zfetch (prefetch streams per file). . .It Sy zfetch_min_sec_reap Ns = Ns Sy 2 Pq uint Min time before an active prefetch stream can be reclaimed . .It Sy zfs_abd_scatter_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int Enables ARC from using scatter/gather lists and forces all allocations to be linear in kernel memory. Disabling can improve performance in some code paths at the expense of fragmented kernel memory. . .It Sy zfs_abd_scatter_max_order Ns = Ns Sy MAX_ORDER\-1 Pq uint Maximum number of consecutive memory pages allocated in a single block for scatter/gather lists. .Pp The value of .Sy MAX_ORDER depends on kernel configuration. . .It Sy zfs_abd_scatter_min_size Ns = Ns Sy 1536 Ns B Po 1.5kB Pc Pq uint This is the minimum allocation size that will use scatter (page-based) ABDs. Smaller allocations will use linear ABDs. . .It Sy zfs_arc_dnode_limit Ns = Ns Sy 0 Ns B Pq ulong When the number of bytes consumed by dnodes in the ARC exceeds this number of bytes, try to unpin some of it in response to demand for non-metadata. This value acts as a ceiling to the amount of dnode metadata, and defaults to .Sy 0 , which indicates that a percent which is based on .Sy zfs_arc_dnode_limit_percent of the ARC meta buffers that may be used for dnodes. .Pp Also see .Sy zfs_arc_meta_prune which serves a similar purpose but is used when the amount of metadata in the ARC exceeds .Sy zfs_arc_meta_limit rather than in response to overall demand for non-metadata. . .It Sy zfs_arc_dnode_limit_percent Ns = Ns Sy 10 Ns % Pq ulong Percentage that can be consumed by dnodes of ARC meta buffers. .Pp See also .Sy zfs_arc_dnode_limit , which serves a similar purpose but has a higher priority if nonzero. . .It Sy zfs_arc_dnode_reduce_percent Ns = Ns Sy 10 Ns % Pq ulong Percentage of ARC dnodes to try to scan in response to demand for non-metadata when the number of bytes consumed by dnodes exceeds .Sy zfs_arc_dnode_limit . . .It Sy zfs_arc_average_blocksize Ns = Ns Sy 8192 Ns B Po 8kB Pc Pq int The ARC's buffer hash table is sized based on the assumption of an average block size of this value. This works out to roughly 1MB of hash table per 1GB of physical memory with 8-byte pointers. For configurations with a known larger average block size, this value can be increased to reduce the memory footprint. . .It Sy zfs_arc_eviction_pct Ns = Ns Sy 200 Ns % Pq int When .Fn arc_is_overflowing , .Fn arc_get_data_impl waits for this percent of the requested amount of data to be evicted. For example, by default, for every .Em 2kB that's evicted, .Em 1kB of it may be "reused" by a new allocation. Since this is above .Sy 100 Ns % , it ensures that progress is made towards getting .Sy arc_size No under Sy arc_c . Since this is finite, it ensures that allocations can still happen, even during the potentially long time that .Sy arc_size No is more than Sy arc_c . . .It Sy zfs_arc_evict_batch_limit Ns = Ns Sy 10 Pq int Number ARC headers to evict per sub-list before proceeding to another sub-list. This batch-style operation prevents entire sub-lists from being evicted at once but comes at a cost of additional unlocking and locking. . .It Sy zfs_arc_grow_retry Ns = Ns Sy 0 Ns s Pq int If set to a non zero value, it will replace the .Sy arc_grow_retry value with this value. The .Sy arc_grow_retry .No value Pq default Sy 5 Ns s is the number of seconds the ARC will wait before trying to resume growth after a memory pressure event. . .It Sy zfs_arc_lotsfree_percent Ns = Ns Sy 10 Ns % Pq int Throttle I/O when free system memory drops below this percentage of total system memory. Setting this value to .Sy 0 will disable the throttle. . .It Sy zfs_arc_max Ns = Ns Sy 0 Ns B Pq ulong Max size of ARC in bytes. If .Sy 0 , then the max size of ARC is determined by the amount of system memory installed. Under Linux, half of system memory will be used as the limit. Under .Fx , the larger of .Sy all_system_memory No \- Sy 1GB and .Sy 5/8 No \(mu Sy all_system_memory will be used as the limit. This value must be at least .Sy 67108864 Ns B Pq 64MB . .Pp This value can be changed dynamically, with some caveats. It cannot be set back to .Sy 0 while running, and reducing it below the current ARC size will not cause the ARC to shrink without memory pressure to induce shrinking. . .It Sy zfs_arc_meta_adjust_restarts Ns = Ns Sy 4096 Pq ulong The number of restart passes to make while scanning the ARC attempting the free buffers in order to stay below the .Sy fs_arc_meta_limit . This value should not need to be tuned but is available to facilitate performance analysis. . .It Sy zfs_arc_meta_limit Ns = Ns Sy 0 Ns B Pq ulong The maximum allowed size in bytes that metadata buffers are allowed to consume in the ARC. When this limit is reached, metadata buffers will be reclaimed, even if the overall .Sy arc_c_max has not been reached. It defaults to .Sy 0 , which indicates that a percentage based on .Sy zfs_arc_meta_limit_percent of the ARC may be used for metadata. .Pp This value my be changed dynamically, except that must be set to an explicit value .Pq cannot be set back to Sy 0 . . .It Sy zfs_arc_meta_limit_percent Ns = Ns Sy 75 Ns % Pq ulong Percentage of ARC buffers that can be used for metadata. .Pp See also .Sy zfs_arc_meta_limit , which serves a similar purpose but has a higher priority if nonzero. . .It Sy zfs_arc_meta_min Ns = Ns Sy 0 Ns B Pq ulong The minimum allowed size in bytes that metadata buffers may consume in the ARC. . .It Sy zfs_arc_meta_prune Ns = Ns Sy 10000 Pq int The number of dentries and inodes to be scanned looking for entries which can be dropped. This may be required when the ARC reaches the .Sy zfs_arc_meta_limit because dentries and inodes can pin buffers in the ARC. Increasing this value will cause to dentry and inode caches to be pruned more aggressively. Setting this value to .Sy 0 will disable pruning the inode and dentry caches. . .It Sy zfs_arc_meta_strategy Ns = Ns Sy 1 Ns | Ns 0 Pq int Define the strategy for ARC metadata buffer eviction (meta reclaim strategy): .Bl -tag -compact -offset 4n -width "0 (META_ONLY)" .It Sy 0 Pq META_ONLY evict only the ARC metadata buffers .It Sy 1 Pq BALANCED additional data buffers may be evicted if required to evict the required number of metadata buffers. .El . .It Sy zfs_arc_min Ns = Ns Sy 0 Ns B Pq ulong Min size of ARC in bytes. .No If set to Sy 0 , arc_c_min will default to consuming the larger of .Sy 32MB and .Sy all_system_memory No / Sy 32 . . .It Sy zfs_arc_min_prefetch_ms Ns = Ns Sy 0 Ns ms Ns Po Ns ≡ Ns 1s Pc Pq int Minimum time prefetched blocks are locked in the ARC. . .It Sy zfs_arc_min_prescient_prefetch_ms Ns = Ns Sy 0 Ns ms Ns Po Ns ≡ Ns 6s Pc Pq int Minimum time "prescient prefetched" blocks are locked in the ARC. These blocks are meant to be prefetched fairly aggressively ahead of the code that may use them. . .It Sy zfs_arc_prune_task_threads Ns = Ns Sy 1 Pq int Number of arc_prune threads. .Fx does not need more than one. Linux may theoretically use one per mount point up to number of CPUs, but that was not proven to be useful. . .It Sy zfs_max_missing_tvds Ns = Ns Sy 0 Pq int Number of missing top-level vdevs which will be allowed during pool import (only in read-only mode). . .It Sy zfs_max_nvlist_src_size Ns = Sy 0 Pq ulong Maximum size in bytes allowed to be passed as .Sy zc_nvlist_src_size for ioctls on .Pa /dev/zfs . This prevents a user from causing the kernel to allocate an excessive amount of memory. When the limit is exceeded, the ioctl fails with .Sy EINVAL and a description of the error is sent to the .Pa zfs-dbgmsg log. This parameter should not need to be touched under normal circumstances. If .Sy 0 , equivalent to a quarter of the user-wired memory limit under .Fx and to .Sy 134217728 Ns B Pq 128MB under Linux. . .It Sy zfs_multilist_num_sublists Ns = Ns Sy 0 Pq int To allow more fine-grained locking, each ARC state contains a series of lists for both data and metadata objects. Locking is performed at the level of these "sub-lists". This parameters controls the number of sub-lists per ARC state, and also applies to other uses of the multilist data structure. .Pp If .Sy 0 , equivalent to the greater of the number of online CPUs and .Sy 4 . . .It Sy zfs_arc_overflow_shift Ns = Ns Sy 8 Pq int The ARC size is considered to be overflowing if it exceeds the current ARC target size .Pq Sy arc_c by thresholds determined by this parameter. Exceeding by .Sy ( arc_c No >> Sy zfs_arc_overflow_shift ) No / Sy 2 starts ARC reclamation process. If that appears insufficient, exceeding by .Sy ( arc_c No >> Sy zfs_arc_overflow_shift ) No \(mu Sy 1.5 blocks new buffer allocation until the reclaim thread catches up. Started reclamation process continues till ARC size returns below the target size. .Pp The default value of .Sy 8 causes the ARC to start reclamation if it exceeds the target size by .Em 0.2% of the target size, and block allocations by .Em 0.6% . . .It Sy zfs_arc_p_min_shift Ns = Ns Sy 0 Pq int If nonzero, this will update .Sy arc_p_min_shift Pq default Sy 4 with the new value. .Sy arc_p_min_shift No is used as a shift of Sy arc_c when calculating the minumum .Sy arc_p No size. . .It Sy zfs_arc_p_dampener_disable Ns = Ns Sy 1 Ns | Ns 0 Pq int Disable .Sy arc_p adapt dampener, which reduces the maximum single adjustment to .Sy arc_p . . .It Sy zfs_arc_shrink_shift Ns = Ns Sy 0 Pq int If nonzero, this will update .Sy arc_shrink_shift Pq default Sy 7 with the new value. . .It Sy zfs_arc_pc_percent Ns = Ns Sy 0 Ns % Po off Pc Pq uint Percent of pagecache to reclaim ARC to. .Pp This tunable allows the ZFS ARC to play more nicely with the kernel's LRU pagecache. It can guarantee that the ARC size won't collapse under scanning pressure on the pagecache, yet still allows the ARC to be reclaimed down to .Sy zfs_arc_min if necessary. This value is specified as percent of pagecache size (as measured by .Sy NR_FILE_PAGES ) , where that percent may exceed .Sy 100 . This only operates during memory pressure/reclaim. . .It Sy zfs_arc_shrinker_limit Ns = Ns Sy 10000 Pq int This is a limit on how many pages the ARC shrinker makes available for eviction in response to one page allocation attempt. Note that in practice, the kernel's shrinker can ask us to evict up to about four times this for one allocation attempt. .Pp The default limit of .Sy 10000 Pq in practice, Em 160MB No per allocation attempt with 4kB pages limits the amount of time spent attempting to reclaim ARC memory to less than 100ms per allocation attempt, even with a small average compressed block size of ~8kB. .Pp The parameter can be set to 0 (zero) to disable the limit, and only applies on Linux. . .It Sy zfs_arc_sys_free Ns = Ns Sy 0 Ns B Pq ulong The target number of bytes the ARC should leave as free memory on the system. If zero, equivalent to the bigger of .Sy 512kB No and Sy all_system_memory/64 . . .It Sy zfs_autoimport_disable Ns = Ns Sy 1 Ns | Ns 0 Pq int Disable pool import at module load by ignoring the cache file .Pq Sy spa_config_path . . .It Sy zfs_checksum_events_per_second Ns = Ns Sy 20 Ns /s Pq uint Rate limit checksum events to this many per second. Note that this should not be set below the ZED thresholds (currently 10 checksums over 10 seconds) or else the daemon may not trigger any action. . .It Sy zfs_commit_timeout_pct Ns = Ns Sy 5 Ns % Pq int This controls the amount of time that a ZIL block (lwb) will remain "open" when it isn't "full", and it has a thread waiting for it to be committed to stable storage. The timeout is scaled based on a percentage of the last lwb latency to avoid significantly impacting the latency of each individual transaction record (itx). . .It Sy zfs_condense_indirect_commit_entry_delay_ms Ns = Ns Sy 0 Ns ms Pq int Vdev indirection layer (used for device removal) sleeps for this many milliseconds during mapping generation. Intended for use with the test suite to throttle vdev removal speed. . .It Sy zfs_condense_indirect_obsolete_pct Ns = Ns Sy 25 Ns % Pq int Minimum percent of obsolete bytes in vdev mapping required to attempt to condense .Pq see Sy zfs_condense_indirect_vdevs_enable . Intended for use with the test suite to facilitate triggering condensing as needed. . .It Sy zfs_condense_indirect_vdevs_enable Ns = Ns Sy 1 Ns | Ns 0 Pq int Enable condensing indirect vdev mappings. When set, attempt to condense indirect vdev mappings if the mapping uses more than .Sy zfs_condense_min_mapping_bytes bytes of memory and if the obsolete space map object uses more than .Sy zfs_condense_max_obsolete_bytes bytes on-disk. The condensing process is an attempt to save memory by removing obsolete mappings. . .It Sy zfs_condense_max_obsolete_bytes Ns = Ns Sy 1073741824 Ns B Po 1GB Pc Pq ulong Only attempt to condense indirect vdev mappings if the on-disk size of the obsolete space map object is greater than this number of bytes .Pq see Sy zfs_condense_indirect_vdevs_enable . . .It Sy zfs_condense_min_mapping_bytes Ns = Ns Sy 131072 Ns B Po 128kB Pc Pq ulong Minimum size vdev mapping to attempt to condense .Pq see Sy zfs_condense_indirect_vdevs_enable . . .It Sy zfs_dbgmsg_enable Ns = Ns Sy 1 Ns | Ns 0 Pq int Internally ZFS keeps a small log to facilitate debugging. The log is enabled by default, and can be disabled by unsetting this option. The contents of the log can be accessed by reading .Pa /proc/spl/kstat/zfs/dbgmsg . Writing .Sy 0 to the file clears the log. .Pp This setting does not influence debug prints due to .Sy zfs_flags . . .It Sy zfs_dbgmsg_maxsize Ns = Ns Sy 4194304 Ns B Po 4MB Pc Pq int Maximum size of the internal ZFS debug log. . .It Sy zfs_dbuf_state_index Ns = Ns Sy 0 Pq int Historically used for controlling what reporting was available under .Pa /proc/spl/kstat/zfs . No effect. . .It Sy zfs_deadman_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int When a pool sync operation takes longer than .Sy zfs_deadman_synctime_ms , or when an individual I/O operation takes longer than .Sy zfs_deadman_ziotime_ms , then the operation is considered to be "hung". If .Sy zfs_deadman_enabled is set, then the deadman behavior is invoked as described by .Sy zfs_deadman_failmode . By default, the deadman is enabled and set to .Sy wait which results in "hung" I/O operations only being logged. The deadman is automatically disabled when a pool gets suspended. . .It Sy zfs_deadman_failmode Ns = Ns Sy wait Pq charp Controls the failure behavior when the deadman detects a "hung" I/O operation. Valid values are: .Bl -tag -compact -offset 4n -width "continue" .It Sy wait Wait for a "hung" operation to complete. For each "hung" operation a "deadman" event will be posted describing that operation. .It Sy continue Attempt to recover from a "hung" operation by re-dispatching it to the I/O pipeline if possible. .It Sy panic Panic the system. This can be used to facilitate automatic fail-over to a properly configured fail-over partner. .El . .It Sy zfs_deadman_checktime_ms Ns = Ns Sy 60000 Ns ms Po 1min Pc Pq int Check time in milliseconds. This defines the frequency at which we check for hung I/O requests and potentially invoke the .Sy zfs_deadman_failmode behavior. . .It Sy zfs_deadman_synctime_ms Ns = Ns Sy 600000 Ns ms Po 10min Pc Pq ulong Interval in milliseconds after which the deadman is triggered and also the interval after which a pool sync operation is considered to be "hung". Once this limit is exceeded the deadman will be invoked every .Sy zfs_deadman_checktime_ms milliseconds until the pool sync completes. . .It Sy zfs_deadman_ziotime_ms Ns = Ns Sy 300000 Ns ms Po 5min Pc Pq ulong Interval in milliseconds after which the deadman is triggered and an individual I/O operation is considered to be "hung". As long as the operation remains "hung", the deadman will be invoked every .Sy zfs_deadman_checktime_ms milliseconds until the operation completes. . .It Sy zfs_dedup_prefetch Ns = Ns Sy 0 Ns | Ns 1 Pq int Enable prefetching dedup-ed blocks which are going to be freed. . .It Sy zfs_delay_min_dirty_percent Ns = Ns Sy 60 Ns % Pq int Start to delay each transaction once there is this amount of dirty data, expressed as a percentage of .Sy zfs_dirty_data_max . This value should be at least .Sy zfs_vdev_async_write_active_max_dirty_percent . .No See Sx ZFS TRANSACTION DELAY . . .It Sy zfs_delay_scale Ns = Ns Sy 500000 Pq int This controls how quickly the transaction delay approaches infinity. Larger values cause longer delays for a given amount of dirty data. .Pp For the smoothest delay, this value should be about 1 billion divided by the maximum number of operations per second. This will smoothly handle between ten times and a tenth of this number. .No See Sx ZFS TRANSACTION DELAY . .Pp .Sy zfs_delay_scale No \(mu Sy zfs_dirty_data_max Em must No be smaller than Sy 2^64 . . .It Sy zfs_disable_ivset_guid_check Ns = Ns Sy 0 Ns | Ns 1 Pq int Disables requirement for IVset GUIDs to be present and match when doing a raw receive of encrypted datasets. Intended for users whose pools were created with OpenZFS pre-release versions and now have compatibility issues. . .It Sy zfs_key_max_salt_uses Ns = Ns Sy 400000000 Po 4*10^8 Pc Pq ulong Maximum number of uses of a single salt value before generating a new one for encrypted datasets. The default value is also the maximum. . .It Sy zfs_object_mutex_size Ns = Ns Sy 64 Pq uint Size of the znode hashtable used for holds. .Pp Due to the need to hold locks on objects that may not exist yet, kernel mutexes are not created per-object and instead a hashtable is used where collisions will result in objects waiting when there is not actually contention on the same object. . .It Sy zfs_slow_io_events_per_second Ns = Ns Sy 20 Ns /s Pq int Rate limit delay and deadman zevents (which report slow I/O operations) to this many per second. . .It Sy zfs_unflushed_max_mem_amt Ns = Ns Sy 1073741824 Ns B Po 1GB Pc Pq ulong Upper-bound limit for unflushed metadata changes to be held by the log spacemap in memory, in bytes. . .It Sy zfs_unflushed_max_mem_ppm Ns = Ns Sy 1000 Ns ppm Po 0.1% Pc Pq ulong Part of overall system memory that ZFS allows to be used for unflushed metadata changes by the log spacemap, in millionths. . .It Sy zfs_unflushed_log_block_max Ns = Ns Sy 262144 Po 256k Pc Pq ulong Describes the maximum number of log spacemap blocks allowed for each pool. The default value means that the space in all the log spacemaps can add up to no more than .Sy 262144 blocks (which means .Em 32GB of logical space before compression and ditto blocks, assuming that blocksize is .Em 128kB ) . .Pp This tunable is important because it involves a trade-off between import time after an unclean export and the frequency of flushing metaslabs. The higher this number is, the more log blocks we allow when the pool is active which means that we flush metaslabs less often and thus decrease the number of I/O operations for spacemap updates per TXG. At the same time though, that means that in the event of an unclean export, there will be more log spacemap blocks for us to read, inducing overhead in the import time of the pool. The lower the number, the amount of flushing increases, destroying log blocks quicker as they become obsolete faster, which leaves less blocks to be read during import time after a crash. .Pp Each log spacemap block existing during pool import leads to approximately one extra logical I/O issued. This is the reason why this tunable is exposed in terms of blocks rather than space used. . .It Sy zfs_unflushed_log_block_min Ns = Ns Sy 1000 Pq ulong If the number of metaslabs is small and our incoming rate is high, we could get into a situation that we are flushing all our metaslabs every TXG. Thus we always allow at least this many log blocks. . .It Sy zfs_unflushed_log_block_pct Ns = Ns Sy 400 Ns % Pq ulong Tunable used to determine the number of blocks that can be used for the spacemap log, expressed as a percentage of the total number of metaslabs in the pool. . .It Sy zfs_unlink_suspend_progress Ns = Ns Sy 0 Ns | Ns 1 Pq uint When enabled, files will not be asynchronously removed from the list of pending unlinks and the space they consume will be leaked. Once this option has been disabled and the dataset is remounted, the pending unlinks will be processed and the freed space returned to the pool. This option is used by the test suite. . .It Sy zfs_delete_blocks Ns = Ns Sy 20480 Pq ulong This is the used to define a large file for the purposes of deletion. Files containing more than .Sy zfs_delete_blocks will be deleted asynchronously, while smaller files are deleted synchronously. Decreasing this value will reduce the time spent in an .Xr unlink 2 system call, at the expense of a longer delay before the freed space is available. . .It Sy zfs_dirty_data_max Ns = Pq int Determines the dirty space limit in bytes. Once this limit is exceeded, new writes are halted until space frees up. This parameter takes precedence over .Sy zfs_dirty_data_max_percent . .No See Sx ZFS TRANSACTION DELAY . .Pp Defaults to .Sy physical_ram/10 , capped at .Sy zfs_dirty_data_max_max . . .It Sy zfs_dirty_data_max_max Ns = Pq int Maximum allowable value of .Sy zfs_dirty_data_max , expressed in bytes. This limit is only enforced at module load time, and will be ignored if .Sy zfs_dirty_data_max is later changed. This parameter takes precedence over .Sy zfs_dirty_data_max_max_percent . .No See Sx ZFS TRANSACTION DELAY . .Pp Defaults to .Sy physical_ram/4 , . .It Sy zfs_dirty_data_max_max_percent Ns = Ns Sy 25 Ns % Pq int Maximum allowable value of .Sy zfs_dirty_data_max , expressed as a percentage of physical RAM. This limit is only enforced at module load time, and will be ignored if .Sy zfs_dirty_data_max is later changed. The parameter .Sy zfs_dirty_data_max_max takes precedence over this one. .No See Sx ZFS TRANSACTION DELAY . . .It Sy zfs_dirty_data_max_percent Ns = Ns Sy 10 Ns % Pq int Determines the dirty space limit, expressed as a percentage of all memory. Once this limit is exceeded, new writes are halted until space frees up. The parameter .Sy zfs_dirty_data_max takes precedence over this one. .No See Sx ZFS TRANSACTION DELAY . .Pp Subject to .Sy zfs_dirty_data_max_max . . .It Sy zfs_dirty_data_sync_percent Ns = Ns Sy 20 Ns % Pq int Start syncing out a transaction group if there's at least this much dirty data .Pq as a percentage of Sy zfs_dirty_data_max . This should be less than .Sy zfs_vdev_async_write_active_min_dirty_percent . . .It Sy zfs_wrlog_data_max Ns = Pq int The upper limit of write-transaction zil log data size in bytes. Once it is reached, write operation is blocked, until log data is cleared out after transaction group sync. Because of some overhead, it should be set at least 2 times the size of .Sy zfs_dirty_data_max .No to prevent harming normal write throughput. It also should be smaller than the size of the slog device if slog is present. .Pp Defaults to .Sy zfs_dirty_data_max*2 . .It Sy zfs_fallocate_reserve_percent Ns = Ns Sy 110 Ns % Pq uint Since ZFS is a copy-on-write filesystem with snapshots, blocks cannot be preallocated for a file in order to guarantee that later writes will not run out of space. Instead, .Xr fallocate 2 space preallocation only checks that sufficient space is currently available in the pool or the user's project quota allocation, and then creates a sparse file of the requested size. The requested space is multiplied by .Sy zfs_fallocate_reserve_percent to allow additional space for indirect blocks and other internal metadata. Setting this to .Sy 0 disables support for .Xr fallocate 2 and causes it to return .Sy EOPNOTSUPP . . .It Sy zfs_fletcher_4_impl Ns = Ns Sy fastest Pq string Select a fletcher 4 implementation. .Pp Supported selectors are: .Sy fastest , scalar , sse2 , ssse3 , avx2 , avx512f , avx512bw , .No and Sy aarch64_neon . All except .Sy fastest No and Sy scalar require instruction set extensions to be available, and will only appear if ZFS detects that they are present at runtime. If multiple implementations of fletcher 4 are available, the .Sy fastest will be chosen using a micro benchmark. Selecting .Sy scalar results in the original CPU-based calculation being used. Selecting any option other than .Sy fastest No or Sy scalar results in vector instructions from the respective CPU instruction set being used. . .It Sy zfs_free_bpobj_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int Enable/disable the processing of the free_bpobj object. . .It Sy zfs_async_block_max_blocks Ns = Ns Sy ULONG_MAX Po unlimited Pc Pq ulong Maximum number of blocks freed in a single TXG. . .It Sy zfs_max_async_dedup_frees Ns = Ns Sy 100000 Po 10^5 Pc Pq ulong Maximum number of dedup blocks freed in a single TXG. . .It Sy zfs_vdev_async_read_max_active Ns = Ns Sy 3 Pq int Maximum asynchronous read I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_async_read_min_active Ns = Ns Sy 1 Pq int Minimum asynchronous read I/O operation active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_async_write_active_max_dirty_percent Ns = Ns Sy 60 Ns % Pq int When the pool has more than this much dirty data, use .Sy zfs_vdev_async_write_max_active to limit active async writes. If the dirty data is between the minimum and maximum, the active I/O limit is linearly interpolated. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_async_write_active_min_dirty_percent Ns = Ns Sy 30 Ns % Pq int When the pool has less than this much dirty data, use .Sy zfs_vdev_async_write_min_active to limit active async writes. If the dirty data is between the minimum and maximum, the active I/O limit is linearly interpolated. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_async_write_max_active Ns = Ns Sy 30 Pq int Maximum asynchronous write I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_async_write_min_active Ns = Ns Sy 2 Pq int Minimum asynchronous write I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . .Pp Lower values are associated with better latency on rotational media but poorer resilver performance. The default value of .Sy 2 was chosen as a compromise. A value of .Sy 3 has been shown to improve resilver performance further at a cost of further increasing latency. . .It Sy zfs_vdev_initializing_max_active Ns = Ns Sy 1 Pq int Maximum initializing I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_initializing_min_active Ns = Ns Sy 1 Pq int Minimum initializing I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_max_active Ns = Ns Sy 1000 Pq int The maximum number of I/O operations active to each device. Ideally, this will be at least the sum of each queue's .Sy max_active . .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_rebuild_max_active Ns = Ns Sy 3 Pq int Maximum sequential resilver I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_rebuild_min_active Ns = Ns Sy 1 Pq int Minimum sequential resilver I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_removal_max_active Ns = Ns Sy 2 Pq int Maximum removal I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_removal_min_active Ns = Ns Sy 1 Pq int Minimum removal I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_scrub_max_active Ns = Ns Sy 2 Pq int Maximum scrub I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_scrub_min_active Ns = Ns Sy 1 Pq int Minimum scrub I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_sync_read_max_active Ns = Ns Sy 10 Pq int Maximum synchronous read I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_sync_read_min_active Ns = Ns Sy 10 Pq int Minimum synchronous read I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_sync_write_max_active Ns = Ns Sy 10 Pq int Maximum synchronous write I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_sync_write_min_active Ns = Ns Sy 10 Pq int Minimum synchronous write I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_trim_max_active Ns = Ns Sy 2 Pq int Maximum trim/discard I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_trim_min_active Ns = Ns Sy 1 Pq int Minimum trim/discard I/O operations active to each device. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_nia_delay Ns = Ns Sy 5 Pq int For non-interactive I/O (scrub, resilver, removal, initialize and rebuild), the number of concurrently-active I/O operations is limited to .Sy zfs_*_min_active , unless the vdev is "idle". When there are no interactive I/O operations active (synchronous or otherwise), and .Sy zfs_vdev_nia_delay operations have completed since the last interactive operation, then the vdev is considered to be "idle", and the number of concurrently-active non-interactive operations is increased to .Sy zfs_*_max_active . .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_nia_credit Ns = Ns Sy 5 Pq int Some HDDs tend to prioritize sequential I/O so strongly, that concurrent random I/O latency reaches several seconds. On some HDDs this happens even if sequential I/O operations are submitted one at a time, and so setting .Sy zfs_*_max_active Ns = Sy 1 does not help. To prevent non-interactive I/O, like scrub, from monopolizing the device, no more than .Sy zfs_vdev_nia_credit operations can be sent while there are outstanding incomplete interactive operations. This enforced wait ensures the HDD services the interactive I/O within a reasonable amount of time. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_queue_depth_pct Ns = Ns Sy 1000 Ns % Pq int Maximum number of queued allocations per top-level vdev expressed as a percentage of .Sy zfs_vdev_async_write_max_active , which allows the system to detect devices that are more capable of handling allocations and to allocate more blocks to those devices. This allows for dynamic allocation distribution when devices are imbalanced, as fuller devices will tend to be slower than empty devices. .Pp Also see .Sy zio_dva_throttle_enabled . . .It Sy zfs_expire_snapshot Ns = Ns Sy 300 Ns s Pq int Time before expiring .Pa .zfs/snapshot . . .It Sy zfs_admin_snapshot Ns = Ns Sy 0 Ns | Ns 1 Pq int Allow the creation, removal, or renaming of entries in the .Sy .zfs/snapshot directory to cause the creation, destruction, or renaming of snapshots. When enabled, this functionality works both locally and over NFS exports which have the .Em no_root_squash option set. . .It Sy zfs_flags Ns = Ns Sy 0 Pq int Set additional debugging flags. The following flags may be bitwise-ored together: .TS box; lbz r l l . Value Symbolic Name Description _ 1 ZFS_DEBUG_DPRINTF Enable dprintf entries in the debug log. * 2 ZFS_DEBUG_DBUF_VERIFY Enable extra dbuf verifications. * 4 ZFS_DEBUG_DNODE_VERIFY Enable extra dnode verifications. 8 ZFS_DEBUG_SNAPNAMES Enable snapshot name verification. 16 ZFS_DEBUG_MODIFY Check for illegally modified ARC buffers. 64 ZFS_DEBUG_ZIO_FREE Enable verification of block frees. 128 ZFS_DEBUG_HISTOGRAM_VERIFY Enable extra spacemap histogram verifications. 256 ZFS_DEBUG_METASLAB_VERIFY Verify space accounting on disk matches in-memory \fBrange_trees\fP. 512 ZFS_DEBUG_SET_ERROR Enable \fBSET_ERROR\fP and dprintf entries in the debug log. 1024 ZFS_DEBUG_INDIRECT_REMAP Verify split blocks created by device removal. 2048 ZFS_DEBUG_TRIM Verify TRIM ranges are always within the allocatable range tree. 4096 ZFS_DEBUG_LOG_SPACEMAP Verify that the log summary is consistent with the spacemap log and enable \fBzfs_dbgmsgs\fP for metaslab loading and flushing. .TE .Sy \& * No Requires debug build. . .It Sy zfs_free_leak_on_eio Ns = Ns Sy 0 Ns | Ns 1 Pq int If destroy encounters an .Sy EIO while reading metadata (e.g. indirect blocks), space referenced by the missing metadata can not be freed. Normally this causes the background destroy to become "stalled", as it is unable to make forward progress. While in this stalled state, all remaining space to free from the error-encountering filesystem is "temporarily leaked". Set this flag to cause it to ignore the .Sy EIO , permanently leak the space from indirect blocks that can not be read, and continue to free everything else that it can. .Pp The default "stalling" behavior is useful if the storage partially fails (i.e. some but not all I/O operations fail), and then later recovers. In this case, we will be able to continue pool operations while it is partially failed, and when it recovers, we can continue to free the space, with no leaks. Note, however, that this case is actually fairly rare. .Pp Typically pools either .Bl -enum -compact -offset 4n -width "1." .It fail completely (but perhaps temporarily, e.g. due to a top-level vdev going offline), or .It have localized, permanent errors (e.g. disk returns the wrong data due to bit flip or firmware bug). .El In the former case, this setting does not matter because the pool will be suspended and the sync thread will not be able to make forward progress regardless. In the latter, because the error is permanent, the best we can do is leak the minimum amount of space, which is what setting this flag will do. It is therefore reasonable for this flag to normally be set, but we chose the more conservative approach of not setting it, so that there is no possibility of leaking space in the "partial temporary" failure case. . .It Sy zfs_free_min_time_ms Ns = Ns Sy 1000 Ns ms Po 1s Pc Pq int During a .Nm zfs Cm destroy operation using the .Sy async_destroy feature, a minimum of this much time will be spent working on freeing blocks per TXG. . .It Sy zfs_obsolete_min_time_ms Ns = Ns Sy 500 Ns ms Pq int Similar to .Sy zfs_free_min_time_ms , but for cleanup of old indirection records for removed vdevs. . .It Sy zfs_immediate_write_sz Ns = Ns Sy 32768 Ns B Po 32kB Pc Pq long Largest data block to write to the ZIL. Larger blocks will be treated as if the dataset being written to had the .Sy logbias Ns = Ns Sy throughput property set. . .It Sy zfs_initialize_value Ns = Ns Sy 16045690984833335022 Po 0xDEADBEEFDEADBEEE Pc Pq ulong Pattern written to vdev free space by .Xr zpool-initialize 8 . . .It Sy zfs_initialize_chunk_size Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq ulong Size of writes used by .Xr zpool-initialize 8 . This option is used by the test suite. . .It Sy zfs_livelist_max_entries Ns = Ns Sy 500000 Po 5*10^5 Pc Pq ulong The threshold size (in block pointers) at which we create a new sub-livelist. Larger sublists are more costly from a memory perspective but the fewer sublists there are, the lower the cost of insertion. . .It Sy zfs_livelist_min_percent_shared Ns = Ns Sy 75 Ns % Pq int If the amount of shared space between a snapshot and its clone drops below this threshold, the clone turns off the livelist and reverts to the old deletion method. This is in place because livelists no long give us a benefit once a clone has been overwritten enough. . .It Sy zfs_livelist_condense_new_alloc Ns = Ns Sy 0 Pq int Incremented each time an extra ALLOC blkptr is added to a livelist entry while it is being condensed. This option is used by the test suite to track race conditions. . .It Sy zfs_livelist_condense_sync_cancel Ns = Ns Sy 0 Pq int Incremented each time livelist condensing is canceled while in .Fn spa_livelist_condense_sync . This option is used by the test suite to track race conditions. . .It Sy zfs_livelist_condense_sync_pause Ns = Ns Sy 0 Ns | Ns 1 Pq int When set, the livelist condense process pauses indefinitely before executing the synctask \(em .Fn spa_livelist_condense_sync . This option is used by the test suite to trigger race conditions. . .It Sy zfs_livelist_condense_zthr_cancel Ns = Ns Sy 0 Pq int Incremented each time livelist condensing is canceled while in .Fn spa_livelist_condense_cb . This option is used by the test suite to track race conditions. . .It Sy zfs_livelist_condense_zthr_pause Ns = Ns Sy 0 Ns | Ns 1 Pq int When set, the livelist condense process pauses indefinitely before executing the open context condensing work in .Fn spa_livelist_condense_cb . This option is used by the test suite to trigger race conditions. . .It Sy zfs_lua_max_instrlimit Ns = Ns Sy 100000000 Po 10^8 Pc Pq ulong The maximum execution time limit that can be set for a ZFS channel program, specified as a number of Lua instructions. . .It Sy zfs_lua_max_memlimit Ns = Ns Sy 104857600 Po 100MB Pc Pq ulong The maximum memory limit that can be set for a ZFS channel program, specified in bytes. . .It Sy zfs_max_dataset_nesting Ns = Ns Sy 50 Pq int The maximum depth of nested datasets. This value can be tuned temporarily to fix existing datasets that exceed the predefined limit. . .It Sy zfs_max_log_walking Ns = Ns Sy 5 Pq ulong The number of past TXGs that the flushing algorithm of the log spacemap feature uses to estimate incoming log blocks. . .It Sy zfs_max_logsm_summary_length Ns = Ns Sy 10 Pq ulong Maximum number of rows allowed in the summary of the spacemap log. . .It Sy zfs_max_recordsize Ns = Ns Sy 1048576 Po 1MB Pc Pq int We currently support block sizes from .Em 512B No to Em 16MB . The benefits of larger blocks, and thus larger I/O, need to be weighed against the cost of COWing a giant block to modify one byte. Additionally, very large blocks can have an impact on I/O latency, and also potentially on the memory allocator. Therefore, we do not allow the recordsize to be set larger than this tunable. Larger blocks can be created by changing it, and pools with larger blocks can always be imported and used, regardless of this setting. . .It Sy zfs_allow_redacted_dataset_mount Ns = Ns Sy 0 Ns | Ns 1 Pq int Allow datasets received with redacted send/receive to be mounted. Normally disabled because these datasets may be missing key data. . .It Sy zfs_min_metaslabs_to_flush Ns = Ns Sy 1 Pq ulong Minimum number of metaslabs to flush per dirty TXG. . .It Sy zfs_metaslab_fragmentation_threshold Ns = Ns Sy 70 Ns % Pq int Allow metaslabs to keep their active state as long as their fragmentation percentage is no more than this value. An active metaslab that exceeds this threshold will no longer keep its active status allowing better metaslabs to be selected. . .It Sy zfs_mg_fragmentation_threshold Ns = Ns Sy 95 Ns % Pq int Metaslab groups are considered eligible for allocations if their fragmentation metric (measured as a percentage) is less than or equal to this value. If a metaslab group exceeds this threshold then it will be skipped unless all metaslab groups within the metaslab class have also crossed this threshold. . .It Sy zfs_mg_noalloc_threshold Ns = Ns Sy 0 Ns % Pq int Defines a threshold at which metaslab groups should be eligible for allocations. The value is expressed as a percentage of free space beyond which a metaslab group is always eligible for allocations. If a metaslab group's free space is less than or equal to the threshold, the allocator will avoid allocating to that group unless all groups in the pool have reached the threshold. Once all groups have reached the threshold, all groups are allowed to accept allocations. The default value of .Sy 0 disables the feature and causes all metaslab groups to be eligible for allocations. .Pp This parameter allows one to deal with pools having heavily imbalanced vdevs such as would be the case when a new vdev has been added. Setting the threshold to a non-zero percentage will stop allocations from being made to vdevs that aren't filled to the specified percentage and allow lesser filled vdevs to acquire more allocations than they otherwise would under the old .Sy zfs_mg_alloc_failures facility. . .It Sy zfs_ddt_data_is_special Ns = Ns Sy 1 Ns | Ns 0 Pq int If enabled, ZFS will place DDT data into the special allocation class. . .It Sy zfs_user_indirect_is_special Ns = Ns Sy 1 Ns | Ns 0 Pq int If enabled, ZFS will place user data indirect blocks into the special allocation class. . .It Sy zfs_multihost_history Ns = Ns Sy 0 Pq int Historical statistics for this many latest multihost updates will be available in .Pa /proc/spl/kstat/zfs/ Ns Ao Ar pool Ac Ns Pa /multihost . . .It Sy zfs_multihost_interval Ns = Ns Sy 1000 Ns ms Po 1s Pc Pq ulong Used to control the frequency of multihost writes which are performed when the .Sy multihost pool property is on. This is one of the factors used to determine the length of the activity check during import. .Pp The multihost write period is .Sy zfs_multihost_interval No / Sy leaf-vdevs . On average a multihost write will be issued for each leaf vdev every .Sy zfs_multihost_interval milliseconds. In practice, the observed period can vary with the I/O load and this observed value is the delay which is stored in the uberblock. . .It Sy zfs_multihost_import_intervals Ns = Ns Sy 20 Pq uint Used to control the duration of the activity test on import. Smaller values of .Sy zfs_multihost_import_intervals will reduce the import time but increase the risk of failing to detect an active pool. The total activity check time is never allowed to drop below one second. .Pp On import the activity check waits a minimum amount of time determined by .Sy zfs_multihost_interval No \(mu Sy zfs_multihost_import_intervals , or the same product computed on the host which last had the pool imported, whichever is greater. The activity check time may be further extended if the value of MMP delay found in the best uberblock indicates actual multihost updates happened at longer intervals than .Sy zfs_multihost_interval . A minimum of .Em 100ms is enforced. .Pp .Sy 0 No is equivalent to Sy 1 . . .It Sy zfs_multihost_fail_intervals Ns = Ns Sy 10 Pq uint Controls the behavior of the pool when multihost write failures or delays are detected. .Pp When .Sy 0 , multihost write failures or delays are ignored. The failures will still be reported to the ZED which depending on its configuration may take action such as suspending the pool or offlining a device. .Pp Otherwise, the pool will be suspended if .Sy zfs_multihost_fail_intervals No \(mu Sy zfs_multihost_interval milliseconds pass without a successful MMP write. This guarantees the activity test will see MMP writes if the pool is imported. .Sy 1 No is equivalent to Sy 2 ; this is necessary to prevent the pool from being suspended due to normal, small I/O latency variations. . .It Sy zfs_no_scrub_io Ns = Ns Sy 0 Ns | Ns 1 Pq int Set to disable scrub I/O. This results in scrubs not actually scrubbing data and simply doing a metadata crawl of the pool instead. . .It Sy zfs_no_scrub_prefetch Ns = Ns Sy 0 Ns | Ns 1 Pq int Set to disable block prefetching for scrubs. . .It Sy zfs_nocacheflush Ns = Ns Sy 0 Ns | Ns 1 Pq int Disable cache flush operations on disks when writing. Setting this will cause pool corruption on power loss if a volatile out-of-order write cache is enabled. . .It Sy zfs_nopwrite_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int Allow no-operation writes. The occurrence of nopwrites will further depend on other pool properties .Pq i.a. the checksumming and compression algorithms . . .It Sy zfs_dmu_offset_next_sync Ns = Ns Sy 1 Ns | Ns 0 Pq int Enable forcing TXG sync to find holes. When enabled forces ZFS to sync data when .Sy SEEK_HOLE No or Sy SEEK_DATA flags are used allowing holes in a file to be accurately reported. When disabled holes will not be reported in recently dirtied files. . .It Sy zfs_pd_bytes_max Ns = Ns Sy 52428800 Ns B Po 50MB Pc Pq int The number of bytes which should be prefetched during a pool traversal, like .Nm zfs Cm send or other data crawling operations. . .It Sy zfs_traverse_indirect_prefetch_limit Ns = Ns Sy 32 Pq int The number of blocks pointed by indirect (non-L0) block which should be prefetched during a pool traversal, like .Nm zfs Cm send or other data crawling operations. . .It Sy zfs_per_txg_dirty_frees_percent Ns = Ns Sy 5 Ns % Pq ulong Control percentage of dirtied indirect blocks from frees allowed into one TXG. After this threshold is crossed, additional frees will wait until the next TXG. .Sy 0 No disables this throttle. . .It Sy zfs_prefetch_disable Ns = Ns Sy 0 Ns | Ns 1 Pq int Disable predictive prefetch. Note that it leaves "prescient" prefetch .Pq for, e.g., Nm zfs Cm send intact. Unlike predictive prefetch, prescient prefetch never issues I/O that ends up not being needed, so it can't hurt performance. . .It Sy zfs_qat_checksum_disable Ns = Ns Sy 0 Ns | Ns 1 Pq int Disable QAT hardware acceleration for SHA256 checksums. May be unset after the ZFS modules have been loaded to initialize the QAT hardware as long as support is compiled in and the QAT driver is present. . .It Sy zfs_qat_compress_disable Ns = Ns Sy 0 Ns | Ns 1 Pq int Disable QAT hardware acceleration for gzip compression. May be unset after the ZFS modules have been loaded to initialize the QAT hardware as long as support is compiled in and the QAT driver is present. . .It Sy zfs_qat_encrypt_disable Ns = Ns Sy 0 Ns | Ns 1 Pq int Disable QAT hardware acceleration for AES-GCM encryption. May be unset after the ZFS modules have been loaded to initialize the QAT hardware as long as support is compiled in and the QAT driver is present. . .It Sy zfs_vnops_read_chunk_size Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq long Bytes to read per chunk. . .It Sy zfs_read_history Ns = Ns Sy 0 Pq int Historical statistics for this many latest reads will be available in .Pa /proc/spl/kstat/zfs/ Ns Ao Ar pool Ac Ns Pa /reads . . .It Sy zfs_read_history_hits Ns = Ns Sy 0 Ns | Ns 1 Pq int Include cache hits in read history . .It Sy zfs_rebuild_max_segment Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq ulong Maximum read segment size to issue when sequentially resilvering a top-level vdev. . .It Sy zfs_rebuild_scrub_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int Automatically start a pool scrub when the last active sequential resilver completes in order to verify the checksums of all blocks which have been resilvered. This is enabled by default and strongly recommended. . .It Sy zfs_rebuild_vdev_limit Ns = Ns Sy 33554432 Ns B Po 32MB Pc Pq ulong Maximum amount of I/O that can be concurrently issued for a sequential resilver per leaf device, given in bytes. . .It Sy zfs_reconstruct_indirect_combinations_max Ns = Ns Sy 4096 Pq int If an indirect split block contains more than this many possible unique combinations when being reconstructed, consider it too computationally expensive to check them all. Instead, try at most this many randomly selected combinations each time the block is accessed. This allows all segment copies to participate fairly in the reconstruction when all combinations cannot be checked and prevents repeated use of one bad copy. . .It Sy zfs_recover Ns = Ns Sy 0 Ns | Ns 1 Pq int Set to attempt to recover from fatal errors. This should only be used as a last resort, as it typically results in leaked space, or worse. . .It Sy zfs_removal_ignore_errors Ns = Ns Sy 0 Ns | Ns 1 Pq int Ignore hard I/O errors during device removal. When set, if a device encounters a hard I/O error during the removal process the removal will not be cancelled. This can result in a normally recoverable block becoming permanently damaged and is hence not recommended. This should only be used as a last resort when the pool cannot be returned to a healthy state prior to removing the device. . .It Sy zfs_removal_suspend_progress Ns = Ns Sy 0 Ns | Ns 1 Pq int This is used by the test suite so that it can ensure that certain actions happen while in the middle of a removal. . .It Sy zfs_remove_max_segment Ns = Ns Sy 16777216 Ns B Po 16MB Pc Pq int The largest contiguous segment that we will attempt to allocate when removing a device. If there is a performance problem with attempting to allocate large blocks, consider decreasing this. The default value is also the maximum. . .It Sy zfs_resilver_disable_defer Ns = Ns Sy 0 Ns | Ns 1 Pq int Ignore the .Sy resilver_defer feature, causing an operation that would start a resilver to immediately restart the one in progress. . .It Sy zfs_resilver_min_time_ms Ns = Ns Sy 3000 Ns ms Po 3s Pc Pq int Resilvers are processed by the sync thread. While resilvering, it will spend at least this much time working on a resilver between TXG flushes. . .It Sy zfs_scan_ignore_errors Ns = Ns Sy 0 Ns | Ns 1 Pq int If set, remove the DTL (dirty time list) upon completion of a pool scan (scrub), even if there were unrepairable errors. Intended to be used during pool repair or recovery to stop resilvering when the pool is next imported. . .It Sy zfs_scrub_min_time_ms Ns = Ns Sy 1000 Ns ms Po 1s Pc Pq int Scrubs are processed by the sync thread. While scrubbing, it will spend at least this much time working on a scrub between TXG flushes. . .It Sy zfs_scan_checkpoint_intval Ns = Ns Sy 7200 Ns s Po 2h Pc Pq int To preserve progress across reboots, the sequential scan algorithm periodically needs to stop metadata scanning and issue all the verification I/O to disk. The frequency of this flushing is determined by this tunable. . .It Sy zfs_scan_fill_weight Ns = Ns Sy 3 Pq int This tunable affects how scrub and resilver I/O segments are ordered. A higher number indicates that we care more about how filled in a segment is, while a lower number indicates we care more about the size of the extent without considering the gaps within a segment. This value is only tunable upon module insertion. Changing the value afterwards will have no effect on scrub or resilver performance. . .It Sy zfs_scan_issue_strategy Ns = Ns Sy 0 Pq int Determines the order that data will be verified while scrubbing or resilvering: .Bl -tag -compact -offset 4n -width "a" .It Sy 1 Data will be verified as sequentially as possible, given the amount of memory reserved for scrubbing .Pq see Sy zfs_scan_mem_lim_fact . This may improve scrub performance if the pool's data is very fragmented. .It Sy 2 The largest mostly-contiguous chunk of found data will be verified first. By deferring scrubbing of small segments, we may later find adjacent data to coalesce and increase the segment size. .It Sy 0 .No Use strategy Sy 1 No during normal verification .No and strategy Sy 2 No while taking a checkpoint. .El . .It Sy zfs_scan_legacy Ns = Ns Sy 0 Ns | Ns 1 Pq int If unset, indicates that scrubs and resilvers will gather metadata in memory before issuing sequential I/O. Otherwise indicates that the legacy algorithm will be used, where I/O is initiated as soon as it is discovered. Unsetting will not affect scrubs or resilvers that are already in progress. . .It Sy zfs_scan_max_ext_gap Ns = Ns Sy 2097152 Ns B Po 2MB Pc Pq int Sets the largest gap in bytes between scrub/resilver I/O operations that will still be considered sequential for sorting purposes. Changing this value will not affect scrubs or resilvers that are already in progress. . .It Sy zfs_scan_mem_lim_fact Ns = Ns Sy 20 Ns ^-1 Pq int Maximum fraction of RAM used for I/O sorting by sequential scan algorithm. This tunable determines the hard limit for I/O sorting memory usage. When the hard limit is reached we stop scanning metadata and start issuing data verification I/O. This is done until we get below the soft limit. . .It Sy zfs_scan_mem_lim_soft_fact Ns = Ns Sy 20 Ns ^-1 Pq int The fraction of the hard limit used to determined the soft limit for I/O sorting by the sequential scan algorithm. When we cross this limit from below no action is taken. When we cross this limit from above it is because we are issuing verification I/O. In this case (unless the metadata scan is done) we stop issuing verification I/O and start scanning metadata again until we get to the hard limit. . .It Sy zfs_scan_strict_mem_lim Ns = Ns Sy 0 Ns | Ns 1 Pq int Enforce tight memory limits on pool scans when a sequential scan is in progress. When disabled, the memory limit may be exceeded by fast disks. . .It Sy zfs_scan_suspend_progress Ns = Ns Sy 0 Ns | Ns 1 Pq int Freezes a scrub/resilver in progress without actually pausing it. Intended for testing/debugging. . .It Sy zfs_scan_vdev_limit Ns = Ns Sy 4194304 Ns B Po 4MB Pc Pq int Maximum amount of data that can be concurrently issued at once for scrubs and resilvers per leaf device, given in bytes. . .It Sy zfs_send_corrupt_data Ns = Ns Sy 0 Ns | Ns 1 Pq int Allow sending of corrupt data (ignore read/checksum errors when sending). . .It Sy zfs_send_unmodified_spill_blocks Ns = Ns Sy 1 Ns | Ns 0 Pq int Include unmodified spill blocks in the send stream. Under certain circumstances, previous versions of ZFS could incorrectly remove the spill block from an existing object. Including unmodified copies of the spill blocks creates a backwards-compatible stream which will recreate a spill block if it was incorrectly removed. . .It Sy zfs_send_no_prefetch_queue_ff Ns = Ns Sy 20 Ns ^\-1 Pq int The fill fraction of the .Nm zfs Cm send internal queues. The fill fraction controls the timing with which internal threads are woken up. . .It Sy zfs_send_no_prefetch_queue_length Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq int The maximum number of bytes allowed in .Nm zfs Cm send Ns 's internal queues. . .It Sy zfs_send_queue_ff Ns = Ns Sy 20 Ns ^\-1 Pq int The fill fraction of the .Nm zfs Cm send prefetch queue. The fill fraction controls the timing with which internal threads are woken up. . .It Sy zfs_send_queue_length Ns = Ns Sy 16777216 Ns B Po 16MB Pc Pq int The maximum number of bytes allowed that will be prefetched by .Nm zfs Cm send . This value must be at least twice the maximum block size in use. . .It Sy zfs_recv_queue_ff Ns = Ns Sy 20 Ns ^\-1 Pq int The fill fraction of the .Nm zfs Cm receive queue. The fill fraction controls the timing with which internal threads are woken up. . .It Sy zfs_recv_queue_length Ns = Ns Sy 16777216 Ns B Po 16MB Pc Pq int The maximum number of bytes allowed in the .Nm zfs Cm receive queue. This value must be at least twice the maximum block size in use. . .It Sy zfs_recv_write_batch_size Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq int The maximum amount of data, in bytes, that .Nm zfs Cm receive will write in one DMU transaction. This is the uncompressed size, even when receiving a compressed send stream. This setting will not reduce the write size below a single block. Capped at a maximum of .Sy 32MB . . .It Sy zfs_override_estimate_recordsize Ns = Ns Sy 0 Ns | Ns 1 Pq ulong Setting this variable overrides the default logic for estimating block sizes when doing a .Nm zfs Cm send . The default heuristic is that the average block size will be the current recordsize. Override this value if most data in your dataset is not of that size and you require accurate zfs send size estimates. . .It Sy zfs_sync_pass_deferred_free Ns = Ns Sy 2 Pq int Flushing of data to disk is done in passes. Defer frees starting in this pass. . .It Sy zfs_spa_discard_memory_limit Ns = Ns Sy 16777216 Ns B Po 16MB Pc Pq int Maximum memory used for prefetching a checkpoint's space map on each vdev while discarding the checkpoint. . .It Sy zfs_special_class_metadata_reserve_pct Ns = Ns Sy 25 Ns % Pq int Only allow small data blocks to be allocated on the special and dedup vdev types when the available free space percentage on these vdevs exceeds this value. This ensures reserved space is available for pool metadata as the special vdevs approach capacity. . .It Sy zfs_sync_pass_dont_compress Ns = Ns Sy 8 Pq int Starting in this sync pass, disable compression (including of metadata). With the default setting, in practice, we don't have this many sync passes, so this has no effect. .Pp The original intent was that disabling compression would help the sync passes to converge. However, in practice, disabling compression increases the average number of sync passes; because when we turn compression off, many blocks' size will change, and thus we have to re-allocate (not overwrite) them. It also increases the number of .Em 128kB allocations (e.g. for indirect blocks and spacemaps) because these will not be compressed. The .Em 128kB allocations are especially detrimental to performance on highly fragmented systems, which may have very few free segments of this size, and may need to load new metaslabs to satisfy these allocations. . .It Sy zfs_sync_pass_rewrite Ns = Ns Sy 2 Pq int Rewrite new block pointers starting in this pass. . .It Sy zfs_sync_taskq_batch_pct Ns = Ns Sy 75 Ns % Pq int This controls the number of threads used by .Sy dp_sync_taskq . The default value of .Sy 75% will create a maximum of one thread per CPU. . .It Sy zfs_trim_extent_bytes_max Ns = Ns Sy 134217728 Ns B Po 128MB Pc Pq uint Maximum size of TRIM command. Larger ranges will be split into chunks no larger than this value before issuing. . .It Sy zfs_trim_extent_bytes_min Ns = Ns Sy 32768 Ns B Po 32kB Pc Pq uint Minimum size of TRIM commands. TRIM ranges smaller than this will be skipped, unless they're part of a larger range which was chunked. This is done because it's common for these small TRIMs to negatively impact overall performance. . .It Sy zfs_trim_metaslab_skip Ns = Ns Sy 0 Ns | Ns 1 Pq uint Skip uninitialized metaslabs during the TRIM process. This option is useful for pools constructed from large thinly-provisioned devices where TRIM operations are slow. As a pool ages, an increasing fraction of the pool's metaslabs will be initialized, progressively degrading the usefulness of this option. This setting is stored when starting a manual TRIM and will persist for the duration of the requested TRIM. . .It Sy zfs_trim_queue_limit Ns = Ns Sy 10 Pq uint Maximum number of queued TRIMs outstanding per leaf vdev. The number of concurrent TRIM commands issued to the device is controlled by .Sy zfs_vdev_trim_min_active No and Sy zfs_vdev_trim_max_active . . .It Sy zfs_trim_txg_batch Ns = Ns Sy 32 Pq uint The number of transaction groups' worth of frees which should be aggregated before TRIM operations are issued to the device. This setting represents a trade-off between issuing larger, more efficient TRIM operations and the delay before the recently trimmed space is available for use by the device. .Pp Increasing this value will allow frees to be aggregated for a longer time. This will result is larger TRIM operations and potentially increased memory usage. Decreasing this value will have the opposite effect. The default of .Sy 32 was determined to be a reasonable compromise. . .It Sy zfs_txg_history Ns = Ns Sy 0 Pq int Historical statistics for this many latest TXGs will be available in .Pa /proc/spl/kstat/zfs/ Ns Ao Ar pool Ac Ns Pa /TXGs . . .It Sy zfs_txg_timeout Ns = Ns Sy 5 Ns s Pq int Flush dirty data to disk at least every this many seconds (maximum TXG duration). . .It Sy zfs_vdev_aggregate_trim Ns = Ns Sy 0 Ns | Ns 1 Pq int Allow TRIM I/O operations to be aggregated. This is normally not helpful because the extents to be trimmed will have been already been aggregated by the metaslab. This option is provided for debugging and performance analysis. . .It Sy zfs_vdev_aggregation_limit Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq int Max vdev I/O aggregation size. . .It Sy zfs_vdev_aggregation_limit_non_rotating Ns = Ns Sy 131072 Ns B Po 128kB Pc Pq int Max vdev I/O aggregation size for non-rotating media. . .It Sy zfs_vdev_cache_bshift Ns = Ns Sy 16 Po 64kB Pc Pq int Shift size to inflate reads to. . .It Sy zfs_vdev_cache_max Ns = Ns Sy 16384 Ns B Po 16kB Pc Pq int Inflate reads smaller than this value to meet the .Sy zfs_vdev_cache_bshift size .Pq default Sy 64kB . . .It Sy zfs_vdev_cache_size Ns = Ns Sy 0 Pq int Total size of the per-disk cache in bytes. .Pp Currently this feature is disabled, as it has been found to not be helpful for performance and in some cases harmful. . .It Sy zfs_vdev_mirror_rotating_inc Ns = Ns Sy 0 Pq int A number by which the balancing algorithm increments the load calculation for the purpose of selecting the least busy mirror member when an I/O operation immediately follows its predecessor on rotational vdevs for the purpose of making decisions based on load. . .It Sy zfs_vdev_mirror_rotating_seek_inc Ns = Ns Sy 5 Pq int A number by which the balancing algorithm increments the load calculation for the purpose of selecting the least busy mirror member when an I/O operation lacks locality as defined by .Sy zfs_vdev_mirror_rotating_seek_offset . Operations within this that are not immediately following the previous operation are incremented by half. . .It Sy zfs_vdev_mirror_rotating_seek_offset Ns = Ns Sy 1048576 Ns B Po 1MB Pc Pq int The maximum distance for the last queued I/O operation in which the balancing algorithm considers an operation to have locality. .No See Sx ZFS I/O SCHEDULER . . .It Sy zfs_vdev_mirror_non_rotating_inc Ns = Ns Sy 0 Pq int A number by which the balancing algorithm increments the load calculation for the purpose of selecting the least busy mirror member on non-rotational vdevs when I/O operations do not immediately follow one another. . .It Sy zfs_vdev_mirror_non_rotating_seek_inc Ns = Ns Sy 1 Pq int A number by which the balancing algorithm increments the load calculation for the purpose of selecting the least busy mirror member when an I/O operation lacks locality as defined by the .Sy zfs_vdev_mirror_rotating_seek_offset . Operations within this that are not immediately following the previous operation are incremented by half. . .It Sy zfs_vdev_read_gap_limit Ns = Ns Sy 32768 Ns B Po 32kB Pc Pq int Aggregate read I/O operations if the on-disk gap between them is within this threshold. . .It Sy zfs_vdev_write_gap_limit Ns = Ns Sy 4096 Ns B Po 4kB Pc Pq int Aggregate write I/O operations if the on-disk gap between them is within this threshold. . .It Sy zfs_vdev_raidz_impl Ns = Ns Sy fastest Pq string Select the raidz parity implementation to use. .Pp Variants that don't depend on CPU-specific features may be selected on module load, as they are supported on all systems. The remaining options may only be set after the module is loaded, as they are available only if the implementations are compiled in and supported on the running system. .Pp Once the module is loaded, .Pa /sys/module/zfs/parameters/zfs_vdev_raidz_impl will show the available options, with the currently selected one enclosed in square brackets. .Pp .TS lb l l . fastest selected by built-in benchmark original original implementation scalar scalar implementation sse2 SSE2 instruction set 64-bit x86 ssse3 SSSE3 instruction set 64-bit x86 avx2 AVX2 instruction set 64-bit x86 avx512f AVX512F instruction set 64-bit x86 avx512bw AVX512F & AVX512BW instruction sets 64-bit x86 aarch64_neon NEON Aarch64/64-bit ARMv8 aarch64_neonx2 NEON with more unrolling Aarch64/64-bit ARMv8 powerpc_altivec Altivec PowerPC .TE . .It Sy zfs_vdev_scheduler Pq charp .Sy DEPRECATED . Prints warning to kernel log for compatibility. . .It Sy zfs_zevent_len_max Ns = Ns Sy 512 Pq int Max event queue length. Events in the queue can be viewed with .Xr zpool-events 8 . . .It Sy zfs_zevent_retain_max Ns = Ns Sy 2000 Pq int Maximum recent zevent records to retain for duplicate checking. Setting this to .Sy 0 disables duplicate detection. . .It Sy zfs_zevent_retain_expire_secs Ns = Ns Sy 900 Ns s Po 15min Pc Pq int Lifespan for a recent ereport that was retained for duplicate checking. . .It Sy zfs_zil_clean_taskq_maxalloc Ns = Ns Sy 1048576 Pq int The maximum number of taskq entries that are allowed to be cached. When this limit is exceeded transaction records (itxs) will be cleaned synchronously. . .It Sy zfs_zil_clean_taskq_minalloc Ns = Ns Sy 1024 Pq int The number of taskq entries that are pre-populated when the taskq is first created and are immediately available for use. . .It Sy zfs_zil_clean_taskq_nthr_pct Ns = Ns Sy 100 Ns % Pq int This controls the number of threads used by .Sy dp_zil_clean_taskq . The default value of .Sy 100% will create a maximum of one thread per cpu. . .It Sy zil_maxblocksize Ns = Ns Sy 131072 Ns B Po 128kB Pc Pq int This sets the maximum block size used by the ZIL. On very fragmented pools, lowering this .Pq typically to Sy 36kB can improve performance. . .It Sy zil_nocacheflush Ns = Ns Sy 0 Ns | Ns 1 Pq int Disable the cache flush commands that are normally sent to disk by the ZIL after an LWB write has completed. Setting this will cause ZIL corruption on power loss if a volatile out-of-order write cache is enabled. . .It Sy zil_replay_disable Ns = Ns Sy 0 Ns | Ns 1 Pq int Disable intent logging replay. Can be disabled for recovery from corrupted ZIL. . .It Sy zil_slog_bulk Ns = Ns Sy 786432 Ns B Po 768kB Pc Pq ulong Limit SLOG write size per commit executed with synchronous priority. Any writes above that will be executed with lower (asynchronous) priority to limit potential SLOG device abuse by single active ZIL writer. . +.It Sy zfs_zil_saxattr Ns = Ns Sy 1 Ns | Ns 0 Pq int +Setting this tunable to zero disables ZIL logging of new +.Sy xattr Ns = Ns Sy sa +records if the +.Sy org.openzfs:zilsaxattr +feature is enabled on the pool. +This would only be necessary to work around bugs in the ZIL logging or replay +code for this record type. +The tunable has no effect if the feature is disabled. +. .It Sy zfs_embedded_slog_min_ms Ns = Ns Sy 64 Pq int Usually, one metaslab from each normal-class vdev is dedicated for use by the ZIL to log synchronous writes. However, if there are fewer than .Sy zfs_embedded_slog_min_ms metaslabs in the vdev, this functionality is disabled. This ensures that we don't set aside an unreasonable amount of space for the ZIL. . .It Sy zio_deadman_log_all Ns = Ns Sy 0 Ns | Ns 1 Pq int If non-zero, the zio deadman will produce debugging messages .Pq see Sy zfs_dbgmsg_enable for all zios, rather than only for leaf zios possessing a vdev. This is meant to be used by developers to gain diagnostic information for hang conditions which don't involve a mutex or other locking primitive: typically conditions in which a thread in the zio pipeline is looping indefinitely. . .It Sy zio_slow_io_ms Ns = Ns Sy 30000 Ns ms Po 30s Pc Pq int When an I/O operation takes more than this much time to complete, it's marked as slow. Each slow operation causes a delay zevent. Slow I/O counters can be seen with .Nm zpool Cm status Fl s . . .It Sy zio_dva_throttle_enabled Ns = Ns Sy 1 Ns | Ns 0 Pq int Throttle block allocations in the I/O pipeline. This allows for dynamic allocation distribution when devices are imbalanced. When enabled, the maximum number of pending allocations per top-level vdev is limited by .Sy zfs_vdev_queue_depth_pct . . .It Sy zfs_xattr_compat Ns = Ns 0 Ns | Ns 1 Pq int Control the naming scheme used when setting new xattrs in the user namespace. If .Sy 0 .Pq the default on Linux , user namespace xattr names are prefixed with the namespace, to be backwards compatible with previous versions of ZFS on Linux. If .Sy 1 .Pq the default on Fx , user namespace xattr names are not prefixed, to be backwards compatible with previous versions of ZFS on illumos and .Fx . .Pp Either naming scheme can be read on this and future versions of ZFS, regardless of this tunable, but legacy ZFS on illumos or .Fx are unable to read user namespace xattrs written in the Linux format, and legacy versions of ZFS on Linux are unable to read user namespace xattrs written in the legacy ZFS format. .Pp An existing xattr with the alternate naming scheme is removed when overwriting the xattr so as to not accumulate duplicates. . .It Sy zio_requeue_io_start_cut_in_line Ns = Ns Sy 0 Ns | Ns 1 Pq int Prioritize requeued I/O. . .It Sy zio_taskq_batch_pct Ns = Ns Sy 80 Ns % Pq uint Percentage of online CPUs which will run a worker thread for I/O. These workers are responsible for I/O work such as compression and checksum calculations. Fractional number of CPUs will be rounded down. .Pp The default value of .Sy 80% was chosen to avoid using all CPUs which can result in latency issues and inconsistent application performance, especially when slower compression and/or checksumming is enabled. . .It Sy zio_taskq_batch_tpq Ns = Ns Sy 0 Pq uint Number of worker threads per taskq. Lower values improve I/O ordering and CPU utilization, while higher reduces lock contention. .Pp If .Sy 0 , generate a system-dependent value close to 6 threads per taskq. . .It Sy zvol_inhibit_dev Ns = Ns Sy 0 Ns | Ns 1 Pq uint Do not create zvol device nodes. This may slightly improve startup time on systems with a very large number of zvols. . .It Sy zvol_major Ns = Ns Sy 230 Pq uint Major number for zvol block devices. . .It Sy zvol_max_discard_blocks Ns = Ns Sy 16384 Pq ulong Discard (TRIM) operations done on zvols will be done in batches of this many blocks, where block size is determined by the .Sy volblocksize property of a zvol. . .It Sy zvol_prefetch_bytes Ns = Ns Sy 131072 Ns B Po 128kB Pc Pq uint When adding a zvol to the system, prefetch this many bytes from the start and end of the volume. Prefetching these regions of the volume is desirable, because they are likely to be accessed immediately by .Xr blkid 8 or the kernel partitioner. . .It Sy zvol_request_sync Ns = Ns Sy 0 Ns | Ns 1 Pq uint When processing I/O requests for a zvol, submit them synchronously. This effectively limits the queue depth to .Em 1 for each I/O submitter. When unset, requests are handled asynchronously by a thread pool. The number of requests which can be handled concurrently is controlled by .Sy zvol_threads . . .It Sy zvol_threads Ns = Ns Sy 32 Pq uint Max number of threads which can handle zvol I/O requests concurrently. . .It Sy zvol_volmode Ns = Ns Sy 1 Pq uint Defines zvol block devices behaviour when .Sy volmode Ns = Ns Sy default : .Bl -tag -compact -offset 4n -width "a" .It Sy 1 .No equivalent to Sy full .It Sy 2 .No equivalent to Sy dev .It Sy 3 .No equivalent to Sy none .El .El . .Sh ZFS I/O SCHEDULER ZFS issues I/O operations to leaf vdevs to satisfy and complete I/O operations. The scheduler determines when and in what order those operations are issued. The scheduler divides operations into five I/O classes, prioritized in the following order: sync read, sync write, async read, async write, and scrub/resilver. Each queue defines the minimum and maximum number of concurrent operations that may be issued to the device. In addition, the device has an aggregate maximum, .Sy zfs_vdev_max_active . Note that the sum of the per-queue minima must not exceed the aggregate maximum. If the sum of the per-queue maxima exceeds the aggregate maximum, then the number of active operations may reach .Sy zfs_vdev_max_active , in which case no further operations will be issued, regardless of whether all per-queue minima have been met. .Pp For many physical devices, throughput increases with the number of concurrent operations, but latency typically suffers. Furthermore, physical devices typically have a limit at which more concurrent operations have no effect on throughput or can actually cause it to decrease. .Pp The scheduler selects the next operation to issue by first looking for an I/O class whose minimum has not been satisfied. Once all are satisfied and the aggregate maximum has not been hit, the scheduler looks for classes whose maximum has not been satisfied. Iteration through the I/O classes is done in the order specified above. No further operations are issued if the aggregate maximum number of concurrent operations has been hit, or if there are no operations queued for an I/O class that has not hit its maximum. Every time an I/O operation is queued or an operation completes, the scheduler looks for new operations to issue. .Pp In general, smaller .Sy max_active Ns s will lead to lower latency of synchronous operations. Larger .Sy max_active Ns s may lead to higher overall throughput, depending on underlying storage. .Pp The ratio of the queues' .Sy max_active Ns s determines the balance of performance between reads, writes, and scrubs. For example, increasing .Sy zfs_vdev_scrub_max_active will cause the scrub or resilver to complete more quickly, but reads and writes to have higher latency and lower throughput. .Pp All I/O classes have a fixed maximum number of outstanding operations, except for the async write class. Asynchronous writes represent the data that is committed to stable storage during the syncing stage for transaction groups. Transaction groups enter the syncing state periodically, so the number of queued async writes will quickly burst up and then bleed down to zero. Rather than servicing them as quickly as possible, the I/O scheduler changes the maximum number of active async write operations according to the amount of dirty data in the pool. Since both throughput and latency typically increase with the number of concurrent operations issued to physical devices, reducing the burstiness in the number of concurrent operations also stabilizes the response time of operations from other – and in particular synchronous – queues. In broad strokes, the I/O scheduler will issue more concurrent operations from the async write queue as there's more dirty data in the pool. . .Ss Async Writes The number of concurrent operations issued for the async write I/O class follows a piece-wise linear function defined by a few adjustable points: .Bd -literal | o---------| <-- \fBzfs_vdev_async_write_max_active\fP ^ | /^ | | | / | | active | / | | I/O | / | | count | / | | | / | | |-------o | | <-- \fBzfs_vdev_async_write_min_active\fP 0|_______^______|_________| 0% | | 100% of \fBzfs_dirty_data_max\fP | | | `-- \fBzfs_vdev_async_write_active_max_dirty_percent\fP `--------- \fBzfs_vdev_async_write_active_min_dirty_percent\fP .Ed .Pp Until the amount of dirty data exceeds a minimum percentage of the dirty data allowed in the pool, the I/O scheduler will limit the number of concurrent operations to the minimum. As that threshold is crossed, the number of concurrent operations issued increases linearly to the maximum at the specified maximum percentage of the dirty data allowed in the pool. .Pp Ideally, the amount of dirty data on a busy pool will stay in the sloped part of the function between .Sy zfs_vdev_async_write_active_min_dirty_percent and .Sy zfs_vdev_async_write_active_max_dirty_percent . If it exceeds the maximum percentage, this indicates that the rate of incoming data is greater than the rate that the backend storage can handle. In this case, we must further throttle incoming writes, as described in the next section. . .Sh ZFS TRANSACTION DELAY We delay transactions when we've determined that the backend storage isn't able to accommodate the rate of incoming writes. .Pp If there is already a transaction waiting, we delay relative to when that transaction will finish waiting. This way the calculated delay time is independent of the number of threads concurrently executing transactions. .Pp 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. .Pp The minimum time for a transaction to take is calculated as .D1 min_time = min( Ns Sy zfs_delay_scale No \(mu Po Sy dirty No \- Sy min Pc / Po Sy max No \- Sy dirty Pc , 100ms) .Pp 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 .Sy zfs_delay_min_dirty_percent . This should typically be at or above .Sy 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 .Sy zfs_delay_scale . Roughly speaking, this variable determines the amount of delay at the midpoint of the curve. .Bd -literal delay 10ms +-------------------------------------------------------------*+ | *| 9ms + *+ | *| 8ms + *+ | * | 7ms + * + | * | 6ms + * + | * | 5ms + * + | * | 4ms + * + | * | 3ms + * + | * | 2ms + (midpoint) * + | | ** | 1ms + v *** + | \fBzfs_delay_scale\fP ----------> ******** | 0 +-------------------------------------*********----------------+ 0% <- \fBzfs_dirty_data_max\fP -> 100% .Ed .Pp Note, that since the delay is added to the outstanding time remaining on the most recent transaction it's effectively the inverse of IOPS. Here, the midpoint of .Em 500us translates to .Em 2000 IOPS . The shape of the curve was chosen such that small changes in the amount of accumulated dirty data in the first three quarters of the curve yield relatively small differences in the amount of delay. .Pp The effects can be easier to understand when the amount of delay is represented on a logarithmic scale: .Bd -literal delay 100ms +-------------------------------------------------------------++ + + | | + *+ 10ms + *+ + ** + | (midpoint) ** | + | ** + 1ms + v **** + + \fBzfs_delay_scale\fP ----------> ***** + | **** | + **** + 100us + ** + + * + | * | + * + 10us + * + + + | | + + +--------------------------------------------------------------+ 0% <- \fBzfs_dirty_data_max\fP -> 100% .Ed .Pp 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 back-end storage, and then by changing the value of .Sy zfs_delay_scale to increase the steepness of the curve. diff --git a/man/man7/zpool-features.7 b/man/man7/zpool-features.7 index d5148fb48bfa..9a202ca8a596 100644 --- a/man/man7/zpool-features.7 +++ b/man/man7/zpool-features.7 @@ -1,838 +1,856 @@ .\" .\" Copyright (c) 2012, 2018 by Delphix. All rights reserved. .\" Copyright (c) 2013 by Saso Kiselkov. All rights reserved. .\" Copyright (c) 2014, Joyent, Inc. All rights reserved. .\" 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] .\" Copyright (c) 2019, Klara Inc. .\" Copyright (c) 2019, Allan Jude .\" Copyright (c) 2021, Colm Buckley .\" .Dd May 31, 2021 .Dt ZPOOL-FEATURES 7 .Os . .Sh NAME .Nm zpool-features .Nd description of ZFS pool features . .Sh DESCRIPTION ZFS pool on-disk format versions are specified via "features" which replace the old on-disk format numbers (the last supported on-disk format number is 28). To enable a feature on a pool use the .Nm zpool Cm upgrade , or set the .Sy feature Ns @ Ns Ar feature-name property to .Sy enabled . Please also see the .Sx Compatibility feature sets section for information on how sets of features may be enabled together. .Pp The pool format does not affect file system version compatibility or the ability to send file systems between pools. .Pp Since most features can be enabled independently of each other, the on-disk format of the pool is specified by the set of all features marked as .Sy active on the pool. If the pool was created by another software version this set may include unsupported features. . .Ss Identifying features Every feature has a GUID of the form .Ar com.example : Ns Ar feature-name . The reversed DNS name ensures that the feature's GUID is unique across all ZFS implementations. When unsupported features are encountered on a pool they will be identified by their GUIDs. Refer to the documentation for the ZFS implementation that created the pool for information about those features. .Pp Each supported feature also has a short name. By convention a feature's short name is the portion of its GUID which follows the .Sq \&: (i.e. .Ar com.example : Ns Ar feature-name would have the short name .Ar feature-name ) , however a feature's short name may differ across ZFS implementations if following the convention would result in name conflicts. . .Ss Feature states Features can be in one of three states: .Bl -tag -width "disabled" .It Sy active This feature's on-disk format changes are in effect on the pool. Support for this feature is required to import the pool in read-write mode. If this feature is not read-only compatible, support is also required to import the pool in read-only mode .Pq see Sx Read-only compatibility . .It Sy enabled An administrator has marked this feature as enabled on the pool, but the feature's on-disk format changes have not been made yet. The pool can still be imported by software that does not support this feature, but changes may be made to the on-disk format at any time which will move the feature to the .Sy active state. Some features may support returning to the .Sy enabled state after becoming .Sy active . See feature-specific documentation for details. .It Sy disabled This feature's on-disk format changes have not been made and will not be made unless an administrator moves the feature to the .Sy enabled state. Features cannot be disabled once they have been enabled. .El .Pp The state of supported features is exposed through pool properties of the form .Sy feature Ns @ Ns Ar short-name . . .Ss Read-only compatibility Some features may make on-disk format changes that do not interfere with other software's ability to read from the pool. These features are referred to as .Dq read-only compatible . If all unsupported features on a pool are read-only compatible, the pool can be imported in read-only mode by setting the .Sy readonly property during import (see .Xr zpool-import 8 for details on importing pools). . .Ss Unsupported features For each unsupported feature enabled on an imported pool, a pool property named .Sy unsupported Ns @ Ns Ar feature-name will indicate why the import was allowed despite the unsupported feature. Possible values for this property are: .Bl -tag -width "readonly" .It Sy inactive The feature is in the .Sy enabled state and therefore the pool's on-disk format is still compatible with software that does not support this feature. .It Sy readonly The feature is read-only compatible and the pool has been imported in read-only mode. .El . .Ss Feature dependencies Some features depend on other features being enabled in order to function. Enabling a feature will automatically enable any features it depends on. . .Ss Compatibility feature sets It is sometimes necessary for a pool to maintain compatibility with a specific on-disk format, by enabling and disabling particular features. The .Sy compatibility feature facilitates this by allowing feature sets to be read from text files. When set to .Sy off (the default), compatibility feature sets are disabled (i.e. all features are enabled); when set to .Sy legacy , no features are enabled. When set to a comma-separated list of filenames (each filename may either be an absolute path, or relative to .Pa /etc/zfs/compatibility.d or .Pa /usr/share/zfs/compatibility.d ) , the lists of requested features are read from those files, separated by whitespace and/or commas. Only features present in all files are enabled. .Pp Simple sanity checks are applied to the files: they must be between 1B and 16kB in size, and must end with a newline character. .Pp The requested features are applied when a pool is created using .Nm zpool Cm create Fl o Sy compatibility Ns = Ns Ar … and controls which features are enabled when using .Nm zpool Cm upgrade . .Nm zpool Cm status will not show a warning about disabled features which are not part of the requested feature set. .Pp The special value .Sy legacy prevents any features from being enabled, either via .Nm zpool Cm upgrade or .Nm zpool Cm set Sy feature Ns @ Ns Ar feature-name Ns = Ns Sy enabled . This setting also prevents pools from being upgraded to newer on-disk versions. This is a safety measure to prevent new features from being accidentally enabled, breaking compatibility. .Pp By convention, compatibility files in .Pa /usr/share/zfs/compatibility.d are provided by the distribution, and include feature sets supported by important versions of popular distributions, and feature sets commonly supported at the start of each year. Compatibility files in .Pa /etc/zfs/compatibility.d , if present, will take precedence over files with the same name in .Pa /usr/share/zfs/compatibility.d . .Pp If an unrecognized feature is found in these files, an error message will be shown. If the unrecognized feature is in a file in .Pa /etc/zfs/compatibility.d , this is treated as an error and processing will stop. If the unrecognized feature is under .Pa /usr/share/zfs/compatibility.d , this is treated as a warning and processing will continue. This difference is to allow distributions to include features which might not be recognized by the currently-installed binaries. .Pp Compatibility files may include comments: any text from .Sq # to the end of the line is ignored. .Pp .Sy Example : .Bd -literal -compact -offset 4n .No example# Nm cat Pa /usr/share/zfs/compatibility.d/grub2 # Features which are supported by GRUB2 async_destroy bookmarks embedded_data empty_bpobj enabled_txg extensible_dataset filesystem_limits hole_birth large_blocks lz4_compress spacemap_histogram .No example# Nm zpool Cm create Fl o Sy compatibility Ns = Ns Ar grub2 Ar bootpool Ar vdev .Ed .Pp See .Xr zpool-create 8 and .Xr zpool-upgrade 8 for more information on how these commands are affected by feature sets. . .de feature .It Sy \\$2 .Bl -tag -compact -width "READ-ONLY COMPATIBLE" .It GUID .Sy \\$1:\\$2 .if !"\\$4"" \{\ .It DEPENDENCIES \fB\\$4\fP\c .if !"\\$5"" , \fB\\$5\fP\c .if !"\\$6"" , \fB\\$6\fP\c .if !"\\$7"" , \fB\\$7\fP\c .if !"\\$8"" , \fB\\$8\fP\c .if !"\\$9"" , \fB\\$9\fP\c .\} .It READ-ONLY COMPATIBLE \\$3 .El .Pp .. . .ds instant-never \ .No This feature becomes Sy active No as soon as it is enabled \ and will never return to being Sy enabled . . .ds remount-upgrade \ .No Each filesystem will be upgraded automatically when remounted, \ or when a new file is created under that filesystem. \ The upgrade can also be triggered on filesystems via \ Nm zfs Cm set Sy version Ns = Ns Sy current Ar fs . \ No The upgrade process runs in the background and may take a while to complete \ for filesystems containing large amounts of files. . .de checksum-spiel When the .Sy \\$1 feature is set to .Sy enabled , the administrator can turn on the .Sy \\$1 checksum on any dataset using .Nm zfs Cm set Sy checksum Ns = Ns Sy \\$1 Ar dset .Po see Xr zfs-set 8 Pc . This feature becomes .Sy active once a .Sy checksum property has been set to .Sy \\$1 , and will return to being .Sy enabled once all filesystems that have ever had their checksum set to .Sy \\$1 are destroyed. .. . .Sh FEATURES The following features are supported on this system: .Bl -tag -width Ds .feature org.zfsonlinux allocation_classes yes This feature enables support for separate allocation classes. .Pp This feature becomes .Sy active when a dedicated allocation class vdev (dedup or special) is created with the .Nm zpool Cm create No or Nm zpool Cm add No commands . With device removal, it can be returned to the .Sy enabled state if all the dedicated allocation class vdevs are removed. . .feature com.delphix async_destroy yes Destroying a file system requires traversing all of its data in order to return its used space to the pool. Without .Sy async_destroy , the file system is not fully removed until all space has been reclaimed. If the destroy operation is interrupted by a reboot or power outage, the next attempt to open the pool will need to complete the destroy operation synchronously. .Pp When .Sy async_destroy is enabled, the file system's data will be reclaimed by a background process, allowing the destroy operation to complete without traversing the entire file system. The background process is able to resume interrupted destroys after the pool has been opened, eliminating the need to finish interrupted destroys as part of the open operation. The amount of space remaining to be reclaimed by the background process is available through the .Sy freeing property. .Pp This feature is only .Sy active while .Sy freeing is non-zero. . .feature com.delphix bookmarks yes extensible_dataset This feature enables use of the .Nm zfs Cm bookmark command. .Pp This feature is .Sy active while any bookmarks exist in the pool. All bookmarks in the pool can be listed by running .Nm zfs Cm list Fl t Sy bookmark Fl r Ar poolname . . .feature com.datto bookmark_v2 no bookmark extensible_dataset This feature enables the creation and management of larger bookmarks which are needed for other features in ZFS. .Pp This feature becomes .Sy active when a v2 bookmark is created and will be returned to the .Sy enabled state when all v2 bookmarks are destroyed. . .feature com.delphix bookmark_written no bookmark extensible_dataset bookmark_v2 This feature enables additional bookmark accounting fields, enabling the .Sy written Ns # Ns Ar bookmark property (space written since a bookmark) and estimates of send stream sizes for incrementals from bookmarks. .Pp This feature becomes .Sy active when a bookmark is created and will be returned to the .Sy enabled state when all bookmarks with these fields are destroyed. . .feature org.openzfs device_rebuild yes This feature enables the ability for the .Nm zpool Cm attach and .Nm zpool Cm replace commands to perform sequential reconstruction (instead of healing reconstruction) when resilvering. .Pp Sequential reconstruction resilvers a device in LBA order without immediately verifying the checksums. Once complete, a scrub is started, which then verifies the checksums. This approach allows full redundancy to be restored to the pool in the minimum amount of time. This two-phase approach will take longer than a healing resilver when the time to verify the checksums is included. However, unless there is additional pool damage, no checksum errors should be reported by the scrub. This feature is incompatible with raidz configurations. . This feature becomes .Sy active while a sequential resilver is in progress, and returns to .Sy enabled when the resilver completes. . .feature com.delphix device_removal no This feature enables the .Nm zpool Cm remove command to remove top-level vdevs, evacuating them to reduce the total size of the pool. .Pp This feature becomes .Sy active when the .Nm zpool Cm remove command is used on a top-level vdev, and will never return to being .Sy enabled . . .feature org.openzfs draid no This feature enables use of the .Sy draid vdev type. dRAID is a variant of RAID-Z which provides integrated distributed hot spares that allow faster resilvering while retaining the benefits of RAID-Z. Data, parity, and spare space are organized in redundancy groups and distributed evenly over all of the devices. .Pp This feature becomes .Sy active when creating a pool which uses the .Sy draid vdev type, or when adding a new .Sy draid vdev to an existing pool. . .feature org.illumos edonr no extensible_dataset This feature enables the use of the Edon-R hash algorithm for checksum, including for nopwrite (if compression is also enabled, an overwrite of a block whose checksum matches the data being written will be ignored). In an abundance of caution, Edon-R requires verification when used with dedup: .Nm zfs Cm set Sy dedup Ns = Ns Sy edonr , Ns Sy verify .Po see Xr zfs-set 8 Pc . .Pp Edon-R is a very high-performance hash algorithm that was part of the NIST SHA-3 competition. It provides extremely high hash performance (over 350% faster than SHA-256), but was not selected because of its unsuitability as a general purpose secure hash algorithm. This implementation utilizes the new salted checksumming functionality in ZFS, which means that the checksum is pre-seeded with a secret 256-bit random key (stored on the pool) before being fed the data block to be checksummed. Thus the produced checksums are unique to a given pool, preventing hash collision attacks on systems with dedup. . .feature com.delphix embedded_data no This feature improves the performance and compression ratio of highly-compressible blocks. Blocks whose contents can compress to 112 bytes or smaller can take advantage of this feature. .Pp When this feature is enabled, the contents of highly-compressible blocks are stored in the block "pointer" itself (a misnomer in this case, as it contains the compressed data, rather than a pointer to its location on disk). Thus the space of the block (one sector, typically 512B or 4kB) is saved, and no additional I/O is needed to read and write the data block. . \*[instant-never] . .feature com.delphix empty_bpobj yes This feature increases the performance of creating and using a large number of snapshots of a single filesystem or volume, and also reduces the disk space required. .Pp When there are many snapshots, each snapshot uses many Block Pointer Objects (bpobjs) to track blocks associated with that snapshot. However, in common use cases, most of these bpobjs are empty. This feature allows us to create each bpobj on-demand, thus eliminating the empty bpobjs. .Pp This feature is .Sy active while there are any filesystems, volumes, or snapshots which were created after enabling this feature. . .feature com.delphix enabled_txg yes Once this feature is enabled, ZFS records the transaction group number in which new features are enabled. This has no user-visible impact, but other features may depend on this feature. .Pp This feature becomes .Sy active as soon as it is enabled and will never return to being .Sy enabled . . .feature com.datto encryption no bookmark_v2 extensible_dataset This feature enables the creation and management of natively encrypted datasets. .Pp This feature becomes .Sy active when an encrypted dataset is created and will be returned to the .Sy enabled state when all datasets that use this feature are destroyed. . .feature com.delphix extensible_dataset no This feature allows more flexible use of internal ZFS data structures, and exists for other features to depend on. .Pp This feature will be .Sy active when the first dependent feature uses it, and will be returned to the .Sy enabled state when all datasets that use this feature are destroyed. . .feature com.joyent filesystem_limits yes extensible_dataset This feature enables filesystem and snapshot limits. These limits can be used to control how many filesystems and/or snapshots can be created at the point in the tree on which the limits are set. .Pp This feature is .Sy active once either of the limit properties has been set on a dataset and will never return to being .Sy enabled . . .feature com.delphix hole_birth no enabled_txg This feature has/had bugs, the result of which is that, if you do a .Nm zfs Cm send Fl i .Pq or Fl R , No since it uses Fl i from an affected dataset, the receiving party will not see any checksum or other errors, but the resulting destination snapshot will not match the source. Its use by .Nm zfs Cm send Fl i has been disabled by default .Pq see Sy send_holes_without_birth_time No in Xr zfs 4 . .Pp This feature improves performance of incremental sends .Pq Nm zfs Cm send Fl i and receives for objects with many holes. The most common case of hole-filled objects is zvols. .Pp An incremental send stream from snapshot .Sy A No to snapshot Sy B contains information about every block that changed between .Sy A No and Sy B . Blocks which did not change between those snapshots can be identified and omitted from the stream using a piece of metadata called the "block birth time", but birth times are not recorded for holes (blocks filled only with zeroes). Since holes created after .Sy A No cannot be distinguished from holes created before Sy A , information about every hole in the entire filesystem or zvol is included in the send stream. .Pp For workloads where holes are rare this is not a problem. However, when incrementally replicating filesystems or zvols with many holes (for example a zvol formatted with another filesystem) a lot of time will be spent sending and receiving unnecessary information about holes that already exist on the receiving side. .Pp Once the .Sy hole_birth feature has been enabled the block birth times of all new holes will be recorded. Incremental sends between snapshots created after this feature is enabled will use this new metadata to avoid sending information about holes that already exist on the receiving side. .Pp \*[instant-never] . .feature org.open-zfs large_blocks no extensible_dataset This feature allows the record size on a dataset to be set larger than 128kB. .Pp This feature becomes .Sy active once a dataset contains a file with a block size larger than 128kB, and will return to being .Sy enabled once all filesystems that have ever had their recordsize larger than 128kB are destroyed. . .feature org.zfsonlinux large_dnode no extensible_dataset This feature allows the size of dnodes in a dataset to be set larger than 512B. . This feature becomes .Sy active once a dataset contains an object with a dnode larger than 512B, which occurs as a result of setting the .Sy dnodesize dataset property to a value other than .Sy legacy . The feature will return to being .Sy enabled once all filesystems that have ever contained a dnode larger than 512B are destroyed. Large dnodes allow more data to be stored in the bonus buffer, thus potentially improving performance by avoiding the use of spill blocks. . .feature com.delphix livelist yes This feature allows clones to be deleted faster than the traditional method when a large number of random/sparse writes have been made to the clone. All blocks allocated and freed after a clone is created are tracked by the the clone's livelist which is referenced during the deletion of the clone. The feature is activated when a clone is created and remains .Sy active until all clones have been destroyed. . .feature com.delphix log_spacemap yes com.delphix:spacemap_v2 This feature improves performance for heavily-fragmented pools, especially when workloads are heavy in random-writes. It does so by logging all the metaslab changes on a single spacemap every TXG instead of scattering multiple writes to all the metaslab spacemaps. .Pp \*[instant-never] . .feature org.illumos lz4_compress no .Sy lz4 is a high-performance real-time compression algorithm that features significantly faster compression and decompression as well as a higher compression ratio than the older .Sy lzjb compression. Typically, .Sy lz4 compression is approximately 50% faster on compressible data and 200% faster on incompressible data than .Sy lzjb . It is also approximately 80% faster on decompression, while giving approximately a 10% better compression ratio. .Pp When the .Sy lz4_compress feature is set to .Sy enabled , the administrator can turn on .Sy lz4 compression on any dataset on the pool using the .Xr zfs-set 8 command. All newly written metadata will be compressed with the .Sy lz4 algorithm. .Pp \*[instant-never] . .feature com.joyent multi_vdev_crash_dump no This feature allows a dump device to be configured with a pool comprised of multiple vdevs. Those vdevs may be arranged in any mirrored or raidz configuration. .Pp When the .Sy multi_vdev_crash_dump feature is set to .Sy enabled , the administrator can use .Xr dumpadm 1M to configure a dump device on a pool comprised of multiple vdevs. .Pp Under .Fx and Linux this feature is unused, but registered for compatibility. New pools created on these systems will have the feature .Sy enabled but will never transition to .Sy active , as this functionality is not required for crash dump support. Existing pools where this feature is .Sy active can be imported. . .feature com.delphix obsolete_counts yes device_removal This feature is an enhancement of .Sy device_removal , which will over time reduce the memory used to track removed devices. When indirect blocks are freed or remapped, we note that their part of the indirect mapping is "obsolete" – no longer needed. .Pp This feature becomes .Sy active when the .Nm zpool Cm remove command is used on a top-level vdev, and will never return to being .Sy enabled . . .feature org.zfsonlinux project_quota yes extensible_dataset This feature allows administrators to account the spaces and objects usage information against the project identifier (ID). .Pp The project ID is an object-based attribute. When upgrading an existing filesystem, objects without a project ID will be assigned a zero project ID. When this feature is enabled, newly created objects inherit their parent directories' project ID if the parent's inherit flag is set .Pq via Nm chattr Sy [+-]P No or Nm zfs Cm project Fl s Ns | Ns Fl C . Otherwise, the new object's project ID will be zero. An object's project ID can be changed at any time by the owner (or privileged user) via .Nm chattr Fl p Ar prjid or .Nm zfs Cm project Fl p Ar prjid . .Pp This feature will become .Sy active as soon as it is enabled and will never return to being .Sy disabled . \*[remount-upgrade] . .feature com.delphix redaction_bookmarks no bookmarks extensible_dataset This feature enables the use of redacted .Nm zfs Cm send Ns s , which create redaction bookmarks storing the list of blocks redacted by the send that created them. For more information about redacted sends, see .Xr zfs-send 8 . . .feature com.delphix redacted_datasets no extensible_dataset This feature enables the receiving of redacted .Nm zfs Cm send streams, which create redacted datasets when received. These datasets are missing some of their blocks, and so cannot be safely mounted, and their contents cannot be safely read. For more information about redacted receives, see .Xr zfs-send 8 . . .feature com.datto resilver_defer yes This feature allows ZFS to postpone new resilvers if an existing one is already in progress. Without this feature, any new resilvers will cause the currently running one to be immediately restarted from the beginning. .Pp This feature becomes .Sy active once a resilver has been deferred, and returns to being .Sy enabled when the deferred resilver begins. . .feature org.illumos sha512 no extensible_dataset This feature enables the use of the SHA-512/256 truncated hash algorithm (FIPS 180-4) for checksum and dedup. The native 64-bit arithmetic of SHA-512 provides an approximate 50% performance boost over SHA-256 on 64-bit hardware and is thus a good minimum-change replacement candidate for systems where hash performance is important, but these systems cannot for whatever reason utilize the faster .Sy skein No and Sy edonr algorithms. .Pp .checksum-spiel sha512 . .feature org.illumos skein no extensible_dataset This feature enables the use of the Skein hash algorithm for checksum and dedup. Skein is a high-performance secure hash algorithm that was a finalist in the NIST SHA-3 competition. It provides a very high security margin and high performance on 64-bit hardware (80% faster than SHA-256). This implementation also utilizes the new salted checksumming functionality in ZFS, which means that the checksum is pre-seeded with a secret 256-bit random key (stored on the pool) before being fed the data block to be checksummed. Thus the produced checksums are unique to a given pool, preventing hash collision attacks on systems with dedup. .Pp .checksum-spiel skein . .feature com.delphix spacemap_histogram yes This features allows ZFS to maintain more information about how free space is organized within the pool. If this feature is .Sy enabled , it will be activated when a new space map object is created, or an existing space map is upgraded to the new format, and never returns back to being .Sy enabled . . .feature com.delphix spacemap_v2 yes This feature enables the use of the new space map encoding which consists of two words (instead of one) whenever it is advantageous. The new encoding allows space maps to represent large regions of space more efficiently on-disk while also increasing their maximum addressable offset. .Pp This feature becomes .Sy active once it is .Sy enabled , and never returns back to being .Sy enabled . . .feature org.zfsonlinux userobj_accounting yes extensible_dataset This feature allows administrators to account the object usage information by user and group. .Pp \*[instant-never] \*[remount-upgrade] . +.feature org.openzfs zilsaxattr yes extensible_dataset +This feature enables +.Sy xattr Ns = Ns Sy sa +extended attribute logging in the ZIL. +If enabled, extended attribute changes +.Pq both Sy xattrdir Ns = Ns Sy dir No and Sy xattr Ns = Ns Sy sa +are guaranteed to be durable if either the dataset had +.Sy sync Ns = Ns Sy always +set at the time the changes were made, or +.Xr sync 2 +is called on the dataset after the changes were made. +.Pp +This feature becomes +.Sy active +when a ZIL is created for at least one dataset and will be returned to the +.Sy enabled +state when it is destroyed for all datasets that use this feature. +. .feature com.delphix zpool_checkpoint yes This feature enables the .Nm zpool Cm checkpoint command that can checkpoint the state of the pool at the time it was issued and later rewind back to it or discard it. .Pp This feature becomes .Sy active when the .Nm zpool Cm checkpoint command is used to checkpoint the pool. The feature will only return back to being .Sy enabled when the pool is rewound or the checkpoint has been discarded. . .feature org.freebsd zstd_compress no extensible_dataset .Sy zstd is a high-performance compression algorithm that features a combination of high compression ratios and high speed. Compared to .Sy gzip , .Sy zstd offers slightly better compression at much higher speeds. Compared to .Sy lz4 , .Sy zstd offers much better compression while being only modestly slower. Typically, .Sy zstd compression speed ranges from 250 to 500 MB/s per thread and decompression speed is over 1 GB/s per thread. .Pp When the .Sy zstd feature is set to .Sy enabled , the administrator can turn on .Sy zstd compression of any dataset using .Nm zfs Cm set Sy compress Ns = Ns Sy zstd Ar dset .Po see Xr zfs-set 8 Pc . This feature becomes .Sy active once a .Sy compress property has been set to .Sy zstd , and will return to being .Sy enabled once all filesystems that have ever had their .Sy compress property set to .Sy zstd are destroyed. .El . .Sh SEE ALSO .Xr zpool 8 diff --git a/module/os/freebsd/zfs/zfs_vnops_os.c b/module/os/freebsd/zfs/zfs_vnops_os.c index 1b0f53c6d8fb..21d121a15846 100644 --- a/module/os/freebsd/zfs/zfs_vnops_os.c +++ b/module/os/freebsd/zfs/zfs_vnops_os.c @@ -1,6347 +1,6347 @@ /* * 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 (c) 2012, 2015 by Delphix. All rights reserved. * Copyright (c) 2014 Integros [integros.com] * Copyright 2017 Nexenta Systems, Inc. */ /* Portions Copyright 2007 Jeremy Teo */ /* Portions Copyright 2010 Robert Milkowski */ #include #include #include #include #include #include #include #include #include #include #if __FreeBSD_version >= 1300102 #include #endif #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #ifndef VN_OPEN_INVFS #define VN_OPEN_INVFS 0x0 #endif VFS_SMR_DECLARE; #if __FreeBSD_version >= 1300047 #define vm_page_wire_lock(pp) #define vm_page_wire_unlock(pp) #else #define vm_page_wire_lock(pp) vm_page_lock(pp) #define vm_page_wire_unlock(pp) vm_page_unlock(pp) #endif #ifdef DEBUG_VFS_LOCKS #define VNCHECKREF(vp) \ VNASSERT((vp)->v_holdcnt > 0 && (vp)->v_usecount > 0, vp, \ ("%s: wrong ref counts", __func__)); #else #define VNCHECKREF(vp) #endif #if __FreeBSD_version >= 1400045 typedef uint64_t cookie_t; #else typedef ulong_t cookie_t; #endif /* * Programming rules. * * Each vnode op performs some logical unit of work. To do this, the ZPL must * properly lock its in-core state, create a DMU transaction, do the work, * record this work in the intent log (ZIL), commit the DMU transaction, * and wait for the intent log to commit if it is a synchronous operation. * Moreover, the vnode ops must work in both normal and log replay context. * The ordering of events is important to avoid deadlocks and references * to freed memory. The example below illustrates the following Big Rules: * * (1) A check must be made in each zfs thread for a mounted file system. * This is done avoiding races using ZFS_ENTER(zfsvfs). * A ZFS_EXIT(zfsvfs) is needed before all returns. Any znodes * must be checked with ZFS_VERIFY_ZP(zp). Both of these macros * can return EIO from the calling function. * * (2) VN_RELE() should always be the last thing except for zil_commit() * (if necessary) and ZFS_EXIT(). This is for 3 reasons: * First, if it's the last reference, the vnode/znode * can be freed, so the zp may point to freed memory. Second, the last * reference will call zfs_zinactive(), which may induce a lot of work -- * pushing cached pages (which acquires range locks) and syncing out * cached atime changes. Third, zfs_zinactive() may require a new tx, * which could deadlock the system if you were already holding one. * If you must call VN_RELE() within a tx then use VN_RELE_ASYNC(). * * (3) All range locks must be grabbed before calling dmu_tx_assign(), * as they can span dmu_tx_assign() calls. * * (4) If ZPL locks are held, pass TXG_NOWAIT as the second argument to * dmu_tx_assign(). This is critical because we don't want to block * while holding locks. * * If no ZPL locks are held (aside from ZFS_ENTER()), use TXG_WAIT. This * reduces lock contention and CPU usage when we must wait (note that if * throughput is constrained by the storage, nearly every transaction * must wait). * * Note, in particular, that if a lock is sometimes acquired before * the tx assigns, and sometimes after (e.g. z_lock), then failing * to use a non-blocking assign can deadlock the system. The scenario: * * Thread A has grabbed a lock before calling dmu_tx_assign(). * Thread B is in an already-assigned tx, and blocks for this lock. * Thread A calls dmu_tx_assign(TXG_WAIT) and blocks in txg_wait_open() * forever, because the previous txg can't quiesce until B's tx commits. * * If dmu_tx_assign() returns ERESTART and zfsvfs->z_assign is TXG_NOWAIT, * then drop all locks, call dmu_tx_wait(), and try again. On subsequent * calls to dmu_tx_assign(), pass TXG_NOTHROTTLE in addition to TXG_NOWAIT, * to indicate that this operation has already called dmu_tx_wait(). * This will ensure that we don't retry forever, waiting a short bit * each time. * * (5) If the operation succeeded, generate the intent log entry for it * before dropping locks. This ensures that the ordering of events * in the intent log matches the order in which they actually occurred. * During ZIL replay the zfs_log_* functions will update the sequence * number to indicate the zil transaction has replayed. * * (6) At the end of each vnode op, the DMU tx must always commit, * regardless of whether there were any errors. * * (7) After dropping all locks, invoke zil_commit(zilog, foid) * to ensure that synchronous semantics are provided when necessary. * * In general, this is how things should be ordered in each vnode op: * * ZFS_ENTER(zfsvfs); // exit if unmounted * top: * zfs_dirent_lookup(&dl, ...) // lock directory entry (may VN_HOLD()) * rw_enter(...); // grab any other locks you need * tx = dmu_tx_create(...); // get DMU tx * dmu_tx_hold_*(); // hold each object you might modify * error = dmu_tx_assign(tx, (waited ? TXG_NOTHROTTLE : 0) | TXG_NOWAIT); * if (error) { * rw_exit(...); // drop locks * zfs_dirent_unlock(dl); // unlock directory entry * VN_RELE(...); // release held vnodes * if (error == ERESTART) { * waited = B_TRUE; * dmu_tx_wait(tx); * dmu_tx_abort(tx); * goto top; * } * dmu_tx_abort(tx); // abort DMU tx * ZFS_EXIT(zfsvfs); // finished in zfs * return (error); // really out of space * } * error = do_real_work(); // do whatever this VOP does * if (error == 0) * zfs_log_*(...); // on success, make ZIL entry * dmu_tx_commit(tx); // commit DMU tx -- error or not * rw_exit(...); // drop locks * zfs_dirent_unlock(dl); // unlock directory entry * VN_RELE(...); // release held vnodes * zil_commit(zilog, foid); // synchronous when necessary * ZFS_EXIT(zfsvfs); // finished in zfs * return (error); // done, report error */ static int zfs_open(vnode_t **vpp, int flag, cred_t *cr) { (void) cr; znode_t *zp = VTOZ(*vpp); zfsvfs_t *zfsvfs = zp->z_zfsvfs; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); if ((flag & FWRITE) && (zp->z_pflags & ZFS_APPENDONLY) && ((flag & FAPPEND) == 0)) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EPERM)); } /* Keep a count of the synchronous opens in the znode */ if (flag & (FSYNC | FDSYNC)) atomic_inc_32(&zp->z_sync_cnt); ZFS_EXIT(zfsvfs); return (0); } static int zfs_close(vnode_t *vp, int flag, int count, offset_t offset, cred_t *cr) { (void) offset, (void) cr; znode_t *zp = VTOZ(vp); zfsvfs_t *zfsvfs = zp->z_zfsvfs; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); /* Decrement the synchronous opens in the znode */ if ((flag & (FSYNC | FDSYNC)) && (count == 1)) atomic_dec_32(&zp->z_sync_cnt); ZFS_EXIT(zfsvfs); return (0); } static int zfs_ioctl(vnode_t *vp, ulong_t com, intptr_t data, int flag, cred_t *cred, int *rvalp) { (void) flag, (void) cred, (void) rvalp; loff_t off; int error; switch (com) { case _FIOFFS: { return (0); /* * The following two ioctls are used by bfu. Faking out, * necessary to avoid bfu errors. */ } case _FIOGDIO: case _FIOSDIO: { return (0); } case F_SEEK_DATA: case F_SEEK_HOLE: { off = *(offset_t *)data; /* offset parameter is in/out */ error = zfs_holey(VTOZ(vp), com, &off); if (error) return (error); *(offset_t *)data = off; return (0); } } return (SET_ERROR(ENOTTY)); } static vm_page_t page_busy(vnode_t *vp, int64_t start, int64_t off, int64_t nbytes) { vm_object_t obj; vm_page_t pp; int64_t end; /* * At present vm_page_clear_dirty extends the cleared range to DEV_BSIZE * aligned boundaries, if the range is not aligned. As a result a * DEV_BSIZE subrange with partially dirty data may get marked as clean. * It may happen that all DEV_BSIZE subranges are marked clean and thus * the whole page would be considered clean despite have some * dirty data. * For this reason we should shrink the range to DEV_BSIZE aligned * boundaries before calling vm_page_clear_dirty. */ end = rounddown2(off + nbytes, DEV_BSIZE); off = roundup2(off, DEV_BSIZE); nbytes = end - off; obj = vp->v_object; zfs_vmobject_assert_wlocked_12(obj); #if __FreeBSD_version < 1300050 for (;;) { if ((pp = vm_page_lookup(obj, OFF_TO_IDX(start))) != NULL && pp->valid) { if (vm_page_xbusied(pp)) { /* * Reference the page before unlocking and * sleeping so that the page daemon is less * likely to reclaim it. */ vm_page_reference(pp); vm_page_lock(pp); zfs_vmobject_wunlock(obj); vm_page_busy_sleep(pp, "zfsmwb", true); zfs_vmobject_wlock(obj); continue; } vm_page_sbusy(pp); } else if (pp != NULL) { ASSERT(!pp->valid); pp = NULL; } if (pp != NULL) { ASSERT3U(pp->valid, ==, VM_PAGE_BITS_ALL); vm_object_pip_add(obj, 1); pmap_remove_write(pp); if (nbytes != 0) vm_page_clear_dirty(pp, off, nbytes); } break; } #else vm_page_grab_valid_unlocked(&pp, obj, OFF_TO_IDX(start), VM_ALLOC_NOCREAT | VM_ALLOC_SBUSY | VM_ALLOC_NORMAL | VM_ALLOC_IGN_SBUSY); if (pp != NULL) { ASSERT3U(pp->valid, ==, VM_PAGE_BITS_ALL); vm_object_pip_add(obj, 1); pmap_remove_write(pp); if (nbytes != 0) vm_page_clear_dirty(pp, off, nbytes); } #endif return (pp); } static void page_unbusy(vm_page_t pp) { vm_page_sunbusy(pp); #if __FreeBSD_version >= 1300041 vm_object_pip_wakeup(pp->object); #else vm_object_pip_subtract(pp->object, 1); #endif } #if __FreeBSD_version > 1300051 static vm_page_t page_hold(vnode_t *vp, int64_t start) { vm_object_t obj; vm_page_t m; obj = vp->v_object; vm_page_grab_valid_unlocked(&m, obj, OFF_TO_IDX(start), VM_ALLOC_NOCREAT | VM_ALLOC_WIRED | VM_ALLOC_IGN_SBUSY | VM_ALLOC_NOBUSY); return (m); } #else static vm_page_t page_hold(vnode_t *vp, int64_t start) { vm_object_t obj; vm_page_t pp; obj = vp->v_object; zfs_vmobject_assert_wlocked(obj); for (;;) { if ((pp = vm_page_lookup(obj, OFF_TO_IDX(start))) != NULL && pp->valid) { if (vm_page_xbusied(pp)) { /* * Reference the page before unlocking and * sleeping so that the page daemon is less * likely to reclaim it. */ vm_page_reference(pp); vm_page_lock(pp); zfs_vmobject_wunlock(obj); vm_page_busy_sleep(pp, "zfsmwb", true); zfs_vmobject_wlock(obj); continue; } ASSERT3U(pp->valid, ==, VM_PAGE_BITS_ALL); vm_page_wire_lock(pp); vm_page_hold(pp); vm_page_wire_unlock(pp); } else pp = NULL; break; } return (pp); } #endif static void page_unhold(vm_page_t pp) { vm_page_wire_lock(pp); #if __FreeBSD_version >= 1300035 vm_page_unwire(pp, PQ_ACTIVE); #else vm_page_unhold(pp); #endif vm_page_wire_unlock(pp); } /* * When a file is memory mapped, we must keep the IO data synchronized * between the DMU cache and the memory mapped pages. What this means: * * On Write: If we find a memory mapped page, we write to *both* * the page and the dmu buffer. */ void update_pages(znode_t *zp, int64_t start, int len, objset_t *os) { vm_object_t obj; struct sf_buf *sf; vnode_t *vp = ZTOV(zp); caddr_t va; int off; ASSERT3P(vp->v_mount, !=, NULL); obj = vp->v_object; ASSERT3P(obj, !=, NULL); off = start & PAGEOFFSET; zfs_vmobject_wlock_12(obj); #if __FreeBSD_version >= 1300041 vm_object_pip_add(obj, 1); #endif for (start &= PAGEMASK; len > 0; start += PAGESIZE) { vm_page_t pp; int nbytes = imin(PAGESIZE - off, len); if ((pp = page_busy(vp, start, off, nbytes)) != NULL) { zfs_vmobject_wunlock_12(obj); va = zfs_map_page(pp, &sf); (void) dmu_read(os, zp->z_id, start + off, nbytes, va + off, DMU_READ_PREFETCH); zfs_unmap_page(sf); zfs_vmobject_wlock_12(obj); page_unbusy(pp); } len -= nbytes; off = 0; } #if __FreeBSD_version >= 1300041 vm_object_pip_wakeup(obj); #else vm_object_pip_wakeupn(obj, 0); #endif zfs_vmobject_wunlock_12(obj); } /* * Read with UIO_NOCOPY flag means that sendfile(2) requests * ZFS to populate a range of page cache pages with data. * * NOTE: this function could be optimized to pre-allocate * all pages in advance, drain exclusive busy on all of them, * map them into contiguous KVA region and populate them * in one single dmu_read() call. */ int mappedread_sf(znode_t *zp, int nbytes, zfs_uio_t *uio) { vnode_t *vp = ZTOV(zp); objset_t *os = zp->z_zfsvfs->z_os; struct sf_buf *sf; vm_object_t obj; vm_page_t pp; int64_t start; caddr_t va; int len = nbytes; int error = 0; ASSERT3U(zfs_uio_segflg(uio), ==, UIO_NOCOPY); ASSERT3P(vp->v_mount, !=, NULL); obj = vp->v_object; ASSERT3P(obj, !=, NULL); ASSERT0(zfs_uio_offset(uio) & PAGEOFFSET); zfs_vmobject_wlock_12(obj); for (start = zfs_uio_offset(uio); len > 0; start += PAGESIZE) { int bytes = MIN(PAGESIZE, len); pp = vm_page_grab_unlocked(obj, OFF_TO_IDX(start), VM_ALLOC_SBUSY | VM_ALLOC_NORMAL | VM_ALLOC_IGN_SBUSY); if (vm_page_none_valid(pp)) { zfs_vmobject_wunlock_12(obj); va = zfs_map_page(pp, &sf); error = dmu_read(os, zp->z_id, start, bytes, va, DMU_READ_PREFETCH); if (bytes != PAGESIZE && error == 0) bzero(va + bytes, PAGESIZE - bytes); zfs_unmap_page(sf); zfs_vmobject_wlock_12(obj); #if __FreeBSD_version >= 1300081 if (error == 0) { vm_page_valid(pp); vm_page_activate(pp); vm_page_do_sunbusy(pp); } else { zfs_vmobject_wlock(obj); if (!vm_page_wired(pp) && pp->valid == 0 && vm_page_busy_tryupgrade(pp)) vm_page_free(pp); else vm_page_sunbusy(pp); zfs_vmobject_wunlock(obj); } #else vm_page_do_sunbusy(pp); vm_page_lock(pp); if (error) { if (pp->wire_count == 0 && pp->valid == 0 && !vm_page_busied(pp)) vm_page_free(pp); } else { pp->valid = VM_PAGE_BITS_ALL; vm_page_activate(pp); } vm_page_unlock(pp); #endif } else { ASSERT3U(pp->valid, ==, VM_PAGE_BITS_ALL); vm_page_do_sunbusy(pp); } if (error) break; zfs_uio_advance(uio, bytes); len -= bytes; } zfs_vmobject_wunlock_12(obj); return (error); } /* * When a file is memory mapped, we must keep the IO data synchronized * between the DMU cache and the memory mapped pages. What this means: * * On Read: We "read" preferentially from memory mapped pages, * else we default from the dmu buffer. * * NOTE: We will always "break up" the IO into PAGESIZE uiomoves when * the file is memory mapped. */ int mappedread(znode_t *zp, int nbytes, zfs_uio_t *uio) { vnode_t *vp = ZTOV(zp); vm_object_t obj; int64_t start; int len = nbytes; int off; int error = 0; ASSERT3P(vp->v_mount, !=, NULL); obj = vp->v_object; ASSERT3P(obj, !=, NULL); start = zfs_uio_offset(uio); off = start & PAGEOFFSET; zfs_vmobject_wlock_12(obj); for (start &= PAGEMASK; len > 0; start += PAGESIZE) { vm_page_t pp; uint64_t bytes = MIN(PAGESIZE - off, len); if ((pp = page_hold(vp, start))) { struct sf_buf *sf; caddr_t va; zfs_vmobject_wunlock_12(obj); va = zfs_map_page(pp, &sf); error = vn_io_fault_uiomove(va + off, bytes, GET_UIO_STRUCT(uio)); zfs_unmap_page(sf); zfs_vmobject_wlock_12(obj); page_unhold(pp); } else { zfs_vmobject_wunlock_12(obj); error = dmu_read_uio_dbuf(sa_get_db(zp->z_sa_hdl), uio, bytes); zfs_vmobject_wlock_12(obj); } len -= bytes; off = 0; if (error) break; } zfs_vmobject_wunlock_12(obj); return (error); } int zfs_write_simple(znode_t *zp, const void *data, size_t len, loff_t pos, size_t *presid) { int error = 0; ssize_t resid; error = vn_rdwr(UIO_WRITE, ZTOV(zp), __DECONST(void *, data), len, pos, UIO_SYSSPACE, IO_SYNC, kcred, NOCRED, &resid, curthread); if (error) { return (SET_ERROR(error)); } else if (presid == NULL) { if (resid != 0) { error = SET_ERROR(EIO); } } else { *presid = resid; } return (error); } void zfs_zrele_async(znode_t *zp) { vnode_t *vp = ZTOV(zp); objset_t *os = ITOZSB(vp)->z_os; VN_RELE_ASYNC(vp, dsl_pool_zrele_taskq(dmu_objset_pool(os))); } static int zfs_dd_callback(struct mount *mp, void *arg, int lkflags, struct vnode **vpp) { int error; *vpp = arg; error = vn_lock(*vpp, lkflags); if (error != 0) vrele(*vpp); return (error); } static int zfs_lookup_lock(vnode_t *dvp, vnode_t *vp, const char *name, int lkflags) { znode_t *zdp = VTOZ(dvp); zfsvfs_t *zfsvfs __unused = zdp->z_zfsvfs; int error; int ltype; if (zfsvfs->z_replay == B_FALSE) ASSERT_VOP_LOCKED(dvp, __func__); if (name[0] == 0 || (name[0] == '.' && name[1] == 0)) { ASSERT3P(dvp, ==, vp); vref(dvp); ltype = lkflags & LK_TYPE_MASK; if (ltype != VOP_ISLOCKED(dvp)) { if (ltype == LK_EXCLUSIVE) vn_lock(dvp, LK_UPGRADE | LK_RETRY); else /* if (ltype == LK_SHARED) */ vn_lock(dvp, LK_DOWNGRADE | LK_RETRY); /* * Relock for the "." case could leave us with * reclaimed vnode. */ if (VN_IS_DOOMED(dvp)) { vrele(dvp); return (SET_ERROR(ENOENT)); } } return (0); } else if (name[0] == '.' && name[1] == '.' && name[2] == 0) { /* * Note that in this case, dvp is the child vnode, and we * are looking up the parent vnode - exactly reverse from * normal operation. Unlocking dvp requires some rather * tricky unlock/relock dance to prevent mp from being freed; * use vn_vget_ino_gen() which takes care of all that. * * XXX Note that there is a time window when both vnodes are * unlocked. It is possible, although highly unlikely, that * during that window the parent-child relationship between * the vnodes may change, for example, get reversed. * In that case we would have a wrong lock order for the vnodes. * All other filesystems seem to ignore this problem, so we * do the same here. * A potential solution could be implemented as follows: * - using LK_NOWAIT when locking the second vnode and retrying * if necessary * - checking that the parent-child relationship still holds * after locking both vnodes and retrying if it doesn't */ error = vn_vget_ino_gen(dvp, zfs_dd_callback, vp, lkflags, &vp); return (error); } else { error = vn_lock(vp, lkflags); if (error != 0) vrele(vp); return (error); } } /* * Lookup an entry in a directory, or an extended attribute directory. * If it exists, return a held vnode reference for it. * * IN: dvp - vnode of directory to search. * nm - name of entry to lookup. * pnp - full pathname to lookup [UNUSED]. * flags - LOOKUP_XATTR set if looking for an attribute. * rdir - root directory vnode [UNUSED]. * cr - credentials of caller. * ct - caller context * * OUT: vpp - vnode of located entry, NULL if not found. * * RETURN: 0 on success, error code on failure. * * Timestamps: * NA */ static int zfs_lookup(vnode_t *dvp, const char *nm, vnode_t **vpp, struct componentname *cnp, int nameiop, cred_t *cr, int flags, boolean_t cached) { znode_t *zdp = VTOZ(dvp); znode_t *zp; zfsvfs_t *zfsvfs = zdp->z_zfsvfs; #if __FreeBSD_version > 1300124 seqc_t dvp_seqc; #endif int error = 0; /* * Fast path lookup, however we must skip DNLC lookup * for case folding or normalizing lookups because the * DNLC code only stores the passed in name. This means * creating 'a' and removing 'A' on a case insensitive * file system would work, but DNLC still thinks 'a' * exists and won't let you create it again on the next * pass through fast path. */ if (!(flags & LOOKUP_XATTR)) { if (dvp->v_type != VDIR) { return (SET_ERROR(ENOTDIR)); } else if (zdp->z_sa_hdl == NULL) { return (SET_ERROR(EIO)); } } DTRACE_PROBE2(zfs__fastpath__lookup__miss, vnode_t *, dvp, const char *, nm); ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zdp); #if __FreeBSD_version > 1300124 dvp_seqc = vn_seqc_read_notmodify(dvp); #endif *vpp = NULL; if (flags & LOOKUP_XATTR) { /* * If the xattr property is off, refuse the lookup request. */ if (!(zfsvfs->z_flags & ZSB_XATTR)) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EOPNOTSUPP)); } /* * We don't allow recursive attributes.. * Maybe someday we will. */ if (zdp->z_pflags & ZFS_XATTR) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EINVAL)); } if ((error = zfs_get_xattrdir(VTOZ(dvp), &zp, cr, flags))) { ZFS_EXIT(zfsvfs); return (error); } *vpp = ZTOV(zp); /* * Do we have permission to get into attribute directory? */ error = zfs_zaccess(zp, ACE_EXECUTE, 0, B_FALSE, cr); if (error) { vrele(ZTOV(zp)); } ZFS_EXIT(zfsvfs); return (error); } /* * Check accessibility of directory if we're not coming in via * VOP_CACHEDLOOKUP. */ if (!cached) { #ifdef NOEXECCHECK if ((cnp->cn_flags & NOEXECCHECK) != 0) { cnp->cn_flags &= ~NOEXECCHECK; } else #endif if ((error = zfs_zaccess(zdp, ACE_EXECUTE, 0, B_FALSE, cr))) { ZFS_EXIT(zfsvfs); return (error); } } if (zfsvfs->z_utf8 && u8_validate(nm, strlen(nm), NULL, U8_VALIDATE_ENTIRE, &error) < 0) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EILSEQ)); } /* * First handle the special cases. */ if ((cnp->cn_flags & ISDOTDOT) != 0) { /* * If we are a snapshot mounted under .zfs, return * the vp for the snapshot directory. */ if (zdp->z_id == zfsvfs->z_root && zfsvfs->z_parent != zfsvfs) { struct componentname cn; vnode_t *zfsctl_vp; int ltype; ZFS_EXIT(zfsvfs); ltype = VOP_ISLOCKED(dvp); VOP_UNLOCK1(dvp); error = zfsctl_root(zfsvfs->z_parent, LK_SHARED, &zfsctl_vp); if (error == 0) { cn.cn_nameptr = "snapshot"; cn.cn_namelen = strlen(cn.cn_nameptr); cn.cn_nameiop = cnp->cn_nameiop; cn.cn_flags = cnp->cn_flags & ~ISDOTDOT; cn.cn_lkflags = cnp->cn_lkflags; error = VOP_LOOKUP(zfsctl_vp, vpp, &cn); vput(zfsctl_vp); } vn_lock(dvp, ltype | LK_RETRY); return (error); } } if (zfs_has_ctldir(zdp) && strcmp(nm, ZFS_CTLDIR_NAME) == 0) { ZFS_EXIT(zfsvfs); if ((cnp->cn_flags & ISLASTCN) != 0 && nameiop != LOOKUP) return (SET_ERROR(ENOTSUP)); error = zfsctl_root(zfsvfs, cnp->cn_lkflags, vpp); return (error); } /* * The loop is retry the lookup if the parent-child relationship * changes during the dot-dot locking complexities. */ for (;;) { uint64_t parent; error = zfs_dirlook(zdp, nm, &zp); if (error == 0) *vpp = ZTOV(zp); ZFS_EXIT(zfsvfs); if (error != 0) break; error = zfs_lookup_lock(dvp, *vpp, nm, cnp->cn_lkflags); if (error != 0) { /* * If we've got a locking error, then the vnode * got reclaimed because of a force unmount. * We never enter doomed vnodes into the name cache. */ *vpp = NULL; return (error); } if ((cnp->cn_flags & ISDOTDOT) == 0) break; ZFS_ENTER(zfsvfs); if (zdp->z_sa_hdl == NULL) { error = SET_ERROR(EIO); } else { error = sa_lookup(zdp->z_sa_hdl, SA_ZPL_PARENT(zfsvfs), &parent, sizeof (parent)); } if (error != 0) { ZFS_EXIT(zfsvfs); vput(ZTOV(zp)); break; } if (zp->z_id == parent) { ZFS_EXIT(zfsvfs); break; } vput(ZTOV(zp)); } if (error != 0) *vpp = NULL; /* Translate errors and add SAVENAME when needed. */ if (cnp->cn_flags & ISLASTCN) { switch (nameiop) { case CREATE: case RENAME: if (error == ENOENT) { error = EJUSTRETURN; cnp->cn_flags |= SAVENAME; break; } zfs_fallthrough; case DELETE: if (error == 0) cnp->cn_flags |= SAVENAME; break; } } #if __FreeBSD_version > 1300124 if ((cnp->cn_flags & ISDOTDOT) != 0) { /* * FIXME: zfs_lookup_lock relocks vnodes and does nothing to * handle races. In particular different callers may end up * with different vnodes and will try to add conflicting * entries to the namecache. * * While finding different result may be acceptable in face * of concurrent modification, adding conflicting entries * trips over an assert in the namecache. * * Ultimately let an entry through once everything settles. */ if (!vn_seqc_consistent(dvp, dvp_seqc)) { cnp->cn_flags &= ~MAKEENTRY; } } #endif /* Insert name into cache (as non-existent) if appropriate. */ if (zfsvfs->z_use_namecache && !zfsvfs->z_replay && error == ENOENT && (cnp->cn_flags & MAKEENTRY) != 0) cache_enter(dvp, NULL, cnp); /* Insert name into cache if appropriate. */ if (zfsvfs->z_use_namecache && !zfsvfs->z_replay && error == 0 && (cnp->cn_flags & MAKEENTRY)) { if (!(cnp->cn_flags & ISLASTCN) || (nameiop != DELETE && nameiop != RENAME)) { cache_enter(dvp, *vpp, cnp); } } return (error); } /* * Attempt to create a new entry in a directory. If the entry * already exists, truncate the file if permissible, else return * an error. Return the vp of the created or trunc'd file. * * IN: dvp - vnode of directory to put new file entry in. * name - name of new file entry. * vap - attributes of new file. * excl - flag indicating exclusive or non-exclusive mode. * mode - mode to open file with. * cr - credentials of caller. * flag - large file flag [UNUSED]. * ct - caller context * vsecp - ACL to be set * * OUT: vpp - vnode of created or trunc'd entry. * * RETURN: 0 on success, error code on failure. * * Timestamps: * dvp - ctime|mtime updated if new entry created * vp - ctime|mtime always, atime if new */ int zfs_create(znode_t *dzp, const char *name, vattr_t *vap, int excl, int mode, znode_t **zpp, cred_t *cr, int flag, vsecattr_t *vsecp) { (void) excl, (void) mode, (void) flag; znode_t *zp; zfsvfs_t *zfsvfs = dzp->z_zfsvfs; zilog_t *zilog; objset_t *os; dmu_tx_t *tx; int error; ksid_t *ksid; uid_t uid; gid_t gid = crgetgid(cr); uint64_t projid = ZFS_DEFAULT_PROJID; zfs_acl_ids_t acl_ids; boolean_t fuid_dirtied; uint64_t txtype; #ifdef DEBUG_VFS_LOCKS vnode_t *dvp = ZTOV(dzp); #endif /* * If we have an ephemeral id, ACL, or XVATTR then * make sure file system is at proper version */ ksid = crgetsid(cr, KSID_OWNER); if (ksid) uid = ksid_getid(ksid); else uid = crgetuid(cr); if (zfsvfs->z_use_fuids == B_FALSE && (vsecp || (vap->va_mask & AT_XVATTR) || IS_EPHEMERAL(uid) || IS_EPHEMERAL(gid))) return (SET_ERROR(EINVAL)); ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(dzp); os = zfsvfs->z_os; zilog = zfsvfs->z_log; if (zfsvfs->z_utf8 && u8_validate(name, strlen(name), NULL, U8_VALIDATE_ENTIRE, &error) < 0) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EILSEQ)); } if (vap->va_mask & AT_XVATTR) { if ((error = secpolicy_xvattr(ZTOV(dzp), (xvattr_t *)vap, crgetuid(cr), cr, vap->va_type)) != 0) { ZFS_EXIT(zfsvfs); return (error); } } *zpp = NULL; if ((vap->va_mode & S_ISVTX) && secpolicy_vnode_stky_modify(cr)) vap->va_mode &= ~S_ISVTX; error = zfs_dirent_lookup(dzp, name, &zp, ZNEW); if (error) { ZFS_EXIT(zfsvfs); return (error); } ASSERT3P(zp, ==, NULL); /* * Create a new file object and update the directory * to reference it. */ if ((error = zfs_zaccess(dzp, ACE_ADD_FILE, 0, B_FALSE, cr))) { goto out; } /* * We only support the creation of regular files in * extended attribute directories. */ if ((dzp->z_pflags & ZFS_XATTR) && (vap->va_type != VREG)) { error = SET_ERROR(EINVAL); goto out; } if ((error = zfs_acl_ids_create(dzp, 0, vap, cr, vsecp, &acl_ids)) != 0) goto out; if (S_ISREG(vap->va_mode) || S_ISDIR(vap->va_mode)) projid = zfs_inherit_projid(dzp); if (zfs_acl_ids_overquota(zfsvfs, &acl_ids, projid)) { zfs_acl_ids_free(&acl_ids); error = SET_ERROR(EDQUOT); goto out; } getnewvnode_reserve_(); tx = dmu_tx_create(os); dmu_tx_hold_sa_create(tx, acl_ids.z_aclp->z_acl_bytes + ZFS_SA_BASE_ATTR_SIZE); fuid_dirtied = zfsvfs->z_fuid_dirty; if (fuid_dirtied) zfs_fuid_txhold(zfsvfs, tx); dmu_tx_hold_zap(tx, dzp->z_id, TRUE, name); dmu_tx_hold_sa(tx, dzp->z_sa_hdl, B_FALSE); if (!zfsvfs->z_use_sa && acl_ids.z_aclp->z_acl_bytes > ZFS_ACE_SPACE) { dmu_tx_hold_write(tx, DMU_NEW_OBJECT, 0, acl_ids.z_aclp->z_acl_bytes); } error = dmu_tx_assign(tx, TXG_WAIT); if (error) { zfs_acl_ids_free(&acl_ids); dmu_tx_abort(tx); getnewvnode_drop_reserve(); ZFS_EXIT(zfsvfs); return (error); } zfs_mknode(dzp, vap, tx, cr, 0, &zp, &acl_ids); if (fuid_dirtied) zfs_fuid_sync(zfsvfs, tx); (void) zfs_link_create(dzp, name, zp, tx, ZNEW); txtype = zfs_log_create_txtype(Z_FILE, vsecp, vap); zfs_log_create(zilog, tx, txtype, dzp, zp, name, vsecp, acl_ids.z_fuidp, vap); zfs_acl_ids_free(&acl_ids); dmu_tx_commit(tx); getnewvnode_drop_reserve(); out: VNCHECKREF(dvp); if (error == 0) { *zpp = zp; } if (zfsvfs->z_os->os_sync == ZFS_SYNC_ALWAYS) zil_commit(zilog, 0); ZFS_EXIT(zfsvfs); return (error); } /* * Remove an entry from a directory. * * IN: dvp - vnode of directory to remove entry from. * name - name of entry to remove. * cr - credentials of caller. * ct - caller context * flags - case flags * * RETURN: 0 on success, error code on failure. * * Timestamps: * dvp - ctime|mtime * vp - ctime (if nlink > 0) */ static int zfs_remove_(vnode_t *dvp, vnode_t *vp, const char *name, cred_t *cr) { znode_t *dzp = VTOZ(dvp); znode_t *zp; znode_t *xzp; zfsvfs_t *zfsvfs = dzp->z_zfsvfs; zilog_t *zilog; uint64_t xattr_obj; uint64_t obj = 0; dmu_tx_t *tx; boolean_t unlinked; uint64_t txtype; int error; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(dzp); zp = VTOZ(vp); ZFS_VERIFY_ZP(zp); zilog = zfsvfs->z_log; xattr_obj = 0; xzp = NULL; if ((error = zfs_zaccess_delete(dzp, zp, cr))) { goto out; } /* * Need to use rmdir for removing directories. */ if (vp->v_type == VDIR) { error = SET_ERROR(EPERM); goto out; } vnevent_remove(vp, dvp, name, ct); obj = zp->z_id; /* are there any extended attributes? */ error = sa_lookup(zp->z_sa_hdl, SA_ZPL_XATTR(zfsvfs), &xattr_obj, sizeof (xattr_obj)); if (error == 0 && xattr_obj) { error = zfs_zget(zfsvfs, xattr_obj, &xzp); ASSERT0(error); } /* * We may delete the znode now, or we may put it in the unlinked set; * it depends on whether we're the last link, and on whether there are * other holds on the vnode. So we dmu_tx_hold() the right things to * allow for either case. */ tx = dmu_tx_create(zfsvfs->z_os); dmu_tx_hold_zap(tx, dzp->z_id, FALSE, name); dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_FALSE); zfs_sa_upgrade_txholds(tx, zp); zfs_sa_upgrade_txholds(tx, dzp); if (xzp) { dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_TRUE); dmu_tx_hold_sa(tx, xzp->z_sa_hdl, B_FALSE); } /* charge as an update -- would be nice not to charge at all */ dmu_tx_hold_zap(tx, zfsvfs->z_unlinkedobj, FALSE, NULL); /* * Mark this transaction as typically resulting in a net free of space */ dmu_tx_mark_netfree(tx); error = dmu_tx_assign(tx, TXG_WAIT); if (error) { dmu_tx_abort(tx); ZFS_EXIT(zfsvfs); return (error); } /* * Remove the directory entry. */ error = zfs_link_destroy(dzp, name, zp, tx, ZEXISTS, &unlinked); if (error) { dmu_tx_commit(tx); goto out; } if (unlinked) { zfs_unlinked_add(zp, tx); vp->v_vflag |= VV_NOSYNC; } /* XXX check changes to linux vnops */ txtype = TX_REMOVE; zfs_log_remove(zilog, tx, txtype, dzp, name, obj, unlinked); dmu_tx_commit(tx); out: if (xzp) vrele(ZTOV(xzp)); if (zfsvfs->z_os->os_sync == ZFS_SYNC_ALWAYS) zil_commit(zilog, 0); ZFS_EXIT(zfsvfs); return (error); } static int zfs_lookup_internal(znode_t *dzp, const char *name, vnode_t **vpp, struct componentname *cnp, int nameiop) { zfsvfs_t *zfsvfs = dzp->z_zfsvfs; int error; cnp->cn_nameptr = __DECONST(char *, name); cnp->cn_namelen = strlen(name); cnp->cn_nameiop = nameiop; cnp->cn_flags = ISLASTCN | SAVENAME; cnp->cn_lkflags = LK_EXCLUSIVE | LK_RETRY; cnp->cn_cred = kcred; #if __FreeBSD_version < 1400037 cnp->cn_thread = curthread; #endif if (zfsvfs->z_use_namecache && !zfsvfs->z_replay) { struct vop_lookup_args a; a.a_gen.a_desc = &vop_lookup_desc; a.a_dvp = ZTOV(dzp); a.a_vpp = vpp; a.a_cnp = cnp; error = vfs_cache_lookup(&a); } else { error = zfs_lookup(ZTOV(dzp), name, vpp, cnp, nameiop, kcred, 0, B_FALSE); } #ifdef ZFS_DEBUG if (error) { printf("got error %d on name %s on op %d\n", error, name, nameiop); kdb_backtrace(); } #endif return (error); } int zfs_remove(znode_t *dzp, const char *name, cred_t *cr, int flags) { vnode_t *vp; int error; struct componentname cn; if ((error = zfs_lookup_internal(dzp, name, &vp, &cn, DELETE))) return (error); error = zfs_remove_(ZTOV(dzp), vp, name, cr); vput(vp); return (error); } /* * Create a new directory and insert it into dvp using the name * provided. Return a pointer to the inserted directory. * * IN: dvp - vnode of directory to add subdir to. * dirname - name of new directory. * vap - attributes of new directory. * cr - credentials of caller. * ct - caller context * flags - case flags * vsecp - ACL to be set * * OUT: vpp - vnode of created directory. * * RETURN: 0 on success, error code on failure. * * Timestamps: * dvp - ctime|mtime updated * vp - ctime|mtime|atime updated */ int zfs_mkdir(znode_t *dzp, const char *dirname, vattr_t *vap, znode_t **zpp, cred_t *cr, int flags, vsecattr_t *vsecp) { (void) flags, (void) vsecp; znode_t *zp; zfsvfs_t *zfsvfs = dzp->z_zfsvfs; zilog_t *zilog; uint64_t txtype; dmu_tx_t *tx; int error; ksid_t *ksid; uid_t uid; gid_t gid = crgetgid(cr); zfs_acl_ids_t acl_ids; boolean_t fuid_dirtied; ASSERT3U(vap->va_type, ==, VDIR); /* * If we have an ephemeral id, ACL, or XVATTR then * make sure file system is at proper version */ ksid = crgetsid(cr, KSID_OWNER); if (ksid) uid = ksid_getid(ksid); else uid = crgetuid(cr); if (zfsvfs->z_use_fuids == B_FALSE && ((vap->va_mask & AT_XVATTR) || IS_EPHEMERAL(uid) || IS_EPHEMERAL(gid))) return (SET_ERROR(EINVAL)); ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(dzp); zilog = zfsvfs->z_log; if (dzp->z_pflags & ZFS_XATTR) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EINVAL)); } if (zfsvfs->z_utf8 && u8_validate(dirname, strlen(dirname), NULL, U8_VALIDATE_ENTIRE, &error) < 0) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EILSEQ)); } if (vap->va_mask & AT_XVATTR) { if ((error = secpolicy_xvattr(ZTOV(dzp), (xvattr_t *)vap, crgetuid(cr), cr, vap->va_type)) != 0) { ZFS_EXIT(zfsvfs); return (error); } } if ((error = zfs_acl_ids_create(dzp, 0, vap, cr, NULL, &acl_ids)) != 0) { ZFS_EXIT(zfsvfs); return (error); } /* * First make sure the new directory doesn't exist. * * Existence is checked first to make sure we don't return * EACCES instead of EEXIST which can cause some applications * to fail. */ *zpp = NULL; if ((error = zfs_dirent_lookup(dzp, dirname, &zp, ZNEW))) { zfs_acl_ids_free(&acl_ids); ZFS_EXIT(zfsvfs); return (error); } ASSERT3P(zp, ==, NULL); if ((error = zfs_zaccess(dzp, ACE_ADD_SUBDIRECTORY, 0, B_FALSE, cr))) { zfs_acl_ids_free(&acl_ids); ZFS_EXIT(zfsvfs); return (error); } if (zfs_acl_ids_overquota(zfsvfs, &acl_ids, zfs_inherit_projid(dzp))) { zfs_acl_ids_free(&acl_ids); ZFS_EXIT(zfsvfs); return (SET_ERROR(EDQUOT)); } /* * Add a new entry to the directory. */ getnewvnode_reserve_(); tx = dmu_tx_create(zfsvfs->z_os); dmu_tx_hold_zap(tx, dzp->z_id, TRUE, dirname); dmu_tx_hold_zap(tx, DMU_NEW_OBJECT, FALSE, NULL); fuid_dirtied = zfsvfs->z_fuid_dirty; if (fuid_dirtied) zfs_fuid_txhold(zfsvfs, tx); if (!zfsvfs->z_use_sa && acl_ids.z_aclp->z_acl_bytes > ZFS_ACE_SPACE) { dmu_tx_hold_write(tx, DMU_NEW_OBJECT, 0, acl_ids.z_aclp->z_acl_bytes); } dmu_tx_hold_sa_create(tx, acl_ids.z_aclp->z_acl_bytes + ZFS_SA_BASE_ATTR_SIZE); error = dmu_tx_assign(tx, TXG_WAIT); if (error) { zfs_acl_ids_free(&acl_ids); dmu_tx_abort(tx); getnewvnode_drop_reserve(); ZFS_EXIT(zfsvfs); return (error); } /* * Create new node. */ zfs_mknode(dzp, vap, tx, cr, 0, &zp, &acl_ids); if (fuid_dirtied) zfs_fuid_sync(zfsvfs, tx); /* * Now put new name in parent dir. */ (void) zfs_link_create(dzp, dirname, zp, tx, ZNEW); *zpp = zp; txtype = zfs_log_create_txtype(Z_DIR, NULL, vap); zfs_log_create(zilog, tx, txtype, dzp, zp, dirname, NULL, acl_ids.z_fuidp, vap); zfs_acl_ids_free(&acl_ids); dmu_tx_commit(tx); getnewvnode_drop_reserve(); if (zfsvfs->z_os->os_sync == ZFS_SYNC_ALWAYS) zil_commit(zilog, 0); ZFS_EXIT(zfsvfs); return (0); } #if __FreeBSD_version < 1300124 static void cache_vop_rmdir(struct vnode *dvp, struct vnode *vp) { cache_purge(dvp); cache_purge(vp); } #endif /* * Remove a directory subdir entry. If the current working * directory is the same as the subdir to be removed, the * remove will fail. * * IN: dvp - vnode of directory to remove from. * name - name of directory to be removed. * cwd - vnode of current working directory. * cr - credentials of caller. * ct - caller context * flags - case flags * * RETURN: 0 on success, error code on failure. * * Timestamps: * dvp - ctime|mtime updated */ static int zfs_rmdir_(vnode_t *dvp, vnode_t *vp, const char *name, cred_t *cr) { znode_t *dzp = VTOZ(dvp); znode_t *zp = VTOZ(vp); zfsvfs_t *zfsvfs = dzp->z_zfsvfs; zilog_t *zilog; dmu_tx_t *tx; int error; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(dzp); ZFS_VERIFY_ZP(zp); zilog = zfsvfs->z_log; if ((error = zfs_zaccess_delete(dzp, zp, cr))) { goto out; } if (vp->v_type != VDIR) { error = SET_ERROR(ENOTDIR); goto out; } vnevent_rmdir(vp, dvp, name, ct); tx = dmu_tx_create(zfsvfs->z_os); dmu_tx_hold_zap(tx, dzp->z_id, FALSE, name); dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_FALSE); dmu_tx_hold_zap(tx, zfsvfs->z_unlinkedobj, FALSE, NULL); zfs_sa_upgrade_txholds(tx, zp); zfs_sa_upgrade_txholds(tx, dzp); dmu_tx_mark_netfree(tx); error = dmu_tx_assign(tx, TXG_WAIT); if (error) { dmu_tx_abort(tx); ZFS_EXIT(zfsvfs); return (error); } error = zfs_link_destroy(dzp, name, zp, tx, ZEXISTS, NULL); if (error == 0) { uint64_t txtype = TX_RMDIR; zfs_log_remove(zilog, tx, txtype, dzp, name, ZFS_NO_OBJECT, B_FALSE); } dmu_tx_commit(tx); cache_vop_rmdir(dvp, vp); out: if (zfsvfs->z_os->os_sync == ZFS_SYNC_ALWAYS) zil_commit(zilog, 0); ZFS_EXIT(zfsvfs); return (error); } int zfs_rmdir(znode_t *dzp, const char *name, znode_t *cwd, cred_t *cr, int flags) { struct componentname cn; vnode_t *vp; int error; if ((error = zfs_lookup_internal(dzp, name, &vp, &cn, DELETE))) return (error); error = zfs_rmdir_(ZTOV(dzp), vp, name, cr); vput(vp); return (error); } /* * Read as many directory entries as will fit into the provided * buffer from the given directory cursor position (specified in * the uio structure). * * IN: vp - vnode of directory to read. * uio - structure supplying read location, range info, * and return buffer. * cr - credentials of caller. * ct - caller context * flags - case flags * * OUT: uio - updated offset and range, buffer filled. * eofp - set to true if end-of-file detected. * * RETURN: 0 on success, error code on failure. * * Timestamps: * vp - atime updated * * Note that the low 4 bits of the cookie returned by zap is always zero. * This allows us to use the low range for "special" directory entries: * We use 0 for '.', and 1 for '..'. If this is the root of the filesystem, * we use the offset 2 for the '.zfs' directory. */ static int zfs_readdir(vnode_t *vp, zfs_uio_t *uio, cred_t *cr, int *eofp, int *ncookies, cookie_t **cookies) { znode_t *zp = VTOZ(vp); iovec_t *iovp; edirent_t *eodp; dirent64_t *odp; zfsvfs_t *zfsvfs = zp->z_zfsvfs; objset_t *os; caddr_t outbuf; size_t bufsize; zap_cursor_t zc; zap_attribute_t zap; uint_t bytes_wanted; uint64_t offset; /* must be unsigned; checks for < 1 */ uint64_t parent; int local_eof; int outcount; int error; uint8_t prefetch; boolean_t check_sysattrs; uint8_t type; int ncooks; cookie_t *cooks = NULL; int flags = 0; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); if ((error = sa_lookup(zp->z_sa_hdl, SA_ZPL_PARENT(zfsvfs), &parent, sizeof (parent))) != 0) { ZFS_EXIT(zfsvfs); return (error); } /* * If we are not given an eof variable, * use a local one. */ if (eofp == NULL) eofp = &local_eof; /* * Check for valid iov_len. */ if (GET_UIO_STRUCT(uio)->uio_iov->iov_len <= 0) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EINVAL)); } /* * Quit if directory has been removed (posix) */ if ((*eofp = zp->z_unlinked) != 0) { ZFS_EXIT(zfsvfs); return (0); } error = 0; os = zfsvfs->z_os; offset = zfs_uio_offset(uio); prefetch = zp->z_zn_prefetch; /* * Initialize the iterator cursor. */ if (offset <= 3) { /* * Start iteration from the beginning of the directory. */ zap_cursor_init(&zc, os, zp->z_id); } else { /* * The offset is a serialized cursor. */ zap_cursor_init_serialized(&zc, os, zp->z_id, offset); } /* * Get space to change directory entries into fs independent format. */ iovp = GET_UIO_STRUCT(uio)->uio_iov; bytes_wanted = iovp->iov_len; if (zfs_uio_segflg(uio) != UIO_SYSSPACE || zfs_uio_iovcnt(uio) != 1) { bufsize = bytes_wanted; outbuf = kmem_alloc(bufsize, KM_SLEEP); odp = (struct dirent64 *)outbuf; } else { bufsize = bytes_wanted; outbuf = NULL; odp = (struct dirent64 *)iovp->iov_base; } eodp = (struct edirent *)odp; if (ncookies != NULL) { /* * Minimum entry size is dirent size and 1 byte for a file name. */ ncooks = zfs_uio_resid(uio) / (sizeof (struct dirent) - sizeof (((struct dirent *)NULL)->d_name) + 1); cooks = malloc(ncooks * sizeof (*cooks), M_TEMP, M_WAITOK); *cookies = cooks; *ncookies = ncooks; } /* * If this VFS supports the system attribute view interface; and * we're looking at an extended attribute directory; and we care * about normalization conflicts on this vfs; then we must check * for normalization conflicts with the sysattr name space. */ #ifdef TODO check_sysattrs = vfs_has_feature(vp->v_vfsp, VFSFT_SYSATTR_VIEWS) && (vp->v_flag & V_XATTRDIR) && zfsvfs->z_norm && (flags & V_RDDIR_ENTFLAGS); #else check_sysattrs = 0; #endif /* * Transform to file-system independent format */ outcount = 0; while (outcount < bytes_wanted) { ino64_t objnum; ushort_t reclen; off64_t *next = NULL; /* * Special case `.', `..', and `.zfs'. */ if (offset == 0) { (void) strcpy(zap.za_name, "."); zap.za_normalization_conflict = 0; objnum = zp->z_id; type = DT_DIR; } else if (offset == 1) { (void) strcpy(zap.za_name, ".."); zap.za_normalization_conflict = 0; objnum = parent; type = DT_DIR; } else if (offset == 2 && zfs_show_ctldir(zp)) { (void) strcpy(zap.za_name, ZFS_CTLDIR_NAME); zap.za_normalization_conflict = 0; objnum = ZFSCTL_INO_ROOT; type = DT_DIR; } else { /* * Grab next entry. */ if ((error = zap_cursor_retrieve(&zc, &zap))) { if ((*eofp = (error == ENOENT)) != 0) break; else goto update; } if (zap.za_integer_length != 8 || zap.za_num_integers != 1) { cmn_err(CE_WARN, "zap_readdir: bad directory " "entry, obj = %lld, offset = %lld\n", (u_longlong_t)zp->z_id, (u_longlong_t)offset); error = SET_ERROR(ENXIO); goto update; } objnum = ZFS_DIRENT_OBJ(zap.za_first_integer); /* * MacOS X can extract the object type here such as: * uint8_t type = ZFS_DIRENT_TYPE(zap.za_first_integer); */ type = ZFS_DIRENT_TYPE(zap.za_first_integer); if (check_sysattrs && !zap.za_normalization_conflict) { #ifdef TODO zap.za_normalization_conflict = xattr_sysattr_casechk(zap.za_name); #else panic("%s:%u: TODO", __func__, __LINE__); #endif } } if (flags & V_RDDIR_ACCFILTER) { /* * If we have no access at all, don't include * this entry in the returned information */ znode_t *ezp; if (zfs_zget(zp->z_zfsvfs, objnum, &ezp) != 0) goto skip_entry; if (!zfs_has_access(ezp, cr)) { vrele(ZTOV(ezp)); goto skip_entry; } vrele(ZTOV(ezp)); } if (flags & V_RDDIR_ENTFLAGS) reclen = EDIRENT_RECLEN(strlen(zap.za_name)); else reclen = DIRENT64_RECLEN(strlen(zap.za_name)); /* * Will this entry fit in the buffer? */ if (outcount + reclen > bufsize) { /* * Did we manage to fit anything in the buffer? */ if (!outcount) { error = SET_ERROR(EINVAL); goto update; } break; } if (flags & V_RDDIR_ENTFLAGS) { /* * Add extended flag entry: */ eodp->ed_ino = objnum; eodp->ed_reclen = reclen; /* NOTE: ed_off is the offset for the *next* entry */ next = &(eodp->ed_off); eodp->ed_eflags = zap.za_normalization_conflict ? ED_CASE_CONFLICT : 0; (void) strncpy(eodp->ed_name, zap.za_name, EDIRENT_NAMELEN(reclen)); eodp = (edirent_t *)((intptr_t)eodp + reclen); } else { /* * Add normal entry: */ odp->d_ino = objnum; odp->d_reclen = reclen; odp->d_namlen = strlen(zap.za_name); /* NOTE: d_off is the offset for the *next* entry. */ next = &odp->d_off; strlcpy(odp->d_name, zap.za_name, odp->d_namlen + 1); odp->d_type = type; dirent_terminate(odp); odp = (dirent64_t *)((intptr_t)odp + reclen); } outcount += reclen; ASSERT3S(outcount, <=, bufsize); /* Prefetch znode */ if (prefetch) dmu_prefetch(os, objnum, 0, 0, 0, ZIO_PRIORITY_SYNC_READ); skip_entry: /* * Move to the next entry, fill in the previous offset. */ if (offset > 2 || (offset == 2 && !zfs_show_ctldir(zp))) { zap_cursor_advance(&zc); offset = zap_cursor_serialize(&zc); } else { offset += 1; } /* Fill the offset right after advancing the cursor. */ if (next != NULL) *next = offset; if (cooks != NULL) { *cooks++ = offset; ncooks--; KASSERT(ncooks >= 0, ("ncookies=%d", ncooks)); } } zp->z_zn_prefetch = B_FALSE; /* a lookup will re-enable pre-fetching */ /* Subtract unused cookies */ if (ncookies != NULL) *ncookies -= ncooks; if (zfs_uio_segflg(uio) == UIO_SYSSPACE && zfs_uio_iovcnt(uio) == 1) { iovp->iov_base += outcount; iovp->iov_len -= outcount; zfs_uio_resid(uio) -= outcount; } else if ((error = zfs_uiomove(outbuf, (long)outcount, UIO_READ, uio))) { /* * Reset the pointer. */ offset = zfs_uio_offset(uio); } update: zap_cursor_fini(&zc); if (zfs_uio_segflg(uio) != UIO_SYSSPACE || zfs_uio_iovcnt(uio) != 1) kmem_free(outbuf, bufsize); if (error == ENOENT) error = 0; ZFS_ACCESSTIME_STAMP(zfsvfs, zp); zfs_uio_setoffset(uio, offset); ZFS_EXIT(zfsvfs); if (error != 0 && cookies != NULL) { free(*cookies, M_TEMP); *cookies = NULL; *ncookies = 0; } return (error); } /* * Get the requested file attributes and place them in the provided * vattr structure. * * IN: vp - vnode of file. * vap - va_mask identifies requested attributes. * If AT_XVATTR set, then optional attrs are requested * flags - ATTR_NOACLCHECK (CIFS server context) * cr - credentials of caller. * * OUT: vap - attribute values. * * RETURN: 0 (always succeeds). */ static int zfs_getattr(vnode_t *vp, vattr_t *vap, int flags, cred_t *cr) { znode_t *zp = VTOZ(vp); zfsvfs_t *zfsvfs = zp->z_zfsvfs; int error = 0; uint32_t blksize; u_longlong_t nblocks; uint64_t mtime[2], ctime[2], crtime[2], rdev; xvattr_t *xvap = (xvattr_t *)vap; /* vap may be an xvattr_t * */ xoptattr_t *xoap = NULL; boolean_t skipaclchk = (flags & ATTR_NOACLCHECK) ? B_TRUE : B_FALSE; sa_bulk_attr_t bulk[4]; int count = 0; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); zfs_fuid_map_ids(zp, cr, &vap->va_uid, &vap->va_gid); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MTIME(zfsvfs), NULL, &mtime, 16); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zfsvfs), NULL, &ctime, 16); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CRTIME(zfsvfs), NULL, &crtime, 16); if (vp->v_type == VBLK || vp->v_type == VCHR) SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_RDEV(zfsvfs), NULL, &rdev, 8); if ((error = sa_bulk_lookup(zp->z_sa_hdl, bulk, count)) != 0) { ZFS_EXIT(zfsvfs); return (error); } /* * If ACL is trivial don't bother looking for ACE_READ_ATTRIBUTES. * Also, if we are the owner don't bother, since owner should * always be allowed to read basic attributes of file. */ if (!(zp->z_pflags & ZFS_ACL_TRIVIAL) && (vap->va_uid != crgetuid(cr))) { if ((error = zfs_zaccess(zp, ACE_READ_ATTRIBUTES, 0, skipaclchk, cr))) { ZFS_EXIT(zfsvfs); return (error); } } /* * Return all attributes. It's cheaper to provide the answer * than to determine whether we were asked the question. */ vap->va_type = IFTOVT(zp->z_mode); vap->va_mode = zp->z_mode & ~S_IFMT; vn_fsid(vp, vap); vap->va_nodeid = zp->z_id; vap->va_nlink = zp->z_links; if ((vp->v_flag & VROOT) && zfs_show_ctldir(zp) && zp->z_links < ZFS_LINK_MAX) vap->va_nlink++; vap->va_size = zp->z_size; if (vp->v_type == VBLK || vp->v_type == VCHR) vap->va_rdev = zfs_cmpldev(rdev); vap->va_gen = zp->z_gen; vap->va_flags = 0; /* FreeBSD: Reset chflags(2) flags. */ vap->va_filerev = zp->z_seq; /* * Add in any requested optional attributes and the create time. * Also set the corresponding bits in the returned attribute bitmap. */ if ((xoap = xva_getxoptattr(xvap)) != NULL && zfsvfs->z_use_fuids) { if (XVA_ISSET_REQ(xvap, XAT_ARCHIVE)) { xoap->xoa_archive = ((zp->z_pflags & ZFS_ARCHIVE) != 0); XVA_SET_RTN(xvap, XAT_ARCHIVE); } if (XVA_ISSET_REQ(xvap, XAT_READONLY)) { xoap->xoa_readonly = ((zp->z_pflags & ZFS_READONLY) != 0); XVA_SET_RTN(xvap, XAT_READONLY); } if (XVA_ISSET_REQ(xvap, XAT_SYSTEM)) { xoap->xoa_system = ((zp->z_pflags & ZFS_SYSTEM) != 0); XVA_SET_RTN(xvap, XAT_SYSTEM); } if (XVA_ISSET_REQ(xvap, XAT_HIDDEN)) { xoap->xoa_hidden = ((zp->z_pflags & ZFS_HIDDEN) != 0); XVA_SET_RTN(xvap, XAT_HIDDEN); } if (XVA_ISSET_REQ(xvap, XAT_NOUNLINK)) { xoap->xoa_nounlink = ((zp->z_pflags & ZFS_NOUNLINK) != 0); XVA_SET_RTN(xvap, XAT_NOUNLINK); } if (XVA_ISSET_REQ(xvap, XAT_IMMUTABLE)) { xoap->xoa_immutable = ((zp->z_pflags & ZFS_IMMUTABLE) != 0); XVA_SET_RTN(xvap, XAT_IMMUTABLE); } if (XVA_ISSET_REQ(xvap, XAT_APPENDONLY)) { xoap->xoa_appendonly = ((zp->z_pflags & ZFS_APPENDONLY) != 0); XVA_SET_RTN(xvap, XAT_APPENDONLY); } if (XVA_ISSET_REQ(xvap, XAT_NODUMP)) { xoap->xoa_nodump = ((zp->z_pflags & ZFS_NODUMP) != 0); XVA_SET_RTN(xvap, XAT_NODUMP); } if (XVA_ISSET_REQ(xvap, XAT_OPAQUE)) { xoap->xoa_opaque = ((zp->z_pflags & ZFS_OPAQUE) != 0); XVA_SET_RTN(xvap, XAT_OPAQUE); } if (XVA_ISSET_REQ(xvap, XAT_AV_QUARANTINED)) { xoap->xoa_av_quarantined = ((zp->z_pflags & ZFS_AV_QUARANTINED) != 0); XVA_SET_RTN(xvap, XAT_AV_QUARANTINED); } if (XVA_ISSET_REQ(xvap, XAT_AV_MODIFIED)) { xoap->xoa_av_modified = ((zp->z_pflags & ZFS_AV_MODIFIED) != 0); XVA_SET_RTN(xvap, XAT_AV_MODIFIED); } if (XVA_ISSET_REQ(xvap, XAT_AV_SCANSTAMP) && vp->v_type == VREG) { zfs_sa_get_scanstamp(zp, xvap); } if (XVA_ISSET_REQ(xvap, XAT_REPARSE)) { xoap->xoa_reparse = ((zp->z_pflags & ZFS_REPARSE) != 0); XVA_SET_RTN(xvap, XAT_REPARSE); } if (XVA_ISSET_REQ(xvap, XAT_GEN)) { xoap->xoa_generation = zp->z_gen; XVA_SET_RTN(xvap, XAT_GEN); } if (XVA_ISSET_REQ(xvap, XAT_OFFLINE)) { xoap->xoa_offline = ((zp->z_pflags & ZFS_OFFLINE) != 0); XVA_SET_RTN(xvap, XAT_OFFLINE); } if (XVA_ISSET_REQ(xvap, XAT_SPARSE)) { xoap->xoa_sparse = ((zp->z_pflags & ZFS_SPARSE) != 0); XVA_SET_RTN(xvap, XAT_SPARSE); } if (XVA_ISSET_REQ(xvap, XAT_PROJINHERIT)) { xoap->xoa_projinherit = ((zp->z_pflags & ZFS_PROJINHERIT) != 0); XVA_SET_RTN(xvap, XAT_PROJINHERIT); } if (XVA_ISSET_REQ(xvap, XAT_PROJID)) { xoap->xoa_projid = zp->z_projid; XVA_SET_RTN(xvap, XAT_PROJID); } } ZFS_TIME_DECODE(&vap->va_atime, zp->z_atime); ZFS_TIME_DECODE(&vap->va_mtime, mtime); ZFS_TIME_DECODE(&vap->va_ctime, ctime); ZFS_TIME_DECODE(&vap->va_birthtime, crtime); sa_object_size(zp->z_sa_hdl, &blksize, &nblocks); vap->va_blksize = blksize; vap->va_bytes = nblocks << 9; /* nblocks * 512 */ if (zp->z_blksz == 0) { /* * Block size hasn't been set; suggest maximal I/O transfers. */ vap->va_blksize = zfsvfs->z_max_blksz; } ZFS_EXIT(zfsvfs); return (0); } /* * Set the file attributes to the values contained in the * vattr structure. * * IN: zp - znode of file to be modified. * vap - new attribute values. * If AT_XVATTR set, then optional attrs are being set * flags - ATTR_UTIME set if non-default time values provided. * - ATTR_NOACLCHECK (CIFS context only). * cr - credentials of caller. * ct - caller context * * RETURN: 0 on success, error code on failure. * * Timestamps: * vp - ctime updated, mtime updated if size changed. */ int zfs_setattr(znode_t *zp, vattr_t *vap, int flags, cred_t *cr) { vnode_t *vp = ZTOV(zp); zfsvfs_t *zfsvfs = zp->z_zfsvfs; objset_t *os; zilog_t *zilog; dmu_tx_t *tx; vattr_t oldva; xvattr_t tmpxvattr; uint_t mask = vap->va_mask; uint_t saved_mask = 0; uint64_t saved_mode; int trim_mask = 0; uint64_t new_mode; uint64_t new_uid, new_gid; uint64_t xattr_obj; uint64_t mtime[2], ctime[2]; uint64_t projid = ZFS_INVALID_PROJID; znode_t *attrzp; int need_policy = FALSE; int err, err2; zfs_fuid_info_t *fuidp = NULL; xvattr_t *xvap = (xvattr_t *)vap; /* vap may be an xvattr_t * */ xoptattr_t *xoap; zfs_acl_t *aclp; boolean_t skipaclchk = (flags & ATTR_NOACLCHECK) ? B_TRUE : B_FALSE; boolean_t fuid_dirtied = B_FALSE; sa_bulk_attr_t bulk[7], xattr_bulk[7]; int count = 0, xattr_count = 0; if (mask == 0) return (0); if (mask & AT_NOSET) return (SET_ERROR(EINVAL)); ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); os = zfsvfs->z_os; zilog = zfsvfs->z_log; /* * Make sure that if we have ephemeral uid/gid or xvattr specified * that file system is at proper version level */ if (zfsvfs->z_use_fuids == B_FALSE && (((mask & AT_UID) && IS_EPHEMERAL(vap->va_uid)) || ((mask & AT_GID) && IS_EPHEMERAL(vap->va_gid)) || (mask & AT_XVATTR))) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EINVAL)); } if (mask & AT_SIZE && vp->v_type == VDIR) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EISDIR)); } if (mask & AT_SIZE && vp->v_type != VREG && vp->v_type != VFIFO) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EINVAL)); } /* * If this is an xvattr_t, then get a pointer to the structure of * optional attributes. If this is NULL, then we have a vattr_t. */ xoap = xva_getxoptattr(xvap); xva_init(&tmpxvattr); /* * Immutable files can only alter immutable bit and atime */ if ((zp->z_pflags & ZFS_IMMUTABLE) && ((mask & (AT_SIZE|AT_UID|AT_GID|AT_MTIME|AT_MODE)) || ((mask & AT_XVATTR) && XVA_ISSET_REQ(xvap, XAT_CREATETIME)))) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EPERM)); } /* * Note: ZFS_READONLY is handled in zfs_zaccess_common. */ /* * Verify timestamps doesn't overflow 32 bits. * ZFS can handle large timestamps, but 32bit syscalls can't * handle times greater than 2039. This check should be removed * once large timestamps are fully supported. */ if (mask & (AT_ATIME | AT_MTIME)) { if (((mask & AT_ATIME) && TIMESPEC_OVERFLOW(&vap->va_atime)) || ((mask & AT_MTIME) && TIMESPEC_OVERFLOW(&vap->va_mtime))) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EOVERFLOW)); } } if (xoap != NULL && (mask & AT_XVATTR)) { if (XVA_ISSET_REQ(xvap, XAT_CREATETIME) && TIMESPEC_OVERFLOW(&vap->va_birthtime)) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EOVERFLOW)); } if (XVA_ISSET_REQ(xvap, XAT_PROJID)) { if (!dmu_objset_projectquota_enabled(os) || (!S_ISREG(zp->z_mode) && !S_ISDIR(zp->z_mode))) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EOPNOTSUPP)); } projid = xoap->xoa_projid; if (unlikely(projid == ZFS_INVALID_PROJID)) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EINVAL)); } if (projid == zp->z_projid && zp->z_pflags & ZFS_PROJID) projid = ZFS_INVALID_PROJID; else need_policy = TRUE; } if (XVA_ISSET_REQ(xvap, XAT_PROJINHERIT) && (xoap->xoa_projinherit != ((zp->z_pflags & ZFS_PROJINHERIT) != 0)) && (!dmu_objset_projectquota_enabled(os) || (!S_ISREG(zp->z_mode) && !S_ISDIR(zp->z_mode)))) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EOPNOTSUPP)); } } attrzp = NULL; aclp = NULL; if (zfsvfs->z_vfs->vfs_flag & VFS_RDONLY) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EROFS)); } /* * First validate permissions */ if (mask & AT_SIZE) { /* * XXX - Note, we are not providing any open * mode flags here (like FNDELAY), so we may * block if there are locks present... this * should be addressed in openat(). */ /* XXX - would it be OK to generate a log record here? */ err = zfs_freesp(zp, vap->va_size, 0, 0, FALSE); if (err) { ZFS_EXIT(zfsvfs); return (err); } } if (mask & (AT_ATIME|AT_MTIME) || ((mask & AT_XVATTR) && (XVA_ISSET_REQ(xvap, XAT_HIDDEN) || XVA_ISSET_REQ(xvap, XAT_READONLY) || XVA_ISSET_REQ(xvap, XAT_ARCHIVE) || XVA_ISSET_REQ(xvap, XAT_OFFLINE) || XVA_ISSET_REQ(xvap, XAT_SPARSE) || XVA_ISSET_REQ(xvap, XAT_CREATETIME) || XVA_ISSET_REQ(xvap, XAT_SYSTEM)))) { need_policy = zfs_zaccess(zp, ACE_WRITE_ATTRIBUTES, 0, skipaclchk, cr); } if (mask & (AT_UID|AT_GID)) { int idmask = (mask & (AT_UID|AT_GID)); int take_owner; int take_group; /* * NOTE: even if a new mode is being set, * we may clear S_ISUID/S_ISGID bits. */ if (!(mask & AT_MODE)) vap->va_mode = zp->z_mode; /* * Take ownership or chgrp to group we are a member of */ take_owner = (mask & AT_UID) && (vap->va_uid == crgetuid(cr)); take_group = (mask & AT_GID) && zfs_groupmember(zfsvfs, vap->va_gid, cr); /* * If both AT_UID and AT_GID are set then take_owner and * take_group must both be set in order to allow taking * ownership. * * Otherwise, send the check through secpolicy_vnode_setattr() * */ if (((idmask == (AT_UID|AT_GID)) && take_owner && take_group) || ((idmask == AT_UID) && take_owner) || ((idmask == AT_GID) && take_group)) { if (zfs_zaccess(zp, ACE_WRITE_OWNER, 0, skipaclchk, cr) == 0) { /* * Remove setuid/setgid for non-privileged users */ secpolicy_setid_clear(vap, vp, cr); trim_mask = (mask & (AT_UID|AT_GID)); } else { need_policy = TRUE; } } else { need_policy = TRUE; } } oldva.va_mode = zp->z_mode; zfs_fuid_map_ids(zp, cr, &oldva.va_uid, &oldva.va_gid); if (mask & AT_XVATTR) { /* * Update xvattr mask to include only those attributes * that are actually changing. * * the bits will be restored prior to actually setting * the attributes so the caller thinks they were set. */ if (XVA_ISSET_REQ(xvap, XAT_APPENDONLY)) { if (xoap->xoa_appendonly != ((zp->z_pflags & ZFS_APPENDONLY) != 0)) { need_policy = TRUE; } else { XVA_CLR_REQ(xvap, XAT_APPENDONLY); XVA_SET_REQ(&tmpxvattr, XAT_APPENDONLY); } } if (XVA_ISSET_REQ(xvap, XAT_PROJINHERIT)) { if (xoap->xoa_projinherit != ((zp->z_pflags & ZFS_PROJINHERIT) != 0)) { need_policy = TRUE; } else { XVA_CLR_REQ(xvap, XAT_PROJINHERIT); XVA_SET_REQ(&tmpxvattr, XAT_PROJINHERIT); } } if (XVA_ISSET_REQ(xvap, XAT_NOUNLINK)) { if (xoap->xoa_nounlink != ((zp->z_pflags & ZFS_NOUNLINK) != 0)) { need_policy = TRUE; } else { XVA_CLR_REQ(xvap, XAT_NOUNLINK); XVA_SET_REQ(&tmpxvattr, XAT_NOUNLINK); } } if (XVA_ISSET_REQ(xvap, XAT_IMMUTABLE)) { if (xoap->xoa_immutable != ((zp->z_pflags & ZFS_IMMUTABLE) != 0)) { need_policy = TRUE; } else { XVA_CLR_REQ(xvap, XAT_IMMUTABLE); XVA_SET_REQ(&tmpxvattr, XAT_IMMUTABLE); } } if (XVA_ISSET_REQ(xvap, XAT_NODUMP)) { if (xoap->xoa_nodump != ((zp->z_pflags & ZFS_NODUMP) != 0)) { need_policy = TRUE; } else { XVA_CLR_REQ(xvap, XAT_NODUMP); XVA_SET_REQ(&tmpxvattr, XAT_NODUMP); } } if (XVA_ISSET_REQ(xvap, XAT_AV_MODIFIED)) { if (xoap->xoa_av_modified != ((zp->z_pflags & ZFS_AV_MODIFIED) != 0)) { need_policy = TRUE; } else { XVA_CLR_REQ(xvap, XAT_AV_MODIFIED); XVA_SET_REQ(&tmpxvattr, XAT_AV_MODIFIED); } } if (XVA_ISSET_REQ(xvap, XAT_AV_QUARANTINED)) { if ((vp->v_type != VREG && xoap->xoa_av_quarantined) || xoap->xoa_av_quarantined != ((zp->z_pflags & ZFS_AV_QUARANTINED) != 0)) { need_policy = TRUE; } else { XVA_CLR_REQ(xvap, XAT_AV_QUARANTINED); XVA_SET_REQ(&tmpxvattr, XAT_AV_QUARANTINED); } } if (XVA_ISSET_REQ(xvap, XAT_REPARSE)) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EPERM)); } if (need_policy == FALSE && (XVA_ISSET_REQ(xvap, XAT_AV_SCANSTAMP) || XVA_ISSET_REQ(xvap, XAT_OPAQUE))) { need_policy = TRUE; } } if (mask & AT_MODE) { if (zfs_zaccess(zp, ACE_WRITE_ACL, 0, skipaclchk, cr) == 0) { err = secpolicy_setid_setsticky_clear(vp, vap, &oldva, cr); if (err) { ZFS_EXIT(zfsvfs); return (err); } trim_mask |= AT_MODE; } else { need_policy = TRUE; } } if (need_policy) { /* * If trim_mask is set then take ownership * has been granted or write_acl is present and user * has the ability to modify mode. In that case remove * UID|GID and or MODE from mask so that * secpolicy_vnode_setattr() doesn't revoke it. */ if (trim_mask) { saved_mask = vap->va_mask; vap->va_mask &= ~trim_mask; if (trim_mask & AT_MODE) { /* * Save the mode, as secpolicy_vnode_setattr() * will overwrite it with ova.va_mode. */ saved_mode = vap->va_mode; } } err = secpolicy_vnode_setattr(cr, vp, vap, &oldva, flags, (int (*)(void *, int, cred_t *))zfs_zaccess_unix, zp); if (err) { ZFS_EXIT(zfsvfs); return (err); } if (trim_mask) { vap->va_mask |= saved_mask; if (trim_mask & AT_MODE) { /* * Recover the mode after * secpolicy_vnode_setattr(). */ vap->va_mode = saved_mode; } } } /* * secpolicy_vnode_setattr, or take ownership may have * changed va_mask */ mask = vap->va_mask; if ((mask & (AT_UID | AT_GID)) || projid != ZFS_INVALID_PROJID) { err = sa_lookup(zp->z_sa_hdl, SA_ZPL_XATTR(zfsvfs), &xattr_obj, sizeof (xattr_obj)); if (err == 0 && xattr_obj) { err = zfs_zget(zp->z_zfsvfs, xattr_obj, &attrzp); if (err == 0) { err = vn_lock(ZTOV(attrzp), LK_EXCLUSIVE); if (err != 0) vrele(ZTOV(attrzp)); } if (err) goto out2; } if (mask & AT_UID) { new_uid = zfs_fuid_create(zfsvfs, (uint64_t)vap->va_uid, cr, ZFS_OWNER, &fuidp); if (new_uid != zp->z_uid && zfs_id_overquota(zfsvfs, DMU_USERUSED_OBJECT, new_uid)) { if (attrzp) vput(ZTOV(attrzp)); err = SET_ERROR(EDQUOT); goto out2; } } if (mask & AT_GID) { new_gid = zfs_fuid_create(zfsvfs, (uint64_t)vap->va_gid, cr, ZFS_GROUP, &fuidp); if (new_gid != zp->z_gid && zfs_id_overquota(zfsvfs, DMU_GROUPUSED_OBJECT, new_gid)) { if (attrzp) vput(ZTOV(attrzp)); err = SET_ERROR(EDQUOT); goto out2; } } if (projid != ZFS_INVALID_PROJID && zfs_id_overquota(zfsvfs, DMU_PROJECTUSED_OBJECT, projid)) { if (attrzp) vput(ZTOV(attrzp)); err = SET_ERROR(EDQUOT); goto out2; } } tx = dmu_tx_create(os); if (mask & AT_MODE) { uint64_t pmode = zp->z_mode; uint64_t acl_obj; new_mode = (pmode & S_IFMT) | (vap->va_mode & ~S_IFMT); if (zp->z_zfsvfs->z_acl_mode == ZFS_ACL_RESTRICTED && !(zp->z_pflags & ZFS_ACL_TRIVIAL)) { err = SET_ERROR(EPERM); goto out; } if ((err = zfs_acl_chmod_setattr(zp, &aclp, new_mode))) goto out; if (!zp->z_is_sa && ((acl_obj = zfs_external_acl(zp)) != 0)) { /* * Are we upgrading ACL from old V0 format * to V1 format? */ if (zfsvfs->z_version >= ZPL_VERSION_FUID && zfs_znode_acl_version(zp) == ZFS_ACL_VERSION_INITIAL) { dmu_tx_hold_free(tx, acl_obj, 0, DMU_OBJECT_END); dmu_tx_hold_write(tx, DMU_NEW_OBJECT, 0, aclp->z_acl_bytes); } else { dmu_tx_hold_write(tx, acl_obj, 0, aclp->z_acl_bytes); } } else if (!zp->z_is_sa && aclp->z_acl_bytes > ZFS_ACE_SPACE) { dmu_tx_hold_write(tx, DMU_NEW_OBJECT, 0, aclp->z_acl_bytes); } dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_TRUE); } else { if (((mask & AT_XVATTR) && XVA_ISSET_REQ(xvap, XAT_AV_SCANSTAMP)) || (projid != ZFS_INVALID_PROJID && !(zp->z_pflags & ZFS_PROJID))) dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_TRUE); else dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_FALSE); } if (attrzp) { dmu_tx_hold_sa(tx, attrzp->z_sa_hdl, B_FALSE); } fuid_dirtied = zfsvfs->z_fuid_dirty; if (fuid_dirtied) zfs_fuid_txhold(zfsvfs, tx); zfs_sa_upgrade_txholds(tx, zp); err = dmu_tx_assign(tx, TXG_WAIT); if (err) goto out; count = 0; /* * Set each attribute requested. * We group settings according to the locks they need to acquire. * * Note: you cannot set ctime directly, although it will be * updated as a side-effect of calling this function. */ if (projid != ZFS_INVALID_PROJID && !(zp->z_pflags & ZFS_PROJID)) { /* * For the existed object that is upgraded from old system, * its on-disk layout has no slot for the project ID attribute. * But quota accounting logic needs to access related slots by * offset directly. So we need to adjust old objects' layout * to make the project ID to some unified and fixed offset. */ if (attrzp) err = sa_add_projid(attrzp->z_sa_hdl, tx, projid); if (err == 0) err = sa_add_projid(zp->z_sa_hdl, tx, projid); if (unlikely(err == EEXIST)) err = 0; else if (err != 0) goto out; else projid = ZFS_INVALID_PROJID; } if (mask & (AT_UID|AT_GID|AT_MODE)) mutex_enter(&zp->z_acl_lock); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_FLAGS(zfsvfs), NULL, &zp->z_pflags, sizeof (zp->z_pflags)); if (attrzp) { if (mask & (AT_UID|AT_GID|AT_MODE)) mutex_enter(&attrzp->z_acl_lock); SA_ADD_BULK_ATTR(xattr_bulk, xattr_count, SA_ZPL_FLAGS(zfsvfs), NULL, &attrzp->z_pflags, sizeof (attrzp->z_pflags)); if (projid != ZFS_INVALID_PROJID) { attrzp->z_projid = projid; SA_ADD_BULK_ATTR(xattr_bulk, xattr_count, SA_ZPL_PROJID(zfsvfs), NULL, &attrzp->z_projid, sizeof (attrzp->z_projid)); } } if (mask & (AT_UID|AT_GID)) { if (mask & AT_UID) { SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_UID(zfsvfs), NULL, &new_uid, sizeof (new_uid)); zp->z_uid = new_uid; if (attrzp) { SA_ADD_BULK_ATTR(xattr_bulk, xattr_count, SA_ZPL_UID(zfsvfs), NULL, &new_uid, sizeof (new_uid)); attrzp->z_uid = new_uid; } } if (mask & AT_GID) { SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_GID(zfsvfs), NULL, &new_gid, sizeof (new_gid)); zp->z_gid = new_gid; if (attrzp) { SA_ADD_BULK_ATTR(xattr_bulk, xattr_count, SA_ZPL_GID(zfsvfs), NULL, &new_gid, sizeof (new_gid)); attrzp->z_gid = new_gid; } } if (!(mask & AT_MODE)) { SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MODE(zfsvfs), NULL, &new_mode, sizeof (new_mode)); new_mode = zp->z_mode; } err = zfs_acl_chown_setattr(zp); ASSERT0(err); if (attrzp) { vn_seqc_write_begin(ZTOV(attrzp)); err = zfs_acl_chown_setattr(attrzp); vn_seqc_write_end(ZTOV(attrzp)); ASSERT0(err); } } if (mask & AT_MODE) { SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MODE(zfsvfs), NULL, &new_mode, sizeof (new_mode)); zp->z_mode = new_mode; ASSERT3P(aclp, !=, NULL); err = zfs_aclset_common(zp, aclp, cr, tx); ASSERT0(err); if (zp->z_acl_cached) zfs_acl_free(zp->z_acl_cached); zp->z_acl_cached = aclp; aclp = NULL; } if (mask & AT_ATIME) { ZFS_TIME_ENCODE(&vap->va_atime, zp->z_atime); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ATIME(zfsvfs), NULL, &zp->z_atime, sizeof (zp->z_atime)); } if (mask & AT_MTIME) { ZFS_TIME_ENCODE(&vap->va_mtime, mtime); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MTIME(zfsvfs), NULL, mtime, sizeof (mtime)); } if (projid != ZFS_INVALID_PROJID) { zp->z_projid = projid; SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_PROJID(zfsvfs), NULL, &zp->z_projid, sizeof (zp->z_projid)); } /* XXX - shouldn't this be done *before* the ATIME/MTIME checks? */ if (mask & AT_SIZE && !(mask & AT_MTIME)) { SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MTIME(zfsvfs), NULL, mtime, sizeof (mtime)); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zfsvfs), NULL, &ctime, sizeof (ctime)); zfs_tstamp_update_setup(zp, CONTENT_MODIFIED, mtime, ctime); } else if (mask != 0) { SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zfsvfs), NULL, &ctime, sizeof (ctime)); zfs_tstamp_update_setup(zp, STATE_CHANGED, mtime, ctime); if (attrzp) { SA_ADD_BULK_ATTR(xattr_bulk, xattr_count, SA_ZPL_CTIME(zfsvfs), NULL, &ctime, sizeof (ctime)); zfs_tstamp_update_setup(attrzp, STATE_CHANGED, mtime, ctime); } } /* * Do this after setting timestamps to prevent timestamp * update from toggling bit */ if (xoap && (mask & AT_XVATTR)) { if (XVA_ISSET_REQ(xvap, XAT_CREATETIME)) xoap->xoa_createtime = vap->va_birthtime; /* * restore trimmed off masks * so that return masks can be set for caller. */ if (XVA_ISSET_REQ(&tmpxvattr, XAT_APPENDONLY)) { XVA_SET_REQ(xvap, XAT_APPENDONLY); } if (XVA_ISSET_REQ(&tmpxvattr, XAT_NOUNLINK)) { XVA_SET_REQ(xvap, XAT_NOUNLINK); } if (XVA_ISSET_REQ(&tmpxvattr, XAT_IMMUTABLE)) { XVA_SET_REQ(xvap, XAT_IMMUTABLE); } if (XVA_ISSET_REQ(&tmpxvattr, XAT_NODUMP)) { XVA_SET_REQ(xvap, XAT_NODUMP); } if (XVA_ISSET_REQ(&tmpxvattr, XAT_AV_MODIFIED)) { XVA_SET_REQ(xvap, XAT_AV_MODIFIED); } if (XVA_ISSET_REQ(&tmpxvattr, XAT_AV_QUARANTINED)) { XVA_SET_REQ(xvap, XAT_AV_QUARANTINED); } if (XVA_ISSET_REQ(&tmpxvattr, XAT_PROJINHERIT)) { XVA_SET_REQ(xvap, XAT_PROJINHERIT); } if (XVA_ISSET_REQ(xvap, XAT_AV_SCANSTAMP)) ASSERT3S(vp->v_type, ==, VREG); zfs_xvattr_set(zp, xvap, tx); } if (fuid_dirtied) zfs_fuid_sync(zfsvfs, tx); if (mask != 0) zfs_log_setattr(zilog, tx, TX_SETATTR, zp, vap, mask, fuidp); if (mask & (AT_UID|AT_GID|AT_MODE)) mutex_exit(&zp->z_acl_lock); if (attrzp) { if (mask & (AT_UID|AT_GID|AT_MODE)) mutex_exit(&attrzp->z_acl_lock); } out: if (err == 0 && attrzp) { err2 = sa_bulk_update(attrzp->z_sa_hdl, xattr_bulk, xattr_count, tx); ASSERT0(err2); } if (attrzp) vput(ZTOV(attrzp)); if (aclp) zfs_acl_free(aclp); if (fuidp) { zfs_fuid_info_free(fuidp); fuidp = NULL; } if (err) { dmu_tx_abort(tx); } else { err2 = sa_bulk_update(zp->z_sa_hdl, bulk, count, tx); dmu_tx_commit(tx); } out2: if (os->os_sync == ZFS_SYNC_ALWAYS) zil_commit(zilog, 0); ZFS_EXIT(zfsvfs); return (err); } /* * Look up the directory entries corresponding to the source and target * directory/name pairs. */ static int zfs_rename_relock_lookup(znode_t *sdzp, const struct componentname *scnp, znode_t **szpp, znode_t *tdzp, const struct componentname *tcnp, znode_t **tzpp) { zfsvfs_t *zfsvfs; znode_t *szp, *tzp; int error; /* * Before using sdzp and tdzp we must ensure that they are live. * As a porting legacy from illumos we have two things to worry * about. One is typical for FreeBSD and it is that the vnode is * not reclaimed (doomed). The other is that the znode is live. * The current code can invalidate the znode without acquiring the * corresponding vnode lock if the object represented by the znode * and vnode is no longer valid after a rollback or receive operation. * z_teardown_lock hidden behind ZFS_ENTER and ZFS_EXIT is the lock * that protects the znodes from the invalidation. */ zfsvfs = sdzp->z_zfsvfs; ASSERT3P(zfsvfs, ==, tdzp->z_zfsvfs); ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(sdzp); ZFS_VERIFY_ZP(tdzp); /* * Re-resolve svp to be certain it still exists and fetch the * correct vnode. */ error = zfs_dirent_lookup(sdzp, scnp->cn_nameptr, &szp, ZEXISTS); if (error != 0) { /* Source entry invalid or not there. */ if ((scnp->cn_flags & ISDOTDOT) != 0 || (scnp->cn_namelen == 1 && scnp->cn_nameptr[0] == '.')) error = SET_ERROR(EINVAL); goto out; } *szpp = szp; /* * Re-resolve tvp, if it disappeared we just carry on. */ error = zfs_dirent_lookup(tdzp, tcnp->cn_nameptr, &tzp, 0); if (error != 0) { vrele(ZTOV(szp)); if ((tcnp->cn_flags & ISDOTDOT) != 0) error = SET_ERROR(EINVAL); goto out; } *tzpp = tzp; out: ZFS_EXIT(zfsvfs); return (error); } /* * We acquire all but fdvp locks using non-blocking acquisitions. If we * fail to acquire any lock in the path we will drop all held locks, * acquire the new lock in a blocking fashion, and then release it and * restart the rename. This acquire/release step ensures that we do not * spin on a lock waiting for release. On error release all vnode locks * and decrement references the way tmpfs_rename() would do. */ static int zfs_rename_relock(struct vnode *sdvp, struct vnode **svpp, struct vnode *tdvp, struct vnode **tvpp, const struct componentname *scnp, const struct componentname *tcnp) { struct vnode *nvp, *svp, *tvp; znode_t *sdzp, *tdzp, *szp, *tzp; int error; VOP_UNLOCK1(tdvp); if (*tvpp != NULL && *tvpp != tdvp) VOP_UNLOCK1(*tvpp); relock: error = vn_lock(sdvp, LK_EXCLUSIVE); if (error) goto out; error = vn_lock(tdvp, LK_EXCLUSIVE | LK_NOWAIT); if (error != 0) { VOP_UNLOCK1(sdvp); if (error != EBUSY) goto out; error = vn_lock(tdvp, LK_EXCLUSIVE); if (error) goto out; VOP_UNLOCK1(tdvp); goto relock; } tdzp = VTOZ(tdvp); sdzp = VTOZ(sdvp); error = zfs_rename_relock_lookup(sdzp, scnp, &szp, tdzp, tcnp, &tzp); if (error != 0) { VOP_UNLOCK1(sdvp); VOP_UNLOCK1(tdvp); goto out; } svp = ZTOV(szp); tvp = tzp != NULL ? ZTOV(tzp) : NULL; /* * Now try acquire locks on svp and tvp. */ nvp = svp; error = vn_lock(nvp, LK_EXCLUSIVE | LK_NOWAIT); if (error != 0) { VOP_UNLOCK1(sdvp); VOP_UNLOCK1(tdvp); if (tvp != NULL) vrele(tvp); if (error != EBUSY) { vrele(nvp); goto out; } error = vn_lock(nvp, LK_EXCLUSIVE); if (error != 0) { vrele(nvp); goto out; } VOP_UNLOCK1(nvp); /* * Concurrent rename race. * XXX ? */ if (nvp == tdvp) { vrele(nvp); error = SET_ERROR(EINVAL); goto out; } vrele(*svpp); *svpp = nvp; goto relock; } vrele(*svpp); *svpp = nvp; if (*tvpp != NULL) vrele(*tvpp); *tvpp = NULL; if (tvp != NULL) { nvp = tvp; error = vn_lock(nvp, LK_EXCLUSIVE | LK_NOWAIT); if (error != 0) { VOP_UNLOCK1(sdvp); VOP_UNLOCK1(tdvp); VOP_UNLOCK1(*svpp); if (error != EBUSY) { vrele(nvp); goto out; } error = vn_lock(nvp, LK_EXCLUSIVE); if (error != 0) { vrele(nvp); goto out; } vput(nvp); goto relock; } *tvpp = nvp; } return (0); out: return (error); } /* * Note that we must use VRELE_ASYNC in this function as it walks * up the directory tree and vrele may need to acquire an exclusive * lock if a last reference to a vnode is dropped. */ static int zfs_rename_check(znode_t *szp, znode_t *sdzp, znode_t *tdzp) { zfsvfs_t *zfsvfs; znode_t *zp, *zp1; uint64_t parent; int error; zfsvfs = tdzp->z_zfsvfs; if (tdzp == szp) return (SET_ERROR(EINVAL)); if (tdzp == sdzp) return (0); if (tdzp->z_id == zfsvfs->z_root) return (0); zp = tdzp; for (;;) { ASSERT(!zp->z_unlinked); if ((error = sa_lookup(zp->z_sa_hdl, SA_ZPL_PARENT(zfsvfs), &parent, sizeof (parent))) != 0) break; if (parent == szp->z_id) { error = SET_ERROR(EINVAL); break; } if (parent == zfsvfs->z_root) break; if (parent == sdzp->z_id) break; error = zfs_zget(zfsvfs, parent, &zp1); if (error != 0) break; if (zp != tdzp) VN_RELE_ASYNC(ZTOV(zp), dsl_pool_zrele_taskq( dmu_objset_pool(zfsvfs->z_os))); zp = zp1; } if (error == ENOTDIR) panic("checkpath: .. not a directory\n"); if (zp != tdzp) VN_RELE_ASYNC(ZTOV(zp), dsl_pool_zrele_taskq(dmu_objset_pool(zfsvfs->z_os))); return (error); } #if __FreeBSD_version < 1300124 static void cache_vop_rename(struct vnode *fdvp, struct vnode *fvp, struct vnode *tdvp, struct vnode *tvp, struct componentname *fcnp, struct componentname *tcnp) { cache_purge(fvp); if (tvp != NULL) cache_purge(tvp); cache_purge_negative(tdvp); } #endif static int zfs_do_rename_impl(vnode_t *sdvp, vnode_t **svpp, struct componentname *scnp, vnode_t *tdvp, vnode_t **tvpp, struct componentname *tcnp, cred_t *cr); /* * Move an entry from the provided source directory to the target * directory. Change the entry name as indicated. * * IN: sdvp - Source directory containing the "old entry". * scnp - Old entry name. * tdvp - Target directory to contain the "new entry". * tcnp - New entry name. * cr - credentials of caller. * INOUT: svpp - Source file * tvpp - Target file, may point to NULL initially * * RETURN: 0 on success, error code on failure. * * Timestamps: * sdvp,tdvp - ctime|mtime updated */ static int zfs_do_rename(vnode_t *sdvp, vnode_t **svpp, struct componentname *scnp, vnode_t *tdvp, vnode_t **tvpp, struct componentname *tcnp, cred_t *cr) { int error; ASSERT_VOP_ELOCKED(tdvp, __func__); if (*tvpp != NULL) ASSERT_VOP_ELOCKED(*tvpp, __func__); /* Reject renames across filesystems. */ if ((*svpp)->v_mount != tdvp->v_mount || ((*tvpp) != NULL && (*svpp)->v_mount != (*tvpp)->v_mount)) { error = SET_ERROR(EXDEV); goto out; } if (zfsctl_is_node(tdvp)) { error = SET_ERROR(EXDEV); goto out; } /* * Lock all four vnodes to ensure safety and semantics of renaming. */ error = zfs_rename_relock(sdvp, svpp, tdvp, tvpp, scnp, tcnp); if (error != 0) { /* no vnodes are locked in the case of error here */ return (error); } error = zfs_do_rename_impl(sdvp, svpp, scnp, tdvp, tvpp, tcnp, cr); VOP_UNLOCK1(sdvp); VOP_UNLOCK1(*svpp); out: if (*tvpp != NULL) VOP_UNLOCK1(*tvpp); if (tdvp != *tvpp) VOP_UNLOCK1(tdvp); return (error); } static int zfs_do_rename_impl(vnode_t *sdvp, vnode_t **svpp, struct componentname *scnp, vnode_t *tdvp, vnode_t **tvpp, struct componentname *tcnp, cred_t *cr) { dmu_tx_t *tx; zfsvfs_t *zfsvfs; zilog_t *zilog; znode_t *tdzp, *sdzp, *tzp, *szp; const char *snm = scnp->cn_nameptr; const char *tnm = tcnp->cn_nameptr; int error; tdzp = VTOZ(tdvp); sdzp = VTOZ(sdvp); zfsvfs = tdzp->z_zfsvfs; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(tdzp); ZFS_VERIFY_ZP(sdzp); zilog = zfsvfs->z_log; if (zfsvfs->z_utf8 && u8_validate(tnm, strlen(tnm), NULL, U8_VALIDATE_ENTIRE, &error) < 0) { error = SET_ERROR(EILSEQ); goto out; } /* If source and target are the same file, there is nothing to do. */ if ((*svpp) == (*tvpp)) { error = 0; goto out; } if (((*svpp)->v_type == VDIR && (*svpp)->v_mountedhere != NULL) || ((*tvpp) != NULL && (*tvpp)->v_type == VDIR && (*tvpp)->v_mountedhere != NULL)) { error = SET_ERROR(EXDEV); goto out; } szp = VTOZ(*svpp); ZFS_VERIFY_ZP(szp); tzp = *tvpp == NULL ? NULL : VTOZ(*tvpp); if (tzp != NULL) ZFS_VERIFY_ZP(tzp); /* * This is to prevent the creation of links into attribute space * by renaming a linked file into/outof an attribute directory. * See the comment in zfs_link() for why this is considered bad. */ if ((tdzp->z_pflags & ZFS_XATTR) != (sdzp->z_pflags & ZFS_XATTR)) { error = SET_ERROR(EINVAL); goto out; } /* * If we are using project inheritance, means if the directory has * ZFS_PROJINHERIT set, then its descendant directories will inherit * not only the project ID, but also the ZFS_PROJINHERIT flag. Under * such case, we only allow renames into our tree when the project * IDs are the same. */ if (tdzp->z_pflags & ZFS_PROJINHERIT && tdzp->z_projid != szp->z_projid) { error = SET_ERROR(EXDEV); goto out; } /* * Must have write access at the source to remove the old entry * and write access at the target to create the new entry. * Note that if target and source are the same, this can be * done in a single check. */ if ((error = zfs_zaccess_rename(sdzp, szp, tdzp, tzp, cr))) goto out; if ((*svpp)->v_type == VDIR) { /* * Avoid ".", "..", and aliases of "." for obvious reasons. */ if ((scnp->cn_namelen == 1 && scnp->cn_nameptr[0] == '.') || sdzp == szp || (scnp->cn_flags | tcnp->cn_flags) & ISDOTDOT) { error = EINVAL; goto out; } /* * Check to make sure rename is valid. * Can't do a move like this: /usr/a/b to /usr/a/b/c/d */ if ((error = zfs_rename_check(szp, sdzp, tdzp))) goto out; } /* * Does target exist? */ if (tzp) { /* * Source and target must be the same type. */ if ((*svpp)->v_type == VDIR) { if ((*tvpp)->v_type != VDIR) { error = SET_ERROR(ENOTDIR); goto out; } else { cache_purge(tdvp); if (sdvp != tdvp) cache_purge(sdvp); } } else { if ((*tvpp)->v_type == VDIR) { error = SET_ERROR(EISDIR); goto out; } } } vn_seqc_write_begin(*svpp); vn_seqc_write_begin(sdvp); if (*tvpp != NULL) vn_seqc_write_begin(*tvpp); if (tdvp != *tvpp) vn_seqc_write_begin(tdvp); vnevent_rename_src(*svpp, sdvp, scnp->cn_nameptr, ct); if (tzp) vnevent_rename_dest(*tvpp, tdvp, tnm, ct); /* * notify the target directory if it is not the same * as source directory. */ if (tdvp != sdvp) { vnevent_rename_dest_dir(tdvp, ct); } tx = dmu_tx_create(zfsvfs->z_os); dmu_tx_hold_sa(tx, szp->z_sa_hdl, B_FALSE); dmu_tx_hold_sa(tx, sdzp->z_sa_hdl, B_FALSE); dmu_tx_hold_zap(tx, sdzp->z_id, FALSE, snm); dmu_tx_hold_zap(tx, tdzp->z_id, TRUE, tnm); if (sdzp != tdzp) { dmu_tx_hold_sa(tx, tdzp->z_sa_hdl, B_FALSE); zfs_sa_upgrade_txholds(tx, tdzp); } if (tzp) { dmu_tx_hold_sa(tx, tzp->z_sa_hdl, B_FALSE); zfs_sa_upgrade_txholds(tx, tzp); } zfs_sa_upgrade_txholds(tx, szp); dmu_tx_hold_zap(tx, zfsvfs->z_unlinkedobj, FALSE, NULL); error = dmu_tx_assign(tx, TXG_WAIT); if (error) { dmu_tx_abort(tx); goto out_seq; } if (tzp) /* Attempt to remove the existing target */ error = zfs_link_destroy(tdzp, tnm, tzp, tx, 0, NULL); if (error == 0) { error = zfs_link_create(tdzp, tnm, szp, tx, ZRENAMING); if (error == 0) { szp->z_pflags |= ZFS_AV_MODIFIED; error = sa_update(szp->z_sa_hdl, SA_ZPL_FLAGS(zfsvfs), (void *)&szp->z_pflags, sizeof (uint64_t), tx); ASSERT0(error); error = zfs_link_destroy(sdzp, snm, szp, tx, ZRENAMING, NULL); if (error == 0) { zfs_log_rename(zilog, tx, TX_RENAME, sdzp, snm, tdzp, tnm, szp); /* * Update path information for the target vnode */ vn_renamepath(tdvp, *svpp, tnm, strlen(tnm)); } else { /* * At this point, we have successfully created * the target name, but have failed to remove * the source name. Since the create was done * with the ZRENAMING flag, there are * complications; for one, the link count is * wrong. The easiest way to deal with this * is to remove the newly created target, and * return the original error. This must * succeed; fortunately, it is very unlikely to * fail, since we just created it. */ VERIFY0(zfs_link_destroy(tdzp, tnm, szp, tx, ZRENAMING, NULL)); } } if (error == 0) { cache_vop_rename(sdvp, *svpp, tdvp, *tvpp, scnp, tcnp); } } dmu_tx_commit(tx); out_seq: vn_seqc_write_end(*svpp); vn_seqc_write_end(sdvp); if (*tvpp != NULL) vn_seqc_write_end(*tvpp); if (tdvp != *tvpp) vn_seqc_write_end(tdvp); out: if (error == 0 && zfsvfs->z_os->os_sync == ZFS_SYNC_ALWAYS) zil_commit(zilog, 0); ZFS_EXIT(zfsvfs); return (error); } int zfs_rename(znode_t *sdzp, const char *sname, znode_t *tdzp, const char *tname, cred_t *cr, int flags) { struct componentname scn, tcn; vnode_t *sdvp, *tdvp; vnode_t *svp, *tvp; int error; svp = tvp = NULL; sdvp = ZTOV(sdzp); tdvp = ZTOV(tdzp); error = zfs_lookup_internal(sdzp, sname, &svp, &scn, DELETE); if (sdzp->z_zfsvfs->z_replay == B_FALSE) VOP_UNLOCK1(sdvp); if (error != 0) goto fail; VOP_UNLOCK1(svp); vn_lock(tdvp, LK_EXCLUSIVE | LK_RETRY); error = zfs_lookup_internal(tdzp, tname, &tvp, &tcn, RENAME); if (error == EJUSTRETURN) tvp = NULL; else if (error != 0) { VOP_UNLOCK1(tdvp); goto fail; } error = zfs_do_rename(sdvp, &svp, &scn, tdvp, &tvp, &tcn, cr); fail: if (svp != NULL) vrele(svp); if (tvp != NULL) vrele(tvp); return (error); } /* * Insert the indicated symbolic reference entry into the directory. * * IN: dvp - Directory to contain new symbolic link. * link - Name for new symlink entry. * vap - Attributes of new entry. * cr - credentials of caller. * ct - caller context * flags - case flags * * RETURN: 0 on success, error code on failure. * * Timestamps: * dvp - ctime|mtime updated */ int zfs_symlink(znode_t *dzp, const char *name, vattr_t *vap, const char *link, znode_t **zpp, cred_t *cr, int flags) { (void) flags; znode_t *zp; dmu_tx_t *tx; zfsvfs_t *zfsvfs = dzp->z_zfsvfs; zilog_t *zilog; uint64_t len = strlen(link); int error; zfs_acl_ids_t acl_ids; boolean_t fuid_dirtied; uint64_t txtype = TX_SYMLINK; ASSERT3S(vap->va_type, ==, VLNK); ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(dzp); zilog = zfsvfs->z_log; if (zfsvfs->z_utf8 && u8_validate(name, strlen(name), NULL, U8_VALIDATE_ENTIRE, &error) < 0) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EILSEQ)); } if (len > MAXPATHLEN) { ZFS_EXIT(zfsvfs); return (SET_ERROR(ENAMETOOLONG)); } if ((error = zfs_acl_ids_create(dzp, 0, vap, cr, NULL, &acl_ids)) != 0) { ZFS_EXIT(zfsvfs); return (error); } /* * Attempt to lock directory; fail if entry already exists. */ error = zfs_dirent_lookup(dzp, name, &zp, ZNEW); if (error) { zfs_acl_ids_free(&acl_ids); ZFS_EXIT(zfsvfs); return (error); } if ((error = zfs_zaccess(dzp, ACE_ADD_FILE, 0, B_FALSE, cr))) { zfs_acl_ids_free(&acl_ids); ZFS_EXIT(zfsvfs); return (error); } if (zfs_acl_ids_overquota(zfsvfs, &acl_ids, 0 /* projid */)) { zfs_acl_ids_free(&acl_ids); ZFS_EXIT(zfsvfs); return (SET_ERROR(EDQUOT)); } getnewvnode_reserve_(); tx = dmu_tx_create(zfsvfs->z_os); fuid_dirtied = zfsvfs->z_fuid_dirty; dmu_tx_hold_write(tx, DMU_NEW_OBJECT, 0, MAX(1, len)); dmu_tx_hold_zap(tx, dzp->z_id, TRUE, name); dmu_tx_hold_sa_create(tx, acl_ids.z_aclp->z_acl_bytes + ZFS_SA_BASE_ATTR_SIZE + len); dmu_tx_hold_sa(tx, dzp->z_sa_hdl, B_FALSE); if (!zfsvfs->z_use_sa && acl_ids.z_aclp->z_acl_bytes > ZFS_ACE_SPACE) { dmu_tx_hold_write(tx, DMU_NEW_OBJECT, 0, acl_ids.z_aclp->z_acl_bytes); } if (fuid_dirtied) zfs_fuid_txhold(zfsvfs, tx); error = dmu_tx_assign(tx, TXG_WAIT); if (error) { zfs_acl_ids_free(&acl_ids); dmu_tx_abort(tx); getnewvnode_drop_reserve(); ZFS_EXIT(zfsvfs); return (error); } /* * Create a new object for the symlink. * for version 4 ZPL datasets the symlink will be an SA attribute */ zfs_mknode(dzp, vap, tx, cr, 0, &zp, &acl_ids); if (fuid_dirtied) zfs_fuid_sync(zfsvfs, tx); if (zp->z_is_sa) error = sa_update(zp->z_sa_hdl, SA_ZPL_SYMLINK(zfsvfs), __DECONST(void *, link), len, tx); else zfs_sa_symlink(zp, __DECONST(char *, link), len, tx); zp->z_size = len; (void) sa_update(zp->z_sa_hdl, SA_ZPL_SIZE(zfsvfs), &zp->z_size, sizeof (zp->z_size), tx); /* * Insert the new object into the directory. */ (void) zfs_link_create(dzp, name, zp, tx, ZNEW); zfs_log_symlink(zilog, tx, txtype, dzp, zp, name, link); *zpp = zp; zfs_acl_ids_free(&acl_ids); dmu_tx_commit(tx); getnewvnode_drop_reserve(); if (zfsvfs->z_os->os_sync == ZFS_SYNC_ALWAYS) zil_commit(zilog, 0); ZFS_EXIT(zfsvfs); return (error); } /* * Return, in the buffer contained in the provided uio structure, * the symbolic path referred to by vp. * * IN: vp - vnode of symbolic link. * uio - structure to contain the link path. * cr - credentials of caller. * ct - caller context * * OUT: uio - structure containing the link path. * * RETURN: 0 on success, error code on failure. * * Timestamps: * vp - atime updated */ static int zfs_readlink(vnode_t *vp, zfs_uio_t *uio, cred_t *cr, caller_context_t *ct) { (void) cr, (void) ct; znode_t *zp = VTOZ(vp); zfsvfs_t *zfsvfs = zp->z_zfsvfs; int error; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); if (zp->z_is_sa) error = sa_lookup_uio(zp->z_sa_hdl, SA_ZPL_SYMLINK(zfsvfs), uio); else error = zfs_sa_readlink(zp, uio); ZFS_ACCESSTIME_STAMP(zfsvfs, zp); ZFS_EXIT(zfsvfs); return (error); } /* * Insert a new entry into directory tdvp referencing svp. * * IN: tdvp - Directory to contain new entry. * svp - vnode of new entry. * name - name of new entry. * cr - credentials of caller. * * RETURN: 0 on success, error code on failure. * * Timestamps: * tdvp - ctime|mtime updated * svp - ctime updated */ int zfs_link(znode_t *tdzp, znode_t *szp, const char *name, cred_t *cr, int flags) { (void) flags; znode_t *tzp; zfsvfs_t *zfsvfs = tdzp->z_zfsvfs; zilog_t *zilog; dmu_tx_t *tx; int error; uint64_t parent; uid_t owner; ASSERT3S(ZTOV(tdzp)->v_type, ==, VDIR); ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(tdzp); zilog = zfsvfs->z_log; /* * POSIX dictates that we return EPERM here. * Better choices include ENOTSUP or EISDIR. */ if (ZTOV(szp)->v_type == VDIR) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EPERM)); } ZFS_VERIFY_ZP(szp); /* * If we are using project inheritance, means if the directory has * ZFS_PROJINHERIT set, then its descendant directories will inherit * not only the project ID, but also the ZFS_PROJINHERIT flag. Under * such case, we only allow hard link creation in our tree when the * project IDs are the same. */ if (tdzp->z_pflags & ZFS_PROJINHERIT && tdzp->z_projid != szp->z_projid) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EXDEV)); } if (szp->z_pflags & (ZFS_APPENDONLY | ZFS_IMMUTABLE | ZFS_READONLY)) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EPERM)); } /* Prevent links to .zfs/shares files */ if ((error = sa_lookup(szp->z_sa_hdl, SA_ZPL_PARENT(zfsvfs), &parent, sizeof (uint64_t))) != 0) { ZFS_EXIT(zfsvfs); return (error); } if (parent == zfsvfs->z_shares_dir) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EPERM)); } if (zfsvfs->z_utf8 && u8_validate(name, strlen(name), NULL, U8_VALIDATE_ENTIRE, &error) < 0) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EILSEQ)); } /* * We do not support links between attributes and non-attributes * because of the potential security risk of creating links * into "normal" file space in order to circumvent restrictions * imposed in attribute space. */ if ((szp->z_pflags & ZFS_XATTR) != (tdzp->z_pflags & ZFS_XATTR)) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EINVAL)); } owner = zfs_fuid_map_id(zfsvfs, szp->z_uid, cr, ZFS_OWNER); if (owner != crgetuid(cr) && secpolicy_basic_link(ZTOV(szp), cr) != 0) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EPERM)); } if ((error = zfs_zaccess(tdzp, ACE_ADD_FILE, 0, B_FALSE, cr))) { ZFS_EXIT(zfsvfs); return (error); } /* * Attempt to lock directory; fail if entry already exists. */ error = zfs_dirent_lookup(tdzp, name, &tzp, ZNEW); if (error) { ZFS_EXIT(zfsvfs); return (error); } tx = dmu_tx_create(zfsvfs->z_os); dmu_tx_hold_sa(tx, szp->z_sa_hdl, B_FALSE); dmu_tx_hold_zap(tx, tdzp->z_id, TRUE, name); zfs_sa_upgrade_txholds(tx, szp); zfs_sa_upgrade_txholds(tx, tdzp); error = dmu_tx_assign(tx, TXG_WAIT); if (error) { dmu_tx_abort(tx); ZFS_EXIT(zfsvfs); return (error); } error = zfs_link_create(tdzp, name, szp, tx, 0); if (error == 0) { uint64_t txtype = TX_LINK; zfs_log_link(zilog, tx, txtype, tdzp, szp, name); } dmu_tx_commit(tx); if (error == 0) { vnevent_link(ZTOV(szp), ct); } if (zfsvfs->z_os->os_sync == ZFS_SYNC_ALWAYS) zil_commit(zilog, 0); ZFS_EXIT(zfsvfs); return (error); } /* * Free or allocate space in a file. Currently, this function only * supports the `F_FREESP' command. However, this command is somewhat * misnamed, as its functionality includes the ability to allocate as * well as free space. * * IN: ip - inode of file to free data in. * cmd - action to take (only F_FREESP supported). * bfp - section of file to free/alloc. * flag - current file open mode flags. * offset - current file offset. * cr - credentials of caller. * * RETURN: 0 on success, error code on failure. * * Timestamps: * ip - ctime|mtime updated */ int zfs_space(znode_t *zp, int cmd, flock64_t *bfp, int flag, offset_t offset, cred_t *cr) { (void) offset; zfsvfs_t *zfsvfs = ZTOZSB(zp); uint64_t off, len; int error; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); if (cmd != F_FREESP) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EINVAL)); } /* * Callers might not be able to detect properly that we are read-only, * so check it explicitly here. */ if (zfs_is_readonly(zfsvfs)) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EROFS)); } if (bfp->l_len < 0) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EINVAL)); } /* * Permissions aren't checked on Solaris because on this OS * zfs_space() can only be called with an opened file handle. * On Linux we can get here through truncate_range() which * operates directly on inodes, so we need to check access rights. */ if ((error = zfs_zaccess(zp, ACE_WRITE_DATA, 0, B_FALSE, cr))) { ZFS_EXIT(zfsvfs); return (error); } off = bfp->l_start; len = bfp->l_len; /* 0 means from off to end of file */ error = zfs_freesp(zp, off, len, flag, TRUE); ZFS_EXIT(zfsvfs); return (error); } static void zfs_inactive(vnode_t *vp, cred_t *cr, caller_context_t *ct) { (void) cr, (void) ct; znode_t *zp = VTOZ(vp); zfsvfs_t *zfsvfs = zp->z_zfsvfs; int error; ZFS_TEARDOWN_INACTIVE_ENTER_READ(zfsvfs); if (zp->z_sa_hdl == NULL) { /* * The fs has been unmounted, or we did a * suspend/resume and this file no longer exists. */ ZFS_TEARDOWN_INACTIVE_EXIT_READ(zfsvfs); vrecycle(vp); return; } if (zp->z_unlinked) { /* * Fast path to recycle a vnode of a removed file. */ ZFS_TEARDOWN_INACTIVE_EXIT_READ(zfsvfs); vrecycle(vp); return; } if (zp->z_atime_dirty && zp->z_unlinked == 0) { dmu_tx_t *tx = dmu_tx_create(zfsvfs->z_os); dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_FALSE); zfs_sa_upgrade_txholds(tx, zp); error = dmu_tx_assign(tx, TXG_WAIT); if (error) { dmu_tx_abort(tx); } else { (void) sa_update(zp->z_sa_hdl, SA_ZPL_ATIME(zfsvfs), (void *)&zp->z_atime, sizeof (zp->z_atime), tx); zp->z_atime_dirty = 0; dmu_tx_commit(tx); } } ZFS_TEARDOWN_INACTIVE_EXIT_READ(zfsvfs); } _Static_assert(sizeof (struct zfid_short) <= sizeof (struct fid), "struct zfid_short bigger than struct fid"); _Static_assert(sizeof (struct zfid_long) <= sizeof (struct fid), "struct zfid_long bigger than struct fid"); static int zfs_fid(vnode_t *vp, fid_t *fidp, caller_context_t *ct) { (void) ct; znode_t *zp = VTOZ(vp); zfsvfs_t *zfsvfs = zp->z_zfsvfs; uint32_t gen; uint64_t gen64; uint64_t object = zp->z_id; zfid_short_t *zfid; int size, i, error; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); if ((error = sa_lookup(zp->z_sa_hdl, SA_ZPL_GEN(zfsvfs), &gen64, sizeof (uint64_t))) != 0) { ZFS_EXIT(zfsvfs); return (error); } gen = (uint32_t)gen64; size = (zfsvfs->z_parent != zfsvfs) ? LONG_FID_LEN : SHORT_FID_LEN; fidp->fid_len = size; zfid = (zfid_short_t *)fidp; zfid->zf_len = size; for (i = 0; i < sizeof (zfid->zf_object); i++) zfid->zf_object[i] = (uint8_t)(object >> (8 * i)); /* Must have a non-zero generation number to distinguish from .zfs */ if (gen == 0) gen = 1; for (i = 0; i < sizeof (zfid->zf_gen); i++) zfid->zf_gen[i] = (uint8_t)(gen >> (8 * i)); if (size == LONG_FID_LEN) { uint64_t objsetid = dmu_objset_id(zfsvfs->z_os); zfid_long_t *zlfid; zlfid = (zfid_long_t *)fidp; for (i = 0; i < sizeof (zlfid->zf_setid); i++) zlfid->zf_setid[i] = (uint8_t)(objsetid >> (8 * i)); /* XXX - this should be the generation number for the objset */ for (i = 0; i < sizeof (zlfid->zf_setgen); i++) zlfid->zf_setgen[i] = 0; } ZFS_EXIT(zfsvfs); return (0); } static int zfs_pathconf(vnode_t *vp, int cmd, ulong_t *valp, cred_t *cr, caller_context_t *ct) { znode_t *zp; zfsvfs_t *zfsvfs; switch (cmd) { case _PC_LINK_MAX: *valp = MIN(LONG_MAX, ZFS_LINK_MAX); return (0); case _PC_FILESIZEBITS: *valp = 64; return (0); case _PC_MIN_HOLE_SIZE: *valp = (int)SPA_MINBLOCKSIZE; return (0); case _PC_ACL_EXTENDED: #if 0 /* POSIX ACLs are not implemented for ZFS on FreeBSD yet. */ zp = VTOZ(vp); zfsvfs = zp->z_zfsvfs; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); *valp = zfsvfs->z_acl_type == ZFSACLTYPE_POSIX ? 1 : 0; ZFS_EXIT(zfsvfs); #else *valp = 0; #endif return (0); case _PC_ACL_NFS4: zp = VTOZ(vp); zfsvfs = zp->z_zfsvfs; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); *valp = zfsvfs->z_acl_type == ZFS_ACLTYPE_NFSV4 ? 1 : 0; ZFS_EXIT(zfsvfs); return (0); case _PC_ACL_PATH_MAX: *valp = ACL_MAX_ENTRIES; return (0); default: return (EOPNOTSUPP); } } static int zfs_getpages(struct vnode *vp, vm_page_t *ma, int count, int *rbehind, int *rahead) { znode_t *zp = VTOZ(vp); zfsvfs_t *zfsvfs = zp->z_zfsvfs; zfs_locked_range_t *lr; vm_object_t object; off_t start, end, obj_size; uint_t blksz; int pgsin_b, pgsin_a; int error; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); start = IDX_TO_OFF(ma[0]->pindex); end = IDX_TO_OFF(ma[count - 1]->pindex + 1); /* * Lock a range covering all required and optional pages. * Note that we need to handle the case of the block size growing. */ for (;;) { blksz = zp->z_blksz; lr = zfs_rangelock_tryenter(&zp->z_rangelock, rounddown(start, blksz), roundup(end, blksz) - rounddown(start, blksz), RL_READER); if (lr == NULL) { if (rahead != NULL) { *rahead = 0; rahead = NULL; } if (rbehind != NULL) { *rbehind = 0; rbehind = NULL; } break; } if (blksz == zp->z_blksz) break; zfs_rangelock_exit(lr); } object = ma[0]->object; zfs_vmobject_wlock(object); obj_size = object->un_pager.vnp.vnp_size; zfs_vmobject_wunlock(object); if (IDX_TO_OFF(ma[count - 1]->pindex) >= obj_size) { if (lr != NULL) zfs_rangelock_exit(lr); ZFS_EXIT(zfsvfs); return (zfs_vm_pagerret_bad); } pgsin_b = 0; if (rbehind != NULL) { pgsin_b = OFF_TO_IDX(start - rounddown(start, blksz)); pgsin_b = MIN(*rbehind, pgsin_b); } pgsin_a = 0; if (rahead != NULL) { pgsin_a = OFF_TO_IDX(roundup(end, blksz) - end); if (end + IDX_TO_OFF(pgsin_a) >= obj_size) pgsin_a = OFF_TO_IDX(round_page(obj_size) - end); pgsin_a = MIN(*rahead, pgsin_a); } /* * NB: we need to pass the exact byte size of the data that we expect * to read after accounting for the file size. This is required because * ZFS will panic if we request DMU to read beyond the end of the last * allocated block. */ error = dmu_read_pages(zfsvfs->z_os, zp->z_id, ma, count, &pgsin_b, &pgsin_a, MIN(end, obj_size) - (end - PAGE_SIZE)); if (lr != NULL) zfs_rangelock_exit(lr); ZFS_ACCESSTIME_STAMP(zfsvfs, zp); dataset_kstats_update_read_kstats(&zfsvfs->z_kstat, count*PAGE_SIZE); ZFS_EXIT(zfsvfs); if (error != 0) return (zfs_vm_pagerret_error); VM_CNT_INC(v_vnodein); VM_CNT_ADD(v_vnodepgsin, count + pgsin_b + pgsin_a); if (rbehind != NULL) *rbehind = pgsin_b; if (rahead != NULL) *rahead = pgsin_a; return (zfs_vm_pagerret_ok); } #ifndef _SYS_SYSPROTO_H_ struct vop_getpages_args { struct vnode *a_vp; vm_page_t *a_m; int a_count; int *a_rbehind; int *a_rahead; }; #endif static int zfs_freebsd_getpages(struct vop_getpages_args *ap) { return (zfs_getpages(ap->a_vp, ap->a_m, ap->a_count, ap->a_rbehind, ap->a_rahead)); } static int zfs_putpages(struct vnode *vp, vm_page_t *ma, size_t len, int flags, int *rtvals) { znode_t *zp = VTOZ(vp); zfsvfs_t *zfsvfs = zp->z_zfsvfs; zfs_locked_range_t *lr; dmu_tx_t *tx; struct sf_buf *sf; vm_object_t object; vm_page_t m; caddr_t va; size_t tocopy; size_t lo_len; vm_ooffset_t lo_off; vm_ooffset_t off; uint_t blksz; int ncount; int pcount; int err; int i; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); object = vp->v_object; pcount = btoc(len); ncount = pcount; KASSERT(ma[0]->object == object, ("mismatching object")); KASSERT(len > 0 && (len & PAGE_MASK) == 0, ("unexpected length")); for (i = 0; i < pcount; i++) rtvals[i] = zfs_vm_pagerret_error; off = IDX_TO_OFF(ma[0]->pindex); blksz = zp->z_blksz; lo_off = rounddown(off, blksz); lo_len = roundup(len + (off - lo_off), blksz); lr = zfs_rangelock_enter(&zp->z_rangelock, lo_off, lo_len, RL_WRITER); zfs_vmobject_wlock(object); if (len + off > object->un_pager.vnp.vnp_size) { if (object->un_pager.vnp.vnp_size > off) { int pgoff; len = object->un_pager.vnp.vnp_size - off; ncount = btoc(len); if ((pgoff = (int)len & PAGE_MASK) != 0) { /* * If the object is locked and the following * conditions hold, then the page's dirty * field cannot be concurrently changed by a * pmap operation. */ m = ma[ncount - 1]; vm_page_assert_sbusied(m); KASSERT(!pmap_page_is_write_mapped(m), ("zfs_putpages: page %p is not read-only", m)); vm_page_clear_dirty(m, pgoff, PAGE_SIZE - pgoff); } } else { len = 0; ncount = 0; } if (ncount < pcount) { for (i = ncount; i < pcount; i++) { rtvals[i] = zfs_vm_pagerret_bad; } } } zfs_vmobject_wunlock(object); if (ncount == 0) goto out; if (zfs_id_overblockquota(zfsvfs, DMU_USERUSED_OBJECT, zp->z_uid) || zfs_id_overblockquota(zfsvfs, DMU_GROUPUSED_OBJECT, zp->z_gid) || (zp->z_projid != ZFS_DEFAULT_PROJID && zfs_id_overblockquota(zfsvfs, DMU_PROJECTUSED_OBJECT, zp->z_projid))) { goto out; } tx = dmu_tx_create(zfsvfs->z_os); dmu_tx_hold_write(tx, zp->z_id, off, len); dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_FALSE); zfs_sa_upgrade_txholds(tx, zp); err = dmu_tx_assign(tx, TXG_WAIT); if (err != 0) { dmu_tx_abort(tx); goto out; } if (zp->z_blksz < PAGE_SIZE) { for (i = 0; len > 0; off += tocopy, len -= tocopy, i++) { tocopy = len > PAGE_SIZE ? PAGE_SIZE : len; va = zfs_map_page(ma[i], &sf); dmu_write(zfsvfs->z_os, zp->z_id, off, tocopy, va, tx); zfs_unmap_page(sf); } } else { err = dmu_write_pages(zfsvfs->z_os, zp->z_id, off, len, ma, tx); } if (err == 0) { uint64_t mtime[2], ctime[2]; sa_bulk_attr_t bulk[3]; int count = 0; SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MTIME(zfsvfs), NULL, &mtime, 16); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zfsvfs), NULL, &ctime, 16); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_FLAGS(zfsvfs), NULL, &zp->z_pflags, 8); zfs_tstamp_update_setup(zp, CONTENT_MODIFIED, mtime, ctime); err = sa_bulk_update(zp->z_sa_hdl, bulk, count, tx); ASSERT0(err); /* * XXX we should be passing a callback to undirty * but that would make the locking messier */ zfs_log_write(zfsvfs->z_log, tx, TX_WRITE, zp, off, len, 0, NULL, NULL); zfs_vmobject_wlock(object); for (i = 0; i < ncount; i++) { rtvals[i] = zfs_vm_pagerret_ok; vm_page_undirty(ma[i]); } zfs_vmobject_wunlock(object); VM_CNT_INC(v_vnodeout); VM_CNT_ADD(v_vnodepgsout, ncount); } dmu_tx_commit(tx); out: zfs_rangelock_exit(lr); if ((flags & (zfs_vm_pagerput_sync | zfs_vm_pagerput_inval)) != 0 || zfsvfs->z_os->os_sync == ZFS_SYNC_ALWAYS) zil_commit(zfsvfs->z_log, zp->z_id); dataset_kstats_update_write_kstats(&zfsvfs->z_kstat, len); ZFS_EXIT(zfsvfs); return (rtvals[0]); } #ifndef _SYS_SYSPROTO_H_ struct vop_putpages_args { struct vnode *a_vp; vm_page_t *a_m; int a_count; int a_sync; int *a_rtvals; }; #endif static int zfs_freebsd_putpages(struct vop_putpages_args *ap) { return (zfs_putpages(ap->a_vp, ap->a_m, ap->a_count, ap->a_sync, ap->a_rtvals)); } #ifndef _SYS_SYSPROTO_H_ struct vop_bmap_args { struct vnode *a_vp; daddr_t a_bn; struct bufobj **a_bop; daddr_t *a_bnp; int *a_runp; int *a_runb; }; #endif static int zfs_freebsd_bmap(struct vop_bmap_args *ap) { if (ap->a_bop != NULL) *ap->a_bop = &ap->a_vp->v_bufobj; if (ap->a_bnp != NULL) *ap->a_bnp = ap->a_bn; if (ap->a_runp != NULL) *ap->a_runp = 0; if (ap->a_runb != NULL) *ap->a_runb = 0; return (0); } #ifndef _SYS_SYSPROTO_H_ struct vop_open_args { struct vnode *a_vp; int a_mode; struct ucred *a_cred; struct thread *a_td; }; #endif static int zfs_freebsd_open(struct vop_open_args *ap) { vnode_t *vp = ap->a_vp; znode_t *zp = VTOZ(vp); int error; error = zfs_open(&vp, ap->a_mode, ap->a_cred); if (error == 0) vnode_create_vobject(vp, zp->z_size, ap->a_td); return (error); } #ifndef _SYS_SYSPROTO_H_ struct vop_close_args { struct vnode *a_vp; int a_fflag; struct ucred *a_cred; struct thread *a_td; }; #endif static int zfs_freebsd_close(struct vop_close_args *ap) { return (zfs_close(ap->a_vp, ap->a_fflag, 1, 0, ap->a_cred)); } #ifndef _SYS_SYSPROTO_H_ struct vop_ioctl_args { struct vnode *a_vp; ulong_t a_command; caddr_t a_data; int a_fflag; struct ucred *cred; struct thread *td; }; #endif static int zfs_freebsd_ioctl(struct vop_ioctl_args *ap) { return (zfs_ioctl(ap->a_vp, ap->a_command, (intptr_t)ap->a_data, ap->a_fflag, ap->a_cred, NULL)); } static int ioflags(int ioflags) { int flags = 0; if (ioflags & IO_APPEND) flags |= FAPPEND; if (ioflags & IO_NDELAY) flags |= FNONBLOCK; if (ioflags & IO_SYNC) flags |= (FSYNC | FDSYNC | FRSYNC); return (flags); } #ifndef _SYS_SYSPROTO_H_ struct vop_read_args { struct vnode *a_vp; struct uio *a_uio; int a_ioflag; struct ucred *a_cred; }; #endif static int zfs_freebsd_read(struct vop_read_args *ap) { zfs_uio_t uio; zfs_uio_init(&uio, ap->a_uio); return (zfs_read(VTOZ(ap->a_vp), &uio, ioflags(ap->a_ioflag), ap->a_cred)); } #ifndef _SYS_SYSPROTO_H_ struct vop_write_args { struct vnode *a_vp; struct uio *a_uio; int a_ioflag; struct ucred *a_cred; }; #endif static int zfs_freebsd_write(struct vop_write_args *ap) { zfs_uio_t uio; zfs_uio_init(&uio, ap->a_uio); return (zfs_write(VTOZ(ap->a_vp), &uio, ioflags(ap->a_ioflag), ap->a_cred)); } #if __FreeBSD_version >= 1300102 /* * VOP_FPLOOKUP_VEXEC routines are subject to special circumstances, see * the comment above cache_fplookup for details. */ static int zfs_freebsd_fplookup_vexec(struct vop_fplookup_vexec_args *v) { vnode_t *vp; znode_t *zp; uint64_t pflags; vp = v->a_vp; zp = VTOZ_SMR(vp); if (__predict_false(zp == NULL)) return (EAGAIN); pflags = atomic_load_64(&zp->z_pflags); if (pflags & ZFS_AV_QUARANTINED) return (EAGAIN); if (pflags & ZFS_XATTR) return (EAGAIN); if ((pflags & ZFS_NO_EXECS_DENIED) == 0) return (EAGAIN); return (0); } #endif #if __FreeBSD_version >= 1300139 static int zfs_freebsd_fplookup_symlink(struct vop_fplookup_symlink_args *v) { vnode_t *vp; znode_t *zp; char *target; vp = v->a_vp; zp = VTOZ_SMR(vp); if (__predict_false(zp == NULL)) { return (EAGAIN); } target = atomic_load_consume_ptr(&zp->z_cached_symlink); if (target == NULL) { return (EAGAIN); } return (cache_symlink_resolve(v->a_fpl, target, strlen(target))); } #endif #ifndef _SYS_SYSPROTO_H_ struct vop_access_args { struct vnode *a_vp; accmode_t a_accmode; struct ucred *a_cred; struct thread *a_td; }; #endif static int zfs_freebsd_access(struct vop_access_args *ap) { vnode_t *vp = ap->a_vp; znode_t *zp = VTOZ(vp); accmode_t accmode; int error = 0; if (ap->a_accmode == VEXEC) { if (zfs_fastaccesschk_execute(zp, ap->a_cred) == 0) return (0); } /* * ZFS itself only knowns about VREAD, VWRITE, VEXEC and VAPPEND, */ accmode = ap->a_accmode & (VREAD|VWRITE|VEXEC|VAPPEND); if (accmode != 0) error = zfs_access(zp, accmode, 0, ap->a_cred); /* * VADMIN has to be handled by vaccess(). */ if (error == 0) { accmode = ap->a_accmode & ~(VREAD|VWRITE|VEXEC|VAPPEND); if (accmode != 0) { #if __FreeBSD_version >= 1300105 error = vaccess(vp->v_type, zp->z_mode, zp->z_uid, zp->z_gid, accmode, ap->a_cred); #else error = vaccess(vp->v_type, zp->z_mode, zp->z_uid, zp->z_gid, accmode, ap->a_cred, NULL); #endif } } /* * For VEXEC, ensure that at least one execute bit is set for * non-directories. */ if (error == 0 && (ap->a_accmode & VEXEC) != 0 && vp->v_type != VDIR && (zp->z_mode & (S_IXUSR | S_IXGRP | S_IXOTH)) == 0) { error = EACCES; } return (error); } #ifndef _SYS_SYSPROTO_H_ struct vop_lookup_args { struct vnode *a_dvp; struct vnode **a_vpp; struct componentname *a_cnp; }; #endif static int zfs_freebsd_lookup(struct vop_lookup_args *ap, boolean_t cached) { struct componentname *cnp = ap->a_cnp; char nm[NAME_MAX + 1]; ASSERT3U(cnp->cn_namelen, <, sizeof (nm)); strlcpy(nm, cnp->cn_nameptr, MIN(cnp->cn_namelen + 1, sizeof (nm))); return (zfs_lookup(ap->a_dvp, nm, ap->a_vpp, cnp, cnp->cn_nameiop, cnp->cn_cred, 0, cached)); } static int zfs_freebsd_cachedlookup(struct vop_cachedlookup_args *ap) { return (zfs_freebsd_lookup((struct vop_lookup_args *)ap, B_TRUE)); } #ifndef _SYS_SYSPROTO_H_ struct vop_lookup_args { struct vnode *a_dvp; struct vnode **a_vpp; struct componentname *a_cnp; }; #endif static int zfs_cache_lookup(struct vop_lookup_args *ap) { zfsvfs_t *zfsvfs; zfsvfs = ap->a_dvp->v_mount->mnt_data; if (zfsvfs->z_use_namecache) return (vfs_cache_lookup(ap)); else return (zfs_freebsd_lookup(ap, B_FALSE)); } #ifndef _SYS_SYSPROTO_H_ struct vop_create_args { struct vnode *a_dvp; struct vnode **a_vpp; struct componentname *a_cnp; struct vattr *a_vap; }; #endif static int zfs_freebsd_create(struct vop_create_args *ap) { zfsvfs_t *zfsvfs; struct componentname *cnp = ap->a_cnp; vattr_t *vap = ap->a_vap; znode_t *zp = NULL; int rc, mode; ASSERT(cnp->cn_flags & SAVENAME); vattr_init_mask(vap); mode = vap->va_mode & ALLPERMS; zfsvfs = ap->a_dvp->v_mount->mnt_data; *ap->a_vpp = NULL; rc = zfs_create(VTOZ(ap->a_dvp), cnp->cn_nameptr, vap, !EXCL, mode, &zp, cnp->cn_cred, 0 /* flag */, NULL /* vsecattr */); if (rc == 0) *ap->a_vpp = ZTOV(zp); if (zfsvfs->z_use_namecache && rc == 0 && (cnp->cn_flags & MAKEENTRY) != 0) cache_enter(ap->a_dvp, *ap->a_vpp, cnp); return (rc); } #ifndef _SYS_SYSPROTO_H_ struct vop_remove_args { struct vnode *a_dvp; struct vnode *a_vp; struct componentname *a_cnp; }; #endif static int zfs_freebsd_remove(struct vop_remove_args *ap) { ASSERT(ap->a_cnp->cn_flags & SAVENAME); return (zfs_remove_(ap->a_dvp, ap->a_vp, ap->a_cnp->cn_nameptr, ap->a_cnp->cn_cred)); } #ifndef _SYS_SYSPROTO_H_ struct vop_mkdir_args { struct vnode *a_dvp; struct vnode **a_vpp; struct componentname *a_cnp; struct vattr *a_vap; }; #endif static int zfs_freebsd_mkdir(struct vop_mkdir_args *ap) { vattr_t *vap = ap->a_vap; znode_t *zp = NULL; int rc; ASSERT(ap->a_cnp->cn_flags & SAVENAME); vattr_init_mask(vap); *ap->a_vpp = NULL; rc = zfs_mkdir(VTOZ(ap->a_dvp), ap->a_cnp->cn_nameptr, vap, &zp, ap->a_cnp->cn_cred, 0, NULL); if (rc == 0) *ap->a_vpp = ZTOV(zp); return (rc); } #ifndef _SYS_SYSPROTO_H_ struct vop_rmdir_args { struct vnode *a_dvp; struct vnode *a_vp; struct componentname *a_cnp; }; #endif static int zfs_freebsd_rmdir(struct vop_rmdir_args *ap) { struct componentname *cnp = ap->a_cnp; ASSERT(cnp->cn_flags & SAVENAME); return (zfs_rmdir_(ap->a_dvp, ap->a_vp, cnp->cn_nameptr, cnp->cn_cred)); } #ifndef _SYS_SYSPROTO_H_ struct vop_readdir_args { struct vnode *a_vp; struct uio *a_uio; struct ucred *a_cred; int *a_eofflag; int *a_ncookies; cookie_t **a_cookies; }; #endif static int zfs_freebsd_readdir(struct vop_readdir_args *ap) { zfs_uio_t uio; zfs_uio_init(&uio, ap->a_uio); return (zfs_readdir(ap->a_vp, &uio, ap->a_cred, ap->a_eofflag, ap->a_ncookies, ap->a_cookies)); } #ifndef _SYS_SYSPROTO_H_ struct vop_fsync_args { struct vnode *a_vp; int a_waitfor; struct thread *a_td; }; #endif static int zfs_freebsd_fsync(struct vop_fsync_args *ap) { vop_stdfsync(ap); return (zfs_fsync(VTOZ(ap->a_vp), 0, ap->a_td->td_ucred)); } #ifndef _SYS_SYSPROTO_H_ struct vop_getattr_args { struct vnode *a_vp; struct vattr *a_vap; struct ucred *a_cred; }; #endif static int zfs_freebsd_getattr(struct vop_getattr_args *ap) { vattr_t *vap = ap->a_vap; xvattr_t xvap; ulong_t fflags = 0; int error; xva_init(&xvap); xvap.xva_vattr = *vap; xvap.xva_vattr.va_mask |= AT_XVATTR; /* Convert chflags into ZFS-type flags. */ /* XXX: what about SF_SETTABLE?. */ XVA_SET_REQ(&xvap, XAT_IMMUTABLE); XVA_SET_REQ(&xvap, XAT_APPENDONLY); XVA_SET_REQ(&xvap, XAT_NOUNLINK); XVA_SET_REQ(&xvap, XAT_NODUMP); XVA_SET_REQ(&xvap, XAT_READONLY); XVA_SET_REQ(&xvap, XAT_ARCHIVE); XVA_SET_REQ(&xvap, XAT_SYSTEM); XVA_SET_REQ(&xvap, XAT_HIDDEN); XVA_SET_REQ(&xvap, XAT_REPARSE); XVA_SET_REQ(&xvap, XAT_OFFLINE); XVA_SET_REQ(&xvap, XAT_SPARSE); error = zfs_getattr(ap->a_vp, (vattr_t *)&xvap, 0, ap->a_cred); if (error != 0) return (error); /* Convert ZFS xattr into chflags. */ #define FLAG_CHECK(fflag, xflag, xfield) do { \ if (XVA_ISSET_RTN(&xvap, (xflag)) && (xfield) != 0) \ fflags |= (fflag); \ } while (0) FLAG_CHECK(SF_IMMUTABLE, XAT_IMMUTABLE, xvap.xva_xoptattrs.xoa_immutable); FLAG_CHECK(SF_APPEND, XAT_APPENDONLY, xvap.xva_xoptattrs.xoa_appendonly); FLAG_CHECK(SF_NOUNLINK, XAT_NOUNLINK, xvap.xva_xoptattrs.xoa_nounlink); FLAG_CHECK(UF_ARCHIVE, XAT_ARCHIVE, xvap.xva_xoptattrs.xoa_archive); FLAG_CHECK(UF_NODUMP, XAT_NODUMP, xvap.xva_xoptattrs.xoa_nodump); FLAG_CHECK(UF_READONLY, XAT_READONLY, xvap.xva_xoptattrs.xoa_readonly); FLAG_CHECK(UF_SYSTEM, XAT_SYSTEM, xvap.xva_xoptattrs.xoa_system); FLAG_CHECK(UF_HIDDEN, XAT_HIDDEN, xvap.xva_xoptattrs.xoa_hidden); FLAG_CHECK(UF_REPARSE, XAT_REPARSE, xvap.xva_xoptattrs.xoa_reparse); FLAG_CHECK(UF_OFFLINE, XAT_OFFLINE, xvap.xva_xoptattrs.xoa_offline); FLAG_CHECK(UF_SPARSE, XAT_SPARSE, xvap.xva_xoptattrs.xoa_sparse); #undef FLAG_CHECK *vap = xvap.xva_vattr; vap->va_flags = fflags; return (0); } #ifndef _SYS_SYSPROTO_H_ struct vop_setattr_args { struct vnode *a_vp; struct vattr *a_vap; struct ucred *a_cred; }; #endif static int zfs_freebsd_setattr(struct vop_setattr_args *ap) { vnode_t *vp = ap->a_vp; vattr_t *vap = ap->a_vap; cred_t *cred = ap->a_cred; xvattr_t xvap; ulong_t fflags; uint64_t zflags; vattr_init_mask(vap); vap->va_mask &= ~AT_NOSET; xva_init(&xvap); xvap.xva_vattr = *vap; zflags = VTOZ(vp)->z_pflags; if (vap->va_flags != VNOVAL) { zfsvfs_t *zfsvfs = VTOZ(vp)->z_zfsvfs; int error; if (zfsvfs->z_use_fuids == B_FALSE) return (EOPNOTSUPP); fflags = vap->va_flags; /* * XXX KDM * We need to figure out whether it makes sense to allow * UF_REPARSE through, since we don't really have other * facilities to handle reparse points and zfs_setattr() * doesn't currently allow setting that attribute anyway. */ if ((fflags & ~(SF_IMMUTABLE|SF_APPEND|SF_NOUNLINK|UF_ARCHIVE| UF_NODUMP|UF_SYSTEM|UF_HIDDEN|UF_READONLY|UF_REPARSE| UF_OFFLINE|UF_SPARSE)) != 0) return (EOPNOTSUPP); /* * Unprivileged processes are not permitted to unset system * flags, or modify flags if any system flags are set. * Privileged non-jail processes may not modify system flags * if securelevel > 0 and any existing system flags are set. * Privileged jail processes behave like privileged non-jail * processes if the PR_ALLOW_CHFLAGS permission bit is set; * otherwise, they behave like unprivileged processes. */ if (secpolicy_fs_owner(vp->v_mount, cred) == 0 || spl_priv_check_cred(cred, PRIV_VFS_SYSFLAGS) == 0) { if (zflags & (ZFS_IMMUTABLE | ZFS_APPENDONLY | ZFS_NOUNLINK)) { error = securelevel_gt(cred, 0); if (error != 0) return (error); } } else { /* * Callers may only modify the file flags on * objects they have VADMIN rights for. */ if ((error = VOP_ACCESS(vp, VADMIN, cred, curthread)) != 0) return (error); if (zflags & (ZFS_IMMUTABLE | ZFS_APPENDONLY | ZFS_NOUNLINK)) { return (EPERM); } if (fflags & (SF_IMMUTABLE | SF_APPEND | SF_NOUNLINK)) { return (EPERM); } } #define FLAG_CHANGE(fflag, zflag, xflag, xfield) do { \ if (((fflags & (fflag)) && !(zflags & (zflag))) || \ ((zflags & (zflag)) && !(fflags & (fflag)))) { \ XVA_SET_REQ(&xvap, (xflag)); \ (xfield) = ((fflags & (fflag)) != 0); \ } \ } while (0) /* Convert chflags into ZFS-type flags. */ /* XXX: what about SF_SETTABLE?. */ FLAG_CHANGE(SF_IMMUTABLE, ZFS_IMMUTABLE, XAT_IMMUTABLE, xvap.xva_xoptattrs.xoa_immutable); FLAG_CHANGE(SF_APPEND, ZFS_APPENDONLY, XAT_APPENDONLY, xvap.xva_xoptattrs.xoa_appendonly); FLAG_CHANGE(SF_NOUNLINK, ZFS_NOUNLINK, XAT_NOUNLINK, xvap.xva_xoptattrs.xoa_nounlink); FLAG_CHANGE(UF_ARCHIVE, ZFS_ARCHIVE, XAT_ARCHIVE, xvap.xva_xoptattrs.xoa_archive); FLAG_CHANGE(UF_NODUMP, ZFS_NODUMP, XAT_NODUMP, xvap.xva_xoptattrs.xoa_nodump); FLAG_CHANGE(UF_READONLY, ZFS_READONLY, XAT_READONLY, xvap.xva_xoptattrs.xoa_readonly); FLAG_CHANGE(UF_SYSTEM, ZFS_SYSTEM, XAT_SYSTEM, xvap.xva_xoptattrs.xoa_system); FLAG_CHANGE(UF_HIDDEN, ZFS_HIDDEN, XAT_HIDDEN, xvap.xva_xoptattrs.xoa_hidden); FLAG_CHANGE(UF_REPARSE, ZFS_REPARSE, XAT_REPARSE, xvap.xva_xoptattrs.xoa_reparse); FLAG_CHANGE(UF_OFFLINE, ZFS_OFFLINE, XAT_OFFLINE, xvap.xva_xoptattrs.xoa_offline); FLAG_CHANGE(UF_SPARSE, ZFS_SPARSE, XAT_SPARSE, xvap.xva_xoptattrs.xoa_sparse); #undef FLAG_CHANGE } if (vap->va_birthtime.tv_sec != VNOVAL) { xvap.xva_vattr.va_mask |= AT_XVATTR; XVA_SET_REQ(&xvap, XAT_CREATETIME); } return (zfs_setattr(VTOZ(vp), (vattr_t *)&xvap, 0, cred)); } #ifndef _SYS_SYSPROTO_H_ struct vop_rename_args { struct vnode *a_fdvp; struct vnode *a_fvp; struct componentname *a_fcnp; struct vnode *a_tdvp; struct vnode *a_tvp; struct componentname *a_tcnp; }; #endif static int zfs_freebsd_rename(struct vop_rename_args *ap) { vnode_t *fdvp = ap->a_fdvp; vnode_t *fvp = ap->a_fvp; vnode_t *tdvp = ap->a_tdvp; vnode_t *tvp = ap->a_tvp; int error; ASSERT(ap->a_fcnp->cn_flags & (SAVENAME|SAVESTART)); ASSERT(ap->a_tcnp->cn_flags & (SAVENAME|SAVESTART)); error = zfs_do_rename(fdvp, &fvp, ap->a_fcnp, tdvp, &tvp, ap->a_tcnp, ap->a_fcnp->cn_cred); vrele(fdvp); vrele(fvp); vrele(tdvp); if (tvp != NULL) vrele(tvp); return (error); } #ifndef _SYS_SYSPROTO_H_ struct vop_symlink_args { struct vnode *a_dvp; struct vnode **a_vpp; struct componentname *a_cnp; struct vattr *a_vap; char *a_target; }; #endif static int zfs_freebsd_symlink(struct vop_symlink_args *ap) { struct componentname *cnp = ap->a_cnp; vattr_t *vap = ap->a_vap; znode_t *zp = NULL; #if __FreeBSD_version >= 1300139 char *symlink; size_t symlink_len; #endif int rc; ASSERT(cnp->cn_flags & SAVENAME); vap->va_type = VLNK; /* FreeBSD: Syscall only sets va_mode. */ vattr_init_mask(vap); *ap->a_vpp = NULL; rc = zfs_symlink(VTOZ(ap->a_dvp), cnp->cn_nameptr, vap, ap->a_target, &zp, cnp->cn_cred, 0 /* flags */); if (rc == 0) { *ap->a_vpp = ZTOV(zp); ASSERT_VOP_ELOCKED(ZTOV(zp), __func__); #if __FreeBSD_version >= 1300139 MPASS(zp->z_cached_symlink == NULL); symlink_len = strlen(ap->a_target); symlink = cache_symlink_alloc(symlink_len + 1, M_WAITOK); if (symlink != NULL) { memcpy(symlink, ap->a_target, symlink_len); symlink[symlink_len] = '\0'; atomic_store_rel_ptr((uintptr_t *)&zp->z_cached_symlink, (uintptr_t)symlink); } #endif } return (rc); } #ifndef _SYS_SYSPROTO_H_ struct vop_readlink_args { struct vnode *a_vp; struct uio *a_uio; struct ucred *a_cred; }; #endif static int zfs_freebsd_readlink(struct vop_readlink_args *ap) { zfs_uio_t uio; int error; #if __FreeBSD_version >= 1300139 znode_t *zp = VTOZ(ap->a_vp); char *symlink, *base; size_t symlink_len; bool trycache; #endif zfs_uio_init(&uio, ap->a_uio); #if __FreeBSD_version >= 1300139 trycache = false; if (zfs_uio_segflg(&uio) == UIO_SYSSPACE && zfs_uio_iovcnt(&uio) == 1) { base = zfs_uio_iovbase(&uio, 0); symlink_len = zfs_uio_iovlen(&uio, 0); trycache = true; } #endif error = zfs_readlink(ap->a_vp, &uio, ap->a_cred, NULL); #if __FreeBSD_version >= 1300139 if (atomic_load_ptr(&zp->z_cached_symlink) != NULL || error != 0 || !trycache) { return (error); } symlink_len -= zfs_uio_resid(&uio); symlink = cache_symlink_alloc(symlink_len + 1, M_WAITOK); if (symlink != NULL) { memcpy(symlink, base, symlink_len); symlink[symlink_len] = '\0'; if (!atomic_cmpset_rel_ptr((uintptr_t *)&zp->z_cached_symlink, (uintptr_t)NULL, (uintptr_t)symlink)) { cache_symlink_free(symlink, symlink_len + 1); } } #endif return (error); } #ifndef _SYS_SYSPROTO_H_ struct vop_link_args { struct vnode *a_tdvp; struct vnode *a_vp; struct componentname *a_cnp; }; #endif static int zfs_freebsd_link(struct vop_link_args *ap) { struct componentname *cnp = ap->a_cnp; vnode_t *vp = ap->a_vp; vnode_t *tdvp = ap->a_tdvp; if (tdvp->v_mount != vp->v_mount) return (EXDEV); ASSERT(cnp->cn_flags & SAVENAME); return (zfs_link(VTOZ(tdvp), VTOZ(vp), cnp->cn_nameptr, cnp->cn_cred, 0)); } #ifndef _SYS_SYSPROTO_H_ struct vop_inactive_args { struct vnode *a_vp; struct thread *a_td; }; #endif static int zfs_freebsd_inactive(struct vop_inactive_args *ap) { vnode_t *vp = ap->a_vp; #if __FreeBSD_version >= 1300123 zfs_inactive(vp, curthread->td_ucred, NULL); #else zfs_inactive(vp, ap->a_td->td_ucred, NULL); #endif return (0); } #if __FreeBSD_version >= 1300042 #ifndef _SYS_SYSPROTO_H_ struct vop_need_inactive_args { struct vnode *a_vp; struct thread *a_td; }; #endif static int zfs_freebsd_need_inactive(struct vop_need_inactive_args *ap) { vnode_t *vp = ap->a_vp; znode_t *zp = VTOZ(vp); zfsvfs_t *zfsvfs = zp->z_zfsvfs; int need; if (vn_need_pageq_flush(vp)) return (1); if (!ZFS_TEARDOWN_INACTIVE_TRY_ENTER_READ(zfsvfs)) return (1); need = (zp->z_sa_hdl == NULL || zp->z_unlinked || zp->z_atime_dirty); ZFS_TEARDOWN_INACTIVE_EXIT_READ(zfsvfs); return (need); } #endif #ifndef _SYS_SYSPROTO_H_ struct vop_reclaim_args { struct vnode *a_vp; struct thread *a_td; }; #endif static int zfs_freebsd_reclaim(struct vop_reclaim_args *ap) { vnode_t *vp = ap->a_vp; znode_t *zp = VTOZ(vp); zfsvfs_t *zfsvfs = zp->z_zfsvfs; ASSERT3P(zp, !=, NULL); #if __FreeBSD_version < 1300042 /* Destroy the vm object and flush associated pages. */ vnode_destroy_vobject(vp); #endif /* * z_teardown_inactive_lock protects from a race with * zfs_znode_dmu_fini in zfsvfs_teardown during * force unmount. */ ZFS_TEARDOWN_INACTIVE_ENTER_READ(zfsvfs); if (zp->z_sa_hdl == NULL) zfs_znode_free(zp); else zfs_zinactive(zp); ZFS_TEARDOWN_INACTIVE_EXIT_READ(zfsvfs); vp->v_data = NULL; return (0); } #ifndef _SYS_SYSPROTO_H_ struct vop_fid_args { struct vnode *a_vp; struct fid *a_fid; }; #endif static int zfs_freebsd_fid(struct vop_fid_args *ap) { return (zfs_fid(ap->a_vp, (void *)ap->a_fid, NULL)); } #ifndef _SYS_SYSPROTO_H_ struct vop_pathconf_args { struct vnode *a_vp; int a_name; register_t *a_retval; } *ap; #endif static int zfs_freebsd_pathconf(struct vop_pathconf_args *ap) { ulong_t val; int error; error = zfs_pathconf(ap->a_vp, ap->a_name, &val, curthread->td_ucred, NULL); if (error == 0) { *ap->a_retval = val; return (error); } if (error != EOPNOTSUPP) return (error); switch (ap->a_name) { case _PC_NAME_MAX: *ap->a_retval = NAME_MAX; return (0); #if __FreeBSD_version >= 1400032 case _PC_DEALLOC_PRESENT: *ap->a_retval = 1; return (0); #endif case _PC_PIPE_BUF: if (ap->a_vp->v_type == VDIR || ap->a_vp->v_type == VFIFO) { *ap->a_retval = PIPE_BUF; return (0); } return (EINVAL); default: return (vop_stdpathconf(ap)); } } static int zfs_xattr_compat = 1; static int zfs_check_attrname(const char *name) { /* We don't allow '/' character in attribute name. */ if (strchr(name, '/') != NULL) return (SET_ERROR(EINVAL)); /* We don't allow attribute names that start with a namespace prefix. */ if (ZFS_XA_NS_PREFIX_FORBIDDEN(name)) return (SET_ERROR(EINVAL)); return (0); } /* * FreeBSD's extended attributes namespace defines file name prefix for ZFS' * extended attribute name: * * NAMESPACE XATTR_COMPAT PREFIX * system * freebsd:system: * user 1 (none, can be used to access ZFS * fsattr(5) attributes created on Solaris) * user 0 user. */ static int zfs_create_attrname(int attrnamespace, const char *name, char *attrname, size_t size, boolean_t compat) { const char *namespace, *prefix, *suffix; bzero(attrname, size); switch (attrnamespace) { case EXTATTR_NAMESPACE_USER: if (compat) { /* * This is the default namespace by which we can access * all attributes created on Solaris. */ prefix = namespace = suffix = ""; } else { /* * This is compatible with the user namespace encoding * on Linux prior to xattr_compat, but nothing * else. */ prefix = ""; namespace = "user"; suffix = "."; } break; case EXTATTR_NAMESPACE_SYSTEM: prefix = "freebsd:"; namespace = EXTATTR_NAMESPACE_SYSTEM_STRING; suffix = ":"; break; case EXTATTR_NAMESPACE_EMPTY: default: return (SET_ERROR(EINVAL)); } if (snprintf(attrname, size, "%s%s%s%s", prefix, namespace, suffix, name) >= size) { return (SET_ERROR(ENAMETOOLONG)); } return (0); } static int zfs_ensure_xattr_cached(znode_t *zp) { int error = 0; ASSERT(RW_LOCK_HELD(&zp->z_xattr_lock)); if (zp->z_xattr_cached != NULL) return (0); if (rw_write_held(&zp->z_xattr_lock)) return (zfs_sa_get_xattr(zp)); if (!rw_tryupgrade(&zp->z_xattr_lock)) { rw_exit(&zp->z_xattr_lock); rw_enter(&zp->z_xattr_lock, RW_WRITER); } if (zp->z_xattr_cached == NULL) error = zfs_sa_get_xattr(zp); rw_downgrade(&zp->z_xattr_lock); return (error); } #ifndef _SYS_SYSPROTO_H_ struct vop_getextattr { IN struct vnode *a_vp; IN int a_attrnamespace; IN const char *a_name; INOUT struct uio *a_uio; OUT size_t *a_size; IN struct ucred *a_cred; IN struct thread *a_td; }; #endif static int zfs_getextattr_dir(struct vop_getextattr_args *ap, const char *attrname) { struct thread *td = ap->a_td; struct nameidata nd; struct vattr va; vnode_t *xvp = NULL, *vp; int error, flags; error = zfs_lookup(ap->a_vp, NULL, &xvp, NULL, 0, ap->a_cred, LOOKUP_XATTR, B_FALSE); if (error != 0) return (error); flags = FREAD; #if __FreeBSD_version < 1400043 NDINIT_ATVP(&nd, LOOKUP, NOFOLLOW, UIO_SYSSPACE, attrname, xvp, td); #else NDINIT_ATVP(&nd, LOOKUP, NOFOLLOW, UIO_SYSSPACE, attrname, xvp); #endif error = vn_open_cred(&nd, &flags, 0, VN_OPEN_INVFS, ap->a_cred, NULL); vp = nd.ni_vp; NDFREE(&nd, NDF_ONLY_PNBUF); if (error != 0) return (SET_ERROR(error)); if (ap->a_size != NULL) { error = VOP_GETATTR(vp, &va, ap->a_cred); if (error == 0) *ap->a_size = (size_t)va.va_size; } else if (ap->a_uio != NULL) error = VOP_READ(vp, ap->a_uio, IO_UNIT, ap->a_cred); VOP_UNLOCK1(vp); vn_close(vp, flags, ap->a_cred, td); return (error); } static int zfs_getextattr_sa(struct vop_getextattr_args *ap, const char *attrname) { znode_t *zp = VTOZ(ap->a_vp); uchar_t *nv_value; uint_t nv_size; int error; error = zfs_ensure_xattr_cached(zp); if (error != 0) return (error); ASSERT(RW_LOCK_HELD(&zp->z_xattr_lock)); ASSERT3P(zp->z_xattr_cached, !=, NULL); error = nvlist_lookup_byte_array(zp->z_xattr_cached, attrname, &nv_value, &nv_size); if (error != 0) return (SET_ERROR(error)); if (ap->a_size != NULL) *ap->a_size = nv_size; else if (ap->a_uio != NULL) error = uiomove(nv_value, nv_size, ap->a_uio); if (error != 0) return (SET_ERROR(error)); return (0); } static int zfs_getextattr_impl(struct vop_getextattr_args *ap, boolean_t compat) { znode_t *zp = VTOZ(ap->a_vp); zfsvfs_t *zfsvfs = ZTOZSB(zp); char attrname[EXTATTR_MAXNAMELEN+1]; int error; error = zfs_create_attrname(ap->a_attrnamespace, ap->a_name, attrname, sizeof (attrname), compat); if (error != 0) return (error); error = ENOENT; if (zfsvfs->z_use_sa && zp->z_is_sa) error = zfs_getextattr_sa(ap, attrname); if (error == ENOENT) error = zfs_getextattr_dir(ap, attrname); return (error); } /* * Vnode operation to retrieve a named extended attribute. */ static int zfs_getextattr(struct vop_getextattr_args *ap) { znode_t *zp = VTOZ(ap->a_vp); zfsvfs_t *zfsvfs = ZTOZSB(zp); int error; /* * If the xattr property is off, refuse the request. */ if (!(zfsvfs->z_flags & ZSB_XATTR)) return (SET_ERROR(EOPNOTSUPP)); error = extattr_check_cred(ap->a_vp, ap->a_attrnamespace, ap->a_cred, ap->a_td, VREAD); if (error != 0) return (SET_ERROR(error)); error = zfs_check_attrname(ap->a_name); if (error != 0) return (error); error = ENOENT; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp) rw_enter(&zp->z_xattr_lock, RW_READER); error = zfs_getextattr_impl(ap, zfs_xattr_compat); if ((error == ENOENT || error == ENOATTR) && ap->a_attrnamespace == EXTATTR_NAMESPACE_USER) { /* * Fall back to the alternate namespace format if we failed to * find a user xattr. */ error = zfs_getextattr_impl(ap, !zfs_xattr_compat); } rw_exit(&zp->z_xattr_lock); ZFS_EXIT(zfsvfs); if (error == ENOENT) error = SET_ERROR(ENOATTR); return (error); } #ifndef _SYS_SYSPROTO_H_ struct vop_deleteextattr { IN struct vnode *a_vp; IN int a_attrnamespace; IN const char *a_name; IN struct ucred *a_cred; IN struct thread *a_td; }; #endif static int zfs_deleteextattr_dir(struct vop_deleteextattr_args *ap, const char *attrname) { struct nameidata nd; vnode_t *xvp = NULL, *vp; int error; error = zfs_lookup(ap->a_vp, NULL, &xvp, NULL, 0, ap->a_cred, LOOKUP_XATTR, B_FALSE); if (error != 0) return (error); #if __FreeBSD_version < 1400043 NDINIT_ATVP(&nd, DELETE, NOFOLLOW | LOCKPARENT | LOCKLEAF, UIO_SYSSPACE, attrname, xvp, ap->a_td); #else NDINIT_ATVP(&nd, DELETE, NOFOLLOW | LOCKPARENT | LOCKLEAF, UIO_SYSSPACE, attrname, xvp); #endif error = namei(&nd); vp = nd.ni_vp; if (error != 0) { NDFREE(&nd, NDF_ONLY_PNBUF); return (SET_ERROR(error)); } error = VOP_REMOVE(nd.ni_dvp, vp, &nd.ni_cnd); NDFREE(&nd, NDF_ONLY_PNBUF); vput(nd.ni_dvp); if (vp == nd.ni_dvp) vrele(vp); else vput(vp); return (error); } static int zfs_deleteextattr_sa(struct vop_deleteextattr_args *ap, const char *attrname) { znode_t *zp = VTOZ(ap->a_vp); nvlist_t *nvl; int error; error = zfs_ensure_xattr_cached(zp); if (error != 0) return (error); ASSERT(RW_WRITE_HELD(&zp->z_xattr_lock)); ASSERT3P(zp->z_xattr_cached, !=, NULL); nvl = zp->z_xattr_cached; error = nvlist_remove(nvl, attrname, DATA_TYPE_BYTE_ARRAY); if (error != 0) error = SET_ERROR(error); else - error = zfs_sa_set_xattr(zp); + error = zfs_sa_set_xattr(zp, attrname, NULL, 0); if (error != 0) { zp->z_xattr_cached = NULL; nvlist_free(nvl); } return (error); } static int zfs_deleteextattr_impl(struct vop_deleteextattr_args *ap, boolean_t compat) { znode_t *zp = VTOZ(ap->a_vp); zfsvfs_t *zfsvfs = ZTOZSB(zp); char attrname[EXTATTR_MAXNAMELEN+1]; int error; error = zfs_create_attrname(ap->a_attrnamespace, ap->a_name, attrname, sizeof (attrname), compat); if (error != 0) return (error); error = ENOENT; if (zfsvfs->z_use_sa && zp->z_is_sa) error = zfs_deleteextattr_sa(ap, attrname); if (error == ENOENT) error = zfs_deleteextattr_dir(ap, attrname); return (error); } /* * Vnode operation to remove a named attribute. */ static int zfs_deleteextattr(struct vop_deleteextattr_args *ap) { znode_t *zp = VTOZ(ap->a_vp); zfsvfs_t *zfsvfs = ZTOZSB(zp); int error; /* * If the xattr property is off, refuse the request. */ if (!(zfsvfs->z_flags & ZSB_XATTR)) return (SET_ERROR(EOPNOTSUPP)); error = extattr_check_cred(ap->a_vp, ap->a_attrnamespace, ap->a_cred, ap->a_td, VWRITE); if (error != 0) return (SET_ERROR(error)); error = zfs_check_attrname(ap->a_name); if (error != 0) return (error); ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); rw_enter(&zp->z_xattr_lock, RW_WRITER); error = zfs_deleteextattr_impl(ap, zfs_xattr_compat); if ((error == ENOENT || error == ENOATTR) && ap->a_attrnamespace == EXTATTR_NAMESPACE_USER) { /* * Fall back to the alternate namespace format if we failed to * find a user xattr. */ error = zfs_deleteextattr_impl(ap, !zfs_xattr_compat); } rw_exit(&zp->z_xattr_lock); ZFS_EXIT(zfsvfs); if (error == ENOENT) error = SET_ERROR(ENOATTR); return (error); } #ifndef _SYS_SYSPROTO_H_ struct vop_setextattr { IN struct vnode *a_vp; IN int a_attrnamespace; IN const char *a_name; INOUT struct uio *a_uio; IN struct ucred *a_cred; IN struct thread *a_td; }; #endif static int zfs_setextattr_dir(struct vop_setextattr_args *ap, const char *attrname) { struct thread *td = ap->a_td; struct nameidata nd; struct vattr va; vnode_t *xvp = NULL, *vp; int error, flags; error = zfs_lookup(ap->a_vp, NULL, &xvp, NULL, 0, ap->a_cred, LOOKUP_XATTR | CREATE_XATTR_DIR, B_FALSE); if (error != 0) return (error); flags = FFLAGS(O_WRONLY | O_CREAT); #if __FreeBSD_version < 1400043 NDINIT_ATVP(&nd, LOOKUP, NOFOLLOW, UIO_SYSSPACE, attrname, xvp, td); #else NDINIT_ATVP(&nd, LOOKUP, NOFOLLOW, UIO_SYSSPACE, attrname, xvp); #endif error = vn_open_cred(&nd, &flags, 0600, VN_OPEN_INVFS, ap->a_cred, NULL); vp = nd.ni_vp; NDFREE(&nd, NDF_ONLY_PNBUF); if (error != 0) return (SET_ERROR(error)); VATTR_NULL(&va); va.va_size = 0; error = VOP_SETATTR(vp, &va, ap->a_cred); if (error == 0) VOP_WRITE(vp, ap->a_uio, IO_UNIT, ap->a_cred); VOP_UNLOCK1(vp); vn_close(vp, flags, ap->a_cred, td); return (error); } static int zfs_setextattr_sa(struct vop_setextattr_args *ap, const char *attrname) { znode_t *zp = VTOZ(ap->a_vp); nvlist_t *nvl; size_t sa_size; int error; error = zfs_ensure_xattr_cached(zp); if (error != 0) return (error); ASSERT(RW_WRITE_HELD(&zp->z_xattr_lock)); ASSERT3P(zp->z_xattr_cached, !=, NULL); nvl = zp->z_xattr_cached; size_t entry_size = ap->a_uio->uio_resid; if (entry_size > DXATTR_MAX_ENTRY_SIZE) return (SET_ERROR(EFBIG)); error = nvlist_size(nvl, &sa_size, NV_ENCODE_XDR); if (error != 0) return (SET_ERROR(error)); if (sa_size > DXATTR_MAX_SA_SIZE) return (SET_ERROR(EFBIG)); uchar_t *buf = kmem_alloc(entry_size, KM_SLEEP); error = uiomove(buf, entry_size, ap->a_uio); if (error != 0) { error = SET_ERROR(error); } else { error = nvlist_add_byte_array(nvl, attrname, buf, entry_size); if (error != 0) error = SET_ERROR(error); } - kmem_free(buf, entry_size); if (error == 0) - error = zfs_sa_set_xattr(zp); + error = zfs_sa_set_xattr(zp, attrname, buf, entry_size); + kmem_free(buf, entry_size); if (error != 0) { zp->z_xattr_cached = NULL; nvlist_free(nvl); } return (error); } static int zfs_setextattr_impl(struct vop_setextattr_args *ap, boolean_t compat) { znode_t *zp = VTOZ(ap->a_vp); zfsvfs_t *zfsvfs = ZTOZSB(zp); char attrname[EXTATTR_MAXNAMELEN+1]; int error; error = zfs_create_attrname(ap->a_attrnamespace, ap->a_name, attrname, sizeof (attrname), compat); if (error != 0) return (error); struct vop_deleteextattr_args vda = { .a_vp = ap->a_vp, .a_attrnamespace = ap->a_attrnamespace, .a_name = ap->a_name, .a_cred = ap->a_cred, .a_td = ap->a_td, }; error = ENOENT; if (zfsvfs->z_use_sa && zp->z_is_sa && zfsvfs->z_xattr_sa) { error = zfs_setextattr_sa(ap, attrname); if (error == 0) { /* * Successfully put into SA, we need to clear the one * in dir if present. */ zfs_deleteextattr_dir(&vda, attrname); } } if (error != 0) { error = zfs_setextattr_dir(ap, attrname); if (error == 0 && zp->z_is_sa) { /* * Successfully put into dir, we need to clear the one * in SA if present. */ zfs_deleteextattr_sa(&vda, attrname); } } if (error == 0 && ap->a_attrnamespace == EXTATTR_NAMESPACE_USER) { /* * Also clear all versions of the alternate compat name. */ zfs_deleteextattr_impl(&vda, !compat); } return (error); } /* * Vnode operation to set a named attribute. */ static int zfs_setextattr(struct vop_setextattr_args *ap) { znode_t *zp = VTOZ(ap->a_vp); zfsvfs_t *zfsvfs = ZTOZSB(zp); int error; /* * If the xattr property is off, refuse the request. */ if (!(zfsvfs->z_flags & ZSB_XATTR)) return (SET_ERROR(EOPNOTSUPP)); error = extattr_check_cred(ap->a_vp, ap->a_attrnamespace, ap->a_cred, ap->a_td, VWRITE); if (error != 0) return (SET_ERROR(error)); error = zfs_check_attrname(ap->a_name); if (error != 0) return (error); ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); rw_enter(&zp->z_xattr_lock, RW_WRITER); error = zfs_setextattr_impl(ap, zfs_xattr_compat); rw_exit(&zp->z_xattr_lock); ZFS_EXIT(zfsvfs); return (error); } #ifndef _SYS_SYSPROTO_H_ struct vop_listextattr { IN struct vnode *a_vp; IN int a_attrnamespace; INOUT struct uio *a_uio; OUT size_t *a_size; IN struct ucred *a_cred; IN struct thread *a_td; }; #endif static int zfs_listextattr_dir(struct vop_listextattr_args *ap, const char *attrprefix) { struct thread *td = ap->a_td; struct nameidata nd; uint8_t dirbuf[sizeof (struct dirent)]; struct iovec aiov; struct uio auio; vnode_t *xvp = NULL, *vp; int error, eof; error = zfs_lookup(ap->a_vp, NULL, &xvp, NULL, 0, ap->a_cred, LOOKUP_XATTR, B_FALSE); if (error != 0) { /* * ENOATTR means that the EA directory does not yet exist, * i.e. there are no extended attributes there. */ if (error == ENOATTR) error = 0; return (error); } #if __FreeBSD_version < 1400043 NDINIT_ATVP(&nd, LOOKUP, NOFOLLOW | LOCKLEAF | LOCKSHARED, UIO_SYSSPACE, ".", xvp, td); #else NDINIT_ATVP(&nd, LOOKUP, NOFOLLOW | LOCKLEAF | LOCKSHARED, UIO_SYSSPACE, ".", xvp); #endif error = namei(&nd); vp = nd.ni_vp; NDFREE(&nd, NDF_ONLY_PNBUF); if (error != 0) return (SET_ERROR(error)); auio.uio_iov = &aiov; auio.uio_iovcnt = 1; auio.uio_segflg = UIO_SYSSPACE; auio.uio_td = td; auio.uio_rw = UIO_READ; auio.uio_offset = 0; size_t plen = strlen(attrprefix); do { aiov.iov_base = (void *)dirbuf; aiov.iov_len = sizeof (dirbuf); auio.uio_resid = sizeof (dirbuf); error = VOP_READDIR(vp, &auio, ap->a_cred, &eof, NULL, NULL); if (error != 0) break; int done = sizeof (dirbuf) - auio.uio_resid; for (int pos = 0; pos < done; ) { struct dirent *dp = (struct dirent *)(dirbuf + pos); pos += dp->d_reclen; /* * XXX: Temporarily we also accept DT_UNKNOWN, as this * is what we get when attribute was created on Solaris. */ if (dp->d_type != DT_REG && dp->d_type != DT_UNKNOWN) continue; else if (plen == 0 && ZFS_XA_NS_PREFIX_FORBIDDEN(dp->d_name)) continue; else if (strncmp(dp->d_name, attrprefix, plen) != 0) continue; uint8_t nlen = dp->d_namlen - plen; if (ap->a_size != NULL) { *ap->a_size += 1 + nlen; } else if (ap->a_uio != NULL) { /* * Format of extattr name entry is one byte for * length and the rest for name. */ error = uiomove(&nlen, 1, ap->a_uio); if (error == 0) { char *namep = dp->d_name + plen; error = uiomove(namep, nlen, ap->a_uio); } if (error != 0) { error = SET_ERROR(error); break; } } } } while (!eof && error == 0); vput(vp); return (error); } static int zfs_listextattr_sa(struct vop_listextattr_args *ap, const char *attrprefix) { znode_t *zp = VTOZ(ap->a_vp); int error; error = zfs_ensure_xattr_cached(zp); if (error != 0) return (error); ASSERT(RW_LOCK_HELD(&zp->z_xattr_lock)); ASSERT3P(zp->z_xattr_cached, !=, NULL); size_t plen = strlen(attrprefix); nvpair_t *nvp = NULL; while ((nvp = nvlist_next_nvpair(zp->z_xattr_cached, nvp)) != NULL) { ASSERT3U(nvpair_type(nvp), ==, DATA_TYPE_BYTE_ARRAY); const char *name = nvpair_name(nvp); if (plen == 0 && ZFS_XA_NS_PREFIX_FORBIDDEN(name)) continue; else if (strncmp(name, attrprefix, plen) != 0) continue; uint8_t nlen = strlen(name) - plen; if (ap->a_size != NULL) { *ap->a_size += 1 + nlen; } else if (ap->a_uio != NULL) { /* * Format of extattr name entry is one byte for * length and the rest for name. */ error = uiomove(&nlen, 1, ap->a_uio); if (error == 0) { char *namep = __DECONST(char *, name) + plen; error = uiomove(namep, nlen, ap->a_uio); } if (error != 0) { error = SET_ERROR(error); break; } } } return (error); } static int zfs_listextattr_impl(struct vop_listextattr_args *ap, boolean_t compat) { znode_t *zp = VTOZ(ap->a_vp); zfsvfs_t *zfsvfs = ZTOZSB(zp); char attrprefix[16]; int error; error = zfs_create_attrname(ap->a_attrnamespace, "", attrprefix, sizeof (attrprefix), compat); if (error != 0) return (error); if (zfsvfs->z_use_sa && zp->z_is_sa) error = zfs_listextattr_sa(ap, attrprefix); if (error == 0) error = zfs_listextattr_dir(ap, attrprefix); return (error); } /* * Vnode operation to retrieve extended attributes on a vnode. */ static int zfs_listextattr(struct vop_listextattr_args *ap) { znode_t *zp = VTOZ(ap->a_vp); zfsvfs_t *zfsvfs = ZTOZSB(zp); int error; if (ap->a_size != NULL) *ap->a_size = 0; /* * If the xattr property is off, refuse the request. */ if (!(zfsvfs->z_flags & ZSB_XATTR)) return (SET_ERROR(EOPNOTSUPP)); error = extattr_check_cred(ap->a_vp, ap->a_attrnamespace, ap->a_cred, ap->a_td, VREAD); if (error != 0) return (SET_ERROR(error)); ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); rw_enter(&zp->z_xattr_lock, RW_READER); error = zfs_listextattr_impl(ap, zfs_xattr_compat); if (error == 0 && ap->a_attrnamespace == EXTATTR_NAMESPACE_USER) { /* Also list user xattrs with the alternate format. */ error = zfs_listextattr_impl(ap, !zfs_xattr_compat); } rw_exit(&zp->z_xattr_lock); ZFS_EXIT(zfsvfs); return (error); } #ifndef _SYS_SYSPROTO_H_ struct vop_getacl_args { struct vnode *vp; acl_type_t type; struct acl *aclp; struct ucred *cred; struct thread *td; }; #endif static int zfs_freebsd_getacl(struct vop_getacl_args *ap) { int error; vsecattr_t vsecattr; if (ap->a_type != ACL_TYPE_NFS4) return (EINVAL); vsecattr.vsa_mask = VSA_ACE | VSA_ACECNT; if ((error = zfs_getsecattr(VTOZ(ap->a_vp), &vsecattr, 0, ap->a_cred))) return (error); error = acl_from_aces(ap->a_aclp, vsecattr.vsa_aclentp, vsecattr.vsa_aclcnt); if (vsecattr.vsa_aclentp != NULL) kmem_free(vsecattr.vsa_aclentp, vsecattr.vsa_aclentsz); return (error); } #ifndef _SYS_SYSPROTO_H_ struct vop_setacl_args { struct vnode *vp; acl_type_t type; struct acl *aclp; struct ucred *cred; struct thread *td; }; #endif static int zfs_freebsd_setacl(struct vop_setacl_args *ap) { int error; vsecattr_t vsecattr; int aclbsize; /* size of acl list in bytes */ aclent_t *aaclp; if (ap->a_type != ACL_TYPE_NFS4) return (EINVAL); if (ap->a_aclp == NULL) return (EINVAL); if (ap->a_aclp->acl_cnt < 1 || ap->a_aclp->acl_cnt > MAX_ACL_ENTRIES) return (EINVAL); /* * With NFSv4 ACLs, chmod(2) may need to add additional entries, * splitting every entry into two and appending "canonical six" * entries at the end. Don't allow for setting an ACL that would * cause chmod(2) to run out of ACL entries. */ if (ap->a_aclp->acl_cnt * 2 + 6 > ACL_MAX_ENTRIES) return (ENOSPC); error = acl_nfs4_check(ap->a_aclp, ap->a_vp->v_type == VDIR); if (error != 0) return (error); vsecattr.vsa_mask = VSA_ACE; aclbsize = ap->a_aclp->acl_cnt * sizeof (ace_t); vsecattr.vsa_aclentp = kmem_alloc(aclbsize, KM_SLEEP); aaclp = vsecattr.vsa_aclentp; vsecattr.vsa_aclentsz = aclbsize; aces_from_acl(vsecattr.vsa_aclentp, &vsecattr.vsa_aclcnt, ap->a_aclp); error = zfs_setsecattr(VTOZ(ap->a_vp), &vsecattr, 0, ap->a_cred); kmem_free(aaclp, aclbsize); return (error); } #ifndef _SYS_SYSPROTO_H_ struct vop_aclcheck_args { struct vnode *vp; acl_type_t type; struct acl *aclp; struct ucred *cred; struct thread *td; }; #endif static int zfs_freebsd_aclcheck(struct vop_aclcheck_args *ap) { return (EOPNOTSUPP); } static int zfs_vptocnp(struct vop_vptocnp_args *ap) { vnode_t *covered_vp; vnode_t *vp = ap->a_vp; zfsvfs_t *zfsvfs = vp->v_vfsp->vfs_data; znode_t *zp = VTOZ(vp); int ltype; int error; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); /* * If we are a snapshot mounted under .zfs, run the operation * on the covered vnode. */ if (zp->z_id != zfsvfs->z_root || zfsvfs->z_parent == zfsvfs) { char name[MAXNAMLEN + 1]; znode_t *dzp; size_t len; error = zfs_znode_parent_and_name(zp, &dzp, name); if (error == 0) { len = strlen(name); if (*ap->a_buflen < len) error = SET_ERROR(ENOMEM); } if (error == 0) { *ap->a_buflen -= len; bcopy(name, ap->a_buf + *ap->a_buflen, len); *ap->a_vpp = ZTOV(dzp); } ZFS_EXIT(zfsvfs); return (error); } ZFS_EXIT(zfsvfs); covered_vp = vp->v_mount->mnt_vnodecovered; #if __FreeBSD_version >= 1300045 enum vgetstate vs = vget_prep(covered_vp); #else vhold(covered_vp); #endif ltype = VOP_ISLOCKED(vp); VOP_UNLOCK1(vp); #if __FreeBSD_version >= 1300045 error = vget_finish(covered_vp, LK_SHARED, vs); #else error = vget(covered_vp, LK_SHARED | LK_VNHELD, curthread); #endif if (error == 0) { #if __FreeBSD_version >= 1300123 error = VOP_VPTOCNP(covered_vp, ap->a_vpp, ap->a_buf, ap->a_buflen); #else error = VOP_VPTOCNP(covered_vp, ap->a_vpp, ap->a_cred, ap->a_buf, ap->a_buflen); #endif vput(covered_vp); } vn_lock(vp, ltype | LK_RETRY); if (VN_IS_DOOMED(vp)) error = SET_ERROR(ENOENT); return (error); } #if __FreeBSD_version >= 1400032 static int zfs_deallocate(struct vop_deallocate_args *ap) { znode_t *zp = VTOZ(ap->a_vp); zfsvfs_t *zfsvfs = zp->z_zfsvfs; zilog_t *zilog; off_t off, len, file_sz; int error; ZFS_ENTER(zfsvfs); ZFS_VERIFY_ZP(zp); /* * Callers might not be able to detect properly that we are read-only, * so check it explicitly here. */ if (zfs_is_readonly(zfsvfs)) { ZFS_EXIT(zfsvfs); return (SET_ERROR(EROFS)); } zilog = zfsvfs->z_log; off = *ap->a_offset; len = *ap->a_len; file_sz = zp->z_size; if (off + len > file_sz) len = file_sz - off; /* Fast path for out-of-range request. */ if (len <= 0) { *ap->a_len = 0; ZFS_EXIT(zfsvfs); return (0); } error = zfs_freesp(zp, off, len, O_RDWR, TRUE); if (error == 0) { if (zfsvfs->z_os->os_sync == ZFS_SYNC_ALWAYS || (ap->a_ioflag & IO_SYNC) != 0) zil_commit(zilog, zp->z_id); *ap->a_offset = off + len; *ap->a_len = 0; } ZFS_EXIT(zfsvfs); return (error); } #endif struct vop_vector zfs_vnodeops; struct vop_vector zfs_fifoops; struct vop_vector zfs_shareops; struct vop_vector zfs_vnodeops = { .vop_default = &default_vnodeops, .vop_inactive = zfs_freebsd_inactive, #if __FreeBSD_version >= 1300042 .vop_need_inactive = zfs_freebsd_need_inactive, #endif .vop_reclaim = zfs_freebsd_reclaim, #if __FreeBSD_version >= 1300102 .vop_fplookup_vexec = zfs_freebsd_fplookup_vexec, #endif #if __FreeBSD_version >= 1300139 .vop_fplookup_symlink = zfs_freebsd_fplookup_symlink, #endif .vop_access = zfs_freebsd_access, .vop_allocate = VOP_EINVAL, #if __FreeBSD_version >= 1400032 .vop_deallocate = zfs_deallocate, #endif .vop_lookup = zfs_cache_lookup, .vop_cachedlookup = zfs_freebsd_cachedlookup, .vop_getattr = zfs_freebsd_getattr, .vop_setattr = zfs_freebsd_setattr, .vop_create = zfs_freebsd_create, .vop_mknod = (vop_mknod_t *)zfs_freebsd_create, .vop_mkdir = zfs_freebsd_mkdir, .vop_readdir = zfs_freebsd_readdir, .vop_fsync = zfs_freebsd_fsync, .vop_open = zfs_freebsd_open, .vop_close = zfs_freebsd_close, .vop_rmdir = zfs_freebsd_rmdir, .vop_ioctl = zfs_freebsd_ioctl, .vop_link = zfs_freebsd_link, .vop_symlink = zfs_freebsd_symlink, .vop_readlink = zfs_freebsd_readlink, .vop_read = zfs_freebsd_read, .vop_write = zfs_freebsd_write, .vop_remove = zfs_freebsd_remove, .vop_rename = zfs_freebsd_rename, .vop_pathconf = zfs_freebsd_pathconf, .vop_bmap = zfs_freebsd_bmap, .vop_fid = zfs_freebsd_fid, .vop_getextattr = zfs_getextattr, .vop_deleteextattr = zfs_deleteextattr, .vop_setextattr = zfs_setextattr, .vop_listextattr = zfs_listextattr, .vop_getacl = zfs_freebsd_getacl, .vop_setacl = zfs_freebsd_setacl, .vop_aclcheck = zfs_freebsd_aclcheck, .vop_getpages = zfs_freebsd_getpages, .vop_putpages = zfs_freebsd_putpages, .vop_vptocnp = zfs_vptocnp, #if __FreeBSD_version >= 1300064 .vop_lock1 = vop_lock, .vop_unlock = vop_unlock, .vop_islocked = vop_islocked, #endif #if __FreeBSD_version >= 1400043 .vop_add_writecount = vop_stdadd_writecount_nomsync, #endif }; VFS_VOP_VECTOR_REGISTER(zfs_vnodeops); struct vop_vector zfs_fifoops = { .vop_default = &fifo_specops, .vop_fsync = zfs_freebsd_fsync, #if __FreeBSD_version >= 1300102 .vop_fplookup_vexec = zfs_freebsd_fplookup_vexec, #endif #if __FreeBSD_version >= 1300139 .vop_fplookup_symlink = zfs_freebsd_fplookup_symlink, #endif .vop_access = zfs_freebsd_access, .vop_getattr = zfs_freebsd_getattr, .vop_inactive = zfs_freebsd_inactive, .vop_read = VOP_PANIC, .vop_reclaim = zfs_freebsd_reclaim, .vop_setattr = zfs_freebsd_setattr, .vop_write = VOP_PANIC, .vop_pathconf = zfs_freebsd_pathconf, .vop_fid = zfs_freebsd_fid, .vop_getacl = zfs_freebsd_getacl, .vop_setacl = zfs_freebsd_setacl, .vop_aclcheck = zfs_freebsd_aclcheck, #if __FreeBSD_version >= 1400043 .vop_add_writecount = vop_stdadd_writecount_nomsync, #endif }; VFS_VOP_VECTOR_REGISTER(zfs_fifoops); /* * special share hidden files vnode operations template */ struct vop_vector zfs_shareops = { .vop_default = &default_vnodeops, #if __FreeBSD_version >= 1300121 .vop_fplookup_vexec = VOP_EAGAIN, #endif #if __FreeBSD_version >= 1300139 .vop_fplookup_symlink = VOP_EAGAIN, #endif .vop_access = zfs_freebsd_access, .vop_inactive = zfs_freebsd_inactive, .vop_reclaim = zfs_freebsd_reclaim, .vop_fid = zfs_freebsd_fid, .vop_pathconf = zfs_freebsd_pathconf, #if __FreeBSD_version >= 1400043 .vop_add_writecount = vop_stdadd_writecount_nomsync, #endif }; VFS_VOP_VECTOR_REGISTER(zfs_shareops); ZFS_MODULE_PARAM(zfs, zfs_, xattr_compat, INT, ZMOD_RW, "Use legacy ZFS xattr naming for writing new user namespace xattrs"); diff --git a/module/os/linux/zfs/zpl_xattr.c b/module/os/linux/zfs/zpl_xattr.c index ce1815771f71..3b8ac517ada9 100644 --- a/module/os/linux/zfs/zpl_xattr.c +++ b/module/os/linux/zfs/zpl_xattr.c @@ -1,1599 +1,1599 @@ /* * 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) 2011, Lawrence Livermore National Security, LLC. * * Extended attributes (xattr) on Solaris are implemented as files * which exist in a hidden xattr directory. These extended attributes * can be accessed using the attropen() system call which opens * the extended attribute. It can then be manipulated just like * a standard file descriptor. This has a couple advantages such * as practically no size limit on the file, and the extended * attributes permissions may differ from those of the parent file. * This interface is really quite clever, but it's also completely * different than what is supported on Linux. It also comes with a * steep performance penalty when accessing small xattrs because they * are not stored with the parent file. * * Under Linux extended attributes are manipulated by the system * calls getxattr(2), setxattr(2), and listxattr(2). They consider * extended attributes to be name/value pairs where the name is a * NULL terminated string. The name must also include one of the * following namespace prefixes: * * user - No restrictions and is available to user applications. * trusted - Restricted to kernel and root (CAP_SYS_ADMIN) use. * system - Used for access control lists (system.nfs4_acl, etc). * security - Used by SELinux to store a files security context. * * The value under Linux to limited to 65536 bytes of binary data. * In practice, individual xattrs tend to be much smaller than this * and are typically less than 100 bytes. A good example of this * are the security.selinux xattrs which are less than 100 bytes and * exist for every file when xattr labeling is enabled. * * The Linux xattr implementation has been written to take advantage of * this typical usage. When the dataset property 'xattr=sa' is set, * then xattrs will be preferentially stored as System Attributes (SA). * This allows tiny xattrs (~100 bytes) to be stored with the dnode and * up to 64k of xattrs to be stored in the spill block. If additional * xattr space is required, which is unlikely under Linux, they will * be stored using the traditional directory approach. * * This optimization results in roughly a 3x performance improvement * when accessing xattrs because it avoids the need to perform a seek * for every xattr value. When multiple xattrs are stored per-file * the performance improvements are even greater because all of the * xattrs stored in the spill block will be cached. * * However, by default SA based xattrs are disabled in the Linux port * to maximize compatibility with other implementations. If you do * enable SA based xattrs then they will not be visible on platforms * which do not support this feature. * * NOTE: One additional consequence of the xattr directory implementation * is that when an extended attribute is manipulated an inode is created. * This inode will exist in the Linux inode cache but there will be no * associated entry in the dentry cache which references it. This is * safe but it may result in some confusion. Enabling SA based xattrs * largely avoids the issue except in the overflow case. */ #include #include #include #include #include #include enum xattr_permission { XAPERM_DENY, XAPERM_ALLOW, XAPERM_COMPAT, }; typedef struct xattr_filldir { size_t size; size_t offset; char *buf; struct dentry *dentry; } xattr_filldir_t; static enum xattr_permission zpl_xattr_permission(xattr_filldir_t *, const char *, int); static int zfs_xattr_compat = 0; /* * Determine is a given xattr name should be visible and if so copy it * in to the provided buffer (xf->buf). */ static int zpl_xattr_filldir(xattr_filldir_t *xf, const char *name, int name_len) { enum xattr_permission perm; /* Check permissions using the per-namespace list xattr handler. */ perm = zpl_xattr_permission(xf, name, name_len); if (perm == XAPERM_DENY) return (0); /* Prefix the name with "user." if it does not have a namespace. */ if (perm == XAPERM_COMPAT) { if (xf->buf) { if (xf->offset + XATTR_USER_PREFIX_LEN + 1 > xf->size) return (-ERANGE); memcpy(xf->buf + xf->offset, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN); xf->buf[xf->offset + XATTR_USER_PREFIX_LEN] = '\0'; } xf->offset += XATTR_USER_PREFIX_LEN; } /* When xf->buf is NULL only calculate the required size. */ if (xf->buf) { if (xf->offset + name_len + 1 > xf->size) return (-ERANGE); memcpy(xf->buf + xf->offset, name, name_len); xf->buf[xf->offset + name_len] = '\0'; } xf->offset += (name_len + 1); return (0); } /* * Read as many directory entry names as will fit in to the provided buffer, * or when no buffer is provided calculate the required buffer size. */ static int zpl_xattr_readdir(struct inode *dxip, xattr_filldir_t *xf) { zap_cursor_t zc; zap_attribute_t zap; int error; zap_cursor_init(&zc, ITOZSB(dxip)->z_os, ITOZ(dxip)->z_id); while ((error = -zap_cursor_retrieve(&zc, &zap)) == 0) { if (zap.za_integer_length != 8 || zap.za_num_integers != 1) { error = -ENXIO; break; } error = zpl_xattr_filldir(xf, zap.za_name, strlen(zap.za_name)); if (error) break; zap_cursor_advance(&zc); } zap_cursor_fini(&zc); if (error == -ENOENT) error = 0; return (error); } static ssize_t zpl_xattr_list_dir(xattr_filldir_t *xf, cred_t *cr) { struct inode *ip = xf->dentry->d_inode; struct inode *dxip = NULL; znode_t *dxzp; int error; /* Lookup the xattr directory */ error = -zfs_lookup(ITOZ(ip), NULL, &dxzp, LOOKUP_XATTR, cr, NULL, NULL); if (error) { if (error == -ENOENT) error = 0; return (error); } dxip = ZTOI(dxzp); error = zpl_xattr_readdir(dxip, xf); iput(dxip); return (error); } static ssize_t zpl_xattr_list_sa(xattr_filldir_t *xf) { znode_t *zp = ITOZ(xf->dentry->d_inode); nvpair_t *nvp = NULL; int error = 0; mutex_enter(&zp->z_lock); if (zp->z_xattr_cached == NULL) error = -zfs_sa_get_xattr(zp); mutex_exit(&zp->z_lock); if (error) return (error); ASSERT(zp->z_xattr_cached); while ((nvp = nvlist_next_nvpair(zp->z_xattr_cached, nvp)) != NULL) { ASSERT3U(nvpair_type(nvp), ==, DATA_TYPE_BYTE_ARRAY); error = zpl_xattr_filldir(xf, nvpair_name(nvp), strlen(nvpair_name(nvp))); if (error) return (error); } return (0); } ssize_t zpl_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size) { znode_t *zp = ITOZ(dentry->d_inode); zfsvfs_t *zfsvfs = ZTOZSB(zp); xattr_filldir_t xf = { buffer_size, 0, buffer, dentry }; cred_t *cr = CRED(); fstrans_cookie_t cookie; int error = 0; crhold(cr); cookie = spl_fstrans_mark(); ZPL_ENTER(zfsvfs); ZPL_VERIFY_ZP(zp); rw_enter(&zp->z_xattr_lock, RW_READER); if (zfsvfs->z_use_sa && zp->z_is_sa) { error = zpl_xattr_list_sa(&xf); if (error) goto out; } error = zpl_xattr_list_dir(&xf, cr); if (error) goto out; error = xf.offset; out: rw_exit(&zp->z_xattr_lock); ZPL_EXIT(zfsvfs); spl_fstrans_unmark(cookie); crfree(cr); return (error); } static int zpl_xattr_get_dir(struct inode *ip, const char *name, void *value, size_t size, cred_t *cr) { fstrans_cookie_t cookie; struct inode *xip = NULL; znode_t *dxzp = NULL; znode_t *xzp = NULL; int error; /* Lookup the xattr directory */ error = -zfs_lookup(ITOZ(ip), NULL, &dxzp, LOOKUP_XATTR, cr, NULL, NULL); if (error) goto out; /* Lookup a specific xattr name in the directory */ error = -zfs_lookup(dxzp, (char *)name, &xzp, 0, cr, NULL, NULL); if (error) goto out; xip = ZTOI(xzp); if (!size) { error = i_size_read(xip); goto out; } if (size < i_size_read(xip)) { error = -ERANGE; goto out; } struct iovec iov; iov.iov_base = (void *)value; iov.iov_len = size; zfs_uio_t uio; zfs_uio_iovec_init(&uio, &iov, 1, 0, UIO_SYSSPACE, size, 0); cookie = spl_fstrans_mark(); error = -zfs_read(ITOZ(xip), &uio, 0, cr); spl_fstrans_unmark(cookie); if (error == 0) error = size - zfs_uio_resid(&uio); out: if (xzp) zrele(xzp); if (dxzp) zrele(dxzp); return (error); } static int zpl_xattr_get_sa(struct inode *ip, const char *name, void *value, size_t size) { znode_t *zp = ITOZ(ip); uchar_t *nv_value; uint_t nv_size; int error = 0; ASSERT(RW_LOCK_HELD(&zp->z_xattr_lock)); mutex_enter(&zp->z_lock); if (zp->z_xattr_cached == NULL) error = -zfs_sa_get_xattr(zp); mutex_exit(&zp->z_lock); if (error) return (error); ASSERT(zp->z_xattr_cached); error = -nvlist_lookup_byte_array(zp->z_xattr_cached, name, &nv_value, &nv_size); if (error) return (error); if (size == 0 || value == NULL) return (nv_size); if (size < nv_size) return (-ERANGE); memcpy(value, nv_value, nv_size); return (nv_size); } static int __zpl_xattr_get(struct inode *ip, const char *name, void *value, size_t size, cred_t *cr) { znode_t *zp = ITOZ(ip); zfsvfs_t *zfsvfs = ZTOZSB(zp); int error; ASSERT(RW_LOCK_HELD(&zp->z_xattr_lock)); if (zfsvfs->z_use_sa && zp->z_is_sa) { error = zpl_xattr_get_sa(ip, name, value, size); if (error != -ENOENT) goto out; } error = zpl_xattr_get_dir(ip, name, value, size, cr); out: if (error == -ENOENT) error = -ENODATA; return (error); } #define XATTR_NOENT 0x0 #define XATTR_IN_SA 0x1 #define XATTR_IN_DIR 0x2 /* check where the xattr resides */ static int __zpl_xattr_where(struct inode *ip, const char *name, int *where, cred_t *cr) { znode_t *zp = ITOZ(ip); zfsvfs_t *zfsvfs = ZTOZSB(zp); int error; ASSERT(where); ASSERT(RW_LOCK_HELD(&zp->z_xattr_lock)); *where = XATTR_NOENT; if (zfsvfs->z_use_sa && zp->z_is_sa) { error = zpl_xattr_get_sa(ip, name, NULL, 0); if (error >= 0) *where |= XATTR_IN_SA; else if (error != -ENOENT) return (error); } error = zpl_xattr_get_dir(ip, name, NULL, 0, cr); if (error >= 0) *where |= XATTR_IN_DIR; else if (error != -ENOENT) return (error); if (*where == (XATTR_IN_SA|XATTR_IN_DIR)) cmn_err(CE_WARN, "ZFS: inode %p has xattr \"%s\"" " in both SA and dir", ip, name); if (*where == XATTR_NOENT) error = -ENODATA; else error = 0; return (error); } static int zpl_xattr_get(struct inode *ip, const char *name, void *value, size_t size) { znode_t *zp = ITOZ(ip); zfsvfs_t *zfsvfs = ZTOZSB(zp); cred_t *cr = CRED(); fstrans_cookie_t cookie; int error; crhold(cr); cookie = spl_fstrans_mark(); ZPL_ENTER(zfsvfs); ZPL_VERIFY_ZP(zp); rw_enter(&zp->z_xattr_lock, RW_READER); error = __zpl_xattr_get(ip, name, value, size, cr); rw_exit(&zp->z_xattr_lock); ZPL_EXIT(zfsvfs); spl_fstrans_unmark(cookie); crfree(cr); return (error); } static int zpl_xattr_set_dir(struct inode *ip, const char *name, const void *value, size_t size, int flags, cred_t *cr) { znode_t *dxzp = NULL; znode_t *xzp = NULL; vattr_t *vap = NULL; int lookup_flags, error; const int xattr_mode = S_IFREG | 0644; loff_t pos = 0; /* * Lookup the xattr directory. When we're adding an entry pass * CREATE_XATTR_DIR to ensure the xattr directory is created. * When removing an entry this flag is not passed to avoid * unnecessarily creating a new xattr directory. */ lookup_flags = LOOKUP_XATTR; if (value != NULL) lookup_flags |= CREATE_XATTR_DIR; error = -zfs_lookup(ITOZ(ip), NULL, &dxzp, lookup_flags, cr, NULL, NULL); if (error) goto out; /* Lookup a specific xattr name in the directory */ error = -zfs_lookup(dxzp, (char *)name, &xzp, 0, cr, NULL, NULL); if (error && (error != -ENOENT)) goto out; error = 0; /* Remove a specific name xattr when value is set to NULL. */ if (value == NULL) { if (xzp) error = -zfs_remove(dxzp, (char *)name, cr, 0); goto out; } /* Lookup failed create a new xattr. */ if (xzp == NULL) { vap = kmem_zalloc(sizeof (vattr_t), KM_SLEEP); vap->va_mode = xattr_mode; vap->va_mask = ATTR_MODE; vap->va_uid = crgetfsuid(cr); vap->va_gid = crgetfsgid(cr); error = -zfs_create(dxzp, (char *)name, vap, 0, 0644, &xzp, cr, 0, NULL); if (error) goto out; } ASSERT(xzp != NULL); error = -zfs_freesp(xzp, 0, 0, xattr_mode, TRUE); if (error) goto out; error = -zfs_write_simple(xzp, value, size, pos, NULL); out: if (error == 0) { ip->i_ctime = current_time(ip); zfs_mark_inode_dirty(ip); } if (vap) kmem_free(vap, sizeof (vattr_t)); if (xzp) zrele(xzp); if (dxzp) zrele(dxzp); if (error == -ENOENT) error = -ENODATA; ASSERT3S(error, <=, 0); return (error); } static int zpl_xattr_set_sa(struct inode *ip, const char *name, const void *value, size_t size, int flags, cred_t *cr) { znode_t *zp = ITOZ(ip); nvlist_t *nvl; size_t sa_size; int error = 0; mutex_enter(&zp->z_lock); if (zp->z_xattr_cached == NULL) error = -zfs_sa_get_xattr(zp); mutex_exit(&zp->z_lock); if (error) return (error); ASSERT(zp->z_xattr_cached); nvl = zp->z_xattr_cached; if (value == NULL) { error = -nvlist_remove(nvl, name, DATA_TYPE_BYTE_ARRAY); if (error == -ENOENT) error = zpl_xattr_set_dir(ip, name, NULL, 0, flags, cr); } else { /* Limited to 32k to keep nvpair memory allocations small */ if (size > DXATTR_MAX_ENTRY_SIZE) return (-EFBIG); /* Prevent the DXATTR SA from consuming the entire SA region */ error = -nvlist_size(nvl, &sa_size, NV_ENCODE_XDR); if (error) return (error); if (sa_size > DXATTR_MAX_SA_SIZE) return (-EFBIG); error = -nvlist_add_byte_array(nvl, name, (uchar_t *)value, size); } /* * Update the SA for additions, modifications, and removals. On * error drop the inconsistent cached version of the nvlist, it * will be reconstructed from the ARC when next accessed. */ if (error == 0) - error = -zfs_sa_set_xattr(zp); + error = -zfs_sa_set_xattr(zp, name, value, size); if (error) { nvlist_free(nvl); zp->z_xattr_cached = NULL; } ASSERT3S(error, <=, 0); return (error); } static int zpl_xattr_set(struct inode *ip, const char *name, const void *value, size_t size, int flags) { znode_t *zp = ITOZ(ip); zfsvfs_t *zfsvfs = ZTOZSB(zp); cred_t *cr = CRED(); fstrans_cookie_t cookie; int where; int error; crhold(cr); cookie = spl_fstrans_mark(); ZPL_ENTER(zfsvfs); ZPL_VERIFY_ZP(zp); rw_enter(&zp->z_xattr_lock, RW_WRITER); /* * Before setting the xattr check to see if it already exists. * This is done to ensure the following optional flags are honored. * * XATTR_CREATE: fail if xattr already exists * XATTR_REPLACE: fail if xattr does not exist * * We also want to know if it resides in sa or dir, so we can make * sure we don't end up with duplicate in both places. */ error = __zpl_xattr_where(ip, name, &where, cr); if (error < 0) { if (error != -ENODATA) goto out; if (flags & XATTR_REPLACE) goto out; /* The xattr to be removed already doesn't exist */ error = 0; if (value == NULL) goto out; } else { error = -EEXIST; if (flags & XATTR_CREATE) goto out; } /* Preferentially store the xattr as a SA for better performance */ if (zfsvfs->z_use_sa && zp->z_is_sa && (zfsvfs->z_xattr_sa || (value == NULL && where & XATTR_IN_SA))) { error = zpl_xattr_set_sa(ip, name, value, size, flags, cr); if (error == 0) { /* * Successfully put into SA, we need to clear the one * in dir. */ if (where & XATTR_IN_DIR) zpl_xattr_set_dir(ip, name, NULL, 0, 0, cr); goto out; } } error = zpl_xattr_set_dir(ip, name, value, size, flags, cr); /* * Successfully put into dir, we need to clear the one in SA. */ if (error == 0 && (where & XATTR_IN_SA)) zpl_xattr_set_sa(ip, name, NULL, 0, 0, cr); out: rw_exit(&zp->z_xattr_lock); ZPL_EXIT(zfsvfs); spl_fstrans_unmark(cookie); crfree(cr); ASSERT3S(error, <=, 0); return (error); } /* * Extended user attributes * * "Extended user attributes may be assigned to files and directories for * storing arbitrary additional information such as the mime type, * character set or encoding of a file. The access permissions for user * attributes are defined by the file permission bits: read permission * is required to retrieve the attribute value, and writer permission is * required to change it. * * The file permission bits of regular files and directories are * interpreted differently from the file permission bits of special * files and symbolic links. For regular files and directories the file * permission bits define access to the file's contents, while for * device special files they define access to the device described by * the special file. The file permissions of symbolic links are not * used in access checks. These differences would allow users to * consume filesystem resources in a way not controllable by disk quotas * for group or world writable special files and directories. * * For this reason, extended user attributes are allowed only for * regular files and directories, and access to extended user attributes * is restricted to the owner and to users with appropriate capabilities * for directories with the sticky bit set (see the chmod(1) manual page * for an explanation of the sticky bit)." - xattr(7) * * ZFS allows extended user attributes to be disabled administratively * by setting the 'xattr=off' property on the dataset. */ static int __zpl_xattr_user_list(struct inode *ip, char *list, size_t list_size, const char *name, size_t name_len) { return (ITOZSB(ip)->z_flags & ZSB_XATTR); } ZPL_XATTR_LIST_WRAPPER(zpl_xattr_user_list); static int __zpl_xattr_user_get(struct inode *ip, const char *name, void *value, size_t size) { int error; /* xattr_resolve_name will do this for us if this is defined */ #ifndef HAVE_XATTR_HANDLER_NAME if (strcmp(name, "") == 0) return (-EINVAL); #endif if (ZFS_XA_NS_PREFIX_FORBIDDEN(name)) return (-EINVAL); if (!(ITOZSB(ip)->z_flags & ZSB_XATTR)) return (-EOPNOTSUPP); /* * Try to look up the name with the namespace prefix first for * compatibility with xattrs from this platform. If that fails, * try again without the namespace prefix for compatibility with * other platforms. */ char *xattr_name = kmem_asprintf("%s%s", XATTR_USER_PREFIX, name); error = zpl_xattr_get(ip, xattr_name, value, size); kmem_strfree(xattr_name); if (error == -ENODATA) error = zpl_xattr_get(ip, name, value, size); return (error); } ZPL_XATTR_GET_WRAPPER(zpl_xattr_user_get); static int __zpl_xattr_user_set(struct inode *ip, const char *name, const void *value, size_t size, int flags) { int error = 0; /* xattr_resolve_name will do this for us if this is defined */ #ifndef HAVE_XATTR_HANDLER_NAME if (strcmp(name, "") == 0) return (-EINVAL); #endif if (ZFS_XA_NS_PREFIX_FORBIDDEN(name)) return (-EINVAL); if (!(ITOZSB(ip)->z_flags & ZSB_XATTR)) return (-EOPNOTSUPP); /* * Remove alternate compat version of the xattr so we only set the * version specified by the zfs_xattr_compat tunable. * * The following flags must be handled correctly: * * XATTR_CREATE: fail if xattr already exists * XATTR_REPLACE: fail if xattr does not exist */ char *prefixed_name = kmem_asprintf("%s%s", XATTR_USER_PREFIX, name); const char *clear_name, *set_name; if (zfs_xattr_compat) { clear_name = prefixed_name; set_name = name; } else { clear_name = name; set_name = prefixed_name; } /* * Clear the old value with the alternative name format, if it exists. */ error = zpl_xattr_set(ip, clear_name, NULL, 0, flags); /* * XATTR_CREATE was specified and we failed to clear the xattr * because it already exists. Stop here. */ if (error == -EEXIST) goto out; /* * If XATTR_REPLACE was specified and we succeeded to clear * an xattr, we don't need to replace anything when setting * the new value. If we failed with -ENODATA that's fine, * there was nothing to be cleared and we can ignore the error. */ if (error == 0) flags &= ~XATTR_REPLACE; /* * Set the new value with the configured name format. */ error = zpl_xattr_set(ip, set_name, value, size, flags); out: kmem_strfree(prefixed_name); return (error); } ZPL_XATTR_SET_WRAPPER(zpl_xattr_user_set); static xattr_handler_t zpl_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, .list = zpl_xattr_user_list, .get = zpl_xattr_user_get, .set = zpl_xattr_user_set, }; /* * Trusted extended attributes * * "Trusted extended attributes are visible and accessible only to * processes that have the CAP_SYS_ADMIN capability. Attributes in this * class are used to implement mechanisms in user space (i.e., outside * the kernel) which keep information in extended attributes to which * ordinary processes should not have access." - xattr(7) */ static int __zpl_xattr_trusted_list(struct inode *ip, char *list, size_t list_size, const char *name, size_t name_len) { return (capable(CAP_SYS_ADMIN)); } ZPL_XATTR_LIST_WRAPPER(zpl_xattr_trusted_list); static int __zpl_xattr_trusted_get(struct inode *ip, const char *name, void *value, size_t size) { char *xattr_name; int error; if (!capable(CAP_SYS_ADMIN)) return (-EACCES); /* xattr_resolve_name will do this for us if this is defined */ #ifndef HAVE_XATTR_HANDLER_NAME if (strcmp(name, "") == 0) return (-EINVAL); #endif xattr_name = kmem_asprintf("%s%s", XATTR_TRUSTED_PREFIX, name); error = zpl_xattr_get(ip, xattr_name, value, size); kmem_strfree(xattr_name); return (error); } ZPL_XATTR_GET_WRAPPER(zpl_xattr_trusted_get); static int __zpl_xattr_trusted_set(struct inode *ip, const char *name, const void *value, size_t size, int flags) { char *xattr_name; int error; if (!capable(CAP_SYS_ADMIN)) return (-EACCES); /* xattr_resolve_name will do this for us if this is defined */ #ifndef HAVE_XATTR_HANDLER_NAME if (strcmp(name, "") == 0) return (-EINVAL); #endif xattr_name = kmem_asprintf("%s%s", XATTR_TRUSTED_PREFIX, name); error = zpl_xattr_set(ip, xattr_name, value, size, flags); kmem_strfree(xattr_name); return (error); } ZPL_XATTR_SET_WRAPPER(zpl_xattr_trusted_set); static xattr_handler_t zpl_xattr_trusted_handler = { .prefix = XATTR_TRUSTED_PREFIX, .list = zpl_xattr_trusted_list, .get = zpl_xattr_trusted_get, .set = zpl_xattr_trusted_set, }; /* * Extended security attributes * * "The security attribute namespace is used by kernel security modules, * such as Security Enhanced Linux, and also to implement file * capabilities (see capabilities(7)). Read and write access * permissions to security attributes depend on the policy implemented * for each security attribute by the security module. When no security * module is loaded, all processes have read access to extended security * attributes, and write access is limited to processes that have the * CAP_SYS_ADMIN capability." - xattr(7) */ static int __zpl_xattr_security_list(struct inode *ip, char *list, size_t list_size, const char *name, size_t name_len) { return (1); } ZPL_XATTR_LIST_WRAPPER(zpl_xattr_security_list); static int __zpl_xattr_security_get(struct inode *ip, const char *name, void *value, size_t size) { char *xattr_name; int error; /* xattr_resolve_name will do this for us if this is defined */ #ifndef HAVE_XATTR_HANDLER_NAME if (strcmp(name, "") == 0) return (-EINVAL); #endif xattr_name = kmem_asprintf("%s%s", XATTR_SECURITY_PREFIX, name); error = zpl_xattr_get(ip, xattr_name, value, size); kmem_strfree(xattr_name); return (error); } ZPL_XATTR_GET_WRAPPER(zpl_xattr_security_get); static int __zpl_xattr_security_set(struct inode *ip, const char *name, const void *value, size_t size, int flags) { char *xattr_name; int error; /* xattr_resolve_name will do this for us if this is defined */ #ifndef HAVE_XATTR_HANDLER_NAME if (strcmp(name, "") == 0) return (-EINVAL); #endif xattr_name = kmem_asprintf("%s%s", XATTR_SECURITY_PREFIX, name); error = zpl_xattr_set(ip, xattr_name, value, size, flags); kmem_strfree(xattr_name); return (error); } ZPL_XATTR_SET_WRAPPER(zpl_xattr_security_set); static int zpl_xattr_security_init_impl(struct inode *ip, const struct xattr *xattrs, void *fs_info) { const struct xattr *xattr; int error = 0; for (xattr = xattrs; xattr->name != NULL; xattr++) { error = __zpl_xattr_security_set(ip, xattr->name, xattr->value, xattr->value_len, 0); if (error < 0) break; } return (error); } int zpl_xattr_security_init(struct inode *ip, struct inode *dip, const struct qstr *qstr) { return security_inode_init_security(ip, dip, qstr, &zpl_xattr_security_init_impl, NULL); } /* * Security xattr namespace handlers. */ static xattr_handler_t zpl_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .list = zpl_xattr_security_list, .get = zpl_xattr_security_get, .set = zpl_xattr_security_set, }; /* * Extended system attributes * * "Extended system attributes are used by the kernel to store system * objects such as Access Control Lists. Read and write access permissions * to system attributes depend on the policy implemented for each system * attribute implemented by filesystems in the kernel." - xattr(7) */ #ifdef CONFIG_FS_POSIX_ACL static int zpl_set_acl_impl(struct inode *ip, struct posix_acl *acl, int type) { char *name, *value = NULL; int error = 0; size_t size = 0; if (S_ISLNK(ip->i_mode)) return (-EOPNOTSUPP); switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { umode_t mode = ip->i_mode; error = posix_acl_equiv_mode(acl, &mode); if (error < 0) { return (error); } else { /* * The mode bits will have been set by * ->zfs_setattr()->zfs_acl_chmod_setattr() * using the ZFS ACL conversion. If they * differ from the Posix ACL conversion dirty * the inode to write the Posix mode bits. */ if (ip->i_mode != mode) { ip->i_mode = mode; ip->i_ctime = current_time(ip); zfs_mark_inode_dirty(ip); } if (error == 0) acl = NULL; } } break; case ACL_TYPE_DEFAULT: name = XATTR_NAME_POSIX_ACL_DEFAULT; if (!S_ISDIR(ip->i_mode)) return (acl ? -EACCES : 0); break; default: return (-EINVAL); } if (acl) { size = posix_acl_xattr_size(acl->a_count); value = kmem_alloc(size, KM_SLEEP); error = zpl_acl_to_xattr(acl, value, size); if (error < 0) { kmem_free(value, size); return (error); } } error = zpl_xattr_set(ip, name, value, size, 0); if (value) kmem_free(value, size); if (!error) { if (acl) zpl_set_cached_acl(ip, type, acl); else zpl_forget_cached_acl(ip, type); } return (error); } #ifdef HAVE_SET_ACL int #ifdef HAVE_SET_ACL_USERNS zpl_set_acl(struct user_namespace *userns, struct inode *ip, struct posix_acl *acl, int type) #else zpl_set_acl(struct inode *ip, struct posix_acl *acl, int type) #endif /* HAVE_SET_ACL_USERNS */ { return (zpl_set_acl_impl(ip, acl, type)); } #endif /* HAVE_SET_ACL */ static struct posix_acl * zpl_get_acl_impl(struct inode *ip, int type) { struct posix_acl *acl; void *value = NULL; char *name; /* * As of Linux 3.14, the kernel get_acl will check this for us. * Also as of Linux 4.7, comparing against ACL_NOT_CACHED is wrong * as the kernel get_acl will set it to temporary sentinel value. */ #ifndef HAVE_KERNEL_GET_ACL_HANDLE_CACHE acl = get_cached_acl(ip, type); if (acl != ACL_NOT_CACHED) return (acl); #endif switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return (ERR_PTR(-EINVAL)); } int size = zpl_xattr_get(ip, name, NULL, 0); if (size > 0) { value = kmem_alloc(size, KM_SLEEP); size = zpl_xattr_get(ip, name, value, size); } if (size > 0) { acl = zpl_acl_from_xattr(value, size); } else if (size == -ENODATA || size == -ENOSYS) { acl = NULL; } else { acl = ERR_PTR(-EIO); } if (size > 0) kmem_free(value, size); /* As of Linux 4.7, the kernel get_acl will set this for us */ #ifndef HAVE_KERNEL_GET_ACL_HANDLE_CACHE if (!IS_ERR(acl)) zpl_set_cached_acl(ip, type, acl); #endif return (acl); } #if defined(HAVE_GET_ACL_RCU) struct posix_acl * zpl_get_acl(struct inode *ip, int type, bool rcu) { if (rcu) return (ERR_PTR(-ECHILD)); return (zpl_get_acl_impl(ip, type)); } #elif defined(HAVE_GET_ACL) struct posix_acl * zpl_get_acl(struct inode *ip, int type) { return (zpl_get_acl_impl(ip, type)); } #else #error "Unsupported iops->get_acl() implementation" #endif /* HAVE_GET_ACL_RCU */ int zpl_init_acl(struct inode *ip, struct inode *dir) { struct posix_acl *acl = NULL; int error = 0; if (ITOZSB(ip)->z_acl_type != ZFS_ACLTYPE_POSIX) return (0); if (!S_ISLNK(ip->i_mode)) { acl = zpl_get_acl_impl(dir, ACL_TYPE_DEFAULT); if (IS_ERR(acl)) return (PTR_ERR(acl)); if (!acl) { ip->i_mode &= ~current_umask(); ip->i_ctime = current_time(ip); zfs_mark_inode_dirty(ip); return (0); } } if (acl) { umode_t mode; if (S_ISDIR(ip->i_mode)) { error = zpl_set_acl_impl(ip, acl, ACL_TYPE_DEFAULT); if (error) goto out; } mode = ip->i_mode; error = __posix_acl_create(&acl, GFP_KERNEL, &mode); if (error >= 0) { ip->i_mode = mode; zfs_mark_inode_dirty(ip); if (error > 0) { error = zpl_set_acl_impl(ip, acl, ACL_TYPE_ACCESS); } } } out: zpl_posix_acl_release(acl); return (error); } int zpl_chmod_acl(struct inode *ip) { struct posix_acl *acl; int error; if (ITOZSB(ip)->z_acl_type != ZFS_ACLTYPE_POSIX) return (0); if (S_ISLNK(ip->i_mode)) return (-EOPNOTSUPP); acl = zpl_get_acl_impl(ip, ACL_TYPE_ACCESS); if (IS_ERR(acl) || !acl) return (PTR_ERR(acl)); error = __posix_acl_chmod(&acl, GFP_KERNEL, ip->i_mode); if (!error) error = zpl_set_acl_impl(ip, acl, ACL_TYPE_ACCESS); zpl_posix_acl_release(acl); return (error); } static int __zpl_xattr_acl_list_access(struct inode *ip, char *list, size_t list_size, const char *name, size_t name_len) { char *xattr_name = XATTR_NAME_POSIX_ACL_ACCESS; size_t xattr_size = sizeof (XATTR_NAME_POSIX_ACL_ACCESS); if (ITOZSB(ip)->z_acl_type != ZFS_ACLTYPE_POSIX) return (0); if (list && xattr_size <= list_size) memcpy(list, xattr_name, xattr_size); return (xattr_size); } ZPL_XATTR_LIST_WRAPPER(zpl_xattr_acl_list_access); static int __zpl_xattr_acl_list_default(struct inode *ip, char *list, size_t list_size, const char *name, size_t name_len) { char *xattr_name = XATTR_NAME_POSIX_ACL_DEFAULT; size_t xattr_size = sizeof (XATTR_NAME_POSIX_ACL_DEFAULT); if (ITOZSB(ip)->z_acl_type != ZFS_ACLTYPE_POSIX) return (0); if (list && xattr_size <= list_size) memcpy(list, xattr_name, xattr_size); return (xattr_size); } ZPL_XATTR_LIST_WRAPPER(zpl_xattr_acl_list_default); static int __zpl_xattr_acl_get_access(struct inode *ip, const char *name, void *buffer, size_t size) { struct posix_acl *acl; int type = ACL_TYPE_ACCESS; int error; /* xattr_resolve_name will do this for us if this is defined */ #ifndef HAVE_XATTR_HANDLER_NAME if (strcmp(name, "") != 0) return (-EINVAL); #endif if (ITOZSB(ip)->z_acl_type != ZFS_ACLTYPE_POSIX) return (-EOPNOTSUPP); acl = zpl_get_acl_impl(ip, type); if (IS_ERR(acl)) return (PTR_ERR(acl)); if (acl == NULL) return (-ENODATA); error = zpl_acl_to_xattr(acl, buffer, size); zpl_posix_acl_release(acl); return (error); } ZPL_XATTR_GET_WRAPPER(zpl_xattr_acl_get_access); static int __zpl_xattr_acl_get_default(struct inode *ip, const char *name, void *buffer, size_t size) { struct posix_acl *acl; int type = ACL_TYPE_DEFAULT; int error; /* xattr_resolve_name will do this for us if this is defined */ #ifndef HAVE_XATTR_HANDLER_NAME if (strcmp(name, "") != 0) return (-EINVAL); #endif if (ITOZSB(ip)->z_acl_type != ZFS_ACLTYPE_POSIX) return (-EOPNOTSUPP); acl = zpl_get_acl_impl(ip, type); if (IS_ERR(acl)) return (PTR_ERR(acl)); if (acl == NULL) return (-ENODATA); error = zpl_acl_to_xattr(acl, buffer, size); zpl_posix_acl_release(acl); return (error); } ZPL_XATTR_GET_WRAPPER(zpl_xattr_acl_get_default); static int __zpl_xattr_acl_set_access(struct inode *ip, const char *name, const void *value, size_t size, int flags) { struct posix_acl *acl; int type = ACL_TYPE_ACCESS; int error = 0; /* xattr_resolve_name will do this for us if this is defined */ #ifndef HAVE_XATTR_HANDLER_NAME if (strcmp(name, "") != 0) return (-EINVAL); #endif if (ITOZSB(ip)->z_acl_type != ZFS_ACLTYPE_POSIX) return (-EOPNOTSUPP); if (!zpl_inode_owner_or_capable(kcred->user_ns, ip)) return (-EPERM); if (value) { acl = zpl_acl_from_xattr(value, size); if (IS_ERR(acl)) return (PTR_ERR(acl)); else if (acl) { error = zpl_posix_acl_valid(ip, acl); if (error) { zpl_posix_acl_release(acl); return (error); } } } else { acl = NULL; } error = zpl_set_acl_impl(ip, acl, type); zpl_posix_acl_release(acl); return (error); } ZPL_XATTR_SET_WRAPPER(zpl_xattr_acl_set_access); static int __zpl_xattr_acl_set_default(struct inode *ip, const char *name, const void *value, size_t size, int flags) { struct posix_acl *acl; int type = ACL_TYPE_DEFAULT; int error = 0; /* xattr_resolve_name will do this for us if this is defined */ #ifndef HAVE_XATTR_HANDLER_NAME if (strcmp(name, "") != 0) return (-EINVAL); #endif if (ITOZSB(ip)->z_acl_type != ZFS_ACLTYPE_POSIX) return (-EOPNOTSUPP); if (!zpl_inode_owner_or_capable(kcred->user_ns, ip)) return (-EPERM); if (value) { acl = zpl_acl_from_xattr(value, size); if (IS_ERR(acl)) return (PTR_ERR(acl)); else if (acl) { error = zpl_posix_acl_valid(ip, acl); if (error) { zpl_posix_acl_release(acl); return (error); } } } else { acl = NULL; } error = zpl_set_acl_impl(ip, acl, type); zpl_posix_acl_release(acl); return (error); } ZPL_XATTR_SET_WRAPPER(zpl_xattr_acl_set_default); /* * ACL access xattr namespace handlers. * * Use .name instead of .prefix when available. xattr_resolve_name will match * whole name and reject anything that has .name only as prefix. */ static xattr_handler_t zpl_xattr_acl_access_handler = { #ifdef HAVE_XATTR_HANDLER_NAME .name = XATTR_NAME_POSIX_ACL_ACCESS, #else .prefix = XATTR_NAME_POSIX_ACL_ACCESS, #endif .list = zpl_xattr_acl_list_access, .get = zpl_xattr_acl_get_access, .set = zpl_xattr_acl_set_access, #if defined(HAVE_XATTR_LIST_SIMPLE) || \ defined(HAVE_XATTR_LIST_DENTRY) || \ defined(HAVE_XATTR_LIST_HANDLER) .flags = ACL_TYPE_ACCESS, #endif }; /* * ACL default xattr namespace handlers. * * Use .name instead of .prefix when available. xattr_resolve_name will match * whole name and reject anything that has .name only as prefix. */ static xattr_handler_t zpl_xattr_acl_default_handler = { #ifdef HAVE_XATTR_HANDLER_NAME .name = XATTR_NAME_POSIX_ACL_DEFAULT, #else .prefix = XATTR_NAME_POSIX_ACL_DEFAULT, #endif .list = zpl_xattr_acl_list_default, .get = zpl_xattr_acl_get_default, .set = zpl_xattr_acl_set_default, #if defined(HAVE_XATTR_LIST_SIMPLE) || \ defined(HAVE_XATTR_LIST_DENTRY) || \ defined(HAVE_XATTR_LIST_HANDLER) .flags = ACL_TYPE_DEFAULT, #endif }; #endif /* CONFIG_FS_POSIX_ACL */ xattr_handler_t *zpl_xattr_handlers[] = { &zpl_xattr_security_handler, &zpl_xattr_trusted_handler, &zpl_xattr_user_handler, #ifdef CONFIG_FS_POSIX_ACL &zpl_xattr_acl_access_handler, &zpl_xattr_acl_default_handler, #endif /* CONFIG_FS_POSIX_ACL */ NULL }; static const struct xattr_handler * zpl_xattr_handler(const char *name) { if (strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) == 0) return (&zpl_xattr_user_handler); if (strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) == 0) return (&zpl_xattr_trusted_handler); if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) == 0) return (&zpl_xattr_security_handler); #ifdef CONFIG_FS_POSIX_ACL if (strncmp(name, XATTR_NAME_POSIX_ACL_ACCESS, sizeof (XATTR_NAME_POSIX_ACL_ACCESS)) == 0) return (&zpl_xattr_acl_access_handler); if (strncmp(name, XATTR_NAME_POSIX_ACL_DEFAULT, sizeof (XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) return (&zpl_xattr_acl_default_handler); #endif /* CONFIG_FS_POSIX_ACL */ return (NULL); } static enum xattr_permission zpl_xattr_permission(xattr_filldir_t *xf, const char *name, int name_len) { const struct xattr_handler *handler; struct dentry *d __maybe_unused = xf->dentry; enum xattr_permission perm = XAPERM_ALLOW; handler = zpl_xattr_handler(name); if (handler == NULL) { /* Do not expose FreeBSD system namespace xattrs. */ if (ZFS_XA_NS_PREFIX_MATCH(FREEBSD, name)) return (XAPERM_DENY); /* * Anything that doesn't match a known namespace gets put in the * user namespace for compatibility with other platforms. */ perm = XAPERM_COMPAT; handler = &zpl_xattr_user_handler; } if (handler->list) { #if defined(HAVE_XATTR_LIST_SIMPLE) if (!handler->list(d)) return (XAPERM_DENY); #elif defined(HAVE_XATTR_LIST_DENTRY) if (!handler->list(d, NULL, 0, name, name_len, 0)) return (XAPERM_DENY); #elif defined(HAVE_XATTR_LIST_HANDLER) if (!handler->list(handler, d, NULL, 0, name, name_len)) return (XAPERM_DENY); #endif } return (perm); } #if !defined(HAVE_POSIX_ACL_RELEASE) || defined(HAVE_POSIX_ACL_RELEASE_GPL_ONLY) struct acl_rel_struct { struct acl_rel_struct *next; struct posix_acl *acl; clock_t time; }; #define ACL_REL_GRACE (60*HZ) #define ACL_REL_WINDOW (1*HZ) #define ACL_REL_SCHED (ACL_REL_GRACE+ACL_REL_WINDOW) /* * Lockless multi-producer single-consumer fifo list. * Nodes are added to tail and removed from head. Tail pointer is our * synchronization point. It always points to the next pointer of the last * node, or head if list is empty. */ static struct acl_rel_struct *acl_rel_head = NULL; static struct acl_rel_struct **acl_rel_tail = &acl_rel_head; static void zpl_posix_acl_free(void *arg) { struct acl_rel_struct *freelist = NULL; struct acl_rel_struct *a; clock_t new_time; boolean_t refire = B_FALSE; ASSERT3P(acl_rel_head, !=, NULL); while (acl_rel_head) { a = acl_rel_head; if (ddi_get_lbolt() - a->time >= ACL_REL_GRACE) { /* * If a is the last node we need to reset tail, but we * need to use cmpxchg to make sure it is still the * last node. */ if (acl_rel_tail == &a->next) { acl_rel_head = NULL; if (cmpxchg(&acl_rel_tail, &a->next, &acl_rel_head) == &a->next) { ASSERT3P(a->next, ==, NULL); a->next = freelist; freelist = a; break; } } /* * a is not last node, make sure next pointer is set * by the adder and advance the head. */ while (READ_ONCE(a->next) == NULL) cpu_relax(); acl_rel_head = a->next; a->next = freelist; freelist = a; } else { /* * a is still in grace period. We are responsible to * reschedule the free task, since adder will only do * so if list is empty. */ new_time = a->time + ACL_REL_SCHED; refire = B_TRUE; break; } } if (refire) taskq_dispatch_delay(system_delay_taskq, zpl_posix_acl_free, NULL, TQ_SLEEP, new_time); while (freelist) { a = freelist; freelist = a->next; kfree(a->acl); kmem_free(a, sizeof (struct acl_rel_struct)); } } void zpl_posix_acl_release_impl(struct posix_acl *acl) { struct acl_rel_struct *a, **prev; a = kmem_alloc(sizeof (struct acl_rel_struct), KM_SLEEP); a->next = NULL; a->acl = acl; a->time = ddi_get_lbolt(); /* atomically points tail to us and get the previous tail */ prev = xchg(&acl_rel_tail, &a->next); ASSERT3P(*prev, ==, NULL); *prev = a; /* if it was empty before, schedule the free task */ if (prev == &acl_rel_head) taskq_dispatch_delay(system_delay_taskq, zpl_posix_acl_free, NULL, TQ_SLEEP, ddi_get_lbolt() + ACL_REL_SCHED); } #endif ZFS_MODULE_PARAM(zfs, zfs_, xattr_compat, INT, ZMOD_RW, "Use legacy ZFS xattr naming for writing new user namespace xattrs"); diff --git a/module/zcommon/zfeature_common.c b/module/zcommon/zfeature_common.c index 529c52316f3e..13dbccae2d4a 100644 --- a/module/zcommon/zfeature_common.c +++ b/module/zcommon/zfeature_common.c @@ -1,709 +1,721 @@ /* * 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) 2011, 2018 by Delphix. All rights reserved. * Copyright (c) 2013 by Saso Kiselkov. All rights reserved. * Copyright (c) 2013, Joyent, Inc. All rights reserved. * Copyright (c) 2014, Nexenta Systems, Inc. All rights reserved. * Copyright (c) 2017, Intel Corporation. * Copyright (c) 2019, Klara Inc. * Copyright (c) 2019, Allan Jude */ #ifndef _KERNEL #include #include #include #include #include #endif #include #include #include #include #include #include #include "zfeature_common.h" /* * Set to disable all feature checks while opening pools, allowing pools with * unsupported features to be opened. Set for testing only. */ boolean_t zfeature_checks_disable = B_FALSE; zfeature_info_t spa_feature_table[SPA_FEATURES]; /* * Valid characters for feature guids. This list is mainly for aesthetic * purposes and could be expanded in the future. There are different allowed * characters in the guids reverse dns portion (before the colon) and its * short name (after the colon). */ static int valid_char(char c, boolean_t after_colon) { return ((c >= 'a' && c <= 'z') || (c >= '0' && c <= '9') || (after_colon && c == '_') || (!after_colon && (c == '.' || c == '-'))); } /* * Every feature guid must contain exactly one colon which separates a reverse * dns organization name from the feature's "short" name (e.g. * "com.company:feature_name"). */ boolean_t zfeature_is_valid_guid(const char *name) { int i; boolean_t has_colon = B_FALSE; i = 0; while (name[i] != '\0') { char c = name[i++]; if (c == ':') { if (has_colon) return (B_FALSE); has_colon = B_TRUE; continue; } if (!valid_char(c, has_colon)) return (B_FALSE); } return (has_colon); } boolean_t zfeature_is_supported(const char *guid) { if (zfeature_checks_disable) return (B_TRUE); for (spa_feature_t i = 0; i < SPA_FEATURES; i++) { zfeature_info_t *feature = &spa_feature_table[i]; if (!feature->fi_zfs_mod_supported) continue; if (strcmp(guid, feature->fi_guid) == 0) return (B_TRUE); } return (B_FALSE); } int zfeature_lookup_guid(const char *guid, spa_feature_t *res) { for (spa_feature_t i = 0; i < SPA_FEATURES; i++) { zfeature_info_t *feature = &spa_feature_table[i]; if (!feature->fi_zfs_mod_supported) continue; if (strcmp(guid, feature->fi_guid) == 0) { if (res != NULL) *res = i; return (0); } } return (ENOENT); } int zfeature_lookup_name(const char *name, spa_feature_t *res) { for (spa_feature_t i = 0; i < SPA_FEATURES; i++) { zfeature_info_t *feature = &spa_feature_table[i]; if (!feature->fi_zfs_mod_supported) continue; if (strcmp(name, feature->fi_uname) == 0) { if (res != NULL) *res = i; return (0); } } return (ENOENT); } boolean_t zfeature_depends_on(spa_feature_t fid, spa_feature_t check) { zfeature_info_t *feature = &spa_feature_table[fid]; for (int i = 0; feature->fi_depends[i] != SPA_FEATURE_NONE; i++) { if (feature->fi_depends[i] == check) return (B_TRUE); } return (B_FALSE); } static boolean_t deps_contains_feature(const spa_feature_t *deps, const spa_feature_t feature) { for (int i = 0; deps[i] != SPA_FEATURE_NONE; i++) if (deps[i] == feature) return (B_TRUE); return (B_FALSE); } #define STRCMP ((int(*)(const void *, const void *))&strcmp) struct zfs_mod_supported_features { void *tree; boolean_t all_features; }; struct zfs_mod_supported_features * zfs_mod_list_supported(const char *scope) { #if defined(__FreeBSD__) || defined(_KERNEL) || defined(LIB_ZPOOL_BUILD) (void) scope; return (NULL); #else struct zfs_mod_supported_features *ret = calloc(1, sizeof (*ret)); if (ret == NULL) return (NULL); DIR *sysfs_dir = NULL; char path[128]; if (snprintf(path, sizeof (path), "%s/%s", ZFS_SYSFS_DIR, scope) < sizeof (path)) sysfs_dir = opendir(path); if (sysfs_dir == NULL && errno == ENOENT) { if (snprintf(path, sizeof (path), "%s/%s", ZFS_SYSFS_ALT_DIR, scope) < sizeof (path)) sysfs_dir = opendir(path); } if (sysfs_dir == NULL) { ret->all_features = errno == ENOENT && (access(ZFS_SYSFS_DIR, F_OK) == 0 || access(ZFS_SYSFS_ALT_DIR, F_OK) == 0); return (ret); } struct dirent *node; while ((node = readdir(sysfs_dir)) != NULL) { if (strcmp(node->d_name, ".") == 0 || strcmp(node->d_name, "..") == 0) continue; char *name = strdup(node->d_name); if (name == NULL) { goto nomem; } if (tsearch(name, &ret->tree, STRCMP) == NULL) { /* * Don't bother checking for duplicate entries: * we're iterating a single directory. */ free(name); goto nomem; } } end: closedir(sysfs_dir); return (ret); nomem: zfs_mod_list_supported_free(ret); ret = NULL; goto end; #endif } void zfs_mod_list_supported_free(struct zfs_mod_supported_features *list) { #if !defined(__FreeBSD__) && !defined(_KERNEL) && !defined(LIB_ZPOOL_BUILD) if (list) { tdestroy(list->tree, free); free(list); } #else (void) list; #endif } #if !defined(_KERNEL) && !defined(LIB_ZPOOL_BUILD) static boolean_t zfs_mod_supported_impl(const char *scope, const char *name, const char *sysfs) { char path[128]; if (snprintf(path, sizeof (path), "%s%s%s%s%s", sysfs, scope == NULL ? "" : "/", scope ?: "", name == NULL ? "" : "/", name ?: "") < sizeof (path)) return (access(path, F_OK) == 0); else return (B_FALSE); } boolean_t zfs_mod_supported(const char *scope, const char *name, const struct zfs_mod_supported_features *sfeatures) { boolean_t supported; if (sfeatures != NULL) return (sfeatures->all_features || tfind(name, &sfeatures->tree, STRCMP)); /* * Check both the primary and alternate sysfs locations to determine * if the required functionality is supported. */ supported = (zfs_mod_supported_impl(scope, name, ZFS_SYSFS_DIR) || zfs_mod_supported_impl(scope, name, ZFS_SYSFS_ALT_DIR)); /* * For backwards compatibility with kernel modules that predate * supported feature/property checking. Report the feature/property * as supported if the kernel module is loaded but the requested * scope directory does not exist. */ if (supported == B_FALSE) { if ((access(ZFS_SYSFS_DIR, F_OK) == 0 && !zfs_mod_supported_impl(scope, NULL, ZFS_SYSFS_DIR)) || (access(ZFS_SYSFS_ALT_DIR, F_OK) == 0 && !zfs_mod_supported_impl(scope, NULL, ZFS_SYSFS_ALT_DIR))) { supported = B_TRUE; } } return (supported); } #endif static boolean_t zfs_mod_supported_feature(const char *name, const struct zfs_mod_supported_features *sfeatures) { /* * The zfs module spa_feature_table[], whether in-kernel or in * libzpool, always supports all the features. libzfs needs to * query the running module, via sysfs, to determine which * features are supported. * * The equivalent _can_ be done on FreeBSD by way of the sysctl * tree, but this has not been done yet. Therefore, we return * that all features are supported. */ #if defined(_KERNEL) || defined(LIB_ZPOOL_BUILD) || defined(__FreeBSD__) (void) name, (void) sfeatures; return (B_TRUE); #else return (zfs_mod_supported(ZFS_SYSFS_POOL_FEATURES, name, sfeatures)); #endif } static void zfeature_register(spa_feature_t fid, const char *guid, const char *name, const char *desc, zfeature_flags_t flags, zfeature_type_t type, const spa_feature_t *deps, const struct zfs_mod_supported_features *sfeatures) { zfeature_info_t *feature = &spa_feature_table[fid]; static const spa_feature_t nodeps[] = { SPA_FEATURE_NONE }; ASSERT(name != NULL); ASSERT(desc != NULL); ASSERT((flags & ZFEATURE_FLAG_READONLY_COMPAT) == 0 || (flags & ZFEATURE_FLAG_MOS) == 0); ASSERT3U(fid, <, SPA_FEATURES); ASSERT(zfeature_is_valid_guid(guid)); if (deps == NULL) deps = nodeps; VERIFY(((flags & ZFEATURE_FLAG_PER_DATASET) == 0) || (deps_contains_feature(deps, SPA_FEATURE_EXTENSIBLE_DATASET))); feature->fi_feature = fid; feature->fi_guid = guid; feature->fi_uname = name; feature->fi_desc = desc; feature->fi_flags = flags; feature->fi_type = type; feature->fi_depends = deps; feature->fi_zfs_mod_supported = zfs_mod_supported_feature(guid, sfeatures); } /* * Every feature has a GUID of the form com.example:feature_name. The * reversed DNS name ensures that the feature's GUID is unique across all ZFS * implementations. This allows companies to independently develop and * release features. Examples include org.delphix and org.datto. Previously, * features developed on one implementation have used that implementation's * domain name (e.g. org.illumos and org.zfsonlinux). Use of the org.openzfs * domain name is recommended for new features which are developed by the * OpenZFS community and its platforms. This domain may optionally be used by * companies developing features for initial release through an OpenZFS * implementation. Use of the org.openzfs domain requires reserving the * feature name in advance with the OpenZFS project. */ void zpool_feature_init(void) { struct zfs_mod_supported_features *sfeatures = zfs_mod_list_supported(ZFS_SYSFS_POOL_FEATURES); zfeature_register(SPA_FEATURE_ASYNC_DESTROY, "com.delphix:async_destroy", "async_destroy", "Destroy filesystems asynchronously.", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); zfeature_register(SPA_FEATURE_EMPTY_BPOBJ, "com.delphix:empty_bpobj", "empty_bpobj", "Snapshots use less space.", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); zfeature_register(SPA_FEATURE_LZ4_COMPRESS, "org.illumos:lz4_compress", "lz4_compress", "LZ4 compression algorithm support.", ZFEATURE_FLAG_ACTIVATE_ON_ENABLE, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); zfeature_register(SPA_FEATURE_MULTI_VDEV_CRASH_DUMP, "com.joyent:multi_vdev_crash_dump", "multi_vdev_crash_dump", "Crash dumps to multiple vdev pools.", 0, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); zfeature_register(SPA_FEATURE_SPACEMAP_HISTOGRAM, "com.delphix:spacemap_histogram", "spacemap_histogram", "Spacemaps maintain space histograms.", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); zfeature_register(SPA_FEATURE_ENABLED_TXG, "com.delphix:enabled_txg", "enabled_txg", "Record txg at which a feature is enabled", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); { static const spa_feature_t hole_birth_deps[] = { SPA_FEATURE_ENABLED_TXG, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_HOLE_BIRTH, "com.delphix:hole_birth", "hole_birth", "Retain hole birth txg for more precise zfs send", ZFEATURE_FLAG_MOS | ZFEATURE_FLAG_ACTIVATE_ON_ENABLE, ZFEATURE_TYPE_BOOLEAN, hole_birth_deps, sfeatures); } zfeature_register(SPA_FEATURE_POOL_CHECKPOINT, "com.delphix:zpool_checkpoint", "zpool_checkpoint", "Pool state can be checkpointed, allowing rewind later.", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); zfeature_register(SPA_FEATURE_SPACEMAP_V2, "com.delphix:spacemap_v2", "spacemap_v2", "Space maps representing large segments are more efficient.", ZFEATURE_FLAG_READONLY_COMPAT | ZFEATURE_FLAG_ACTIVATE_ON_ENABLE, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); zfeature_register(SPA_FEATURE_EXTENSIBLE_DATASET, "com.delphix:extensible_dataset", "extensible_dataset", "Enhanced dataset functionality, used by other features.", 0, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); { static const spa_feature_t bookmarks_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_BOOKMARKS, "com.delphix:bookmarks", "bookmarks", "\"zfs bookmark\" command", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, bookmarks_deps, sfeatures); } { static const spa_feature_t filesystem_limits_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_FS_SS_LIMIT, "com.joyent:filesystem_limits", "filesystem_limits", "Filesystem and snapshot limits.", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, filesystem_limits_deps, sfeatures); } zfeature_register(SPA_FEATURE_EMBEDDED_DATA, "com.delphix:embedded_data", "embedded_data", "Blocks which compress very well use even less space.", ZFEATURE_FLAG_MOS | ZFEATURE_FLAG_ACTIVATE_ON_ENABLE, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); { static const spa_feature_t livelist_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_LIVELIST, "com.delphix:livelist", "livelist", "Improved clone deletion performance.", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, livelist_deps, sfeatures); } { static const spa_feature_t log_spacemap_deps[] = { SPA_FEATURE_SPACEMAP_V2, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_LOG_SPACEMAP, "com.delphix:log_spacemap", "log_spacemap", "Log metaslab changes on a single spacemap and " "flush them periodically.", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, log_spacemap_deps, sfeatures); } { static const spa_feature_t large_blocks_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_LARGE_BLOCKS, "org.open-zfs:large_blocks", "large_blocks", "Support for blocks larger than 128KB.", ZFEATURE_FLAG_PER_DATASET, ZFEATURE_TYPE_BOOLEAN, large_blocks_deps, sfeatures); } { static const spa_feature_t large_dnode_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_LARGE_DNODE, "org.zfsonlinux:large_dnode", "large_dnode", "Variable on-disk size of dnodes.", ZFEATURE_FLAG_PER_DATASET, ZFEATURE_TYPE_BOOLEAN, large_dnode_deps, sfeatures); } { static const spa_feature_t sha512_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_SHA512, "org.illumos:sha512", "sha512", "SHA-512/256 hash algorithm.", ZFEATURE_FLAG_PER_DATASET, ZFEATURE_TYPE_BOOLEAN, sha512_deps, sfeatures); } { static const spa_feature_t skein_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_SKEIN, "org.illumos:skein", "skein", "Skein hash algorithm.", ZFEATURE_FLAG_PER_DATASET, ZFEATURE_TYPE_BOOLEAN, skein_deps, sfeatures); } { static const spa_feature_t edonr_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_EDONR, "org.illumos:edonr", "edonr", "Edon-R hash algorithm.", ZFEATURE_FLAG_PER_DATASET, ZFEATURE_TYPE_BOOLEAN, edonr_deps, sfeatures); } { static const spa_feature_t redact_books_deps[] = { SPA_FEATURE_BOOKMARK_V2, SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_BOOKMARKS, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_REDACTION_BOOKMARKS, "com.delphix:redaction_bookmarks", "redaction_bookmarks", "Support for bookmarks which store redaction lists for zfs " "redacted send/recv.", 0, ZFEATURE_TYPE_BOOLEAN, redact_books_deps, sfeatures); } { static const spa_feature_t redact_datasets_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_REDACTED_DATASETS, "com.delphix:redacted_datasets", "redacted_datasets", "Support for redacted datasets, produced by receiving " "a redacted zfs send stream.", ZFEATURE_FLAG_PER_DATASET, ZFEATURE_TYPE_UINT64_ARRAY, redact_datasets_deps, sfeatures); } { static const spa_feature_t bookmark_written_deps[] = { SPA_FEATURE_BOOKMARK_V2, SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_BOOKMARKS, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_BOOKMARK_WRITTEN, "com.delphix:bookmark_written", "bookmark_written", "Additional accounting, enabling the written# " "property (space written since a bookmark), " "and estimates of send stream sizes for incrementals from " "bookmarks.", 0, ZFEATURE_TYPE_BOOLEAN, bookmark_written_deps, sfeatures); } zfeature_register(SPA_FEATURE_DEVICE_REMOVAL, "com.delphix:device_removal", "device_removal", "Top-level vdevs can be removed, reducing logical pool size.", ZFEATURE_FLAG_MOS, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); { static const spa_feature_t obsolete_counts_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_DEVICE_REMOVAL, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_OBSOLETE_COUNTS, "com.delphix:obsolete_counts", "obsolete_counts", "Reduce memory used by removed devices when their blocks " "are freed or remapped.", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, obsolete_counts_deps, sfeatures); } { static const spa_feature_t userobj_accounting_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_USEROBJ_ACCOUNTING, "org.zfsonlinux:userobj_accounting", "userobj_accounting", "User/Group object accounting.", ZFEATURE_FLAG_READONLY_COMPAT | ZFEATURE_FLAG_PER_DATASET, ZFEATURE_TYPE_BOOLEAN, userobj_accounting_deps, sfeatures); } { static const spa_feature_t bookmark_v2_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_BOOKMARKS, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_BOOKMARK_V2, "com.datto:bookmark_v2", "bookmark_v2", "Support for larger bookmarks", 0, ZFEATURE_TYPE_BOOLEAN, bookmark_v2_deps, sfeatures); } { static const spa_feature_t encryption_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_BOOKMARK_V2, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_ENCRYPTION, "com.datto:encryption", "encryption", "Support for dataset level encryption", ZFEATURE_FLAG_PER_DATASET, ZFEATURE_TYPE_BOOLEAN, encryption_deps, sfeatures); } { static const spa_feature_t project_quota_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_PROJECT_QUOTA, "org.zfsonlinux:project_quota", "project_quota", "space/object accounting based on project ID.", ZFEATURE_FLAG_READONLY_COMPAT | ZFEATURE_FLAG_PER_DATASET, ZFEATURE_TYPE_BOOLEAN, project_quota_deps, sfeatures); } zfeature_register(SPA_FEATURE_ALLOCATION_CLASSES, "org.zfsonlinux:allocation_classes", "allocation_classes", "Support for separate allocation classes.", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); zfeature_register(SPA_FEATURE_RESILVER_DEFER, "com.datto:resilver_defer", "resilver_defer", "Support for deferring new resilvers when one is already running.", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); zfeature_register(SPA_FEATURE_DEVICE_REBUILD, "org.openzfs:device_rebuild", "device_rebuild", "Support for sequential mirror/dRAID device rebuilds", ZFEATURE_FLAG_READONLY_COMPAT, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); { static const spa_feature_t zstd_deps[] = { SPA_FEATURE_EXTENSIBLE_DATASET, SPA_FEATURE_NONE }; zfeature_register(SPA_FEATURE_ZSTD_COMPRESS, "org.freebsd:zstd_compress", "zstd_compress", "zstd compression algorithm support.", ZFEATURE_FLAG_PER_DATASET, ZFEATURE_TYPE_BOOLEAN, zstd_deps, sfeatures); } zfeature_register(SPA_FEATURE_DRAID, "org.openzfs:draid", "draid", "Support for distributed spare RAID", ZFEATURE_FLAG_MOS, ZFEATURE_TYPE_BOOLEAN, NULL, sfeatures); + { + static const spa_feature_t zilsaxattr_deps[] = { + SPA_FEATURE_EXTENSIBLE_DATASET, + SPA_FEATURE_NONE + }; + zfeature_register(SPA_FEATURE_ZILSAXATTR, + "org.openzfs:zilsaxattr", "zilsaxattr", + "Support for xattr=sa extended attribute logging in ZIL.", + ZFEATURE_FLAG_PER_DATASET | ZFEATURE_FLAG_READONLY_COMPAT, + ZFEATURE_TYPE_BOOLEAN, zilsaxattr_deps, sfeatures); + } + zfs_mod_list_supported_free(sfeatures); } #if defined(_KERNEL) EXPORT_SYMBOL(zfeature_lookup_guid); EXPORT_SYMBOL(zfeature_lookup_name); EXPORT_SYMBOL(zfeature_is_supported); EXPORT_SYMBOL(zfeature_is_valid_guid); EXPORT_SYMBOL(zfeature_depends_on); EXPORT_SYMBOL(zpool_feature_init); EXPORT_SYMBOL(spa_feature_table); #endif diff --git a/module/zfs/zfs_log.c b/module/zfs/zfs_log.c index babf0406eba5..9df801870a4f 100644 --- a/module/zfs/zfs_log.c +++ b/module/zfs/zfs_log.c @@ -1,790 +1,824 @@ /* * 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 (c) 2015, 2018 by Delphix. All rights reserved. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include /* * These zfs_log_* functions must be called within a dmu tx, in one * of 2 contexts depending on zilog->z_replay: * * Non replay mode * --------------- * We need to record the transaction so that if it is committed to * the Intent Log then it can be replayed. An intent log transaction * structure (itx_t) is allocated and all the information necessary to * possibly replay the transaction is saved in it. The itx is then assigned * a sequence number and inserted in the in-memory list anchored in the zilog. * * Replay mode * ----------- * We need to mark the intent log record as replayed in the log header. * This is done in the same transaction as the replay so that they * commit atomically. */ int zfs_log_create_txtype(zil_create_t type, vsecattr_t *vsecp, vattr_t *vap) { int isxvattr = (vap->va_mask & ATTR_XVATTR); switch (type) { case Z_FILE: if (vsecp == NULL && !isxvattr) return (TX_CREATE); if (vsecp && isxvattr) return (TX_CREATE_ACL_ATTR); if (vsecp) return (TX_CREATE_ACL); else return (TX_CREATE_ATTR); case Z_DIR: if (vsecp == NULL && !isxvattr) return (TX_MKDIR); if (vsecp && isxvattr) return (TX_MKDIR_ACL_ATTR); if (vsecp) return (TX_MKDIR_ACL); else return (TX_MKDIR_ATTR); case Z_XATTRDIR: return (TX_MKXATTR); } ASSERT(0); return (TX_MAX_TYPE); } /* * build up the log data necessary for logging xvattr_t * First lr_attr_t is initialized. following the lr_attr_t * is the mapsize and attribute bitmap copied from the xvattr_t. * Following the bitmap and bitmapsize two 64 bit words are reserved * for the create time which may be set. Following the create time * records a single 64 bit integer which has the bits to set on * replay for the xvattr. */ static void zfs_log_xvattr(lr_attr_t *lrattr, xvattr_t *xvap) { uint32_t *bitmap; uint64_t *attrs; uint64_t *crtime; xoptattr_t *xoap; void *scanstamp; int i; xoap = xva_getxoptattr(xvap); ASSERT(xoap); lrattr->lr_attr_masksize = xvap->xva_mapsize; bitmap = &lrattr->lr_attr_bitmap; for (i = 0; i != xvap->xva_mapsize; i++, bitmap++) { *bitmap = xvap->xva_reqattrmap[i]; } /* Now pack the attributes up in a single uint64_t */ attrs = (uint64_t *)bitmap; *attrs = 0; crtime = attrs + 1; bzero(crtime, 2 * sizeof (uint64_t)); scanstamp = (caddr_t)(crtime + 2); bzero(scanstamp, AV_SCANSTAMP_SZ); if (XVA_ISSET_REQ(xvap, XAT_READONLY)) *attrs |= (xoap->xoa_readonly == 0) ? 0 : XAT0_READONLY; if (XVA_ISSET_REQ(xvap, XAT_HIDDEN)) *attrs |= (xoap->xoa_hidden == 0) ? 0 : XAT0_HIDDEN; if (XVA_ISSET_REQ(xvap, XAT_SYSTEM)) *attrs |= (xoap->xoa_system == 0) ? 0 : XAT0_SYSTEM; if (XVA_ISSET_REQ(xvap, XAT_ARCHIVE)) *attrs |= (xoap->xoa_archive == 0) ? 0 : XAT0_ARCHIVE; if (XVA_ISSET_REQ(xvap, XAT_IMMUTABLE)) *attrs |= (xoap->xoa_immutable == 0) ? 0 : XAT0_IMMUTABLE; if (XVA_ISSET_REQ(xvap, XAT_NOUNLINK)) *attrs |= (xoap->xoa_nounlink == 0) ? 0 : XAT0_NOUNLINK; if (XVA_ISSET_REQ(xvap, XAT_APPENDONLY)) *attrs |= (xoap->xoa_appendonly == 0) ? 0 : XAT0_APPENDONLY; if (XVA_ISSET_REQ(xvap, XAT_OPAQUE)) *attrs |= (xoap->xoa_opaque == 0) ? 0 : XAT0_APPENDONLY; if (XVA_ISSET_REQ(xvap, XAT_NODUMP)) *attrs |= (xoap->xoa_nodump == 0) ? 0 : XAT0_NODUMP; if (XVA_ISSET_REQ(xvap, XAT_AV_QUARANTINED)) *attrs |= (xoap->xoa_av_quarantined == 0) ? 0 : XAT0_AV_QUARANTINED; if (XVA_ISSET_REQ(xvap, XAT_AV_MODIFIED)) *attrs |= (xoap->xoa_av_modified == 0) ? 0 : XAT0_AV_MODIFIED; if (XVA_ISSET_REQ(xvap, XAT_CREATETIME)) ZFS_TIME_ENCODE(&xoap->xoa_createtime, crtime); if (XVA_ISSET_REQ(xvap, XAT_AV_SCANSTAMP)) { ASSERT(!XVA_ISSET_REQ(xvap, XAT_PROJID)); bcopy(xoap->xoa_av_scanstamp, 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(&xoap->xoa_projid, scanstamp, sizeof (uint64_t)); } if (XVA_ISSET_REQ(xvap, XAT_REPARSE)) *attrs |= (xoap->xoa_reparse == 0) ? 0 : XAT0_REPARSE; if (XVA_ISSET_REQ(xvap, XAT_OFFLINE)) *attrs |= (xoap->xoa_offline == 0) ? 0 : XAT0_OFFLINE; if (XVA_ISSET_REQ(xvap, XAT_SPARSE)) *attrs |= (xoap->xoa_sparse == 0) ? 0 : XAT0_SPARSE; if (XVA_ISSET_REQ(xvap, XAT_PROJINHERIT)) *attrs |= (xoap->xoa_projinherit == 0) ? 0 : XAT0_PROJINHERIT; } static void * zfs_log_fuid_ids(zfs_fuid_info_t *fuidp, void *start) { zfs_fuid_t *zfuid; uint64_t *fuidloc = start; /* First copy in the ACE FUIDs */ for (zfuid = list_head(&fuidp->z_fuids); zfuid; zfuid = list_next(&fuidp->z_fuids, zfuid)) { *fuidloc++ = zfuid->z_logfuid; } return (fuidloc); } static void * zfs_log_fuid_domains(zfs_fuid_info_t *fuidp, void *start) { zfs_fuid_domain_t *zdomain; /* now copy in the domain info, if any */ if (fuidp->z_domain_str_sz != 0) { for (zdomain = list_head(&fuidp->z_domains); zdomain; zdomain = list_next(&fuidp->z_domains, zdomain)) { bcopy((void *)zdomain->z_domain, start, strlen(zdomain->z_domain) + 1); start = (caddr_t)start + strlen(zdomain->z_domain) + 1; } } return (start); } /* * If zp is an xattr node, check whether the xattr owner is unlinked. * We don't want to log anything if the owner is unlinked. */ static int zfs_xattr_owner_unlinked(znode_t *zp) { int unlinked = 0; znode_t *dzp; #ifdef __FreeBSD__ znode_t *tzp = zp; /* * zrele drops the vnode lock which violates the VOP locking contract * on FreeBSD. See comment at the top of zfs_replay.c for more detail. */ /* * if zp is XATTR node, keep walking up via z_xattr_parent until we * get the owner */ while (tzp->z_pflags & ZFS_XATTR) { ASSERT3U(zp->z_xattr_parent, !=, 0); if (zfs_zget(ZTOZSB(tzp), tzp->z_xattr_parent, &dzp) != 0) { unlinked = 1; break; } if (tzp != zp) zrele(tzp); tzp = dzp; unlinked = tzp->z_unlinked; } if (tzp != zp) zrele(tzp); #else zhold(zp); /* * if zp is XATTR node, keep walking up via z_xattr_parent until we * get the owner */ while (zp->z_pflags & ZFS_XATTR) { ASSERT3U(zp->z_xattr_parent, !=, 0); if (zfs_zget(ZTOZSB(zp), zp->z_xattr_parent, &dzp) != 0) { unlinked = 1; break; } zrele(zp); zp = dzp; unlinked = zp->z_unlinked; } zrele(zp); #endif return (unlinked); } /* * Handles TX_CREATE, TX_CREATE_ATTR, TX_MKDIR, TX_MKDIR_ATTR and * TK_MKXATTR transactions. * * TX_CREATE and TX_MKDIR are standard creates, but they may have FUID * domain information appended prior to the name. In this case the * uid/gid in the log record will be a log centric FUID. * * TX_CREATE_ACL_ATTR and TX_MKDIR_ACL_ATTR handle special creates that * may contain attributes, ACL and optional fuid information. * * TX_CREATE_ACL and TX_MKDIR_ACL handle special creates that specify * and ACL and normal users/groups in the ACEs. * * There may be an optional xvattr attribute information similar * to zfs_log_setattr. * * Also, after the file name "domain" strings may be appended. */ void zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, znode_t *dzp, znode_t *zp, const char *name, vsecattr_t *vsecp, zfs_fuid_info_t *fuidp, vattr_t *vap) { itx_t *itx; lr_create_t *lr; lr_acl_create_t *lracl; size_t aclsize = 0; size_t xvatsize = 0; size_t txsize; xvattr_t *xvap = (xvattr_t *)vap; void *end; size_t lrsize; size_t namesize = strlen(name) + 1; size_t fuidsz = 0; if (zil_replaying(zilog, tx) || zfs_xattr_owner_unlinked(dzp)) return; /* * If we have FUIDs present then add in space for * domains and ACE fuid's if any. */ if (fuidp) { fuidsz += fuidp->z_domain_str_sz; fuidsz += fuidp->z_fuid_cnt * sizeof (uint64_t); } if (vap->va_mask & ATTR_XVATTR) xvatsize = ZIL_XVAT_SIZE(xvap->xva_mapsize); if ((int)txtype == TX_CREATE_ATTR || (int)txtype == TX_MKDIR_ATTR || (int)txtype == TX_CREATE || (int)txtype == TX_MKDIR || (int)txtype == TX_MKXATTR) { txsize = sizeof (*lr) + namesize + fuidsz + xvatsize; lrsize = sizeof (*lr); } else { txsize = sizeof (lr_acl_create_t) + namesize + fuidsz + ZIL_ACE_LENGTH(aclsize) + xvatsize; lrsize = sizeof (lr_acl_create_t); } itx = zil_itx_create(txtype, txsize); lr = (lr_create_t *)&itx->itx_lr; lr->lr_doid = dzp->z_id; lr->lr_foid = zp->z_id; /* Store dnode slot count in 8 bits above object id. */ LR_FOID_SET_SLOTS(lr->lr_foid, zp->z_dnodesize >> DNODE_SHIFT); lr->lr_mode = zp->z_mode; if (!IS_EPHEMERAL(KUID_TO_SUID(ZTOUID(zp)))) { lr->lr_uid = (uint64_t)KUID_TO_SUID(ZTOUID(zp)); } else { lr->lr_uid = fuidp->z_fuid_owner; } if (!IS_EPHEMERAL(KGID_TO_SGID(ZTOGID(zp)))) { lr->lr_gid = (uint64_t)KGID_TO_SGID(ZTOGID(zp)); } else { lr->lr_gid = fuidp->z_fuid_group; } (void) sa_lookup(zp->z_sa_hdl, SA_ZPL_GEN(ZTOZSB(zp)), &lr->lr_gen, sizeof (uint64_t)); (void) sa_lookup(zp->z_sa_hdl, SA_ZPL_CRTIME(ZTOZSB(zp)), lr->lr_crtime, sizeof (uint64_t) * 2); if (sa_lookup(zp->z_sa_hdl, SA_ZPL_RDEV(ZTOZSB(zp)), &lr->lr_rdev, sizeof (lr->lr_rdev)) != 0) lr->lr_rdev = 0; /* * Fill in xvattr info if any */ if (vap->va_mask & ATTR_XVATTR) { zfs_log_xvattr((lr_attr_t *)((caddr_t)lr + lrsize), xvap); end = (caddr_t)lr + lrsize + xvatsize; } else { end = (caddr_t)lr + lrsize; } /* Now fill in any ACL info */ if (vsecp) { lracl = (lr_acl_create_t *)&itx->itx_lr; lracl->lr_aclcnt = vsecp->vsa_aclcnt; lracl->lr_acl_bytes = aclsize; lracl->lr_domcnt = fuidp ? fuidp->z_domain_cnt : 0; lracl->lr_fuidcnt = fuidp ? fuidp->z_fuid_cnt : 0; if (vsecp->vsa_aclflags & VSA_ACE_ACLFLAGS) lracl->lr_acl_flags = (uint64_t)vsecp->vsa_aclflags; else lracl->lr_acl_flags = 0; bcopy(vsecp->vsa_aclentp, end, aclsize); end = (caddr_t)end + ZIL_ACE_LENGTH(aclsize); } /* drop in FUID info */ if (fuidp) { end = zfs_log_fuid_ids(fuidp, end); end = zfs_log_fuid_domains(fuidp, end); } /* * Now place file name in log record */ bcopy(name, end, namesize); zil_itx_assign(zilog, itx, tx); } /* * Handles both TX_REMOVE and TX_RMDIR transactions. */ void zfs_log_remove(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, znode_t *dzp, const char *name, uint64_t foid, boolean_t unlinked) { itx_t *itx; lr_remove_t *lr; size_t namesize = strlen(name) + 1; if (zil_replaying(zilog, tx) || zfs_xattr_owner_unlinked(dzp)) return; itx = zil_itx_create(txtype, sizeof (*lr) + namesize); lr = (lr_remove_t *)&itx->itx_lr; lr->lr_doid = dzp->z_id; bcopy(name, (char *)(lr + 1), namesize); itx->itx_oid = foid; /* * Object ids can be re-instantiated in the next txg so * remove any async transactions to avoid future leaks. * This can happen if a fsync occurs on the re-instantiated * object for a WR_INDIRECT or WR_NEED_COPY write, which gets * the new file data and flushes a write record for the old object. */ if (unlinked) { ASSERT((txtype & ~TX_CI) == TX_REMOVE); zil_remove_async(zilog, foid); } zil_itx_assign(zilog, itx, tx); } /* * Handles TX_LINK transactions. */ void zfs_log_link(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, znode_t *dzp, znode_t *zp, const char *name) { itx_t *itx; lr_link_t *lr; size_t namesize = strlen(name) + 1; if (zil_replaying(zilog, tx)) return; itx = zil_itx_create(txtype, sizeof (*lr) + namesize); lr = (lr_link_t *)&itx->itx_lr; lr->lr_doid = dzp->z_id; lr->lr_link_obj = zp->z_id; bcopy(name, (char *)(lr + 1), namesize); zil_itx_assign(zilog, itx, tx); } /* * Handles TX_SYMLINK transactions. */ void zfs_log_symlink(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, znode_t *dzp, znode_t *zp, const char *name, const char *link) { itx_t *itx; lr_create_t *lr; size_t namesize = strlen(name) + 1; size_t linksize = strlen(link) + 1; if (zil_replaying(zilog, tx)) return; itx = zil_itx_create(txtype, sizeof (*lr) + namesize + linksize); lr = (lr_create_t *)&itx->itx_lr; lr->lr_doid = dzp->z_id; lr->lr_foid = zp->z_id; lr->lr_uid = KUID_TO_SUID(ZTOUID(zp)); lr->lr_gid = KGID_TO_SGID(ZTOGID(zp)); lr->lr_mode = zp->z_mode; (void) sa_lookup(zp->z_sa_hdl, SA_ZPL_GEN(ZTOZSB(zp)), &lr->lr_gen, sizeof (uint64_t)); (void) sa_lookup(zp->z_sa_hdl, SA_ZPL_CRTIME(ZTOZSB(zp)), lr->lr_crtime, sizeof (uint64_t) * 2); bcopy(name, (char *)(lr + 1), namesize); bcopy(link, (char *)(lr + 1) + namesize, linksize); zil_itx_assign(zilog, itx, tx); } /* * Handles TX_RENAME transactions. */ void zfs_log_rename(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, znode_t *sdzp, const char *sname, znode_t *tdzp, const char *dname, znode_t *szp) { itx_t *itx; lr_rename_t *lr; size_t snamesize = strlen(sname) + 1; size_t dnamesize = strlen(dname) + 1; if (zil_replaying(zilog, tx)) return; itx = zil_itx_create(txtype, sizeof (*lr) + snamesize + dnamesize); lr = (lr_rename_t *)&itx->itx_lr; lr->lr_sdoid = sdzp->z_id; lr->lr_tdoid = tdzp->z_id; bcopy(sname, (char *)(lr + 1), snamesize); bcopy(dname, (char *)(lr + 1) + snamesize, dnamesize); itx->itx_oid = szp->z_id; zil_itx_assign(zilog, itx, tx); } /* * zfs_log_write() handles TX_WRITE transactions. The specified callback is * called as soon as the write is on stable storage (be it via a DMU sync or a * ZIL commit). */ static long zfs_immediate_write_sz = 32768; void zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype, znode_t *zp, offset_t off, ssize_t resid, int ioflag, zil_callback_t callback, void *callback_data) { dmu_buf_impl_t *db = (dmu_buf_impl_t *)sa_get_db(zp->z_sa_hdl); uint32_t blocksize = zp->z_blksz; itx_wr_state_t write_state; uintptr_t fsync_cnt; uint64_t gen = 0; ssize_t size = resid; if (zil_replaying(zilog, tx) || zp->z_unlinked || zfs_xattr_owner_unlinked(zp)) { if (callback != NULL) callback(callback_data); return; } if (zilog->zl_logbias == ZFS_LOGBIAS_THROUGHPUT) write_state = WR_INDIRECT; else if (!spa_has_slogs(zilog->zl_spa) && resid >= zfs_immediate_write_sz) write_state = WR_INDIRECT; else if (ioflag & (O_SYNC | O_DSYNC)) write_state = WR_COPIED; else write_state = WR_NEED_COPY; if ((fsync_cnt = (uintptr_t)tsd_get(zfs_fsyncer_key)) != 0) { (void) tsd_set(zfs_fsyncer_key, (void *)(fsync_cnt - 1)); } (void) sa_lookup(zp->z_sa_hdl, SA_ZPL_GEN(ZTOZSB(zp)), &gen, sizeof (gen)); while (resid) { itx_t *itx; lr_write_t *lr; itx_wr_state_t wr_state = write_state; ssize_t len = resid; /* * A WR_COPIED record must fit entirely in one log block. * Large writes can use WR_NEED_COPY, which the ZIL will * split into multiple records across several log blocks * if necessary. */ if (wr_state == WR_COPIED && resid > zil_max_copied_data(zilog)) wr_state = WR_NEED_COPY; else if (wr_state == WR_INDIRECT) len = MIN(blocksize - P2PHASE(off, blocksize), resid); itx = zil_itx_create(txtype, sizeof (*lr) + (wr_state == WR_COPIED ? len : 0)); lr = (lr_write_t *)&itx->itx_lr; /* * For WR_COPIED records, copy the data into the lr_write_t. */ if (wr_state == WR_COPIED) { int err; DB_DNODE_ENTER(db); err = dmu_read_by_dnode(DB_DNODE(db), off, len, lr + 1, DMU_READ_NO_PREFETCH); if (err != 0) { zil_itx_destroy(itx); itx = zil_itx_create(txtype, sizeof (*lr)); lr = (lr_write_t *)&itx->itx_lr; wr_state = WR_NEED_COPY; } DB_DNODE_EXIT(db); } itx->itx_wr_state = wr_state; lr->lr_foid = zp->z_id; lr->lr_offset = off; lr->lr_length = len; lr->lr_blkoff = 0; BP_ZERO(&lr->lr_blkptr); itx->itx_private = ZTOZSB(zp); itx->itx_gen = gen; if (!(ioflag & (O_SYNC | O_DSYNC)) && (zp->z_sync_cnt == 0) && (fsync_cnt == 0)) itx->itx_sync = B_FALSE; itx->itx_callback = callback; itx->itx_callback_data = callback_data; zil_itx_assign(zilog, itx, tx); off += len; resid -= len; } if (write_state == WR_COPIED || write_state == WR_NEED_COPY) { dsl_pool_wrlog_count(zilog->zl_dmu_pool, size, tx->tx_txg); } } /* * Handles TX_TRUNCATE transactions. */ void zfs_log_truncate(zilog_t *zilog, dmu_tx_t *tx, int txtype, znode_t *zp, uint64_t off, uint64_t len) { itx_t *itx; lr_truncate_t *lr; if (zil_replaying(zilog, tx) || zp->z_unlinked || zfs_xattr_owner_unlinked(zp)) return; itx = zil_itx_create(txtype, sizeof (*lr)); lr = (lr_truncate_t *)&itx->itx_lr; lr->lr_foid = zp->z_id; lr->lr_offset = off; lr->lr_length = len; itx->itx_sync = (zp->z_sync_cnt != 0); zil_itx_assign(zilog, itx, tx); } /* * Handles TX_SETATTR transactions. */ void zfs_log_setattr(zilog_t *zilog, dmu_tx_t *tx, int txtype, znode_t *zp, vattr_t *vap, uint_t mask_applied, zfs_fuid_info_t *fuidp) { itx_t *itx; lr_setattr_t *lr; xvattr_t *xvap = (xvattr_t *)vap; size_t recsize = sizeof (lr_setattr_t); void *start; if (zil_replaying(zilog, tx) || zp->z_unlinked) return; /* * If XVATTR set, then log record size needs to allow * for lr_attr_t + xvattr mask, mapsize and create time * plus actual attribute values */ if (vap->va_mask & ATTR_XVATTR) recsize = sizeof (*lr) + ZIL_XVAT_SIZE(xvap->xva_mapsize); if (fuidp) recsize += fuidp->z_domain_str_sz; itx = zil_itx_create(txtype, recsize); lr = (lr_setattr_t *)&itx->itx_lr; lr->lr_foid = zp->z_id; lr->lr_mask = (uint64_t)mask_applied; lr->lr_mode = (uint64_t)vap->va_mode; if ((mask_applied & ATTR_UID) && IS_EPHEMERAL(vap->va_uid)) lr->lr_uid = fuidp->z_fuid_owner; else lr->lr_uid = (uint64_t)vap->va_uid; if ((mask_applied & ATTR_GID) && IS_EPHEMERAL(vap->va_gid)) lr->lr_gid = fuidp->z_fuid_group; else lr->lr_gid = (uint64_t)vap->va_gid; lr->lr_size = (uint64_t)vap->va_size; ZFS_TIME_ENCODE(&vap->va_atime, lr->lr_atime); ZFS_TIME_ENCODE(&vap->va_mtime, lr->lr_mtime); start = (lr_setattr_t *)(lr + 1); if (vap->va_mask & ATTR_XVATTR) { zfs_log_xvattr((lr_attr_t *)start, xvap); start = (caddr_t)start + ZIL_XVAT_SIZE(xvap->xva_mapsize); } /* * Now stick on domain information if any on end */ if (fuidp) (void) zfs_log_fuid_domains(fuidp, start); itx->itx_sync = (zp->z_sync_cnt != 0); zil_itx_assign(zilog, itx, tx); } +/* + * Handles TX_SETSAXATTR transactions. + */ +void +zfs_log_setsaxattr(zilog_t *zilog, dmu_tx_t *tx, int txtype, + znode_t *zp, const char *name, const void *value, size_t size) +{ + itx_t *itx; + lr_setsaxattr_t *lr; + size_t recsize = sizeof (lr_setsaxattr_t); + void *xattrstart; + int namelen; + + if (zil_replaying(zilog, tx) || zp->z_unlinked) + return; + + namelen = strlen(name) + 1; + recsize += (namelen + size); + itx = zil_itx_create(txtype, recsize); + lr = (lr_setsaxattr_t *)&itx->itx_lr; + lr->lr_foid = zp->z_id; + xattrstart = (char *)(lr + 1); + bcopy(name, xattrstart, namelen); + if (value != NULL) { + bcopy(value, (char *)xattrstart + namelen, size); + lr->lr_size = size; + } else { + lr->lr_size = 0; + } + + itx->itx_sync = (zp->z_sync_cnt != 0); + zil_itx_assign(zilog, itx, tx); +} + /* * Handles TX_ACL transactions. */ void zfs_log_acl(zilog_t *zilog, dmu_tx_t *tx, znode_t *zp, vsecattr_t *vsecp, zfs_fuid_info_t *fuidp) { itx_t *itx; lr_acl_v0_t *lrv0; lr_acl_t *lr; int txtype; int lrsize; size_t txsize; size_t aclbytes = vsecp->vsa_aclentsz; if (zil_replaying(zilog, tx) || zp->z_unlinked) return; txtype = (ZTOZSB(zp)->z_version < ZPL_VERSION_FUID) ? TX_ACL_V0 : TX_ACL; if (txtype == TX_ACL) lrsize = sizeof (*lr); else lrsize = sizeof (*lrv0); txsize = lrsize + ((txtype == TX_ACL) ? ZIL_ACE_LENGTH(aclbytes) : aclbytes) + (fuidp ? fuidp->z_domain_str_sz : 0) + sizeof (uint64_t) * (fuidp ? fuidp->z_fuid_cnt : 0); itx = zil_itx_create(txtype, txsize); lr = (lr_acl_t *)&itx->itx_lr; lr->lr_foid = zp->z_id; if (txtype == TX_ACL) { lr->lr_acl_bytes = aclbytes; lr->lr_domcnt = fuidp ? fuidp->z_domain_cnt : 0; lr->lr_fuidcnt = fuidp ? fuidp->z_fuid_cnt : 0; if (vsecp->vsa_mask & VSA_ACE_ACLFLAGS) lr->lr_acl_flags = (uint64_t)vsecp->vsa_aclflags; else lr->lr_acl_flags = 0; } lr->lr_aclcnt = (uint64_t)vsecp->vsa_aclcnt; if (txtype == TX_ACL_V0) { lrv0 = (lr_acl_v0_t *)lr; bcopy(vsecp->vsa_aclentp, (ace_t *)(lrv0 + 1), aclbytes); } else { void *start = (ace_t *)(lr + 1); bcopy(vsecp->vsa_aclentp, start, aclbytes); start = (caddr_t)start + ZIL_ACE_LENGTH(aclbytes); if (fuidp) { start = zfs_log_fuid_ids(fuidp, start); (void) zfs_log_fuid_domains(fuidp, start); } } itx->itx_sync = (zp->z_sync_cnt != 0); zil_itx_assign(zilog, itx, tx); } ZFS_MODULE_PARAM(zfs, zfs_, immediate_write_sz, LONG, ZMOD_RW, "Largest data block to write to zil"); diff --git a/module/zfs/zfs_replay.c b/module/zfs/zfs_replay.c index 860ca59298ec..3ccd96dc256d 100644 --- a/module/zfs/zfs_replay.c +++ b/module/zfs/zfs_replay.c @@ -1,992 +1,1075 @@ /* * 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 (c) 2012 Cyril Plisko. All rights reserved. * Copyright (c) 2013, 2017 by Delphix. All rights reserved. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include +#include +#include /* * NB: FreeBSD expects to be able to do vnode locking in lookup and * hold the locks across all subsequent VOPs until vput is called. * This means that its zfs vnops routines can't do any internal locking. * In order to have the same contract as the Linux vnops there would * needed to be duplicate locked vnops. If the vnops were used more widely * in common code this would likely be preferable. However, currently * this is the only file where this is the case. */ /* * Functions to replay ZFS intent log (ZIL) records * The functions are called through a function vector (zfs_replay_vector) * which is indexed by the transaction type. */ 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_mode = mode; #if defined(__FreeBSD__) || defined(__APPLE__) vap->va_type = IFTOVT(mode); #endif vap->va_uid = (uid_t)(IS_EPHEMERAL(uid)) ? -1 : uid; vap->va_gid = (gid_t)(IS_EPHEMERAL(gid)) ? -1 : gid; vap->va_rdev = zfs_cmpldev(rdev); vap->va_nodeid = nodeid; } static int zfs_replay_error(void *arg1, void *arg2, boolean_t byteswap) { (void) arg1, (void) arg2, (void) 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; znode_t *zp; 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); zfs_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(dzp, name, &xva.xva_vattr, 0, 0, &zp, 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); zfs_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(dzp, name, &xva.xva_vattr, &zp, kcred, vflg, &vsec); break; default: error = SET_ERROR(ENOTSUP); } bail: if (error == 0 && zp != NULL) { #ifdef __FreeBSD__ VOP_UNLOCK1(ZTOV(zp)); #endif zrele(zp); } zrele(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; znode_t *zp = 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; zfs_fallthrough; case TX_CREATE: if (name == NULL) name = (char *)start; error = zfs_create(dzp, name, &xva.xva_vattr, 0, 0, &zp, 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; zfs_fallthrough; case TX_MKDIR: if (name == NULL) name = (char *)(lr + 1); error = zfs_mkdir(dzp, name, &xva.xva_vattr, &zp, kcred, vflg, NULL); break; case TX_MKXATTR: error = zfs_make_xattrdir(dzp, &xva.xva_vattr, &zp, kcred); break; case TX_SYMLINK: name = (char *)(lr + 1); link = name + strlen(name) + 1; error = zfs_symlink(dzp, name, &xva.xva_vattr, link, &zp, kcred, vflg); break; default: error = SET_ERROR(ENOTSUP); } out: if (error == 0 && zp != NULL) { #ifdef __FreeBSD__ VOP_UNLOCK1(ZTOV(zp)); #endif zrele(zp); } zrele(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(dzp, name, kcred, vflg); break; case TX_RMDIR: error = zfs_rmdir(dzp, name, NULL, kcred, vflg); break; default: error = SET_ERROR(ENOTSUP); } zrele(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) { zrele(dzp); return (error); } if (lr->lr_common.lrc_txtype & TX_CI) vflg |= FIGNORECASE; error = zfs_link(dzp, zp, name, kcred, vflg); zrele(zp); zrele(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) { zrele(sdzp); return (error); } if (lr->lr_common.lrc_txtype & TX_CI) vflg |= FIGNORECASE; error = zfs_rename(sdzp, sname, tdzp, tname, kcred, vflg); zrele(tdzp); zrele(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; 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; } error = zfs_write_simple(zp, data, length, offset, NULL); zrele(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) { zrele(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); } zrele(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(zp, F_FREESP, &fl, O_RDWR | O_LARGEFILE, lr->lr_offset, kcred); zrele(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(zp, vap, 0, kcred); zfs_fuid_info_free(zfsvfs->z_fuid_replay); zfsvfs->z_fuid_replay = NULL; zrele(zp); return (error); } +static int +zfs_replay_setsaxattr(void *arg1, void *arg2, boolean_t byteswap) +{ + zfsvfs_t *zfsvfs = arg1; + lr_setsaxattr_t *lr = arg2; + znode_t *zp; + nvlist_t *nvl; + size_t sa_size; + char *name; + char *value; + size_t size; + int error = 0; + + ASSERT(spa_feature_is_active(zfsvfs->z_os->os_spa, + SPA_FEATURE_ZILSAXATTR)); + if (byteswap) + byteswap_uint64_array(lr, sizeof (*lr)); + + if ((error = zfs_zget(zfsvfs, lr->lr_foid, &zp)) != 0) + return (error); + + rw_enter(&zp->z_xattr_lock, RW_WRITER); + mutex_enter(&zp->z_lock); + if (zp->z_xattr_cached == NULL) + error = zfs_sa_get_xattr(zp); + mutex_exit(&zp->z_lock); + + if (error) + goto out; + + ASSERT(zp->z_xattr_cached); + nvl = zp->z_xattr_cached; + + /* Get xattr name, value and size from log record */ + size = lr->lr_size; + name = (char *)(lr + 1); + if (size == 0) { + value = NULL; + error = nvlist_remove(nvl, name, DATA_TYPE_BYTE_ARRAY); + } else { + value = name + strlen(name) + 1; + /* Limited to 32k to keep nvpair memory allocations small */ + if (size > DXATTR_MAX_ENTRY_SIZE) { + error = SET_ERROR(EFBIG); + goto out; + } + + /* Prevent the DXATTR SA from consuming the entire SA region */ + error = nvlist_size(nvl, &sa_size, NV_ENCODE_XDR); + if (error) + goto out; + + if (sa_size > DXATTR_MAX_SA_SIZE) { + error = SET_ERROR(EFBIG); + goto out; + } + + error = nvlist_add_byte_array(nvl, name, (uchar_t *)value, + size); + } + + /* + * Update the SA for additions, modifications, and removals. On + * error drop the inconsistent cached version of the nvlist, it + * will be reconstructed from the ARC when next accessed. + */ + if (error == 0) + error = zfs_sa_set_xattr(zp, name, value, size); + + if (error) { + nvlist_free(nvl); + zp->z_xattr_cached = NULL; + } + +out: + rw_exit(&zp->z_xattr_lock); + zrele(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(zp, &vsa, 0, kcred); zrele(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(zp, &vsa, 0, kcred); if (zfsvfs->z_fuid_replay) zfs_fuid_info_free(zfsvfs->z_fuid_replay); zfsvfs->z_fuid_replay = NULL; zrele(zp); return (error); } /* * Callback vectors for replaying records */ zil_replay_func_t *const 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 */ + zfs_replay_setsaxattr, /* TX_SETSAXATTR */ }; diff --git a/module/zfs/zfs_sa.c b/module/zfs/zfs_sa.c index 817f63048789..1f15cae00da8 100644 --- a/module/zfs/zfs_sa.c +++ b/module/zfs/zfs_sa.c @@ -1,446 +1,471 @@ /* * 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) 2010, Oracle and/or its affiliates. All rights reserved. */ #include #include #include #include #include #include #include +#include /* * ZPL attribute registration table. * Order of attributes doesn't matter * a unique value will be assigned for each * attribute that is file system specific * * This is just the set of ZPL attributes that this * version of ZFS deals with natively. The file system * could have other attributes stored in files, but they will be * ignored. The SA framework will preserve them, just that * this version of ZFS won't change or delete them. */ const sa_attr_reg_t zfs_attr_table[ZPL_END+1] = { {"ZPL_ATIME", sizeof (uint64_t) * 2, SA_UINT64_ARRAY, 0}, {"ZPL_MTIME", sizeof (uint64_t) * 2, SA_UINT64_ARRAY, 1}, {"ZPL_CTIME", sizeof (uint64_t) * 2, SA_UINT64_ARRAY, 2}, {"ZPL_CRTIME", sizeof (uint64_t) * 2, SA_UINT64_ARRAY, 3}, {"ZPL_GEN", sizeof (uint64_t), SA_UINT64_ARRAY, 4}, {"ZPL_MODE", sizeof (uint64_t), SA_UINT64_ARRAY, 5}, {"ZPL_SIZE", sizeof (uint64_t), SA_UINT64_ARRAY, 6}, {"ZPL_PARENT", sizeof (uint64_t), SA_UINT64_ARRAY, 7}, {"ZPL_LINKS", sizeof (uint64_t), SA_UINT64_ARRAY, 8}, {"ZPL_XATTR", sizeof (uint64_t), SA_UINT64_ARRAY, 9}, {"ZPL_RDEV", sizeof (uint64_t), SA_UINT64_ARRAY, 10}, {"ZPL_FLAGS", sizeof (uint64_t), SA_UINT64_ARRAY, 11}, {"ZPL_UID", sizeof (uint64_t), SA_UINT64_ARRAY, 12}, {"ZPL_GID", sizeof (uint64_t), SA_UINT64_ARRAY, 13}, {"ZPL_PAD", sizeof (uint64_t) * 4, SA_UINT64_ARRAY, 14}, {"ZPL_ZNODE_ACL", 88, SA_UINT8_ARRAY, 15}, {"ZPL_DACL_COUNT", sizeof (uint64_t), SA_UINT64_ARRAY, 0}, {"ZPL_SYMLINK", 0, SA_UINT8_ARRAY, 0}, {"ZPL_SCANSTAMP", 32, SA_UINT8_ARRAY, 0}, {"ZPL_DACL_ACES", 0, SA_ACL, 0}, {"ZPL_DXATTR", 0, SA_UINT8_ARRAY, 0}, {"ZPL_PROJID", sizeof (uint64_t), SA_UINT64_ARRAY, 0}, {NULL, 0, 0, 0} }; + #ifdef _KERNEL +static int zfs_zil_saxattr = 1; + int zfs_sa_readlink(znode_t *zp, zfs_uio_t *uio) { dmu_buf_t *db = sa_get_db(zp->z_sa_hdl); size_t bufsz; int error; bufsz = zp->z_size; if (bufsz + ZFS_OLD_ZNODE_PHYS_SIZE <= db->db_size) { error = zfs_uiomove((caddr_t)db->db_data + ZFS_OLD_ZNODE_PHYS_SIZE, MIN((size_t)bufsz, zfs_uio_resid(uio)), UIO_READ, uio); } else { dmu_buf_t *dbp; if ((error = dmu_buf_hold(ZTOZSB(zp)->z_os, zp->z_id, 0, FTAG, &dbp, DMU_READ_NO_PREFETCH)) == 0) { error = zfs_uiomove(dbp->db_data, MIN((size_t)bufsz, zfs_uio_resid(uio)), UIO_READ, uio); dmu_buf_rele(dbp, FTAG); } } return (error); } void zfs_sa_symlink(znode_t *zp, char *link, int len, dmu_tx_t *tx) { dmu_buf_t *db = sa_get_db(zp->z_sa_hdl); if (ZFS_OLD_ZNODE_PHYS_SIZE + len <= dmu_bonus_max()) { VERIFY0(dmu_set_bonus(db, len + ZFS_OLD_ZNODE_PHYS_SIZE, tx)); if (len) { bcopy(link, (caddr_t)db->db_data + ZFS_OLD_ZNODE_PHYS_SIZE, len); } } else { dmu_buf_t *dbp; zfs_grow_blocksize(zp, len, tx); VERIFY0(dmu_buf_hold(ZTOZSB(zp)->z_os, zp->z_id, 0, FTAG, &dbp, DMU_READ_NO_PREFETCH)); dmu_buf_will_dirty(dbp, tx); ASSERT3U(len, <=, dbp->db_size); bcopy(link, dbp->db_data, len); dmu_buf_rele(dbp, FTAG); } } void zfs_sa_get_scanstamp(znode_t *zp, xvattr_t *xvap) { zfsvfs_t *zfsvfs = ZTOZSB(zp); xoptattr_t *xoap; ASSERT(MUTEX_HELD(&zp->z_lock)); VERIFY((xoap = xva_getxoptattr(xvap)) != NULL); if (zp->z_is_sa) { if (sa_lookup(zp->z_sa_hdl, SA_ZPL_SCANSTAMP(zfsvfs), &xoap->xoa_av_scanstamp, sizeof (xoap->xoa_av_scanstamp)) != 0) return; } else { dmu_object_info_t doi; dmu_buf_t *db = sa_get_db(zp->z_sa_hdl); int len; if (!(zp->z_pflags & ZFS_BONUS_SCANSTAMP)) return; sa_object_info(zp->z_sa_hdl, &doi); len = sizeof (xoap->xoa_av_scanstamp) + ZFS_OLD_ZNODE_PHYS_SIZE; if (len <= doi.doi_bonus_size) { (void) memcpy(xoap->xoa_av_scanstamp, (caddr_t)db->db_data + ZFS_OLD_ZNODE_PHYS_SIZE, sizeof (xoap->xoa_av_scanstamp)); } } XVA_SET_RTN(xvap, XAT_AV_SCANSTAMP); } void zfs_sa_set_scanstamp(znode_t *zp, xvattr_t *xvap, dmu_tx_t *tx) { zfsvfs_t *zfsvfs = ZTOZSB(zp); xoptattr_t *xoap; ASSERT(MUTEX_HELD(&zp->z_lock)); VERIFY((xoap = xva_getxoptattr(xvap)) != NULL); if (zp->z_is_sa) VERIFY(0 == sa_update(zp->z_sa_hdl, SA_ZPL_SCANSTAMP(zfsvfs), &xoap->xoa_av_scanstamp, sizeof (xoap->xoa_av_scanstamp), tx)); else { dmu_object_info_t doi; dmu_buf_t *db = sa_get_db(zp->z_sa_hdl); int len; sa_object_info(zp->z_sa_hdl, &doi); len = sizeof (xoap->xoa_av_scanstamp) + ZFS_OLD_ZNODE_PHYS_SIZE; if (len > doi.doi_bonus_size) VERIFY(dmu_set_bonus(db, len, tx) == 0); (void) memcpy((caddr_t)db->db_data + ZFS_OLD_ZNODE_PHYS_SIZE, xoap->xoa_av_scanstamp, sizeof (xoap->xoa_av_scanstamp)); zp->z_pflags |= ZFS_BONUS_SCANSTAMP; VERIFY(0 == sa_update(zp->z_sa_hdl, SA_ZPL_FLAGS(zfsvfs), &zp->z_pflags, sizeof (uint64_t), tx)); } } int zfs_sa_get_xattr(znode_t *zp) { zfsvfs_t *zfsvfs = ZTOZSB(zp); char *obj; int size; int error; ASSERT(RW_LOCK_HELD(&zp->z_xattr_lock)); ASSERT(!zp->z_xattr_cached); ASSERT(zp->z_is_sa); error = sa_size(zp->z_sa_hdl, SA_ZPL_DXATTR(zfsvfs), &size); if (error) { if (error == ENOENT) return nvlist_alloc(&zp->z_xattr_cached, NV_UNIQUE_NAME, KM_SLEEP); else return (error); } obj = vmem_alloc(size, KM_SLEEP); error = sa_lookup(zp->z_sa_hdl, SA_ZPL_DXATTR(zfsvfs), obj, size); if (error == 0) error = nvlist_unpack(obj, size, &zp->z_xattr_cached, KM_SLEEP); vmem_free(obj, size); return (error); } int -zfs_sa_set_xattr(znode_t *zp) +zfs_sa_set_xattr(znode_t *zp, const char *name, const void *value, size_t vsize) { zfsvfs_t *zfsvfs = ZTOZSB(zp); + zilog_t *zilog; dmu_tx_t *tx; char *obj; size_t size; - int error; + int error, logsaxattr = 0; ASSERT(RW_WRITE_HELD(&zp->z_xattr_lock)); ASSERT(zp->z_xattr_cached); ASSERT(zp->z_is_sa); error = nvlist_size(zp->z_xattr_cached, &size, NV_ENCODE_XDR); if ((error == 0) && (size > SA_ATTR_MAX_LEN)) error = SET_ERROR(EFBIG); if (error) goto out; obj = vmem_alloc(size, KM_SLEEP); error = nvlist_pack(zp->z_xattr_cached, &obj, &size, NV_ENCODE_XDR, KM_SLEEP); if (error) goto out_free; + zilog = zfsvfs->z_log; + + /* + * Users enable ZIL logging of xattr=sa operations by enabling the + * SPA_FEATURE_ZILSAXATTR feature on the pool. Feature is activated + * during zil_process_commit_list/zil_create, if enabled. + */ + if (spa_feature_is_enabled(zfsvfs->z_os->os_spa, + SPA_FEATURE_ZILSAXATTR) && zfs_zil_saxattr) + logsaxattr = 1; + tx = dmu_tx_create(zfsvfs->z_os); dmu_tx_hold_sa_create(tx, size); dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_TRUE); error = dmu_tx_assign(tx, TXG_WAIT); if (error) { dmu_tx_abort(tx); } else { int count = 0; sa_bulk_attr_t bulk[2]; uint64_t ctime[2]; + if (logsaxattr) + zfs_log_setsaxattr(zilog, tx, TX_SETSAXATTR, zp, name, + value, vsize); + zfs_tstamp_update_setup(zp, STATE_CHANGED, NULL, ctime); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_DXATTR(zfsvfs), NULL, obj, size); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zfsvfs), NULL, &ctime, 16); VERIFY0(sa_bulk_update(zp->z_sa_hdl, bulk, count, tx)); dmu_tx_commit(tx); + if (logsaxattr && zfsvfs->z_os->os_sync == ZFS_SYNC_ALWAYS) + zil_commit(zilog, 0); } out_free: vmem_free(obj, size); out: return (error); } /* * I'm not convinced we should do any of this upgrade. * since the SA code can read both old/new znode formats * with probably little to no performance difference. * * All new files will be created with the new format. */ void zfs_sa_upgrade(sa_handle_t *hdl, dmu_tx_t *tx) { dmu_buf_t *db = sa_get_db(hdl); znode_t *zp = sa_get_userdata(hdl); zfsvfs_t *zfsvfs = ZTOZSB(zp); int count = 0; sa_bulk_attr_t *bulk, *sa_attrs; zfs_acl_locator_cb_t locate = { 0 }; uint64_t uid, gid, mode, rdev, xattr, parent, tmp_gen; uint64_t crtime[2], mtime[2], ctime[2], atime[2]; uint64_t links; zfs_acl_phys_t znode_acl; char scanstamp[AV_SCANSTAMP_SZ]; boolean_t drop_lock = B_FALSE; /* * No upgrade if ACL isn't cached * since we won't know which locks are held * and ready the ACL would require special "locked" * interfaces that would be messy */ if (zp->z_acl_cached == NULL || Z_ISLNK(ZTOTYPE(zp))) return; /* * If the z_lock is held and we aren't the owner * the just return since we don't want to deadlock * trying to update the status of z_is_sa. This * file can then be upgraded at a later time. * * Otherwise, we know we are doing the * sa_update() that caused us to enter this function. */ if (MUTEX_NOT_HELD(&zp->z_lock)) { if (mutex_tryenter(&zp->z_lock) == 0) return; else drop_lock = B_TRUE; } /* First do a bulk query of the attributes that aren't cached */ bulk = kmem_alloc(sizeof (sa_bulk_attr_t) * ZPL_END, KM_SLEEP); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ATIME(zfsvfs), NULL, &atime, 16); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MTIME(zfsvfs), NULL, &mtime, 16); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zfsvfs), NULL, &ctime, 16); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CRTIME(zfsvfs), NULL, &crtime, 16); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MODE(zfsvfs), NULL, &mode, 8); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_PARENT(zfsvfs), NULL, &parent, 8); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_XATTR(zfsvfs), NULL, &xattr, 8); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_RDEV(zfsvfs), NULL, &rdev, 8); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_UID(zfsvfs), NULL, &uid, 8); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_GID(zfsvfs), NULL, &gid, 8); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_GEN(zfsvfs), NULL, &tmp_gen, 8); SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ZNODE_ACL(zfsvfs), NULL, &znode_acl, 88); if (sa_bulk_lookup_locked(hdl, bulk, count) != 0) goto done; if (dmu_objset_projectquota_enabled(hdl->sa_os) && !(zp->z_pflags & ZFS_PROJID)) { zp->z_pflags |= ZFS_PROJID; zp->z_projid = ZFS_DEFAULT_PROJID; } /* * While the order here doesn't matter its best to try and organize * it is such a way to pick up an already existing layout number */ count = 0; sa_attrs = kmem_zalloc(sizeof (sa_bulk_attr_t) * ZPL_END, KM_SLEEP); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_MODE(zfsvfs), NULL, &mode, 8); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_SIZE(zfsvfs), NULL, &zp->z_size, 8); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_GEN(zfsvfs), NULL, &tmp_gen, 8); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_UID(zfsvfs), NULL, &uid, 8); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_GID(zfsvfs), NULL, &gid, 8); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_PARENT(zfsvfs), NULL, &parent, 8); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_FLAGS(zfsvfs), NULL, &zp->z_pflags, 8); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_ATIME(zfsvfs), NULL, &atime, 16); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_MTIME(zfsvfs), NULL, &mtime, 16); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_CTIME(zfsvfs), NULL, &ctime, 16); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_CRTIME(zfsvfs), NULL, &crtime, 16); links = ZTONLNK(zp); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_LINKS(zfsvfs), NULL, &links, 8); if (dmu_objset_projectquota_enabled(hdl->sa_os)) SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_PROJID(zfsvfs), NULL, &zp->z_projid, 8); if (Z_ISBLK(ZTOTYPE(zp)) || Z_ISCHR(ZTOTYPE(zp))) SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_RDEV(zfsvfs), NULL, &rdev, 8); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_DACL_COUNT(zfsvfs), NULL, &zp->z_acl_cached->z_acl_count, 8); if (zp->z_acl_cached->z_version < ZFS_ACL_VERSION_FUID) zfs_acl_xform(zp, zp->z_acl_cached, CRED()); locate.cb_aclp = zp->z_acl_cached; SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_DACL_ACES(zfsvfs), zfs_acl_data_locator, &locate, zp->z_acl_cached->z_acl_bytes); if (xattr) SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_XATTR(zfsvfs), NULL, &xattr, 8); /* if scanstamp then add scanstamp */ if (zp->z_pflags & ZFS_BONUS_SCANSTAMP) { bcopy((caddr_t)db->db_data + ZFS_OLD_ZNODE_PHYS_SIZE, scanstamp, AV_SCANSTAMP_SZ); SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_SCANSTAMP(zfsvfs), NULL, scanstamp, AV_SCANSTAMP_SZ); zp->z_pflags &= ~ZFS_BONUS_SCANSTAMP; } VERIFY(dmu_set_bonustype(db, DMU_OT_SA, tx) == 0); VERIFY(sa_replace_all_by_template_locked(hdl, sa_attrs, count, tx) == 0); if (znode_acl.z_acl_extern_obj) VERIFY(0 == dmu_object_free(zfsvfs->z_os, znode_acl.z_acl_extern_obj, tx)); zp->z_is_sa = B_TRUE; kmem_free(sa_attrs, sizeof (sa_bulk_attr_t) * ZPL_END); done: kmem_free(bulk, sizeof (sa_bulk_attr_t) * ZPL_END); if (drop_lock) mutex_exit(&zp->z_lock); } void zfs_sa_upgrade_txholds(dmu_tx_t *tx, znode_t *zp) { if (!ZTOZSB(zp)->z_use_sa || zp->z_is_sa) return; dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_TRUE); if (zfs_external_acl(zp)) { dmu_tx_hold_free(tx, zfs_external_acl(zp), 0, DMU_OBJECT_END); } } +ZFS_MODULE_PARAM(zfs, zfs_, zil_saxattr, INT, ZMOD_RW, + "Disable xattr=sa extended attribute logging in ZIL by settng 0."); + EXPORT_SYMBOL(zfs_attr_table); EXPORT_SYMBOL(zfs_sa_readlink); EXPORT_SYMBOL(zfs_sa_symlink); EXPORT_SYMBOL(zfs_sa_get_scanstamp); EXPORT_SYMBOL(zfs_sa_set_scanstamp); EXPORT_SYMBOL(zfs_sa_get_xattr); EXPORT_SYMBOL(zfs_sa_set_xattr); EXPORT_SYMBOL(zfs_sa_upgrade); EXPORT_SYMBOL(zfs_sa_upgrade_txholds); #endif diff --git a/module/zfs/zil.c b/module/zfs/zil.c index 87a50a5c4950..10f89c916421 100644 --- a/module/zfs/zil.c +++ b/module/zfs/zil.c @@ -1,3733 +1,3807 @@ /* * 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 (c) 2011, 2018 by Delphix. All rights reserved. * Copyright (c) 2014 Integros [integros.com] * Copyright (c) 2018 Datto Inc. */ /* Portions Copyright 2010 Robert Milkowski */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include /* * The ZFS Intent Log (ZIL) saves "transaction records" (itxs) of system * calls that change the file system. Each itx has enough information to * be able to replay them after a system crash, power loss, or * equivalent failure mode. These are stored in memory until either: * * 1. they are committed to the pool by the DMU transaction group * (txg), at which point they can be discarded; or * 2. they are committed to the on-disk ZIL for the dataset being * modified (e.g. due to an fsync, O_DSYNC, or other synchronous * requirement). * * In the event of a crash or power loss, the itxs contained by each * dataset's on-disk ZIL will be replayed when that dataset is first * instantiated (e.g. if the dataset is a normal filesystem, when it is * first mounted). * * As hinted at above, there is one ZIL per dataset (both the in-memory * representation, and the on-disk representation). The on-disk format * consists of 3 parts: * * - a single, per-dataset, ZIL header; which points to a chain of * - zero or more ZIL blocks; each of which contains * - zero or more ZIL records * * A ZIL record holds the information necessary to replay a single * system call transaction. A ZIL block can hold many ZIL records, and * the blocks are chained together, similarly to a singly linked list. * * Each ZIL block contains a block pointer (blkptr_t) to the next ZIL * block in the chain, and the ZIL header points to the first block in * the chain. * * Note, there is not a fixed place in the pool to hold these ZIL * blocks; they are dynamically allocated and freed as needed from the * blocks available on the pool, though they can be preferentially * allocated from a dedicated "log" vdev. */ /* * This controls the amount of time that a ZIL block (lwb) will remain * "open" when it isn't "full", and it has a thread waiting for it to be * committed to stable storage. Please refer to the zil_commit_waiter() * function (and the comments within it) for more details. */ static int zfs_commit_timeout_pct = 5; /* * See zil.h for more information about these fields. */ static zil_stats_t zil_stats = { { "zil_commit_count", KSTAT_DATA_UINT64 }, { "zil_commit_writer_count", KSTAT_DATA_UINT64 }, { "zil_itx_count", KSTAT_DATA_UINT64 }, { "zil_itx_indirect_count", KSTAT_DATA_UINT64 }, { "zil_itx_indirect_bytes", KSTAT_DATA_UINT64 }, { "zil_itx_copied_count", KSTAT_DATA_UINT64 }, { "zil_itx_copied_bytes", KSTAT_DATA_UINT64 }, { "zil_itx_needcopy_count", KSTAT_DATA_UINT64 }, { "zil_itx_needcopy_bytes", KSTAT_DATA_UINT64 }, { "zil_itx_metaslab_normal_count", KSTAT_DATA_UINT64 }, { "zil_itx_metaslab_normal_bytes", KSTAT_DATA_UINT64 }, { "zil_itx_metaslab_slog_count", KSTAT_DATA_UINT64 }, { "zil_itx_metaslab_slog_bytes", KSTAT_DATA_UINT64 }, }; static kstat_t *zil_ksp; /* * Disable intent logging replay. This global ZIL switch affects all pools. */ int zil_replay_disable = 0; /* * Disable the DKIOCFLUSHWRITECACHE commands that are normally sent to * the disk(s) by the ZIL after an LWB write has completed. Setting this * will cause ZIL corruption on power loss if a volatile out-of-order * write cache is enabled. */ static int zil_nocacheflush = 0; /* * Limit SLOG write size per commit executed with synchronous priority. * Any writes above that will be executed with lower (asynchronous) priority * to limit potential SLOG device abuse by single active ZIL writer. */ static unsigned long zil_slog_bulk = 768 * 1024; static kmem_cache_t *zil_lwb_cache; static kmem_cache_t *zil_zcw_cache; #define LWB_EMPTY(lwb) ((BP_GET_LSIZE(&lwb->lwb_blk) - \ sizeof (zil_chain_t)) == (lwb->lwb_sz - lwb->lwb_nused)) static int zil_bp_compare(const void *x1, const void *x2) { const dva_t *dva1 = &((zil_bp_node_t *)x1)->zn_dva; const dva_t *dva2 = &((zil_bp_node_t *)x2)->zn_dva; int cmp = TREE_CMP(DVA_GET_VDEV(dva1), DVA_GET_VDEV(dva2)); if (likely(cmp)) return (cmp); return (TREE_CMP(DVA_GET_OFFSET(dva1), DVA_GET_OFFSET(dva2))); } static void zil_bp_tree_init(zilog_t *zilog) { avl_create(&zilog->zl_bp_tree, zil_bp_compare, sizeof (zil_bp_node_t), offsetof(zil_bp_node_t, zn_node)); } static void zil_bp_tree_fini(zilog_t *zilog) { avl_tree_t *t = &zilog->zl_bp_tree; zil_bp_node_t *zn; void *cookie = NULL; while ((zn = avl_destroy_nodes(t, &cookie)) != NULL) kmem_free(zn, sizeof (zil_bp_node_t)); avl_destroy(t); } int zil_bp_tree_add(zilog_t *zilog, const blkptr_t *bp) { avl_tree_t *t = &zilog->zl_bp_tree; const dva_t *dva; zil_bp_node_t *zn; avl_index_t where; if (BP_IS_EMBEDDED(bp)) return (0); dva = BP_IDENTITY(bp); if (avl_find(t, dva, &where) != NULL) return (SET_ERROR(EEXIST)); zn = kmem_alloc(sizeof (zil_bp_node_t), KM_SLEEP); zn->zn_dva = *dva; avl_insert(t, zn, where); return (0); } static zil_header_t * zil_header_in_syncing_context(zilog_t *zilog) { return ((zil_header_t *)zilog->zl_header); } static void zil_init_log_chain(zilog_t *zilog, blkptr_t *bp) { zio_cksum_t *zc = &bp->blk_cksum; (void) random_get_pseudo_bytes((void *)&zc->zc_word[ZIL_ZC_GUID_0], sizeof (zc->zc_word[ZIL_ZC_GUID_0])); (void) random_get_pseudo_bytes((void *)&zc->zc_word[ZIL_ZC_GUID_1], sizeof (zc->zc_word[ZIL_ZC_GUID_1])); zc->zc_word[ZIL_ZC_OBJSET] = dmu_objset_id(zilog->zl_os); zc->zc_word[ZIL_ZC_SEQ] = 1ULL; } /* * Read a log block and make sure it's valid. */ static int zil_read_log_block(zilog_t *zilog, boolean_t decrypt, const blkptr_t *bp, blkptr_t *nbp, void *dst, char **end) { enum zio_flag zio_flags = ZIO_FLAG_CANFAIL; arc_flags_t aflags = ARC_FLAG_WAIT; arc_buf_t *abuf = NULL; zbookmark_phys_t zb; int error; if (zilog->zl_header->zh_claim_txg == 0) zio_flags |= ZIO_FLAG_SPECULATIVE | ZIO_FLAG_SCRUB; if (!(zilog->zl_header->zh_flags & ZIL_CLAIM_LR_SEQ_VALID)) zio_flags |= ZIO_FLAG_SPECULATIVE; if (!decrypt) zio_flags |= ZIO_FLAG_RAW; 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 = arc_read(NULL, zilog->zl_spa, bp, arc_getbuf_func, &abuf, ZIO_PRIORITY_SYNC_READ, zio_flags, &aflags, &zb); if (error == 0) { zio_cksum_t cksum = bp->blk_cksum; /* * Validate the checksummed log block. * * Sequence numbers should be... sequential. The checksum * verifier for the next block should be bp's checksum plus 1. * * Also check the log chain linkage and size used. */ cksum.zc_word[ZIL_ZC_SEQ]++; if (BP_GET_CHECKSUM(bp) == ZIO_CHECKSUM_ZILOG2) { zil_chain_t *zilc = abuf->b_data; char *lr = (char *)(zilc + 1); uint64_t len = zilc->zc_nused - sizeof (zil_chain_t); if (bcmp(&cksum, &zilc->zc_next_blk.blk_cksum, sizeof (cksum)) || BP_IS_HOLE(&zilc->zc_next_blk)) { error = SET_ERROR(ECKSUM); } else { ASSERT3U(len, <=, SPA_OLD_MAXBLOCKSIZE); bcopy(lr, dst, len); *end = (char *)dst + len; *nbp = zilc->zc_next_blk; } } else { char *lr = abuf->b_data; uint64_t size = BP_GET_LSIZE(bp); zil_chain_t *zilc = (zil_chain_t *)(lr + size) - 1; if (bcmp(&cksum, &zilc->zc_next_blk.blk_cksum, sizeof (cksum)) || BP_IS_HOLE(&zilc->zc_next_blk) || (zilc->zc_nused > (size - sizeof (*zilc)))) { error = SET_ERROR(ECKSUM); } else { ASSERT3U(zilc->zc_nused, <=, SPA_OLD_MAXBLOCKSIZE); bcopy(lr, dst, zilc->zc_nused); *end = (char *)dst + zilc->zc_nused; *nbp = zilc->zc_next_blk; } } arc_buf_destroy(abuf, &abuf); } return (error); } /* * Read a TX_WRITE log data block. */ static int zil_read_log_data(zilog_t *zilog, const lr_write_t *lr, void *wbuf) { enum zio_flag zio_flags = ZIO_FLAG_CANFAIL; const blkptr_t *bp = &lr->lr_blkptr; arc_flags_t aflags = ARC_FLAG_WAIT; arc_buf_t *abuf = NULL; zbookmark_phys_t zb; int error; if (BP_IS_HOLE(bp)) { if (wbuf != NULL) bzero(wbuf, MAX(BP_GET_LSIZE(bp), lr->lr_length)); return (0); } if (zilog->zl_header->zh_claim_txg == 0) zio_flags |= ZIO_FLAG_SPECULATIVE | ZIO_FLAG_SCRUB; /* * If we are not using the resulting data, we are just checking that * it hasn't been corrupted so we don't need to waste CPU time * decompressing and decrypting it. */ if (wbuf == NULL) zio_flags |= ZIO_FLAG_RAW; 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(NULL, zilog->zl_spa, bp, arc_getbuf_func, &abuf, ZIO_PRIORITY_SYNC_READ, zio_flags, &aflags, &zb); if (error == 0) { if (wbuf != NULL) bcopy(abuf->b_data, wbuf, arc_buf_size(abuf)); arc_buf_destroy(abuf, &abuf); } return (error); } /* * Parse the intent log, and call parse_func for each valid record within. */ int zil_parse(zilog_t *zilog, zil_parse_blk_func_t *parse_blk_func, zil_parse_lr_func_t *parse_lr_func, void *arg, uint64_t txg, boolean_t decrypt) { const zil_header_t *zh = zilog->zl_header; boolean_t claimed = !!zh->zh_claim_txg; uint64_t claim_blk_seq = claimed ? zh->zh_claim_blk_seq : UINT64_MAX; uint64_t claim_lr_seq = claimed ? zh->zh_claim_lr_seq : UINT64_MAX; uint64_t max_blk_seq = 0; uint64_t max_lr_seq = 0; uint64_t blk_count = 0; uint64_t lr_count = 0; blkptr_t blk, next_blk; char *lrbuf, *lrp; int error = 0; bzero(&next_blk, sizeof (blkptr_t)); /* * Old logs didn't record the maximum zh_claim_lr_seq. */ if (!(zh->zh_flags & ZIL_CLAIM_LR_SEQ_VALID)) claim_lr_seq = UINT64_MAX; /* * Starting at the block pointed to by zh_log we read the log chain. * For each block in the chain we strongly check that block to * ensure its validity. We stop when an invalid block is found. * For each block pointer in the chain we call parse_blk_func(). * For each record in each valid block we call parse_lr_func(). * If the log has been claimed, stop if we encounter a sequence * number greater than the highest claimed sequence number. */ lrbuf = zio_buf_alloc(SPA_OLD_MAXBLOCKSIZE); zil_bp_tree_init(zilog); for (blk = zh->zh_log; !BP_IS_HOLE(&blk); blk = next_blk) { uint64_t blk_seq = blk.blk_cksum.zc_word[ZIL_ZC_SEQ]; int reclen; char *end = NULL; if (blk_seq > claim_blk_seq) break; error = parse_blk_func(zilog, &blk, arg, txg); if (error != 0) break; ASSERT3U(max_blk_seq, <, blk_seq); max_blk_seq = blk_seq; blk_count++; if (max_lr_seq == claim_lr_seq && max_blk_seq == claim_blk_seq) break; error = zil_read_log_block(zilog, decrypt, &blk, &next_blk, lrbuf, &end); if (error != 0) break; for (lrp = lrbuf; lrp < end; lrp += reclen) { lr_t *lr = (lr_t *)lrp; reclen = lr->lrc_reclen; ASSERT3U(reclen, >=, sizeof (lr_t)); if (lr->lrc_seq > claim_lr_seq) goto done; error = parse_lr_func(zilog, lr, arg, txg); if (error != 0) goto done; ASSERT3U(max_lr_seq, <, lr->lrc_seq); max_lr_seq = lr->lrc_seq; lr_count++; } } done: zilog->zl_parse_error = error; zilog->zl_parse_blk_seq = max_blk_seq; zilog->zl_parse_lr_seq = max_lr_seq; zilog->zl_parse_blk_count = blk_count; zilog->zl_parse_lr_count = lr_count; ASSERT(!claimed || !(zh->zh_flags & ZIL_CLAIM_LR_SEQ_VALID) || (max_blk_seq == claim_blk_seq && max_lr_seq == claim_lr_seq) || (decrypt && error == EIO)); zil_bp_tree_fini(zilog); zio_buf_free(lrbuf, SPA_OLD_MAXBLOCKSIZE); return (error); } static int zil_clear_log_block(zilog_t *zilog, const blkptr_t *bp, void *tx, uint64_t first_txg) { (void) tx; ASSERT(!BP_IS_HOLE(bp)); /* * As we call this function from the context of a rewind to a * checkpoint, each ZIL block whose txg is later than the txg * that we rewind to is invalid. Thus, we return -1 so * zil_parse() doesn't attempt to read it. */ if (bp->blk_birth >= first_txg) return (-1); if (zil_bp_tree_add(zilog, bp) != 0) return (0); zio_free(zilog->zl_spa, first_txg, bp); return (0); } static int zil_noop_log_record(zilog_t *zilog, const lr_t *lrc, void *tx, uint64_t first_txg) { (void) zilog, (void) lrc, (void) tx, (void) first_txg; return (0); } static int zil_claim_log_block(zilog_t *zilog, const blkptr_t *bp, void *tx, uint64_t first_txg) { /* * Claim log block if not already committed and not already claimed. * If tx == NULL, just verify that the block is claimable. */ if (BP_IS_HOLE(bp) || bp->blk_birth < first_txg || zil_bp_tree_add(zilog, bp) != 0) return (0); return (zio_wait(zio_claim(NULL, zilog->zl_spa, tx == NULL ? 0 : first_txg, bp, spa_claim_notify, NULL, ZIO_FLAG_CANFAIL | ZIO_FLAG_SPECULATIVE | ZIO_FLAG_SCRUB))); } static int zil_claim_log_record(zilog_t *zilog, const lr_t *lrc, void *tx, uint64_t first_txg) { lr_write_t *lr = (lr_write_t *)lrc; int error; if (lrc->lrc_txtype != TX_WRITE) return (0); /* * If the block is not readable, don't claim it. This can happen * in normal operation when a log block is written to disk before * some of the dmu_sync() blocks it points to. In this case, the * transaction cannot have been committed to anyone (we would have * waited for all writes to be stable first), so it is semantically * correct to declare this the end of the log. */ if (lr->lr_blkptr.blk_birth >= first_txg) { error = zil_read_log_data(zilog, lr, NULL); if (error != 0) return (error); } return (zil_claim_log_block(zilog, &lr->lr_blkptr, tx, first_txg)); } static int zil_free_log_block(zilog_t *zilog, const blkptr_t *bp, void *tx, uint64_t claim_txg) { (void) claim_txg; zio_free(zilog->zl_spa, dmu_tx_get_txg(tx), bp); return (0); } static int zil_free_log_record(zilog_t *zilog, const lr_t *lrc, void *tx, uint64_t claim_txg) { lr_write_t *lr = (lr_write_t *)lrc; blkptr_t *bp = &lr->lr_blkptr; /* * If we previously claimed it, we need to free it. */ if (claim_txg != 0 && lrc->lrc_txtype == TX_WRITE && bp->blk_birth >= claim_txg && zil_bp_tree_add(zilog, bp) == 0 && !BP_IS_HOLE(bp)) zio_free(zilog->zl_spa, dmu_tx_get_txg(tx), bp); return (0); } static int zil_lwb_vdev_compare(const void *x1, const void *x2) { const uint64_t v1 = ((zil_vdev_node_t *)x1)->zv_vdev; const uint64_t v2 = ((zil_vdev_node_t *)x2)->zv_vdev; return (TREE_CMP(v1, v2)); } static lwb_t * zil_alloc_lwb(zilog_t *zilog, blkptr_t *bp, boolean_t slog, uint64_t txg, boolean_t fastwrite) { lwb_t *lwb; lwb = kmem_cache_alloc(zil_lwb_cache, KM_SLEEP); lwb->lwb_zilog = zilog; lwb->lwb_blk = *bp; lwb->lwb_fastwrite = fastwrite; lwb->lwb_slog = slog; lwb->lwb_state = LWB_STATE_CLOSED; lwb->lwb_buf = zio_buf_alloc(BP_GET_LSIZE(bp)); lwb->lwb_max_txg = txg; lwb->lwb_write_zio = NULL; lwb->lwb_root_zio = NULL; lwb->lwb_tx = NULL; lwb->lwb_issued_timestamp = 0; if (BP_GET_CHECKSUM(bp) == ZIO_CHECKSUM_ZILOG2) { lwb->lwb_nused = sizeof (zil_chain_t); lwb->lwb_sz = BP_GET_LSIZE(bp); } else { lwb->lwb_nused = 0; lwb->lwb_sz = BP_GET_LSIZE(bp) - sizeof (zil_chain_t); } mutex_enter(&zilog->zl_lock); list_insert_tail(&zilog->zl_lwb_list, lwb); mutex_exit(&zilog->zl_lock); ASSERT(!MUTEX_HELD(&lwb->lwb_vdev_lock)); ASSERT(avl_is_empty(&lwb->lwb_vdev_tree)); VERIFY(list_is_empty(&lwb->lwb_waiters)); VERIFY(list_is_empty(&lwb->lwb_itxs)); return (lwb); } static void zil_free_lwb(zilog_t *zilog, lwb_t *lwb) { ASSERT(MUTEX_HELD(&zilog->zl_lock)); ASSERT(!MUTEX_HELD(&lwb->lwb_vdev_lock)); VERIFY(list_is_empty(&lwb->lwb_waiters)); VERIFY(list_is_empty(&lwb->lwb_itxs)); ASSERT(avl_is_empty(&lwb->lwb_vdev_tree)); ASSERT3P(lwb->lwb_write_zio, ==, NULL); ASSERT3P(lwb->lwb_root_zio, ==, NULL); ASSERT3U(lwb->lwb_max_txg, <=, spa_syncing_txg(zilog->zl_spa)); ASSERT(lwb->lwb_state == LWB_STATE_CLOSED || lwb->lwb_state == LWB_STATE_FLUSH_DONE); /* * Clear the zilog's field to indicate this lwb is no longer * valid, and prevent use-after-free errors. */ if (zilog->zl_last_lwb_opened == lwb) zilog->zl_last_lwb_opened = NULL; kmem_cache_free(zil_lwb_cache, lwb); } /* * Called when we create in-memory log transactions so that we know * to cleanup the itxs at the end of spa_sync(). */ static void zilog_dirty(zilog_t *zilog, uint64_t txg) { dsl_pool_t *dp = zilog->zl_dmu_pool; dsl_dataset_t *ds = dmu_objset_ds(zilog->zl_os); ASSERT(spa_writeable(zilog->zl_spa)); if (ds->ds_is_snapshot) panic("dirtying snapshot!"); if (txg_list_add(&dp->dp_dirty_zilogs, zilog, txg)) { /* up the hold count until we can be written out */ dmu_buf_add_ref(ds->ds_dbuf, zilog); zilog->zl_dirty_max_txg = MAX(txg, zilog->zl_dirty_max_txg); } } /* * Determine if the zil is dirty in the specified txg. Callers wanting to * ensure that the dirty state does not change must hold the itxg_lock for * the specified txg. Holding the lock will ensure that the zil cannot be * dirtied (zil_itx_assign) or cleaned (zil_clean) while we check its current * state. */ static boolean_t __maybe_unused zilog_is_dirty_in_txg(zilog_t *zilog, uint64_t txg) { dsl_pool_t *dp = zilog->zl_dmu_pool; if (txg_list_member(&dp->dp_dirty_zilogs, zilog, txg & TXG_MASK)) return (B_TRUE); return (B_FALSE); } /* * Determine if the zil is dirty. The zil is considered dirty if it has * any pending itx records that have not been cleaned by zil_clean(). */ static boolean_t zilog_is_dirty(zilog_t *zilog) { dsl_pool_t *dp = zilog->zl_dmu_pool; for (int t = 0; t < TXG_SIZE; t++) { if (txg_list_member(&dp->dp_dirty_zilogs, zilog, t)) return (B_TRUE); } return (B_FALSE); } +/* + * Its called in zil_commit context (zil_process_commit_list()/zil_create()). + * It activates SPA_FEATURE_ZILSAXATTR feature, if its enabled. + * Check dsl_dataset_feature_is_active to avoid txg_wait_synced() on every + * zil_commit. + */ +static void +zil_commit_activate_saxattr_feature(zilog_t *zilog) +{ + dsl_dataset_t *ds = dmu_objset_ds(zilog->zl_os); + uint64_t txg = 0; + dmu_tx_t *tx = NULL; + + if (spa_feature_is_enabled(zilog->zl_spa, + SPA_FEATURE_ZILSAXATTR) && + dmu_objset_type(zilog->zl_os) != DMU_OST_ZVOL && + !dsl_dataset_feature_is_active(ds, + SPA_FEATURE_ZILSAXATTR)) { + tx = dmu_tx_create(zilog->zl_os); + VERIFY0(dmu_tx_assign(tx, TXG_WAIT)); + dsl_dataset_dirty(ds, tx); + txg = dmu_tx_get_txg(tx); + + mutex_enter(&ds->ds_lock); + ds->ds_feature_activation[SPA_FEATURE_ZILSAXATTR] = + (void *)B_TRUE; + mutex_exit(&ds->ds_lock); + dmu_tx_commit(tx); + txg_wait_synced(zilog->zl_dmu_pool, txg); + } +} + /* * Create an on-disk intent log. */ static lwb_t * zil_create(zilog_t *zilog) { const zil_header_t *zh = zilog->zl_header; lwb_t *lwb = NULL; uint64_t txg = 0; dmu_tx_t *tx = NULL; blkptr_t blk; int error = 0; boolean_t fastwrite = FALSE; boolean_t slog = FALSE; + dsl_dataset_t *ds = dmu_objset_ds(zilog->zl_os); + /* * Wait for any previous destroy to complete. */ txg_wait_synced(zilog->zl_dmu_pool, zilog->zl_destroy_txg); ASSERT(zh->zh_claim_txg == 0); ASSERT(zh->zh_replay_seq == 0); blk = zh->zh_log; /* * Allocate an initial log block if: * - there isn't one already * - the existing block is the wrong endianness */ if (BP_IS_HOLE(&blk) || BP_SHOULD_BYTESWAP(&blk)) { tx = dmu_tx_create(zilog->zl_os); VERIFY0(dmu_tx_assign(tx, TXG_WAIT)); dsl_dataset_dirty(dmu_objset_ds(zilog->zl_os), tx); txg = dmu_tx_get_txg(tx); if (!BP_IS_HOLE(&blk)) { zio_free(zilog->zl_spa, txg, &blk); BP_ZERO(&blk); } error = zio_alloc_zil(zilog->zl_spa, zilog->zl_os, txg, &blk, ZIL_MIN_BLKSZ, &slog); fastwrite = TRUE; if (error == 0) zil_init_log_chain(zilog, &blk); } /* * Allocate a log write block (lwb) for the first log block. */ if (error == 0) lwb = zil_alloc_lwb(zilog, &blk, slog, txg, fastwrite); /* * If we just allocated the first log block, commit our transaction * and wait for zil_sync() to stuff the block pointer into zh_log. * (zh is part of the MOS, so we cannot modify it in open context.) */ if (tx != NULL) { + /* + * If "zilsaxattr" feature is enabled on zpool, then activate + * it now when we're creating the ZIL chain. We can't wait with + * this until we write the first xattr log record because we + * need to wait for the feature activation to sync out. + */ + if (spa_feature_is_enabled(zilog->zl_spa, + SPA_FEATURE_ZILSAXATTR) && dmu_objset_type(zilog->zl_os) != + DMU_OST_ZVOL) { + mutex_enter(&ds->ds_lock); + ds->ds_feature_activation[SPA_FEATURE_ZILSAXATTR] = + (void *)B_TRUE; + mutex_exit(&ds->ds_lock); + } + dmu_tx_commit(tx); txg_wait_synced(zilog->zl_dmu_pool, txg); + } else { + /* + * This branch covers the case where we enable the feature on a + * zpool that has existing ZIL headers. + */ + zil_commit_activate_saxattr_feature(zilog); } + IMPLY(spa_feature_is_enabled(zilog->zl_spa, SPA_FEATURE_ZILSAXATTR) && + dmu_objset_type(zilog->zl_os) != DMU_OST_ZVOL, + dsl_dataset_feature_is_active(ds, SPA_FEATURE_ZILSAXATTR)); ASSERT(error != 0 || bcmp(&blk, &zh->zh_log, sizeof (blk)) == 0); IMPLY(error == 0, lwb != NULL); return (lwb); } /* * In one tx, free all log blocks and clear the log header. If keep_first * is set, then we're replaying a log with no content. We want to keep the * first block, however, so that the first synchronous transaction doesn't * require a txg_wait_synced() in zil_create(). We don't need to * txg_wait_synced() here either when keep_first is set, because both * zil_create() and zil_destroy() will wait for any in-progress destroys * to complete. */ void zil_destroy(zilog_t *zilog, boolean_t keep_first) { const zil_header_t *zh = zilog->zl_header; lwb_t *lwb; dmu_tx_t *tx; uint64_t txg; /* * Wait for any previous destroy to complete. */ txg_wait_synced(zilog->zl_dmu_pool, zilog->zl_destroy_txg); zilog->zl_old_header = *zh; /* debugging aid */ if (BP_IS_HOLE(&zh->zh_log)) return; tx = dmu_tx_create(zilog->zl_os); VERIFY0(dmu_tx_assign(tx, TXG_WAIT)); dsl_dataset_dirty(dmu_objset_ds(zilog->zl_os), tx); txg = dmu_tx_get_txg(tx); mutex_enter(&zilog->zl_lock); ASSERT3U(zilog->zl_destroy_txg, <, txg); zilog->zl_destroy_txg = txg; zilog->zl_keep_first = keep_first; if (!list_is_empty(&zilog->zl_lwb_list)) { ASSERT(zh->zh_claim_txg == 0); VERIFY(!keep_first); while ((lwb = list_head(&zilog->zl_lwb_list)) != NULL) { if (lwb->lwb_fastwrite) metaslab_fastwrite_unmark(zilog->zl_spa, &lwb->lwb_blk); list_remove(&zilog->zl_lwb_list, lwb); if (lwb->lwb_buf != NULL) zio_buf_free(lwb->lwb_buf, lwb->lwb_sz); zio_free(zilog->zl_spa, txg, &lwb->lwb_blk); zil_free_lwb(zilog, lwb); } } else if (!keep_first) { zil_destroy_sync(zilog, tx); } mutex_exit(&zilog->zl_lock); dmu_tx_commit(tx); } void zil_destroy_sync(zilog_t *zilog, dmu_tx_t *tx) { ASSERT(list_is_empty(&zilog->zl_lwb_list)); (void) zil_parse(zilog, zil_free_log_block, zil_free_log_record, tx, zilog->zl_header->zh_claim_txg, B_FALSE); } int zil_claim(dsl_pool_t *dp, dsl_dataset_t *ds, void *txarg) { dmu_tx_t *tx = txarg; zilog_t *zilog; uint64_t first_txg; zil_header_t *zh; objset_t *os; int error; error = dmu_objset_own_obj(dp, ds->ds_object, DMU_OST_ANY, B_FALSE, B_FALSE, FTAG, &os); if (error != 0) { /* * EBUSY indicates that the objset is inconsistent, in which * case it can not have a ZIL. */ if (error != EBUSY) { cmn_err(CE_WARN, "can't open objset for %llu, error %u", (unsigned long long)ds->ds_object, error); } return (0); } zilog = dmu_objset_zil(os); zh = zil_header_in_syncing_context(zilog); ASSERT3U(tx->tx_txg, ==, spa_first_txg(zilog->zl_spa)); first_txg = spa_min_claim_txg(zilog->zl_spa); /* * If the spa_log_state is not set to be cleared, check whether * the current uberblock is a checkpoint one and if the current * header has been claimed before moving on. * * If the current uberblock is a checkpointed uberblock then * one of the following scenarios took place: * * 1] We are currently rewinding to the checkpoint of the pool. * 2] We crashed in the middle of a checkpoint rewind but we * did manage to write the checkpointed uberblock to the * vdev labels, so when we tried to import the pool again * the checkpointed uberblock was selected from the import * procedure. * * In both cases we want to zero out all the ZIL blocks, except * the ones that have been claimed at the time of the checkpoint * (their zh_claim_txg != 0). The reason is that these blocks * may be corrupted since we may have reused their locations on * disk after we took the checkpoint. * * We could try to set spa_log_state to SPA_LOG_CLEAR earlier * when we first figure out whether the current uberblock is * checkpointed or not. Unfortunately, that would discard all * the logs, including the ones that are claimed, and we would * leak space. */ if (spa_get_log_state(zilog->zl_spa) == SPA_LOG_CLEAR || (zilog->zl_spa->spa_uberblock.ub_checkpoint_txg != 0 && zh->zh_claim_txg == 0)) { if (!BP_IS_HOLE(&zh->zh_log)) { (void) zil_parse(zilog, zil_clear_log_block, zil_noop_log_record, tx, first_txg, B_FALSE); } BP_ZERO(&zh->zh_log); if (os->os_encrypted) os->os_next_write_raw[tx->tx_txg & TXG_MASK] = B_TRUE; dsl_dataset_dirty(dmu_objset_ds(os), tx); dmu_objset_disown(os, B_FALSE, FTAG); return (0); } /* * If we are not rewinding and opening the pool normally, then * the min_claim_txg should be equal to the first txg of the pool. */ ASSERT3U(first_txg, ==, spa_first_txg(zilog->zl_spa)); /* * Claim all log blocks if we haven't already done so, and remember * the highest claimed sequence number. This ensures that if we can * read only part of the log now (e.g. due to a missing device), * but we can read the entire log later, we will not try to replay * or destroy beyond the last block we successfully claimed. */ ASSERT3U(zh->zh_claim_txg, <=, first_txg); if (zh->zh_claim_txg == 0 && !BP_IS_HOLE(&zh->zh_log)) { (void) zil_parse(zilog, zil_claim_log_block, zil_claim_log_record, tx, first_txg, B_FALSE); zh->zh_claim_txg = first_txg; zh->zh_claim_blk_seq = zilog->zl_parse_blk_seq; zh->zh_claim_lr_seq = zilog->zl_parse_lr_seq; if (zilog->zl_parse_lr_count || zilog->zl_parse_blk_count > 1) zh->zh_flags |= ZIL_REPLAY_NEEDED; zh->zh_flags |= ZIL_CLAIM_LR_SEQ_VALID; if (os->os_encrypted) os->os_next_write_raw[tx->tx_txg & TXG_MASK] = B_TRUE; dsl_dataset_dirty(dmu_objset_ds(os), tx); } ASSERT3U(first_txg, ==, (spa_last_synced_txg(zilog->zl_spa) + 1)); dmu_objset_disown(os, B_FALSE, FTAG); return (0); } /* * Check the log by walking the log chain. * Checksum errors are ok as they indicate the end of the chain. * Any other error (no device or read failure) returns an error. */ int zil_check_log_chain(dsl_pool_t *dp, dsl_dataset_t *ds, void *tx) { (void) dp; zilog_t *zilog; objset_t *os; blkptr_t *bp; int error; ASSERT(tx == NULL); error = dmu_objset_from_ds(ds, &os); if (error != 0) { cmn_err(CE_WARN, "can't open objset %llu, error %d", (unsigned long long)ds->ds_object, error); return (0); } zilog = dmu_objset_zil(os); bp = (blkptr_t *)&zilog->zl_header->zh_log; if (!BP_IS_HOLE(bp)) { vdev_t *vd; boolean_t valid = B_TRUE; /* * Check the first block and determine if it's on a log device * which may have been removed or faulted prior to loading this * pool. If so, there's no point in checking the rest of the * log as its content should have already been synced to the * pool. */ spa_config_enter(os->os_spa, SCL_STATE, FTAG, RW_READER); vd = vdev_lookup_top(os->os_spa, DVA_GET_VDEV(&bp->blk_dva[0])); if (vd->vdev_islog && vdev_is_dead(vd)) valid = vdev_log_state_valid(vd); spa_config_exit(os->os_spa, SCL_STATE, FTAG); if (!valid) return (0); /* * Check whether the current uberblock is checkpointed (e.g. * we are rewinding) and whether the current header has been * claimed or not. If it hasn't then skip verifying it. We * do this because its ZIL blocks may be part of the pool's * state before the rewind, which is no longer valid. */ zil_header_t *zh = zil_header_in_syncing_context(zilog); if (zilog->zl_spa->spa_uberblock.ub_checkpoint_txg != 0 && zh->zh_claim_txg == 0) return (0); } /* * Because tx == NULL, zil_claim_log_block() will not actually claim * any blocks, but just determine whether it is possible to do so. * In addition to checking the log chain, zil_claim_log_block() * will invoke zio_claim() with a done func of spa_claim_notify(), * which will update spa_max_claim_txg. See spa_load() for details. */ error = zil_parse(zilog, zil_claim_log_block, zil_claim_log_record, tx, zilog->zl_header->zh_claim_txg ? -1ULL : spa_min_claim_txg(os->os_spa), B_FALSE); return ((error == ECKSUM || error == ENOENT) ? 0 : error); } /* * When an itx is "skipped", this function is used to properly mark the * waiter as "done, and signal any thread(s) waiting on it. An itx can * be skipped (and not committed to an lwb) for a variety of reasons, * one of them being that the itx was committed via spa_sync(), prior to * it being committed to an lwb; this can happen if a thread calling * zil_commit() is racing with spa_sync(). */ static void zil_commit_waiter_skip(zil_commit_waiter_t *zcw) { mutex_enter(&zcw->zcw_lock); ASSERT3B(zcw->zcw_done, ==, B_FALSE); zcw->zcw_done = B_TRUE; cv_broadcast(&zcw->zcw_cv); mutex_exit(&zcw->zcw_lock); } /* * This function is used when the given waiter is to be linked into an * lwb's "lwb_waiter" list; i.e. when the itx is committed to the lwb. * At this point, the waiter will no longer be referenced by the itx, * and instead, will be referenced by the lwb. */ static void zil_commit_waiter_link_lwb(zil_commit_waiter_t *zcw, lwb_t *lwb) { /* * The lwb_waiters field of the lwb is protected by the zilog's * zl_lock, thus it must be held when calling this function. */ ASSERT(MUTEX_HELD(&lwb->lwb_zilog->zl_lock)); mutex_enter(&zcw->zcw_lock); ASSERT(!list_link_active(&zcw->zcw_node)); ASSERT3P(zcw->zcw_lwb, ==, NULL); ASSERT3P(lwb, !=, NULL); ASSERT(lwb->lwb_state == LWB_STATE_OPENED || lwb->lwb_state == LWB_STATE_ISSUED || lwb->lwb_state == LWB_STATE_WRITE_DONE); list_insert_tail(&lwb->lwb_waiters, zcw); zcw->zcw_lwb = lwb; mutex_exit(&zcw->zcw_lock); } /* * This function is used when zio_alloc_zil() fails to allocate a ZIL * block, and the given waiter must be linked to the "nolwb waiters" * list inside of zil_process_commit_list(). */ static void zil_commit_waiter_link_nolwb(zil_commit_waiter_t *zcw, list_t *nolwb) { mutex_enter(&zcw->zcw_lock); ASSERT(!list_link_active(&zcw->zcw_node)); ASSERT3P(zcw->zcw_lwb, ==, NULL); list_insert_tail(nolwb, zcw); mutex_exit(&zcw->zcw_lock); } void zil_lwb_add_block(lwb_t *lwb, const blkptr_t *bp) { avl_tree_t *t = &lwb->lwb_vdev_tree; avl_index_t where; zil_vdev_node_t *zv, zvsearch; int ndvas = BP_GET_NDVAS(bp); int i; if (zil_nocacheflush) return; mutex_enter(&lwb->lwb_vdev_lock); for (i = 0; i < ndvas; i++) { zvsearch.zv_vdev = DVA_GET_VDEV(&bp->blk_dva[i]); if (avl_find(t, &zvsearch, &where) == NULL) { zv = kmem_alloc(sizeof (*zv), KM_SLEEP); zv->zv_vdev = zvsearch.zv_vdev; avl_insert(t, zv, where); } } mutex_exit(&lwb->lwb_vdev_lock); } static void zil_lwb_flush_defer(lwb_t *lwb, lwb_t *nlwb) { avl_tree_t *src = &lwb->lwb_vdev_tree; avl_tree_t *dst = &nlwb->lwb_vdev_tree; void *cookie = NULL; zil_vdev_node_t *zv; ASSERT3S(lwb->lwb_state, ==, LWB_STATE_WRITE_DONE); ASSERT3S(nlwb->lwb_state, !=, LWB_STATE_WRITE_DONE); ASSERT3S(nlwb->lwb_state, !=, LWB_STATE_FLUSH_DONE); /* * While 'lwb' is at a point in its lifetime where lwb_vdev_tree does * not need the protection of lwb_vdev_lock (it will only be modified * while holding zilog->zl_lock) as its writes and those of its * children have all completed. The younger 'nlwb' may be waiting on * future writes to additional vdevs. */ mutex_enter(&nlwb->lwb_vdev_lock); /* * Tear down the 'lwb' vdev tree, ensuring that entries which do not * exist in 'nlwb' are moved to it, freeing any would-be duplicates. */ while ((zv = avl_destroy_nodes(src, &cookie)) != NULL) { avl_index_t where; if (avl_find(dst, zv, &where) == NULL) { avl_insert(dst, zv, where); } else { kmem_free(zv, sizeof (*zv)); } } mutex_exit(&nlwb->lwb_vdev_lock); } void zil_lwb_add_txg(lwb_t *lwb, uint64_t txg) { lwb->lwb_max_txg = MAX(lwb->lwb_max_txg, txg); } /* * This function is a called after all vdevs associated with a given lwb * write have completed their DKIOCFLUSHWRITECACHE command; or as soon * as the lwb write completes, if "zil_nocacheflush" is set. Further, * all "previous" lwb's will have completed before this function is * called; i.e. this function is called for all previous lwbs before * it's called for "this" lwb (enforced via zio the dependencies * configured in zil_lwb_set_zio_dependency()). * * The intention is for this function to be called as soon as the * contents of an lwb are considered "stable" on disk, and will survive * any sudden loss of power. At this point, any threads waiting for the * lwb to reach this state are signalled, and the "waiter" structures * are marked "done". */ static void zil_lwb_flush_vdevs_done(zio_t *zio) { lwb_t *lwb = zio->io_private; zilog_t *zilog = lwb->lwb_zilog; dmu_tx_t *tx = lwb->lwb_tx; zil_commit_waiter_t *zcw; itx_t *itx; spa_config_exit(zilog->zl_spa, SCL_STATE, lwb); zio_buf_free(lwb->lwb_buf, lwb->lwb_sz); mutex_enter(&zilog->zl_lock); /* * Ensure the lwb buffer pointer is cleared before releasing the * txg. If we have had an allocation failure and the txg is * waiting to sync then we want zil_sync() to remove the lwb so * that it's not picked up as the next new one in * zil_process_commit_list(). zil_sync() will only remove the * lwb if lwb_buf is null. */ lwb->lwb_buf = NULL; lwb->lwb_tx = NULL; ASSERT3U(lwb->lwb_issued_timestamp, >, 0); zilog->zl_last_lwb_latency = gethrtime() - lwb->lwb_issued_timestamp; lwb->lwb_root_zio = NULL; ASSERT3S(lwb->lwb_state, ==, LWB_STATE_WRITE_DONE); lwb->lwb_state = LWB_STATE_FLUSH_DONE; if (zilog->zl_last_lwb_opened == lwb) { /* * Remember the highest committed log sequence number * for ztest. We only update this value when all the log * writes succeeded, because ztest wants to ASSERT that * it got the whole log chain. */ zilog->zl_commit_lr_seq = zilog->zl_lr_seq; } while ((itx = list_head(&lwb->lwb_itxs)) != NULL) { list_remove(&lwb->lwb_itxs, itx); zil_itx_destroy(itx); } while ((zcw = list_head(&lwb->lwb_waiters)) != NULL) { mutex_enter(&zcw->zcw_lock); ASSERT(list_link_active(&zcw->zcw_node)); list_remove(&lwb->lwb_waiters, zcw); ASSERT3P(zcw->zcw_lwb, ==, lwb); zcw->zcw_lwb = NULL; /* * We expect any ZIO errors from child ZIOs to have been * propagated "up" to this specific LWB's root ZIO, in * order for this error handling to work correctly. This * includes ZIO errors from either this LWB's write or * flush, as well as any errors from other dependent LWBs * (e.g. a root LWB ZIO that might be a child of this LWB). * * With that said, it's important to note that LWB flush * errors are not propagated up to the LWB root ZIO. * This is incorrect behavior, and results in VDEV flush * errors not being handled correctly here. See the * comment above the call to "zio_flush" for details. */ zcw->zcw_zio_error = zio->io_error; ASSERT3B(zcw->zcw_done, ==, B_FALSE); zcw->zcw_done = B_TRUE; cv_broadcast(&zcw->zcw_cv); mutex_exit(&zcw->zcw_lock); } mutex_exit(&zilog->zl_lock); /* * Now that we've written this log block, we have a stable pointer * to the next block in the chain, so it's OK to let the txg in * which we allocated the next block sync. */ dmu_tx_commit(tx); } /* * This is called when an lwb's write zio completes. The callback's * purpose is to issue the DKIOCFLUSHWRITECACHE commands for the vdevs * in the lwb's lwb_vdev_tree. The tree will contain the vdevs involved * in writing out this specific lwb's data, and in the case that cache * flushes have been deferred, vdevs involved in writing the data for * previous lwbs. The writes corresponding to all the vdevs in the * lwb_vdev_tree will have completed by the time this is called, due to * the zio dependencies configured in zil_lwb_set_zio_dependency(), * which takes deferred flushes into account. The lwb will be "done" * once zil_lwb_flush_vdevs_done() is called, which occurs in the zio * completion callback for the lwb's root zio. */ static void zil_lwb_write_done(zio_t *zio) { lwb_t *lwb = zio->io_private; spa_t *spa = zio->io_spa; zilog_t *zilog = lwb->lwb_zilog; avl_tree_t *t = &lwb->lwb_vdev_tree; void *cookie = NULL; zil_vdev_node_t *zv; lwb_t *nlwb; ASSERT3S(spa_config_held(spa, SCL_STATE, RW_READER), !=, 0); ASSERT(BP_GET_COMPRESS(zio->io_bp) == ZIO_COMPRESS_OFF); ASSERT(BP_GET_TYPE(zio->io_bp) == DMU_OT_INTENT_LOG); ASSERT(BP_GET_LEVEL(zio->io_bp) == 0); ASSERT(BP_GET_BYTEORDER(zio->io_bp) == ZFS_HOST_BYTEORDER); ASSERT(!BP_IS_GANG(zio->io_bp)); ASSERT(!BP_IS_HOLE(zio->io_bp)); ASSERT(BP_GET_FILL(zio->io_bp) == 0); abd_free(zio->io_abd); mutex_enter(&zilog->zl_lock); ASSERT3S(lwb->lwb_state, ==, LWB_STATE_ISSUED); lwb->lwb_state = LWB_STATE_WRITE_DONE; lwb->lwb_write_zio = NULL; lwb->lwb_fastwrite = FALSE; nlwb = list_next(&zilog->zl_lwb_list, lwb); mutex_exit(&zilog->zl_lock); if (avl_numnodes(t) == 0) return; /* * If there was an IO error, we're not going to call zio_flush() * on these vdevs, so we simply empty the tree and free the * nodes. We avoid calling zio_flush() since there isn't any * good reason for doing so, after the lwb block failed to be * written out. * * Additionally, we don't perform any further error handling at * this point (e.g. setting "zcw_zio_error" appropriately), as * we expect that to occur in "zil_lwb_flush_vdevs_done" (thus, * we expect any error seen here, to have been propagated to * that function). */ if (zio->io_error != 0) { while ((zv = avl_destroy_nodes(t, &cookie)) != NULL) kmem_free(zv, sizeof (*zv)); return; } /* * If this lwb does not have any threads waiting for it to * complete, we want to defer issuing the DKIOCFLUSHWRITECACHE * command to the vdevs written to by "this" lwb, and instead * rely on the "next" lwb to handle the DKIOCFLUSHWRITECACHE * command for those vdevs. Thus, we merge the vdev tree of * "this" lwb with the vdev tree of the "next" lwb in the list, * and assume the "next" lwb will handle flushing the vdevs (or * deferring the flush(s) again). * * This is a useful performance optimization, especially for * workloads with lots of async write activity and few sync * write and/or fsync activity, as it has the potential to * coalesce multiple flush commands to a vdev into one. */ if (list_head(&lwb->lwb_waiters) == NULL && nlwb != NULL) { zil_lwb_flush_defer(lwb, nlwb); ASSERT(avl_is_empty(&lwb->lwb_vdev_tree)); return; } while ((zv = avl_destroy_nodes(t, &cookie)) != NULL) { vdev_t *vd = vdev_lookup_top(spa, zv->zv_vdev); if (vd != NULL) { /* * The "ZIO_FLAG_DONT_PROPAGATE" is currently * always used within "zio_flush". This means, * any errors when flushing the vdev(s), will * (unfortunately) not be handled correctly, * since these "zio_flush" errors will not be * propagated up to "zil_lwb_flush_vdevs_done". */ zio_flush(lwb->lwb_root_zio, vd); } kmem_free(zv, sizeof (*zv)); } } static void zil_lwb_set_zio_dependency(zilog_t *zilog, lwb_t *lwb) { lwb_t *last_lwb_opened = zilog->zl_last_lwb_opened; ASSERT(MUTEX_HELD(&zilog->zl_issuer_lock)); ASSERT(MUTEX_HELD(&zilog->zl_lock)); /* * The zilog's "zl_last_lwb_opened" field is used to build the * lwb/zio dependency chain, which is used to preserve the * ordering of lwb completions that is required by the semantics * of the ZIL. Each new lwb zio becomes a parent of the * "previous" lwb zio, such that the new lwb's zio cannot * complete until the "previous" lwb's zio completes. * * This is required by the semantics of zil_commit(); the commit * waiters attached to the lwbs will be woken in the lwb zio's * completion callback, so this zio dependency graph ensures the * waiters are woken in the correct order (the same order the * lwbs were created). */ if (last_lwb_opened != NULL && last_lwb_opened->lwb_state != LWB_STATE_FLUSH_DONE) { ASSERT(last_lwb_opened->lwb_state == LWB_STATE_OPENED || last_lwb_opened->lwb_state == LWB_STATE_ISSUED || last_lwb_opened->lwb_state == LWB_STATE_WRITE_DONE); ASSERT3P(last_lwb_opened->lwb_root_zio, !=, NULL); zio_add_child(lwb->lwb_root_zio, last_lwb_opened->lwb_root_zio); /* * If the previous lwb's write hasn't already completed, * we also want to order the completion of the lwb write * zios (above, we only order the completion of the lwb * root zios). This is required because of how we can * defer the DKIOCFLUSHWRITECACHE commands for each lwb. * * When the DKIOCFLUSHWRITECACHE commands are deferred, * the previous lwb will rely on this lwb to flush the * vdevs written to by that previous lwb. Thus, we need * to ensure this lwb doesn't issue the flush until * after the previous lwb's write completes. We ensure * this ordering by setting the zio parent/child * relationship here. * * Without this relationship on the lwb's write zio, * it's possible for this lwb's write to complete prior * to the previous lwb's write completing; and thus, the * vdevs for the previous lwb would be flushed prior to * that lwb's data being written to those vdevs (the * vdevs are flushed in the lwb write zio's completion * handler, zil_lwb_write_done()). */ if (last_lwb_opened->lwb_state != LWB_STATE_WRITE_DONE) { ASSERT(last_lwb_opened->lwb_state == LWB_STATE_OPENED || last_lwb_opened->lwb_state == LWB_STATE_ISSUED); ASSERT3P(last_lwb_opened->lwb_write_zio, !=, NULL); zio_add_child(lwb->lwb_write_zio, last_lwb_opened->lwb_write_zio); } } } /* * This function's purpose is to "open" an lwb such that it is ready to * accept new itxs being committed to it. To do this, the lwb's zio * structures are created, and linked to the lwb. This function is * idempotent; if the passed in lwb has already been opened, this * function is essentially a no-op. */ static void zil_lwb_write_open(zilog_t *zilog, lwb_t *lwb) { zbookmark_phys_t zb; zio_priority_t prio; ASSERT(MUTEX_HELD(&zilog->zl_issuer_lock)); ASSERT3P(lwb, !=, NULL); EQUIV(lwb->lwb_root_zio == NULL, lwb->lwb_state == LWB_STATE_CLOSED); EQUIV(lwb->lwb_root_zio != NULL, lwb->lwb_state == LWB_STATE_OPENED); SET_BOOKMARK(&zb, lwb->lwb_blk.blk_cksum.zc_word[ZIL_ZC_OBJSET], ZB_ZIL_OBJECT, ZB_ZIL_LEVEL, lwb->lwb_blk.blk_cksum.zc_word[ZIL_ZC_SEQ]); /* Lock so zil_sync() doesn't fastwrite_unmark after zio is created */ mutex_enter(&zilog->zl_lock); if (lwb->lwb_root_zio == NULL) { abd_t *lwb_abd = abd_get_from_buf(lwb->lwb_buf, BP_GET_LSIZE(&lwb->lwb_blk)); if (!lwb->lwb_fastwrite) { metaslab_fastwrite_mark(zilog->zl_spa, &lwb->lwb_blk); lwb->lwb_fastwrite = 1; } if (!lwb->lwb_slog || zilog->zl_cur_used <= zil_slog_bulk) prio = ZIO_PRIORITY_SYNC_WRITE; else prio = ZIO_PRIORITY_ASYNC_WRITE; lwb->lwb_root_zio = zio_root(zilog->zl_spa, zil_lwb_flush_vdevs_done, lwb, ZIO_FLAG_CANFAIL); ASSERT3P(lwb->lwb_root_zio, !=, NULL); lwb->lwb_write_zio = zio_rewrite(lwb->lwb_root_zio, zilog->zl_spa, 0, &lwb->lwb_blk, lwb_abd, BP_GET_LSIZE(&lwb->lwb_blk), zil_lwb_write_done, lwb, prio, ZIO_FLAG_CANFAIL | ZIO_FLAG_FASTWRITE, &zb); ASSERT3P(lwb->lwb_write_zio, !=, NULL); lwb->lwb_state = LWB_STATE_OPENED; zil_lwb_set_zio_dependency(zilog, lwb); zilog->zl_last_lwb_opened = lwb; } mutex_exit(&zilog->zl_lock); ASSERT3P(lwb->lwb_root_zio, !=, NULL); ASSERT3P(lwb->lwb_write_zio, !=, NULL); ASSERT3S(lwb->lwb_state, ==, LWB_STATE_OPENED); } /* * Define a limited set of intent log block sizes. * * These must be a multiple of 4KB. Note only the amount used (again * aligned to 4KB) actually gets written. However, we can't always just * allocate SPA_OLD_MAXBLOCKSIZE as the slog space could be exhausted. */ static const struct { uint64_t limit; uint64_t blksz; } zil_block_buckets[] = { { 4096, 4096 }, /* non TX_WRITE */ { 8192 + 4096, 8192 + 4096 }, /* database */ { 32768 + 4096, 32768 + 4096 }, /* NFS writes */ { 65536 + 4096, 65536 + 4096 }, /* 64KB writes */ { 131072, 131072 }, /* < 128KB writes */ { 131072 +4096, 65536 + 4096 }, /* 128KB writes */ { UINT64_MAX, SPA_OLD_MAXBLOCKSIZE}, /* > 128KB writes */ }; /* * Maximum block size used by the ZIL. This is picked up when the ZIL is * initialized. Otherwise this should not be used directly; see * zl_max_block_size instead. */ static int zil_maxblocksize = SPA_OLD_MAXBLOCKSIZE; /* * Start a log block write and advance to the next log block. * Calls are serialized. */ static lwb_t * zil_lwb_write_issue(zilog_t *zilog, lwb_t *lwb) { lwb_t *nlwb = NULL; zil_chain_t *zilc; spa_t *spa = zilog->zl_spa; blkptr_t *bp; dmu_tx_t *tx; uint64_t txg; uint64_t zil_blksz, wsz; int i, error; boolean_t slog; ASSERT(MUTEX_HELD(&zilog->zl_issuer_lock)); ASSERT3P(lwb->lwb_root_zio, !=, NULL); ASSERT3P(lwb->lwb_write_zio, !=, NULL); ASSERT3S(lwb->lwb_state, ==, LWB_STATE_OPENED); if (BP_GET_CHECKSUM(&lwb->lwb_blk) == ZIO_CHECKSUM_ZILOG2) { zilc = (zil_chain_t *)lwb->lwb_buf; bp = &zilc->zc_next_blk; } else { zilc = (zil_chain_t *)(lwb->lwb_buf + lwb->lwb_sz); bp = &zilc->zc_next_blk; } ASSERT(lwb->lwb_nused <= lwb->lwb_sz); /* * Allocate the next block and save its address in this block * before writing it in order to establish the log chain. * Note that if the allocation of nlwb synced before we wrote * the block that points at it (lwb), we'd leak it if we crashed. * Therefore, we don't do dmu_tx_commit() until zil_lwb_write_done(). * We dirty the dataset to ensure that zil_sync() will be called * to clean up in the event of allocation failure or I/O failure. */ tx = dmu_tx_create(zilog->zl_os); /* * Since we are not going to create any new dirty data, and we * can even help with clearing the existing dirty data, we * should not be subject to the dirty data based delays. We * use TXG_NOTHROTTLE to bypass the delay mechanism. */ VERIFY0(dmu_tx_assign(tx, TXG_WAIT | TXG_NOTHROTTLE)); dsl_dataset_dirty(dmu_objset_ds(zilog->zl_os), tx); txg = dmu_tx_get_txg(tx); lwb->lwb_tx = tx; /* * Log blocks are pre-allocated. Here we select the size of the next * block, based on size used in the last block. * - first find the smallest bucket that will fit the block from a * limited set of block sizes. This is because it's faster to write * blocks allocated from the same metaslab as they are adjacent or * close. * - next find the maximum from the new suggested size and an array of * previous sizes. This lessens a picket fence effect of wrongly * guessing the size if we have a stream of say 2k, 64k, 2k, 64k * requests. * * Note we only write what is used, but we can't just allocate * the maximum block size because we can exhaust the available * pool log space. */ zil_blksz = zilog->zl_cur_used + sizeof (zil_chain_t); for (i = 0; zil_blksz > zil_block_buckets[i].limit; i++) continue; zil_blksz = MIN(zil_block_buckets[i].blksz, zilog->zl_max_block_size); zilog->zl_prev_blks[zilog->zl_prev_rotor] = zil_blksz; for (i = 0; i < ZIL_PREV_BLKS; i++) zil_blksz = MAX(zil_blksz, zilog->zl_prev_blks[i]); zilog->zl_prev_rotor = (zilog->zl_prev_rotor + 1) & (ZIL_PREV_BLKS - 1); BP_ZERO(bp); error = zio_alloc_zil(spa, zilog->zl_os, txg, bp, zil_blksz, &slog); if (slog) { ZIL_STAT_BUMP(zil_itx_metaslab_slog_count); ZIL_STAT_INCR(zil_itx_metaslab_slog_bytes, lwb->lwb_nused); } else { ZIL_STAT_BUMP(zil_itx_metaslab_normal_count); ZIL_STAT_INCR(zil_itx_metaslab_normal_bytes, lwb->lwb_nused); } if (error == 0) { ASSERT3U(bp->blk_birth, ==, txg); bp->blk_cksum = lwb->lwb_blk.blk_cksum; bp->blk_cksum.zc_word[ZIL_ZC_SEQ]++; /* * Allocate a new log write block (lwb). */ nlwb = zil_alloc_lwb(zilog, bp, slog, txg, TRUE); } if (BP_GET_CHECKSUM(&lwb->lwb_blk) == ZIO_CHECKSUM_ZILOG2) { /* For Slim ZIL only write what is used. */ wsz = P2ROUNDUP_TYPED(lwb->lwb_nused, ZIL_MIN_BLKSZ, uint64_t); ASSERT3U(wsz, <=, lwb->lwb_sz); zio_shrink(lwb->lwb_write_zio, wsz); } else { wsz = lwb->lwb_sz; } zilc->zc_pad = 0; zilc->zc_nused = lwb->lwb_nused; zilc->zc_eck.zec_cksum = lwb->lwb_blk.blk_cksum; /* * clear unused data for security */ bzero(lwb->lwb_buf + lwb->lwb_nused, wsz - lwb->lwb_nused); spa_config_enter(zilog->zl_spa, SCL_STATE, lwb, RW_READER); zil_lwb_add_block(lwb, &lwb->lwb_blk); lwb->lwb_issued_timestamp = gethrtime(); lwb->lwb_state = LWB_STATE_ISSUED; zio_nowait(lwb->lwb_root_zio); zio_nowait(lwb->lwb_write_zio); /* * If there was an allocation failure then nlwb will be null which * forces a txg_wait_synced(). */ return (nlwb); } /* * Maximum amount of write data that can be put into single log block. */ uint64_t zil_max_log_data(zilog_t *zilog) { return (zilog->zl_max_block_size - sizeof (zil_chain_t) - sizeof (lr_write_t)); } /* * Maximum amount of log space we agree to waste to reduce number of * WR_NEED_COPY chunks to reduce zl_get_data() overhead (~12%). */ static inline uint64_t zil_max_waste_space(zilog_t *zilog) { return (zil_max_log_data(zilog) / 8); } /* * Maximum amount of write data for WR_COPIED. For correctness, consumers * must fall back to WR_NEED_COPY if we can't fit the entire record into one * maximum sized log block, because each WR_COPIED record must fit in a * single log block. For space efficiency, we want to fit two records into a * max-sized log block. */ uint64_t zil_max_copied_data(zilog_t *zilog) { return ((zilog->zl_max_block_size - sizeof (zil_chain_t)) / 2 - sizeof (lr_write_t)); } static lwb_t * zil_lwb_commit(zilog_t *zilog, itx_t *itx, lwb_t *lwb) { lr_t *lrcb, *lrc; lr_write_t *lrwb, *lrw; char *lr_buf; uint64_t dlen, dnow, dpad, lwb_sp, reclen, txg, max_log_data; ASSERT(MUTEX_HELD(&zilog->zl_issuer_lock)); ASSERT3P(lwb, !=, NULL); ASSERT3P(lwb->lwb_buf, !=, NULL); zil_lwb_write_open(zilog, lwb); lrc = &itx->itx_lr; lrw = (lr_write_t *)lrc; /* * A commit itx doesn't represent any on-disk state; instead * it's simply used as a place holder on the commit list, and * provides a mechanism for attaching a "commit waiter" onto the * correct lwb (such that the waiter can be signalled upon * completion of that lwb). Thus, we don't process this itx's * log record if it's a commit itx (these itx's don't have log * records), and instead link the itx's waiter onto the lwb's * list of waiters. * * For more details, see the comment above zil_commit(). */ if (lrc->lrc_txtype == TX_COMMIT) { mutex_enter(&zilog->zl_lock); zil_commit_waiter_link_lwb(itx->itx_private, lwb); itx->itx_private = NULL; mutex_exit(&zilog->zl_lock); return (lwb); } if (lrc->lrc_txtype == TX_WRITE && itx->itx_wr_state == WR_NEED_COPY) { dlen = P2ROUNDUP_TYPED( lrw->lr_length, sizeof (uint64_t), uint64_t); dpad = dlen - lrw->lr_length; } else { dlen = dpad = 0; } reclen = lrc->lrc_reclen; zilog->zl_cur_used += (reclen + dlen); txg = lrc->lrc_txg; ASSERT3U(zilog->zl_cur_used, <, UINT64_MAX - (reclen + dlen)); cont: /* * If this record won't fit in the current log block, start a new one. * For WR_NEED_COPY optimize layout for minimal number of chunks. */ lwb_sp = lwb->lwb_sz - lwb->lwb_nused; max_log_data = zil_max_log_data(zilog); if (reclen > lwb_sp || (reclen + dlen > lwb_sp && lwb_sp < zil_max_waste_space(zilog) && (dlen % max_log_data == 0 || lwb_sp < reclen + dlen % max_log_data))) { lwb = zil_lwb_write_issue(zilog, lwb); if (lwb == NULL) return (NULL); zil_lwb_write_open(zilog, lwb); ASSERT(LWB_EMPTY(lwb)); lwb_sp = lwb->lwb_sz - lwb->lwb_nused; /* * There must be enough space in the new, empty log block to * hold reclen. For WR_COPIED, we need to fit the whole * record in one block, and reclen is the header size + the * data size. For WR_NEED_COPY, we can create multiple * records, splitting the data into multiple blocks, so we * only need to fit one word of data per block; in this case * reclen is just the header size (no data). */ ASSERT3U(reclen + MIN(dlen, sizeof (uint64_t)), <=, lwb_sp); } dnow = MIN(dlen, lwb_sp - reclen); lr_buf = lwb->lwb_buf + lwb->lwb_nused; bcopy(lrc, lr_buf, reclen); lrcb = (lr_t *)lr_buf; /* Like lrc, but inside lwb. */ lrwb = (lr_write_t *)lrcb; /* Like lrw, but inside lwb. */ ZIL_STAT_BUMP(zil_itx_count); /* * If it's a write, fetch the data or get its blkptr as appropriate. */ if (lrc->lrc_txtype == TX_WRITE) { if (txg > spa_freeze_txg(zilog->zl_spa)) txg_wait_synced(zilog->zl_dmu_pool, txg); if (itx->itx_wr_state == WR_COPIED) { ZIL_STAT_BUMP(zil_itx_copied_count); ZIL_STAT_INCR(zil_itx_copied_bytes, lrw->lr_length); } else { char *dbuf; int error; if (itx->itx_wr_state == WR_NEED_COPY) { dbuf = lr_buf + reclen; lrcb->lrc_reclen += dnow; if (lrwb->lr_length > dnow) lrwb->lr_length = dnow; lrw->lr_offset += dnow; lrw->lr_length -= dnow; ZIL_STAT_BUMP(zil_itx_needcopy_count); ZIL_STAT_INCR(zil_itx_needcopy_bytes, dnow); } else { ASSERT3S(itx->itx_wr_state, ==, WR_INDIRECT); dbuf = NULL; ZIL_STAT_BUMP(zil_itx_indirect_count); ZIL_STAT_INCR(zil_itx_indirect_bytes, lrw->lr_length); } /* * We pass in the "lwb_write_zio" rather than * "lwb_root_zio" so that the "lwb_write_zio" * becomes the parent of any zio's created by * the "zl_get_data" callback. The vdevs are * flushed after the "lwb_write_zio" completes, * so we want to make sure that completion * callback waits for these additional zio's, * such that the vdevs used by those zio's will * be included in the lwb's vdev tree, and those * vdevs will be properly flushed. If we passed * in "lwb_root_zio" here, then these additional * vdevs may not be flushed; e.g. if these zio's * completed after "lwb_write_zio" completed. */ error = zilog->zl_get_data(itx->itx_private, itx->itx_gen, lrwb, dbuf, lwb, lwb->lwb_write_zio); if (dbuf != NULL && error == 0 && dnow == dlen) /* Zero any padding bytes in the last block. */ bzero((char *)dbuf + lrwb->lr_length, dpad); if (error == EIO) { txg_wait_synced(zilog->zl_dmu_pool, txg); return (lwb); } if (error != 0) { ASSERT(error == ENOENT || error == EEXIST || error == EALREADY); return (lwb); } } } /* * We're actually making an entry, so update lrc_seq to be the * log record sequence number. Note that this is generally not * equal to the itx sequence number because not all transactions * are synchronous, and sometimes spa_sync() gets there first. */ lrcb->lrc_seq = ++zilog->zl_lr_seq; lwb->lwb_nused += reclen + dnow; zil_lwb_add_txg(lwb, txg); ASSERT3U(lwb->lwb_nused, <=, lwb->lwb_sz); ASSERT0(P2PHASE(lwb->lwb_nused, sizeof (uint64_t))); dlen -= dnow; if (dlen > 0) { zilog->zl_cur_used += reclen; goto cont; } return (lwb); } itx_t * zil_itx_create(uint64_t txtype, size_t olrsize) { size_t itxsize, lrsize; itx_t *itx; lrsize = P2ROUNDUP_TYPED(olrsize, sizeof (uint64_t), size_t); itxsize = offsetof(itx_t, itx_lr) + lrsize; itx = zio_data_buf_alloc(itxsize); itx->itx_lr.lrc_txtype = txtype; itx->itx_lr.lrc_reclen = lrsize; itx->itx_lr.lrc_seq = 0; /* defensive */ bzero((char *)&itx->itx_lr + olrsize, lrsize - olrsize); itx->itx_sync = B_TRUE; /* default is synchronous */ itx->itx_callback = NULL; itx->itx_callback_data = NULL; itx->itx_size = itxsize; return (itx); } void zil_itx_destroy(itx_t *itx) { IMPLY(itx->itx_lr.lrc_txtype == TX_COMMIT, itx->itx_callback == NULL); IMPLY(itx->itx_callback != NULL, itx->itx_lr.lrc_txtype != TX_COMMIT); if (itx->itx_callback != NULL) itx->itx_callback(itx->itx_callback_data); zio_data_buf_free(itx, itx->itx_size); } /* * Free up the sync and async itxs. The itxs_t has already been detached * so no locks are needed. */ static void zil_itxg_clean(void *arg) { itx_t *itx; list_t *list; avl_tree_t *t; void *cookie; itxs_t *itxs = arg; itx_async_node_t *ian; list = &itxs->i_sync_list; while ((itx = list_head(list)) != NULL) { /* * In the general case, commit itxs will not be found * here, as they'll be committed to an lwb via * zil_lwb_commit(), and free'd in that function. Having * said that, it is still possible for commit itxs to be * found here, due to the following race: * * - a thread calls zil_commit() which assigns the * commit itx to a per-txg i_sync_list * - zil_itxg_clean() is called (e.g. via spa_sync()) * while the waiter is still on the i_sync_list * * There's nothing to prevent syncing the txg while the * waiter is on the i_sync_list. This normally doesn't * happen because spa_sync() is slower than zil_commit(), * but if zil_commit() calls txg_wait_synced() (e.g. * because zil_create() or zil_commit_writer_stall() is * called) we will hit this case. */ if (itx->itx_lr.lrc_txtype == TX_COMMIT) zil_commit_waiter_skip(itx->itx_private); list_remove(list, itx); zil_itx_destroy(itx); } cookie = NULL; t = &itxs->i_async_tree; while ((ian = avl_destroy_nodes(t, &cookie)) != NULL) { list = &ian->ia_list; while ((itx = list_head(list)) != NULL) { list_remove(list, itx); /* commit itxs should never be on the async lists. */ ASSERT3U(itx->itx_lr.lrc_txtype, !=, TX_COMMIT); zil_itx_destroy(itx); } list_destroy(list); kmem_free(ian, sizeof (itx_async_node_t)); } avl_destroy(t); kmem_free(itxs, sizeof (itxs_t)); } static int zil_aitx_compare(const void *x1, const void *x2) { const uint64_t o1 = ((itx_async_node_t *)x1)->ia_foid; const uint64_t o2 = ((itx_async_node_t *)x2)->ia_foid; return (TREE_CMP(o1, o2)); } /* * Remove all async itx with the given oid. */ void zil_remove_async(zilog_t *zilog, uint64_t oid) { uint64_t otxg, txg; itx_async_node_t *ian; avl_tree_t *t; avl_index_t where; list_t clean_list; itx_t *itx; ASSERT(oid != 0); list_create(&clean_list, sizeof (itx_t), offsetof(itx_t, itx_node)); if (spa_freeze_txg(zilog->zl_spa) != UINT64_MAX) /* ziltest support */ otxg = ZILTEST_TXG; else otxg = spa_last_synced_txg(zilog->zl_spa) + 1; for (txg = otxg; txg < (otxg + TXG_CONCURRENT_STATES); txg++) { itxg_t *itxg = &zilog->zl_itxg[txg & TXG_MASK]; mutex_enter(&itxg->itxg_lock); if (itxg->itxg_txg != txg) { mutex_exit(&itxg->itxg_lock); continue; } /* * Locate the object node and append its list. */ t = &itxg->itxg_itxs->i_async_tree; ian = avl_find(t, &oid, &where); if (ian != NULL) list_move_tail(&clean_list, &ian->ia_list); mutex_exit(&itxg->itxg_lock); } while ((itx = list_head(&clean_list)) != NULL) { list_remove(&clean_list, itx); /* commit itxs should never be on the async lists. */ ASSERT3U(itx->itx_lr.lrc_txtype, !=, TX_COMMIT); zil_itx_destroy(itx); } list_destroy(&clean_list); } void zil_itx_assign(zilog_t *zilog, itx_t *itx, dmu_tx_t *tx) { uint64_t txg; itxg_t *itxg; itxs_t *itxs, *clean = NULL; /* * Ensure the data of a renamed file is committed before the rename. */ if ((itx->itx_lr.lrc_txtype & ~TX_CI) == TX_RENAME) zil_async_to_sync(zilog, itx->itx_oid); if (spa_freeze_txg(zilog->zl_spa) != UINT64_MAX) txg = ZILTEST_TXG; else txg = dmu_tx_get_txg(tx); itxg = &zilog->zl_itxg[txg & TXG_MASK]; mutex_enter(&itxg->itxg_lock); itxs = itxg->itxg_itxs; if (itxg->itxg_txg != txg) { if (itxs != NULL) { /* * The zil_clean callback hasn't got around to cleaning * this itxg. Save the itxs for release below. * This should be rare. */ zfs_dbgmsg("zil_itx_assign: missed itx cleanup for " "txg %llu", (u_longlong_t)itxg->itxg_txg); clean = itxg->itxg_itxs; } itxg->itxg_txg = txg; itxs = itxg->itxg_itxs = kmem_zalloc(sizeof (itxs_t), KM_SLEEP); list_create(&itxs->i_sync_list, sizeof (itx_t), offsetof(itx_t, itx_node)); avl_create(&itxs->i_async_tree, zil_aitx_compare, sizeof (itx_async_node_t), offsetof(itx_async_node_t, ia_node)); } if (itx->itx_sync) { list_insert_tail(&itxs->i_sync_list, itx); } else { avl_tree_t *t = &itxs->i_async_tree; uint64_t foid = LR_FOID_GET_OBJ(((lr_ooo_t *)&itx->itx_lr)->lr_foid); itx_async_node_t *ian; avl_index_t where; ian = avl_find(t, &foid, &where); if (ian == NULL) { ian = kmem_alloc(sizeof (itx_async_node_t), KM_SLEEP); list_create(&ian->ia_list, sizeof (itx_t), offsetof(itx_t, itx_node)); ian->ia_foid = foid; avl_insert(t, ian, where); } list_insert_tail(&ian->ia_list, itx); } itx->itx_lr.lrc_txg = dmu_tx_get_txg(tx); /* * We don't want to dirty the ZIL using ZILTEST_TXG, because * zil_clean() will never be called using ZILTEST_TXG. Thus, we * need to be careful to always dirty the ZIL using the "real" * TXG (not itxg_txg) even when the SPA is frozen. */ zilog_dirty(zilog, dmu_tx_get_txg(tx)); mutex_exit(&itxg->itxg_lock); /* Release the old itxs now we've dropped the lock */ if (clean != NULL) zil_itxg_clean(clean); } /* * If there are any in-memory intent log transactions which have now been * synced then start up a taskq to free them. We should only do this after we * have written out the uberblocks (i.e. txg has been committed) so that * don't inadvertently clean out in-memory log records that would be required * by zil_commit(). */ void zil_clean(zilog_t *zilog, uint64_t synced_txg) { itxg_t *itxg = &zilog->zl_itxg[synced_txg & TXG_MASK]; itxs_t *clean_me; ASSERT3U(synced_txg, <, ZILTEST_TXG); mutex_enter(&itxg->itxg_lock); if (itxg->itxg_itxs == NULL || itxg->itxg_txg == ZILTEST_TXG) { mutex_exit(&itxg->itxg_lock); return; } ASSERT3U(itxg->itxg_txg, <=, synced_txg); ASSERT3U(itxg->itxg_txg, !=, 0); clean_me = itxg->itxg_itxs; itxg->itxg_itxs = NULL; itxg->itxg_txg = 0; mutex_exit(&itxg->itxg_lock); /* * Preferably start a task queue to free up the old itxs but * if taskq_dispatch can't allocate resources to do that then * free it in-line. This should be rare. Note, using TQ_SLEEP * created a bad performance problem. */ ASSERT3P(zilog->zl_dmu_pool, !=, NULL); ASSERT3P(zilog->zl_dmu_pool->dp_zil_clean_taskq, !=, NULL); taskqid_t id = taskq_dispatch(zilog->zl_dmu_pool->dp_zil_clean_taskq, zil_itxg_clean, clean_me, TQ_NOSLEEP); if (id == TASKQID_INVALID) zil_itxg_clean(clean_me); } /* * This function will traverse the queue of itxs that need to be * committed, and move them onto the ZIL's zl_itx_commit_list. */ static void zil_get_commit_list(zilog_t *zilog) { uint64_t otxg, txg; list_t *commit_list = &zilog->zl_itx_commit_list; ASSERT(MUTEX_HELD(&zilog->zl_issuer_lock)); if (spa_freeze_txg(zilog->zl_spa) != UINT64_MAX) /* ziltest support */ otxg = ZILTEST_TXG; else otxg = spa_last_synced_txg(zilog->zl_spa) + 1; /* * This is inherently racy, since there is nothing to prevent * the last synced txg from changing. That's okay since we'll * only commit things in the future. */ for (txg = otxg; txg < (otxg + TXG_CONCURRENT_STATES); txg++) { itxg_t *itxg = &zilog->zl_itxg[txg & TXG_MASK]; mutex_enter(&itxg->itxg_lock); if (itxg->itxg_txg != txg) { mutex_exit(&itxg->itxg_lock); continue; } /* * If we're adding itx records to the zl_itx_commit_list, * then the zil better be dirty in this "txg". We can assert * that here since we're holding the itxg_lock which will * prevent spa_sync from cleaning it. Once we add the itxs * to the zl_itx_commit_list we must commit it to disk even * if it's unnecessary (i.e. the txg was synced). */ ASSERT(zilog_is_dirty_in_txg(zilog, txg) || spa_freeze_txg(zilog->zl_spa) != UINT64_MAX); list_move_tail(commit_list, &itxg->itxg_itxs->i_sync_list); mutex_exit(&itxg->itxg_lock); } } /* * Move the async itxs for a specified object to commit into sync lists. */ void zil_async_to_sync(zilog_t *zilog, uint64_t foid) { uint64_t otxg, txg; itx_async_node_t *ian; avl_tree_t *t; avl_index_t where; if (spa_freeze_txg(zilog->zl_spa) != UINT64_MAX) /* ziltest support */ otxg = ZILTEST_TXG; else otxg = spa_last_synced_txg(zilog->zl_spa) + 1; /* * This is inherently racy, since there is nothing to prevent * the last synced txg from changing. */ for (txg = otxg; txg < (otxg + TXG_CONCURRENT_STATES); txg++) { itxg_t *itxg = &zilog->zl_itxg[txg & TXG_MASK]; mutex_enter(&itxg->itxg_lock); if (itxg->itxg_txg != txg) { mutex_exit(&itxg->itxg_lock); continue; } /* * If a foid is specified then find that node and append its * list. Otherwise walk the tree appending all the lists * to the sync list. We add to the end rather than the * beginning to ensure the create has happened. */ t = &itxg->itxg_itxs->i_async_tree; if (foid != 0) { ian = avl_find(t, &foid, &where); if (ian != NULL) { list_move_tail(&itxg->itxg_itxs->i_sync_list, &ian->ia_list); } } else { void *cookie = NULL; while ((ian = avl_destroy_nodes(t, &cookie)) != NULL) { list_move_tail(&itxg->itxg_itxs->i_sync_list, &ian->ia_list); list_destroy(&ian->ia_list); kmem_free(ian, sizeof (itx_async_node_t)); } } mutex_exit(&itxg->itxg_lock); } } /* * This function will prune commit itxs that are at the head of the * commit list (it won't prune past the first non-commit itx), and * either: a) attach them to the last lwb that's still pending * completion, or b) skip them altogether. * * This is used as a performance optimization to prevent commit itxs * from generating new lwbs when it's unnecessary to do so. */ static void zil_prune_commit_list(zilog_t *zilog) { itx_t *itx; ASSERT(MUTEX_HELD(&zilog->zl_issuer_lock)); while ((itx = list_head(&zilog->zl_itx_commit_list)) != NULL) { lr_t *lrc = &itx->itx_lr; if (lrc->lrc_txtype != TX_COMMIT) break; mutex_enter(&zilog->zl_lock); lwb_t *last_lwb = zilog->zl_last_lwb_opened; if (last_lwb == NULL || last_lwb->lwb_state == LWB_STATE_FLUSH_DONE) { /* * All of the itxs this waiter was waiting on * must have already completed (or there were * never any itx's for it to wait on), so it's * safe to skip this waiter and mark it done. */ zil_commit_waiter_skip(itx->itx_private); } else { zil_commit_waiter_link_lwb(itx->itx_private, last_lwb); itx->itx_private = NULL; } mutex_exit(&zilog->zl_lock); list_remove(&zilog->zl_itx_commit_list, itx); zil_itx_destroy(itx); } IMPLY(itx != NULL, itx->itx_lr.lrc_txtype != TX_COMMIT); } static void zil_commit_writer_stall(zilog_t *zilog) { /* * When zio_alloc_zil() fails to allocate the next lwb block on * disk, we must call txg_wait_synced() to ensure all of the * lwbs in the zilog's zl_lwb_list are synced and then freed (in * zil_sync()), such that any subsequent ZIL writer (i.e. a call * to zil_process_commit_list()) will have to call zil_create(), * and start a new ZIL chain. * * Since zil_alloc_zil() failed, the lwb that was previously * issued does not have a pointer to the "next" lwb on disk. * Thus, if another ZIL writer thread was to allocate the "next" * on-disk lwb, that block could be leaked in the event of a * crash (because the previous lwb on-disk would not point to * it). * * We must hold the zilog's zl_issuer_lock while we do this, to * ensure no new threads enter zil_process_commit_list() until * all lwb's in the zl_lwb_list have been synced and freed * (which is achieved via the txg_wait_synced() call). */ ASSERT(MUTEX_HELD(&zilog->zl_issuer_lock)); txg_wait_synced(zilog->zl_dmu_pool, 0); ASSERT3P(list_tail(&zilog->zl_lwb_list), ==, NULL); } /* * This function will traverse the commit list, creating new lwbs as * needed, and committing the itxs from the commit list to these newly * created lwbs. Additionally, as a new lwb is created, the previous * lwb will be issued to the zio layer to be written to disk. */ static void zil_process_commit_list(zilog_t *zilog) { spa_t *spa = zilog->zl_spa; list_t nolwb_itxs; list_t nolwb_waiters; lwb_t *lwb; itx_t *itx; ASSERT(MUTEX_HELD(&zilog->zl_issuer_lock)); /* * Return if there's nothing to commit before we dirty the fs by * calling zil_create(). */ if (list_head(&zilog->zl_itx_commit_list) == NULL) return; list_create(&nolwb_itxs, sizeof (itx_t), offsetof(itx_t, itx_node)); list_create(&nolwb_waiters, sizeof (zil_commit_waiter_t), offsetof(zil_commit_waiter_t, zcw_node)); lwb = list_tail(&zilog->zl_lwb_list); if (lwb == NULL) { lwb = zil_create(zilog); } else { + /* + * Activate SPA_FEATURE_ZILSAXATTR for the cases where ZIL will + * have already been created (zl_lwb_list not empty). + */ + zil_commit_activate_saxattr_feature(zilog); ASSERT3S(lwb->lwb_state, !=, LWB_STATE_ISSUED); ASSERT3S(lwb->lwb_state, !=, LWB_STATE_WRITE_DONE); ASSERT3S(lwb->lwb_state, !=, LWB_STATE_FLUSH_DONE); } while ((itx = list_head(&zilog->zl_itx_commit_list)) != NULL) { lr_t *lrc = &itx->itx_lr; uint64_t txg = lrc->lrc_txg; ASSERT3U(txg, !=, 0); if (lrc->lrc_txtype == TX_COMMIT) { DTRACE_PROBE2(zil__process__commit__itx, zilog_t *, zilog, itx_t *, itx); } else { DTRACE_PROBE2(zil__process__normal__itx, zilog_t *, zilog, itx_t *, itx); } list_remove(&zilog->zl_itx_commit_list, itx); boolean_t synced = txg <= spa_last_synced_txg(spa); boolean_t frozen = txg > spa_freeze_txg(spa); /* * If the txg of this itx has already been synced out, then * we don't need to commit this itx to an lwb. This is * because the data of this itx will have already been * written to the main pool. This is inherently racy, and * it's still ok to commit an itx whose txg has already * been synced; this will result in a write that's * unnecessary, but will do no harm. * * With that said, we always want to commit TX_COMMIT itxs * to an lwb, regardless of whether or not that itx's txg * has been synced out. We do this to ensure any OPENED lwb * will always have at least one zil_commit_waiter_t linked * to the lwb. * * As a counter-example, if we skipped TX_COMMIT itx's * whose txg had already been synced, the following * situation could occur if we happened to be racing with * spa_sync: * * 1. We commit a non-TX_COMMIT itx to an lwb, where the * itx's txg is 10 and the last synced txg is 9. * 2. spa_sync finishes syncing out txg 10. * 3. We move to the next itx in the list, it's a TX_COMMIT * whose txg is 10, so we skip it rather than committing * it to the lwb used in (1). * * If the itx that is skipped in (3) is the last TX_COMMIT * itx in the commit list, than it's possible for the lwb * used in (1) to remain in the OPENED state indefinitely. * * To prevent the above scenario from occurring, ensuring * that once an lwb is OPENED it will transition to ISSUED * and eventually DONE, we always commit TX_COMMIT itx's to * an lwb here, even if that itx's txg has already been * synced. * * Finally, if the pool is frozen, we _always_ commit the * itx. The point of freezing the pool is to prevent data * from being written to the main pool via spa_sync, and * instead rely solely on the ZIL to persistently store the * data; i.e. when the pool is frozen, the last synced txg * value can't be trusted. */ if (frozen || !synced || lrc->lrc_txtype == TX_COMMIT) { if (lwb != NULL) { lwb = zil_lwb_commit(zilog, itx, lwb); if (lwb == NULL) list_insert_tail(&nolwb_itxs, itx); else list_insert_tail(&lwb->lwb_itxs, itx); } else { if (lrc->lrc_txtype == TX_COMMIT) { zil_commit_waiter_link_nolwb( itx->itx_private, &nolwb_waiters); } list_insert_tail(&nolwb_itxs, itx); } } else { ASSERT3S(lrc->lrc_txtype, !=, TX_COMMIT); zil_itx_destroy(itx); } } if (lwb == NULL) { /* * This indicates zio_alloc_zil() failed to allocate the * "next" lwb on-disk. When this happens, we must stall * the ZIL write pipeline; see the comment within * zil_commit_writer_stall() for more details. */ zil_commit_writer_stall(zilog); /* * Additionally, we have to signal and mark the "nolwb" * waiters as "done" here, since without an lwb, we * can't do this via zil_lwb_flush_vdevs_done() like * normal. */ zil_commit_waiter_t *zcw; while ((zcw = list_head(&nolwb_waiters)) != NULL) { zil_commit_waiter_skip(zcw); list_remove(&nolwb_waiters, zcw); } /* * And finally, we have to destroy the itx's that * couldn't be committed to an lwb; this will also call * the itx's callback if one exists for the itx. */ while ((itx = list_head(&nolwb_itxs)) != NULL) { list_remove(&nolwb_itxs, itx); zil_itx_destroy(itx); } } else { ASSERT(list_is_empty(&nolwb_waiters)); ASSERT3P(lwb, !=, NULL); ASSERT3S(lwb->lwb_state, !=, LWB_STATE_ISSUED); ASSERT3S(lwb->lwb_state, !=, LWB_STATE_WRITE_DONE); ASSERT3S(lwb->lwb_state, !=, LWB_STATE_FLUSH_DONE); /* * At this point, the ZIL block pointed at by the "lwb" * variable is in one of the following states: "closed" * or "open". * * If it's "closed", then no itxs have been committed to * it, so there's no point in issuing its zio (i.e. it's * "empty"). * * If it's "open", then it contains one or more itxs that * eventually need to be committed to stable storage. In * this case we intentionally do not issue the lwb's zio * to disk yet, and instead rely on one of the following * two mechanisms for issuing the zio: * * 1. Ideally, there will be more ZIL activity occurring * on the system, such that this function will be * immediately called again (not necessarily by the same * thread) and this lwb's zio will be issued via * zil_lwb_commit(). This way, the lwb is guaranteed to * be "full" when it is issued to disk, and we'll make * use of the lwb's size the best we can. * * 2. If there isn't sufficient ZIL activity occurring on * the system, such that this lwb's zio isn't issued via * zil_lwb_commit(), zil_commit_waiter() will issue the * lwb's zio. If this occurs, the lwb is not guaranteed * to be "full" by the time its zio is issued, and means * the size of the lwb was "too large" given the amount * of ZIL activity occurring on the system at that time. * * We do this for a couple of reasons: * * 1. To try and reduce the number of IOPs needed to * write the same number of itxs. If an lwb has space * available in its buffer for more itxs, and more itxs * will be committed relatively soon (relative to the * latency of performing a write), then it's beneficial * to wait for these "next" itxs. This way, more itxs * can be committed to stable storage with fewer writes. * * 2. To try and use the largest lwb block size that the * incoming rate of itxs can support. Again, this is to * try and pack as many itxs into as few lwbs as * possible, without significantly impacting the latency * of each individual itx. */ } } /* * This function is responsible for ensuring the passed in commit waiter * (and associated commit itx) is committed to an lwb. If the waiter is * not already committed to an lwb, all itxs in the zilog's queue of * itxs will be processed. The assumption is the passed in waiter's * commit itx will found in the queue just like the other non-commit * itxs, such that when the entire queue is processed, the waiter will * have been committed to an lwb. * * The lwb associated with the passed in waiter is not guaranteed to * have been issued by the time this function completes. If the lwb is * not issued, we rely on future calls to zil_commit_writer() to issue * the lwb, or the timeout mechanism found in zil_commit_waiter(). */ static void zil_commit_writer(zilog_t *zilog, zil_commit_waiter_t *zcw) { ASSERT(!MUTEX_HELD(&zilog->zl_lock)); ASSERT(spa_writeable(zilog->zl_spa)); mutex_enter(&zilog->zl_issuer_lock); if (zcw->zcw_lwb != NULL || zcw->zcw_done) { /* * It's possible that, while we were waiting to acquire * the "zl_issuer_lock", another thread committed this * waiter to an lwb. If that occurs, we bail out early, * without processing any of the zilog's queue of itxs. * * On certain workloads and system configurations, the * "zl_issuer_lock" can become highly contended. In an * attempt to reduce this contention, we immediately drop * the lock if the waiter has already been processed. * * We've measured this optimization to reduce CPU spent * contending on this lock by up to 5%, using a system * with 32 CPUs, low latency storage (~50 usec writes), * and 1024 threads performing sync writes. */ goto out; } ZIL_STAT_BUMP(zil_commit_writer_count); zil_get_commit_list(zilog); zil_prune_commit_list(zilog); zil_process_commit_list(zilog); out: mutex_exit(&zilog->zl_issuer_lock); } static void zil_commit_waiter_timeout(zilog_t *zilog, zil_commit_waiter_t *zcw) { ASSERT(!MUTEX_HELD(&zilog->zl_issuer_lock)); ASSERT(MUTEX_HELD(&zcw->zcw_lock)); ASSERT3B(zcw->zcw_done, ==, B_FALSE); lwb_t *lwb = zcw->zcw_lwb; ASSERT3P(lwb, !=, NULL); ASSERT3S(lwb->lwb_state, !=, LWB_STATE_CLOSED); /* * If the lwb has already been issued by another thread, we can * immediately return since there's no work to be done (the * point of this function is to issue the lwb). Additionally, we * do this prior to acquiring the zl_issuer_lock, to avoid * acquiring it when it's not necessary to do so. */ if (lwb->lwb_state == LWB_STATE_ISSUED || lwb->lwb_state == LWB_STATE_WRITE_DONE || lwb->lwb_state == LWB_STATE_FLUSH_DONE) return; /* * In order to call zil_lwb_write_issue() we must hold the * zilog's "zl_issuer_lock". We can't simply acquire that lock, * since we're already holding the commit waiter's "zcw_lock", * and those two locks are acquired in the opposite order * elsewhere. */ mutex_exit(&zcw->zcw_lock); mutex_enter(&zilog->zl_issuer_lock); mutex_enter(&zcw->zcw_lock); /* * Since we just dropped and re-acquired the commit waiter's * lock, we have to re-check to see if the waiter was marked * "done" during that process. If the waiter was marked "done", * the "lwb" pointer is no longer valid (it can be free'd after * the waiter is marked "done"), so without this check we could * wind up with a use-after-free error below. */ if (zcw->zcw_done) goto out; ASSERT3P(lwb, ==, zcw->zcw_lwb); /* * We've already checked this above, but since we hadn't acquired * the zilog's zl_issuer_lock, we have to perform this check a * second time while holding the lock. * * We don't need to hold the zl_lock since the lwb cannot transition * from OPENED to ISSUED while we hold the zl_issuer_lock. The lwb * _can_ transition from ISSUED to DONE, but it's OK to race with * that transition since we treat the lwb the same, whether it's in * the ISSUED or DONE states. * * The important thing, is we treat the lwb differently depending on * if it's ISSUED or OPENED, and block any other threads that might * attempt to issue this lwb. For that reason we hold the * zl_issuer_lock when checking the lwb_state; we must not call * zil_lwb_write_issue() if the lwb had already been issued. * * See the comment above the lwb_state_t structure definition for * more details on the lwb states, and locking requirements. */ if (lwb->lwb_state == LWB_STATE_ISSUED || lwb->lwb_state == LWB_STATE_WRITE_DONE || lwb->lwb_state == LWB_STATE_FLUSH_DONE) goto out; ASSERT3S(lwb->lwb_state, ==, LWB_STATE_OPENED); /* * As described in the comments above zil_commit_waiter() and * zil_process_commit_list(), we need to issue this lwb's zio * since we've reached the commit waiter's timeout and it still * hasn't been issued. */ lwb_t *nlwb = zil_lwb_write_issue(zilog, lwb); IMPLY(nlwb != NULL, lwb->lwb_state != LWB_STATE_OPENED); /* * Since the lwb's zio hadn't been issued by the time this thread * reached its timeout, we reset the zilog's "zl_cur_used" field * to influence the zil block size selection algorithm. * * By having to issue the lwb's zio here, it means the size of the * lwb was too large, given the incoming throughput of itxs. By * setting "zl_cur_used" to zero, we communicate this fact to the * block size selection algorithm, so it can take this information * into account, and potentially select a smaller size for the * next lwb block that is allocated. */ zilog->zl_cur_used = 0; if (nlwb == NULL) { /* * When zil_lwb_write_issue() returns NULL, this * indicates zio_alloc_zil() failed to allocate the * "next" lwb on-disk. When this occurs, the ZIL write * pipeline must be stalled; see the comment within the * zil_commit_writer_stall() function for more details. * * We must drop the commit waiter's lock prior to * calling zil_commit_writer_stall() or else we can wind * up with the following deadlock: * * - This thread is waiting for the txg to sync while * holding the waiter's lock; txg_wait_synced() is * used within txg_commit_writer_stall(). * * - The txg can't sync because it is waiting for this * lwb's zio callback to call dmu_tx_commit(). * * - The lwb's zio callback can't call dmu_tx_commit() * because it's blocked trying to acquire the waiter's * lock, which occurs prior to calling dmu_tx_commit() */ mutex_exit(&zcw->zcw_lock); zil_commit_writer_stall(zilog); mutex_enter(&zcw->zcw_lock); } out: mutex_exit(&zilog->zl_issuer_lock); ASSERT(MUTEX_HELD(&zcw->zcw_lock)); } /* * This function is responsible for performing the following two tasks: * * 1. its primary responsibility is to block until the given "commit * waiter" is considered "done". * * 2. its secondary responsibility is to issue the zio for the lwb that * the given "commit waiter" is waiting on, if this function has * waited "long enough" and the lwb is still in the "open" state. * * Given a sufficient amount of itxs being generated and written using * the ZIL, the lwb's zio will be issued via the zil_lwb_commit() * function. If this does not occur, this secondary responsibility will * ensure the lwb is issued even if there is not other synchronous * activity on the system. * * For more details, see zil_process_commit_list(); more specifically, * the comment at the bottom of that function. */ static void zil_commit_waiter(zilog_t *zilog, zil_commit_waiter_t *zcw) { ASSERT(!MUTEX_HELD(&zilog->zl_lock)); ASSERT(!MUTEX_HELD(&zilog->zl_issuer_lock)); ASSERT(spa_writeable(zilog->zl_spa)); mutex_enter(&zcw->zcw_lock); /* * The timeout is scaled based on the lwb latency to avoid * significantly impacting the latency of each individual itx. * For more details, see the comment at the bottom of the * zil_process_commit_list() function. */ int pct = MAX(zfs_commit_timeout_pct, 1); hrtime_t sleep = (zilog->zl_last_lwb_latency * pct) / 100; hrtime_t wakeup = gethrtime() + sleep; boolean_t timedout = B_FALSE; while (!zcw->zcw_done) { ASSERT(MUTEX_HELD(&zcw->zcw_lock)); lwb_t *lwb = zcw->zcw_lwb; /* * Usually, the waiter will have a non-NULL lwb field here, * but it's possible for it to be NULL as a result of * zil_commit() racing with spa_sync(). * * When zil_clean() is called, it's possible for the itxg * list (which may be cleaned via a taskq) to contain * commit itxs. When this occurs, the commit waiters linked * off of these commit itxs will not be committed to an * lwb. Additionally, these commit waiters will not be * marked done until zil_commit_waiter_skip() is called via * zil_itxg_clean(). * * Thus, it's possible for this commit waiter (i.e. the * "zcw" variable) to be found in this "in between" state; * where it's "zcw_lwb" field is NULL, and it hasn't yet * been skipped, so it's "zcw_done" field is still B_FALSE. */ IMPLY(lwb != NULL, lwb->lwb_state != LWB_STATE_CLOSED); if (lwb != NULL && lwb->lwb_state == LWB_STATE_OPENED) { ASSERT3B(timedout, ==, B_FALSE); /* * If the lwb hasn't been issued yet, then we * need to wait with a timeout, in case this * function needs to issue the lwb after the * timeout is reached; responsibility (2) from * the comment above this function. */ int rc = cv_timedwait_hires(&zcw->zcw_cv, &zcw->zcw_lock, wakeup, USEC2NSEC(1), CALLOUT_FLAG_ABSOLUTE); if (rc != -1 || zcw->zcw_done) continue; timedout = B_TRUE; zil_commit_waiter_timeout(zilog, zcw); if (!zcw->zcw_done) { /* * If the commit waiter has already been * marked "done", it's possible for the * waiter's lwb structure to have already * been freed. Thus, we can only reliably * make these assertions if the waiter * isn't done. */ ASSERT3P(lwb, ==, zcw->zcw_lwb); ASSERT3S(lwb->lwb_state, !=, LWB_STATE_OPENED); } } else { /* * If the lwb isn't open, then it must have already * been issued. In that case, there's no need to * use a timeout when waiting for the lwb to * complete. * * Additionally, if the lwb is NULL, the waiter * will soon be signaled and marked done via * zil_clean() and zil_itxg_clean(), so no timeout * is required. */ IMPLY(lwb != NULL, lwb->lwb_state == LWB_STATE_ISSUED || lwb->lwb_state == LWB_STATE_WRITE_DONE || lwb->lwb_state == LWB_STATE_FLUSH_DONE); cv_wait(&zcw->zcw_cv, &zcw->zcw_lock); } } mutex_exit(&zcw->zcw_lock); } static zil_commit_waiter_t * zil_alloc_commit_waiter(void) { zil_commit_waiter_t *zcw = kmem_cache_alloc(zil_zcw_cache, KM_SLEEP); cv_init(&zcw->zcw_cv, NULL, CV_DEFAULT, NULL); mutex_init(&zcw->zcw_lock, NULL, MUTEX_DEFAULT, NULL); list_link_init(&zcw->zcw_node); zcw->zcw_lwb = NULL; zcw->zcw_done = B_FALSE; zcw->zcw_zio_error = 0; return (zcw); } static void zil_free_commit_waiter(zil_commit_waiter_t *zcw) { ASSERT(!list_link_active(&zcw->zcw_node)); ASSERT3P(zcw->zcw_lwb, ==, NULL); ASSERT3B(zcw->zcw_done, ==, B_TRUE); mutex_destroy(&zcw->zcw_lock); cv_destroy(&zcw->zcw_cv); kmem_cache_free(zil_zcw_cache, zcw); } /* * This function is used to create a TX_COMMIT itx and assign it. This * way, it will be linked into the ZIL's list of synchronous itxs, and * then later committed to an lwb (or skipped) when * zil_process_commit_list() is called. */ static void zil_commit_itx_assign(zilog_t *zilog, zil_commit_waiter_t *zcw) { dmu_tx_t *tx = dmu_tx_create(zilog->zl_os); VERIFY0(dmu_tx_assign(tx, TXG_WAIT)); itx_t *itx = zil_itx_create(TX_COMMIT, sizeof (lr_t)); itx->itx_sync = B_TRUE; itx->itx_private = zcw; zil_itx_assign(zilog, itx, tx); dmu_tx_commit(tx); } /* * Commit ZFS Intent Log transactions (itxs) to stable storage. * * When writing ZIL transactions to the on-disk representation of the * ZIL, the itxs are committed to a Log Write Block (lwb). Multiple * itxs can be committed to a single lwb. Once a lwb is written and * committed to stable storage (i.e. the lwb is written, and vdevs have * been flushed), each itx that was committed to that lwb is also * considered to be committed to stable storage. * * When an itx is committed to an lwb, the log record (lr_t) contained * by the itx is copied into the lwb's zio buffer, and once this buffer * is written to disk, it becomes an on-disk ZIL block. * * As itxs are generated, they're inserted into the ZIL's queue of * uncommitted itxs. The semantics of zil_commit() are such that it will * block until all itxs that were in the queue when it was called, are * committed to stable storage. * * If "foid" is zero, this means all "synchronous" and "asynchronous" * itxs, for all objects in the dataset, will be committed to stable * storage prior to zil_commit() returning. If "foid" is non-zero, all * "synchronous" itxs for all objects, but only "asynchronous" itxs * that correspond to the foid passed in, will be committed to stable * storage prior to zil_commit() returning. * * Generally speaking, when zil_commit() is called, the consumer doesn't * actually care about _all_ of the uncommitted itxs. Instead, they're * simply trying to waiting for a specific itx to be committed to disk, * but the interface(s) for interacting with the ZIL don't allow such * fine-grained communication. A better interface would allow a consumer * to create and assign an itx, and then pass a reference to this itx to * zil_commit(); such that zil_commit() would return as soon as that * specific itx was committed to disk (instead of waiting for _all_ * itxs to be committed). * * When a thread calls zil_commit() a special "commit itx" will be * generated, along with a corresponding "waiter" for this commit itx. * zil_commit() will wait on this waiter's CV, such that when the waiter * is marked done, and signaled, zil_commit() will return. * * This commit itx is inserted into the queue of uncommitted itxs. This * provides an easy mechanism for determining which itxs were in the * queue prior to zil_commit() having been called, and which itxs were * added after zil_commit() was called. * * The commit it is special; it doesn't have any on-disk representation. * When a commit itx is "committed" to an lwb, the waiter associated * with it is linked onto the lwb's list of waiters. Then, when that lwb * completes, each waiter on the lwb's list is marked done and signaled * -- allowing the thread waiting on the waiter to return from zil_commit(). * * It's important to point out a few critical factors that allow us * to make use of the commit itxs, commit waiters, per-lwb lists of * commit waiters, and zio completion callbacks like we're doing: * * 1. The list of waiters for each lwb is traversed, and each commit * waiter is marked "done" and signaled, in the zio completion * callback of the lwb's zio[*]. * * * Actually, the waiters are signaled in the zio completion * callback of the root zio for the DKIOCFLUSHWRITECACHE commands * that are sent to the vdevs upon completion of the lwb zio. * * 2. When the itxs are inserted into the ZIL's queue of uncommitted * itxs, the order in which they are inserted is preserved[*]; as * itxs are added to the queue, they are added to the tail of * in-memory linked lists. * * When committing the itxs to lwbs (to be written to disk), they * are committed in the same order in which the itxs were added to * the uncommitted queue's linked list(s); i.e. the linked list of * itxs to commit is traversed from head to tail, and each itx is * committed to an lwb in that order. * * * To clarify: * * - the order of "sync" itxs is preserved w.r.t. other * "sync" itxs, regardless of the corresponding objects. * - the order of "async" itxs is preserved w.r.t. other * "async" itxs corresponding to the same object. * - the order of "async" itxs is *not* preserved w.r.t. other * "async" itxs corresponding to different objects. * - the order of "sync" itxs w.r.t. "async" itxs (or vice * versa) is *not* preserved, even for itxs that correspond * to the same object. * * For more details, see: zil_itx_assign(), zil_async_to_sync(), * zil_get_commit_list(), and zil_process_commit_list(). * * 3. The lwbs represent a linked list of blocks on disk. Thus, any * lwb cannot be considered committed to stable storage, until its * "previous" lwb is also committed to stable storage. This fact, * coupled with the fact described above, means that itxs are * committed in (roughly) the order in which they were generated. * This is essential because itxs are dependent on prior itxs. * Thus, we *must not* deem an itx as being committed to stable * storage, until *all* prior itxs have also been committed to * stable storage. * * To enforce this ordering of lwb zio's, while still leveraging as * much of the underlying storage performance as possible, we rely * on two fundamental concepts: * * 1. The creation and issuance of lwb zio's is protected by * the zilog's "zl_issuer_lock", which ensures only a single * thread is creating and/or issuing lwb's at a time * 2. The "previous" lwb is a child of the "current" lwb * (leveraging the zio parent-child dependency graph) * * By relying on this parent-child zio relationship, we can have * many lwb zio's concurrently issued to the underlying storage, * but the order in which they complete will be the same order in * which they were created. */ void zil_commit(zilog_t *zilog, uint64_t foid) { /* * We should never attempt to call zil_commit on a snapshot for * a couple of reasons: * * 1. A snapshot may never be modified, thus it cannot have any * in-flight itxs that would have modified the dataset. * * 2. By design, when zil_commit() is called, a commit itx will * be assigned to this zilog; as a result, the zilog will be * dirtied. We must not dirty the zilog of a snapshot; there's * checks in the code that enforce this invariant, and will * cause a panic if it's not upheld. */ ASSERT3B(dmu_objset_is_snapshot(zilog->zl_os), ==, B_FALSE); if (zilog->zl_sync == ZFS_SYNC_DISABLED) return; if (!spa_writeable(zilog->zl_spa)) { /* * If the SPA is not writable, there should never be any * pending itxs waiting to be committed to disk. If that * weren't true, we'd skip writing those itxs out, and * would break the semantics of zil_commit(); thus, we're * verifying that truth before we return to the caller. */ ASSERT(list_is_empty(&zilog->zl_lwb_list)); ASSERT3P(zilog->zl_last_lwb_opened, ==, NULL); for (int i = 0; i < TXG_SIZE; i++) ASSERT3P(zilog->zl_itxg[i].itxg_itxs, ==, NULL); return; } /* * If the ZIL is suspended, we don't want to dirty it by calling * zil_commit_itx_assign() below, nor can we write out * lwbs like would be done in zil_commit_write(). Thus, we * simply rely on txg_wait_synced() to maintain the necessary * semantics, and avoid calling those functions altogether. */ if (zilog->zl_suspend > 0) { txg_wait_synced(zilog->zl_dmu_pool, 0); return; } zil_commit_impl(zilog, foid); } void zil_commit_impl(zilog_t *zilog, uint64_t foid) { ZIL_STAT_BUMP(zil_commit_count); /* * Move the "async" itxs for the specified foid to the "sync" * queues, such that they will be later committed (or skipped) * to an lwb when zil_process_commit_list() is called. * * Since these "async" itxs must be committed prior to this * call to zil_commit returning, we must perform this operation * before we call zil_commit_itx_assign(). */ zil_async_to_sync(zilog, foid); /* * We allocate a new "waiter" structure which will initially be * linked to the commit itx using the itx's "itx_private" field. * Since the commit itx doesn't represent any on-disk state, * when it's committed to an lwb, rather than copying the its * lr_t into the lwb's buffer, the commit itx's "waiter" will be * added to the lwb's list of waiters. Then, when the lwb is * committed to stable storage, each waiter in the lwb's list of * waiters will be marked "done", and signalled. * * We must create the waiter and assign the commit itx prior to * calling zil_commit_writer(), or else our specific commit itx * is not guaranteed to be committed to an lwb prior to calling * zil_commit_waiter(). */ zil_commit_waiter_t *zcw = zil_alloc_commit_waiter(); zil_commit_itx_assign(zilog, zcw); zil_commit_writer(zilog, zcw); zil_commit_waiter(zilog, zcw); if (zcw->zcw_zio_error != 0) { /* * If there was an error writing out the ZIL blocks that * this thread is waiting on, then we fallback to * relying on spa_sync() to write out the data this * thread is waiting on. Obviously this has performance * implications, but the expectation is for this to be * an exceptional case, and shouldn't occur often. */ DTRACE_PROBE2(zil__commit__io__error, zilog_t *, zilog, zil_commit_waiter_t *, zcw); txg_wait_synced(zilog->zl_dmu_pool, 0); } zil_free_commit_waiter(zcw); } /* * Called in syncing context to free committed log blocks and update log header. */ void zil_sync(zilog_t *zilog, dmu_tx_t *tx) { zil_header_t *zh = zil_header_in_syncing_context(zilog); uint64_t txg = dmu_tx_get_txg(tx); spa_t *spa = zilog->zl_spa; uint64_t *replayed_seq = &zilog->zl_replayed_seq[txg & TXG_MASK]; lwb_t *lwb; /* * We don't zero out zl_destroy_txg, so make sure we don't try * to destroy it twice. */ if (spa_sync_pass(spa) != 1) return; mutex_enter(&zilog->zl_lock); ASSERT(zilog->zl_stop_sync == 0); if (*replayed_seq != 0) { ASSERT(zh->zh_replay_seq < *replayed_seq); zh->zh_replay_seq = *replayed_seq; *replayed_seq = 0; } if (zilog->zl_destroy_txg == txg) { blkptr_t blk = zh->zh_log; + dsl_dataset_t *ds = dmu_objset_ds(zilog->zl_os); ASSERT(list_head(&zilog->zl_lwb_list) == NULL); bzero(zh, sizeof (zil_header_t)); bzero(zilog->zl_replayed_seq, sizeof (zilog->zl_replayed_seq)); if (zilog->zl_keep_first) { /* * If this block was part of log chain that couldn't * be claimed because a device was missing during * zil_claim(), but that device later returns, * then this block could erroneously appear valid. * To guard against this, assign a new GUID to the new * log chain so it doesn't matter what blk points to. */ zil_init_log_chain(zilog, &blk); zh->zh_log = blk; + } else { + /* + * A destroyed ZIL chain can't contain any TX_SETSAXATTR + * records. So, deactivate the feature for this dataset. + * We activate it again when we start a new ZIL chain. + */ + if (dsl_dataset_feature_is_active(ds, + SPA_FEATURE_ZILSAXATTR)) + dsl_dataset_deactivate_feature(ds, + SPA_FEATURE_ZILSAXATTR, tx); } } while ((lwb = list_head(&zilog->zl_lwb_list)) != NULL) { zh->zh_log = lwb->lwb_blk; if (lwb->lwb_buf != NULL || lwb->lwb_max_txg > txg) break; list_remove(&zilog->zl_lwb_list, lwb); zio_free(spa, txg, &lwb->lwb_blk); zil_free_lwb(zilog, lwb); /* * If we don't have anything left in the lwb list then * we've had an allocation failure and we need to zero * out the zil_header blkptr so that we don't end * up freeing the same block twice. */ if (list_head(&zilog->zl_lwb_list) == NULL) BP_ZERO(&zh->zh_log); } /* * Remove fastwrite on any blocks that have been pre-allocated for * the next commit. This prevents fastwrite counter pollution by * unused, long-lived LWBs. */ for (; lwb != NULL; lwb = list_next(&zilog->zl_lwb_list, lwb)) { if (lwb->lwb_fastwrite && !lwb->lwb_write_zio) { metaslab_fastwrite_unmark(zilog->zl_spa, &lwb->lwb_blk); lwb->lwb_fastwrite = 0; } } mutex_exit(&zilog->zl_lock); } static int zil_lwb_cons(void *vbuf, void *unused, int kmflag) { (void) unused, (void) kmflag; lwb_t *lwb = vbuf; list_create(&lwb->lwb_itxs, sizeof (itx_t), offsetof(itx_t, itx_node)); list_create(&lwb->lwb_waiters, sizeof (zil_commit_waiter_t), offsetof(zil_commit_waiter_t, zcw_node)); avl_create(&lwb->lwb_vdev_tree, zil_lwb_vdev_compare, sizeof (zil_vdev_node_t), offsetof(zil_vdev_node_t, zv_node)); mutex_init(&lwb->lwb_vdev_lock, NULL, MUTEX_DEFAULT, NULL); return (0); } static void zil_lwb_dest(void *vbuf, void *unused) { (void) unused; lwb_t *lwb = vbuf; mutex_destroy(&lwb->lwb_vdev_lock); avl_destroy(&lwb->lwb_vdev_tree); list_destroy(&lwb->lwb_waiters); list_destroy(&lwb->lwb_itxs); } void zil_init(void) { zil_lwb_cache = kmem_cache_create("zil_lwb_cache", sizeof (lwb_t), 0, zil_lwb_cons, zil_lwb_dest, NULL, NULL, NULL, 0); zil_zcw_cache = kmem_cache_create("zil_zcw_cache", sizeof (zil_commit_waiter_t), 0, NULL, NULL, NULL, NULL, NULL, 0); zil_ksp = kstat_create("zfs", 0, "zil", "misc", KSTAT_TYPE_NAMED, sizeof (zil_stats) / sizeof (kstat_named_t), KSTAT_FLAG_VIRTUAL); if (zil_ksp != NULL) { zil_ksp->ks_data = &zil_stats; kstat_install(zil_ksp); } } void zil_fini(void) { kmem_cache_destroy(zil_zcw_cache); kmem_cache_destroy(zil_lwb_cache); if (zil_ksp != NULL) { kstat_delete(zil_ksp); zil_ksp = NULL; } } void zil_set_sync(zilog_t *zilog, uint64_t sync) { zilog->zl_sync = sync; } void zil_set_logbias(zilog_t *zilog, uint64_t logbias) { zilog->zl_logbias = logbias; } zilog_t * zil_alloc(objset_t *os, zil_header_t *zh_phys) { zilog_t *zilog; zilog = kmem_zalloc(sizeof (zilog_t), KM_SLEEP); zilog->zl_header = zh_phys; zilog->zl_os = os; zilog->zl_spa = dmu_objset_spa(os); zilog->zl_dmu_pool = dmu_objset_pool(os); zilog->zl_destroy_txg = TXG_INITIAL - 1; zilog->zl_logbias = dmu_objset_logbias(os); zilog->zl_sync = dmu_objset_syncprop(os); zilog->zl_dirty_max_txg = 0; zilog->zl_last_lwb_opened = NULL; zilog->zl_last_lwb_latency = 0; zilog->zl_max_block_size = zil_maxblocksize; mutex_init(&zilog->zl_lock, NULL, MUTEX_DEFAULT, NULL); mutex_init(&zilog->zl_issuer_lock, NULL, MUTEX_DEFAULT, NULL); for (int i = 0; i < TXG_SIZE; i++) { mutex_init(&zilog->zl_itxg[i].itxg_lock, NULL, MUTEX_DEFAULT, NULL); } list_create(&zilog->zl_lwb_list, sizeof (lwb_t), offsetof(lwb_t, lwb_node)); list_create(&zilog->zl_itx_commit_list, sizeof (itx_t), offsetof(itx_t, itx_node)); cv_init(&zilog->zl_cv_suspend, NULL, CV_DEFAULT, NULL); return (zilog); } void zil_free(zilog_t *zilog) { int i; zilog->zl_stop_sync = 1; ASSERT0(zilog->zl_suspend); ASSERT0(zilog->zl_suspending); ASSERT(list_is_empty(&zilog->zl_lwb_list)); list_destroy(&zilog->zl_lwb_list); ASSERT(list_is_empty(&zilog->zl_itx_commit_list)); list_destroy(&zilog->zl_itx_commit_list); for (i = 0; i < TXG_SIZE; i++) { /* * It's possible for an itx to be generated that doesn't dirty * a txg (e.g. ztest TX_TRUNCATE). So there's no zil_clean() * callback to remove the entry. We remove those here. * * Also free up the ziltest itxs. */ if (zilog->zl_itxg[i].itxg_itxs) zil_itxg_clean(zilog->zl_itxg[i].itxg_itxs); mutex_destroy(&zilog->zl_itxg[i].itxg_lock); } mutex_destroy(&zilog->zl_issuer_lock); mutex_destroy(&zilog->zl_lock); cv_destroy(&zilog->zl_cv_suspend); kmem_free(zilog, sizeof (zilog_t)); } /* * Open an intent log. */ zilog_t * zil_open(objset_t *os, zil_get_data_t *get_data) { zilog_t *zilog = dmu_objset_zil(os); ASSERT3P(zilog->zl_get_data, ==, NULL); ASSERT3P(zilog->zl_last_lwb_opened, ==, NULL); ASSERT(list_is_empty(&zilog->zl_lwb_list)); zilog->zl_get_data = get_data; return (zilog); } /* * Close an intent log. */ void zil_close(zilog_t *zilog) { lwb_t *lwb; uint64_t txg; if (!dmu_objset_is_snapshot(zilog->zl_os)) { zil_commit(zilog, 0); } else { ASSERT3P(list_tail(&zilog->zl_lwb_list), ==, NULL); ASSERT0(zilog->zl_dirty_max_txg); ASSERT3B(zilog_is_dirty(zilog), ==, B_FALSE); } mutex_enter(&zilog->zl_lock); lwb = list_tail(&zilog->zl_lwb_list); if (lwb == NULL) txg = zilog->zl_dirty_max_txg; else txg = MAX(zilog->zl_dirty_max_txg, lwb->lwb_max_txg); mutex_exit(&zilog->zl_lock); /* * We need to use txg_wait_synced() to wait long enough for the * ZIL to be clean, and to wait for all pending lwbs to be * written out. */ if (txg != 0) txg_wait_synced(zilog->zl_dmu_pool, txg); if (zilog_is_dirty(zilog)) zfs_dbgmsg("zil (%px) is dirty, txg %llu", zilog, (u_longlong_t)txg); if (txg < spa_freeze_txg(zilog->zl_spa)) VERIFY(!zilog_is_dirty(zilog)); zilog->zl_get_data = NULL; /* * We should have only one lwb left on the list; remove it now. */ mutex_enter(&zilog->zl_lock); lwb = list_head(&zilog->zl_lwb_list); if (lwb != NULL) { ASSERT3P(lwb, ==, list_tail(&zilog->zl_lwb_list)); ASSERT3S(lwb->lwb_state, !=, LWB_STATE_ISSUED); if (lwb->lwb_fastwrite) metaslab_fastwrite_unmark(zilog->zl_spa, &lwb->lwb_blk); list_remove(&zilog->zl_lwb_list, lwb); zio_buf_free(lwb->lwb_buf, lwb->lwb_sz); zil_free_lwb(zilog, lwb); } mutex_exit(&zilog->zl_lock); } static char *suspend_tag = "zil suspending"; /* * Suspend an intent log. While in suspended mode, we still honor * synchronous semantics, but we rely on txg_wait_synced() to do it. * On old version pools, we suspend the log briefly when taking a * snapshot so that it will have an empty intent log. * * Long holds are not really intended to be used the way we do here -- * held for such a short time. A concurrent caller of dsl_dataset_long_held() * could fail. Therefore we take pains to only put a long hold if it is * actually necessary. Fortunately, it will only be necessary if the * objset is currently mounted (or the ZVOL equivalent). In that case it * will already have a long hold, so we are not really making things any worse. * * Ideally, we would locate the existing long-holder (i.e. the zfsvfs_t or * zvol_state_t), and use their mechanism to prevent their hold from being * dropped (e.g. VFS_HOLD()). However, that would be even more pain for * very little gain. * * if cookiep == NULL, this does both the suspend & resume. * Otherwise, it returns with the dataset "long held", and the cookie * should be passed into zil_resume(). */ int zil_suspend(const char *osname, void **cookiep) { objset_t *os; zilog_t *zilog; const zil_header_t *zh; int error; error = dmu_objset_hold(osname, suspend_tag, &os); if (error != 0) return (error); zilog = dmu_objset_zil(os); mutex_enter(&zilog->zl_lock); zh = zilog->zl_header; if (zh->zh_flags & ZIL_REPLAY_NEEDED) { /* unplayed log */ mutex_exit(&zilog->zl_lock); dmu_objset_rele(os, suspend_tag); return (SET_ERROR(EBUSY)); } /* * Don't put a long hold in the cases where we can avoid it. This * is when there is no cookie so we are doing a suspend & resume * (i.e. called from zil_vdev_offline()), and there's nothing to do * for the suspend because it's already suspended, or there's no ZIL. */ if (cookiep == NULL && !zilog->zl_suspending && (zilog->zl_suspend > 0 || BP_IS_HOLE(&zh->zh_log))) { mutex_exit(&zilog->zl_lock); dmu_objset_rele(os, suspend_tag); return (0); } dsl_dataset_long_hold(dmu_objset_ds(os), suspend_tag); dsl_pool_rele(dmu_objset_pool(os), suspend_tag); zilog->zl_suspend++; if (zilog->zl_suspend > 1) { /* * Someone else is already suspending it. * Just wait for them to finish. */ while (zilog->zl_suspending) cv_wait(&zilog->zl_cv_suspend, &zilog->zl_lock); mutex_exit(&zilog->zl_lock); if (cookiep == NULL) zil_resume(os); else *cookiep = os; return (0); } /* * If there is no pointer to an on-disk block, this ZIL must not * be active (e.g. filesystem not mounted), so there's nothing * to clean up. */ if (BP_IS_HOLE(&zh->zh_log)) { ASSERT(cookiep != NULL); /* fast path already handled */ *cookiep = os; mutex_exit(&zilog->zl_lock); return (0); } /* * The ZIL has work to do. Ensure that the associated encryption * key will remain mapped while we are committing the log by * grabbing a reference to it. If the key isn't loaded we have no * choice but to return an error until the wrapping key is loaded. */ if (os->os_encrypted && dsl_dataset_create_key_mapping(dmu_objset_ds(os)) != 0) { zilog->zl_suspend--; mutex_exit(&zilog->zl_lock); dsl_dataset_long_rele(dmu_objset_ds(os), suspend_tag); dsl_dataset_rele(dmu_objset_ds(os), suspend_tag); return (SET_ERROR(EACCES)); } zilog->zl_suspending = B_TRUE; mutex_exit(&zilog->zl_lock); /* * We need to use zil_commit_impl to ensure we wait for all * LWB_STATE_OPENED and LWB_STATE_ISSUED lwbs to be committed * to disk before proceeding. If we used zil_commit instead, it * would just call txg_wait_synced(), because zl_suspend is set. * txg_wait_synced() doesn't wait for these lwb's to be * LWB_STATE_FLUSH_DONE before returning. */ zil_commit_impl(zilog, 0); /* * Now that we've ensured all lwb's are LWB_STATE_FLUSH_DONE, we * use txg_wait_synced() to ensure the data from the zilog has * migrated to the main pool before calling zil_destroy(). */ txg_wait_synced(zilog->zl_dmu_pool, 0); zil_destroy(zilog, B_FALSE); mutex_enter(&zilog->zl_lock); zilog->zl_suspending = B_FALSE; cv_broadcast(&zilog->zl_cv_suspend); mutex_exit(&zilog->zl_lock); if (os->os_encrypted) dsl_dataset_remove_key_mapping(dmu_objset_ds(os)); if (cookiep == NULL) zil_resume(os); else *cookiep = os; return (0); } void zil_resume(void *cookie) { objset_t *os = cookie; zilog_t *zilog = dmu_objset_zil(os); mutex_enter(&zilog->zl_lock); ASSERT(zilog->zl_suspend != 0); zilog->zl_suspend--; mutex_exit(&zilog->zl_lock); dsl_dataset_long_rele(dmu_objset_ds(os), suspend_tag); dsl_dataset_rele(dmu_objset_ds(os), suspend_tag); } typedef struct zil_replay_arg { zil_replay_func_t *const *zr_replay; void *zr_arg; boolean_t zr_byteswap; char *zr_lr; } zil_replay_arg_t; static int zil_replay_error(zilog_t *zilog, const lr_t *lr, int error) { char name[ZFS_MAX_DATASET_NAME_LEN]; zilog->zl_replaying_seq--; /* didn't actually replay this one */ dmu_objset_name(zilog->zl_os, name); cmn_err(CE_WARN, "ZFS replay transaction error %d, " "dataset %s, seq 0x%llx, txtype %llu %s\n", error, name, (u_longlong_t)lr->lrc_seq, (u_longlong_t)(lr->lrc_txtype & ~TX_CI), (lr->lrc_txtype & TX_CI) ? "CI" : ""); return (error); } static int zil_replay_log_record(zilog_t *zilog, const lr_t *lr, void *zra, uint64_t claim_txg) { zil_replay_arg_t *zr = zra; const zil_header_t *zh = zilog->zl_header; uint64_t reclen = lr->lrc_reclen; uint64_t txtype = lr->lrc_txtype; int error = 0; zilog->zl_replaying_seq = lr->lrc_seq; if (lr->lrc_seq <= zh->zh_replay_seq) /* already replayed */ return (0); if (lr->lrc_txg < claim_txg) /* already committed */ return (0); /* Strip case-insensitive bit, still present in log record */ txtype &= ~TX_CI; if (txtype == 0 || txtype >= TX_MAX_TYPE) return (zil_replay_error(zilog, lr, EINVAL)); /* * If this record type can be logged out of order, the object * (lr_foid) may no longer exist. That's legitimate, not an error. */ if (TX_OOO(txtype)) { error = dmu_object_info(zilog->zl_os, LR_FOID_GET_OBJ(((lr_ooo_t *)lr)->lr_foid), NULL); if (error == ENOENT || error == EEXIST) return (0); } /* * Make a copy of the data so we can revise and extend it. */ bcopy(lr, zr->zr_lr, reclen); /* * If this is a TX_WRITE with a blkptr, suck in the data. */ if (txtype == TX_WRITE && reclen == sizeof (lr_write_t)) { error = zil_read_log_data(zilog, (lr_write_t *)lr, zr->zr_lr + reclen); if (error != 0) return (zil_replay_error(zilog, lr, error)); } /* * The log block containing this lr may have been byteswapped * so that we can easily examine common fields like lrc_txtype. * However, the log is a mix of different record types, and only the * replay vectors know how to byteswap their records. Therefore, if * the lr was byteswapped, undo it before invoking the replay vector. */ if (zr->zr_byteswap) byteswap_uint64_array(zr->zr_lr, reclen); /* * We must now do two things atomically: replay this log record, * and update the log header sequence number to reflect the fact that * we did so. At the end of each replay function the sequence number * is updated if we are in replay mode. */ error = zr->zr_replay[txtype](zr->zr_arg, zr->zr_lr, zr->zr_byteswap); if (error != 0) { /* * The DMU's dnode layer doesn't see removes until the txg * commits, so a subsequent claim can spuriously fail with * EEXIST. So if we receive any error we try syncing out * any removes then retry the transaction. Note that we * specify B_FALSE for byteswap now, so we don't do it twice. */ txg_wait_synced(spa_get_dsl(zilog->zl_spa), 0); error = zr->zr_replay[txtype](zr->zr_arg, zr->zr_lr, B_FALSE); if (error != 0) return (zil_replay_error(zilog, lr, error)); } return (0); } static int zil_incr_blks(zilog_t *zilog, const blkptr_t *bp, void *arg, uint64_t claim_txg) { (void) bp, (void) arg, (void) claim_txg; zilog->zl_replay_blks++; return (0); } /* * If this dataset has a non-empty intent log, replay it and destroy it. */ void zil_replay(objset_t *os, void *arg, zil_replay_func_t *const replay_func[TX_MAX_TYPE]) { zilog_t *zilog = dmu_objset_zil(os); const zil_header_t *zh = zilog->zl_header; zil_replay_arg_t zr; if ((zh->zh_flags & ZIL_REPLAY_NEEDED) == 0) { zil_destroy(zilog, B_TRUE); return; } zr.zr_replay = replay_func; zr.zr_arg = arg; zr.zr_byteswap = BP_SHOULD_BYTESWAP(&zh->zh_log); zr.zr_lr = vmem_alloc(2 * SPA_MAXBLOCKSIZE, KM_SLEEP); /* * Wait for in-progress removes to sync before starting replay. */ txg_wait_synced(zilog->zl_dmu_pool, 0); zilog->zl_replay = B_TRUE; zilog->zl_replay_time = ddi_get_lbolt(); ASSERT(zilog->zl_replay_blks == 0); (void) zil_parse(zilog, zil_incr_blks, zil_replay_log_record, &zr, zh->zh_claim_txg, B_TRUE); vmem_free(zr.zr_lr, 2 * SPA_MAXBLOCKSIZE); zil_destroy(zilog, B_FALSE); txg_wait_synced(zilog->zl_dmu_pool, zilog->zl_destroy_txg); zilog->zl_replay = B_FALSE; } boolean_t zil_replaying(zilog_t *zilog, dmu_tx_t *tx) { if (zilog->zl_sync == ZFS_SYNC_DISABLED) return (B_TRUE); if (zilog->zl_replay) { dsl_dataset_dirty(dmu_objset_ds(zilog->zl_os), tx); zilog->zl_replayed_seq[dmu_tx_get_txg(tx) & TXG_MASK] = zilog->zl_replaying_seq; return (B_TRUE); } return (B_FALSE); } int zil_reset(const char *osname, void *arg) { (void) arg; int error = zil_suspend(osname, NULL); /* EACCES means crypto key not loaded */ if ((error == EACCES) || (error == EBUSY)) return (SET_ERROR(error)); if (error != 0) return (SET_ERROR(EEXIST)); return (0); } EXPORT_SYMBOL(zil_alloc); EXPORT_SYMBOL(zil_free); EXPORT_SYMBOL(zil_open); EXPORT_SYMBOL(zil_close); EXPORT_SYMBOL(zil_replay); EXPORT_SYMBOL(zil_replaying); EXPORT_SYMBOL(zil_destroy); EXPORT_SYMBOL(zil_destroy_sync); EXPORT_SYMBOL(zil_itx_create); EXPORT_SYMBOL(zil_itx_destroy); EXPORT_SYMBOL(zil_itx_assign); EXPORT_SYMBOL(zil_commit); EXPORT_SYMBOL(zil_claim); EXPORT_SYMBOL(zil_check_log_chain); EXPORT_SYMBOL(zil_sync); EXPORT_SYMBOL(zil_clean); EXPORT_SYMBOL(zil_suspend); EXPORT_SYMBOL(zil_resume); EXPORT_SYMBOL(zil_lwb_add_block); EXPORT_SYMBOL(zil_bp_tree_add); EXPORT_SYMBOL(zil_set_sync); EXPORT_SYMBOL(zil_set_logbias); ZFS_MODULE_PARAM(zfs, zfs_, commit_timeout_pct, INT, ZMOD_RW, "ZIL block open timeout percentage"); ZFS_MODULE_PARAM(zfs_zil, zil_, replay_disable, INT, ZMOD_RW, "Disable intent logging replay"); ZFS_MODULE_PARAM(zfs_zil, zil_, nocacheflush, INT, ZMOD_RW, "Disable ZIL cache flushes"); ZFS_MODULE_PARAM(zfs_zil, zil_, slog_bulk, ULONG, ZMOD_RW, "Limit in bytes slog sync writes per commit"); ZFS_MODULE_PARAM(zfs_zil, zil_, maxblocksize, INT, ZMOD_RW, "Limit in bytes of ZIL log block size"); diff --git a/tests/runfiles/common.run b/tests/runfiles/common.run index a7ddb146e59b..95deef0104f4 100644 --- a/tests/runfiles/common.run +++ b/tests/runfiles/common.run @@ -1,966 +1,966 @@ # # This file and its contents are supplied under the terms of the # Common Development and Distribution License ("CDDL"), version 1.0. # You may only use this file in accordance with the terms of version # 1.0 of the CDDL. # # A full copy of the text of the CDDL should have accompanied this # source. A copy of the CDDL is also available via the Internet at # http://www.illumos.org/license/CDDL. # # This run file contains all of the common functional tests. When # adding a new test consider also adding it to the sanity.run file # if the new test runs to completion in only a few seconds. # # Approximate run time: 4-5 hours # [DEFAULT] pre = setup quiet = False pre_user = root user = root timeout = 600 post_user = root post = cleanup failsafe_user = root failsafe = callbacks/zfs_failsafe outputdir = /var/tmp/test_results tags = ['functional'] [tests/functional/acl/off] tests = ['posixmode'] tags = ['functional', 'acl'] [tests/functional/alloc_class] tests = ['alloc_class_001_pos', 'alloc_class_002_neg', 'alloc_class_003_pos', 'alloc_class_004_pos', 'alloc_class_005_pos', 'alloc_class_006_pos', 'alloc_class_007_pos', 'alloc_class_008_pos', 'alloc_class_009_pos', 'alloc_class_010_pos', 'alloc_class_011_neg', 'alloc_class_012_pos', 'alloc_class_013_pos'] tags = ['functional', 'alloc_class'] [tests/functional/arc] tests = ['dbufstats_001_pos', 'dbufstats_002_pos', 'dbufstats_003_pos', 'arcstats_runtime_tuning'] tags = ['functional', 'arc'] [tests/functional/atime] tests = ['atime_001_pos', 'atime_002_neg', 'root_atime_off', 'root_atime_on'] tags = ['functional', 'atime'] [tests/functional/bootfs] tests = ['bootfs_001_pos', 'bootfs_002_neg', 'bootfs_003_pos', 'bootfs_004_neg', 'bootfs_005_neg', 'bootfs_006_pos', 'bootfs_007_pos', 'bootfs_008_pos'] tags = ['functional', 'bootfs'] [tests/functional/btree] tests = ['btree_positive', 'btree_negative'] tags = ['functional', 'btree'] pre = post = [tests/functional/cache] tests = ['cache_001_pos', 'cache_002_pos', 'cache_003_pos', 'cache_004_neg', 'cache_005_neg', 'cache_006_pos', 'cache_007_neg', 'cache_008_neg', 'cache_009_pos', 'cache_010_pos', 'cache_011_pos', 'cache_012_pos'] tags = ['functional', 'cache'] [tests/functional/cachefile] tests = ['cachefile_001_pos', 'cachefile_002_pos', 'cachefile_003_pos', 'cachefile_004_pos'] tags = ['functional', 'cachefile'] [tests/functional/casenorm] tests = ['case_all_values', 'norm_all_values', 'mixed_create_failure', 'sensitive_none_lookup', 'sensitive_none_delete', 'sensitive_formd_lookup', 'sensitive_formd_delete', 'insensitive_none_lookup', 'insensitive_none_delete', 'insensitive_formd_lookup', 'insensitive_formd_delete', 'mixed_none_lookup', 'mixed_none_lookup_ci', 'mixed_none_delete', 'mixed_formd_lookup', 'mixed_formd_lookup_ci', 'mixed_formd_delete'] tags = ['functional', 'casenorm'] [tests/functional/channel_program/lua_core] tests = ['tst.args_to_lua', 'tst.divide_by_zero', 'tst.exists', 'tst.integer_illegal', 'tst.integer_overflow', 'tst.language_functions_neg', 'tst.language_functions_pos', 'tst.large_prog', 'tst.libraries', 'tst.memory_limit', 'tst.nested_neg', 'tst.nested_pos', 'tst.nvlist_to_lua', 'tst.recursive_neg', 'tst.recursive_pos', 'tst.return_large', 'tst.return_nvlist_neg', 'tst.return_nvlist_pos', 'tst.return_recursive_table', 'tst.stack_gsub', 'tst.timeout'] tags = ['functional', 'channel_program', 'lua_core'] [tests/functional/channel_program/synctask_core] tests = ['tst.destroy_fs', 'tst.destroy_snap', 'tst.get_count_and_limit', 'tst.get_index_props', 'tst.get_mountpoint', 'tst.get_neg', 'tst.get_number_props', 'tst.get_string_props', 'tst.get_type', 'tst.get_userquota', 'tst.get_written', 'tst.inherit', 'tst.list_bookmarks', 'tst.list_children', 'tst.list_clones', 'tst.list_holds', 'tst.list_snapshots', 'tst.list_system_props', 'tst.list_user_props', 'tst.parse_args_neg','tst.promote_conflict', 'tst.promote_multiple', 'tst.promote_simple', 'tst.rollback_mult', 'tst.rollback_one', 'tst.set_props', 'tst.snapshot_destroy', 'tst.snapshot_neg', 'tst.snapshot_recursive', 'tst.snapshot_simple', 'tst.bookmark.create', 'tst.bookmark.copy', 'tst.terminate_by_signal' ] tags = ['functional', 'channel_program', 'synctask_core'] [tests/functional/checksum] tests = ['run_edonr_test', 'run_sha2_test', 'run_skein_test', 'filetest_001_pos', 'filetest_002_pos'] tags = ['functional', 'checksum'] [tests/functional/clean_mirror] tests = [ 'clean_mirror_001_pos', 'clean_mirror_002_pos', 'clean_mirror_003_pos', 'clean_mirror_004_pos'] tags = ['functional', 'clean_mirror'] [tests/functional/cli_root/zdb] tests = ['zdb_002_pos', 'zdb_003_pos', 'zdb_004_pos', 'zdb_005_pos', 'zdb_006_pos', 'zdb_args_neg', 'zdb_args_pos', 'zdb_block_size_histogram', 'zdb_checksum', 'zdb_decompress', 'zdb_display_block', 'zdb_label_checksum', 'zdb_object_range_neg', 'zdb_object_range_pos', 'zdb_objset_id', 'zdb_decompress_zstd', 'zdb_recover', 'zdb_recover_2'] pre = post = tags = ['functional', 'cli_root', 'zdb'] [tests/functional/cli_root/zfs] tests = ['zfs_001_neg', 'zfs_002_pos'] tags = ['functional', 'cli_root', 'zfs'] [tests/functional/cli_root/zfs_bookmark] tests = ['zfs_bookmark_cliargs'] tags = ['functional', 'cli_root', 'zfs_bookmark'] [tests/functional/cli_root/zfs_change-key] tests = ['zfs_change-key', 'zfs_change-key_child', 'zfs_change-key_format', 'zfs_change-key_inherit', 'zfs_change-key_load', 'zfs_change-key_location', 'zfs_change-key_pbkdf2iters', 'zfs_change-key_clones'] tags = ['functional', 'cli_root', 'zfs_change-key'] [tests/functional/cli_root/zfs_clone] tests = ['zfs_clone_001_neg', 'zfs_clone_002_pos', 'zfs_clone_003_pos', 'zfs_clone_004_pos', 'zfs_clone_005_pos', 'zfs_clone_006_pos', 'zfs_clone_007_pos', 'zfs_clone_008_neg', 'zfs_clone_009_neg', 'zfs_clone_010_pos', 'zfs_clone_encrypted', 'zfs_clone_deeply_nested'] tags = ['functional', 'cli_root', 'zfs_clone'] [tests/functional/cli_root/zfs_copies] tests = ['zfs_copies_001_pos', 'zfs_copies_002_pos', 'zfs_copies_003_pos', 'zfs_copies_004_neg', 'zfs_copies_005_neg', 'zfs_copies_006_pos'] tags = ['functional', 'cli_root', 'zfs_copies'] [tests/functional/cli_root/zfs_create] tests = ['zfs_create_001_pos', 'zfs_create_002_pos', 'zfs_create_003_pos', 'zfs_create_004_pos', 'zfs_create_005_pos', 'zfs_create_006_pos', 'zfs_create_007_pos', 'zfs_create_008_neg', 'zfs_create_009_neg', 'zfs_create_010_neg', 'zfs_create_011_pos', 'zfs_create_012_pos', 'zfs_create_013_pos', 'zfs_create_014_pos', 'zfs_create_encrypted', 'zfs_create_crypt_combos', 'zfs_create_dryrun', 'zfs_create_nomount', 'zfs_create_verbose'] tags = ['functional', 'cli_root', 'zfs_create'] [tests/functional/cli_root/zfs_destroy] tests = ['zfs_clone_livelist_condense_and_disable', 'zfs_clone_livelist_condense_races', 'zfs_clone_livelist_dedup', 'zfs_destroy_001_pos', 'zfs_destroy_002_pos', 'zfs_destroy_003_pos', 'zfs_destroy_004_pos', 'zfs_destroy_005_neg', 'zfs_destroy_006_neg', 'zfs_destroy_007_neg', 'zfs_destroy_008_pos', 'zfs_destroy_009_pos', 'zfs_destroy_010_pos', 'zfs_destroy_011_pos', 'zfs_destroy_012_pos', 'zfs_destroy_013_neg', 'zfs_destroy_014_pos', 'zfs_destroy_015_pos', 'zfs_destroy_016_pos', 'zfs_destroy_clone_livelist', 'zfs_destroy_dev_removal', 'zfs_destroy_dev_removal_condense'] tags = ['functional', 'cli_root', 'zfs_destroy'] [tests/functional/cli_root/zfs_diff] tests = ['zfs_diff_changes', 'zfs_diff_cliargs', 'zfs_diff_timestamp', 'zfs_diff_types', 'zfs_diff_encrypted', 'zfs_diff_mangle'] tags = ['functional', 'cli_root', 'zfs_diff'] [tests/functional/cli_root/zfs_get] tests = ['zfs_get_001_pos', 'zfs_get_002_pos', 'zfs_get_003_pos', 'zfs_get_004_pos', 'zfs_get_005_neg', 'zfs_get_006_neg', 'zfs_get_007_neg', 'zfs_get_008_pos', 'zfs_get_009_pos', 'zfs_get_010_neg'] tags = ['functional', 'cli_root', 'zfs_get'] [tests/functional/cli_root/zfs_ids_to_path] tests = ['zfs_ids_to_path_001_pos'] tags = ['functional', 'cli_root', 'zfs_ids_to_path'] [tests/functional/cli_root/zfs_inherit] tests = ['zfs_inherit_001_neg', 'zfs_inherit_002_neg', 'zfs_inherit_003_pos', 'zfs_inherit_mountpoint'] tags = ['functional', 'cli_root', 'zfs_inherit'] [tests/functional/cli_root/zfs_load-key] tests = ['zfs_load-key', 'zfs_load-key_all', 'zfs_load-key_file', 'zfs_load-key_https', 'zfs_load-key_location', 'zfs_load-key_noop', 'zfs_load-key_recursive'] tags = ['functional', 'cli_root', 'zfs_load-key'] [tests/functional/cli_root/zfs_mount] tests = ['zfs_mount_001_pos', 'zfs_mount_002_pos', 'zfs_mount_003_pos', 'zfs_mount_004_pos', 'zfs_mount_005_pos', 'zfs_mount_007_pos', 'zfs_mount_009_neg', 'zfs_mount_010_neg', 'zfs_mount_011_neg', 'zfs_mount_012_pos', 'zfs_mount_all_001_pos', 'zfs_mount_encrypted', 'zfs_mount_remount', 'zfs_mount_all_fail', 'zfs_mount_all_mountpoints', 'zfs_mount_test_race'] tags = ['functional', 'cli_root', 'zfs_mount'] [tests/functional/cli_root/zfs_program] tests = ['zfs_program_json'] tags = ['functional', 'cli_root', 'zfs_program'] [tests/functional/cli_root/zfs_promote] tests = ['zfs_promote_001_pos', 'zfs_promote_002_pos', 'zfs_promote_003_pos', 'zfs_promote_004_pos', 'zfs_promote_005_pos', 'zfs_promote_006_neg', 'zfs_promote_007_neg', 'zfs_promote_008_pos', 'zfs_promote_encryptionroot'] tags = ['functional', 'cli_root', 'zfs_promote'] [tests/functional/cli_root/zfs_property] tests = ['zfs_written_property_001_pos'] tags = ['functional', 'cli_root', 'zfs_property'] [tests/functional/cli_root/zfs_receive] tests = ['zfs_receive_001_pos', 'zfs_receive_002_pos', 'zfs_receive_003_pos', 'zfs_receive_004_neg', 'zfs_receive_005_neg', 'zfs_receive_006_pos', 'zfs_receive_007_neg', 'zfs_receive_008_pos', 'zfs_receive_009_neg', 'zfs_receive_010_pos', 'zfs_receive_011_pos', 'zfs_receive_012_pos', 'zfs_receive_013_pos', 'zfs_receive_014_pos', 'zfs_receive_015_pos', 'zfs_receive_016_pos', 'receive-o-x_props_override', 'receive-o-x_props_aliases', 'zfs_receive_from_encrypted', 'zfs_receive_to_encrypted', 'zfs_receive_raw', 'zfs_receive_raw_incremental', 'zfs_receive_-e', 'zfs_receive_raw_-d', 'zfs_receive_from_zstd', 'zfs_receive_new_props', 'zfs_receive_-wR-encrypted-mix'] tags = ['functional', 'cli_root', 'zfs_receive'] [tests/functional/cli_root/zfs_rename] tests = ['zfs_rename_001_pos', 'zfs_rename_002_pos', 'zfs_rename_003_pos', 'zfs_rename_004_neg', 'zfs_rename_005_neg', 'zfs_rename_006_pos', 'zfs_rename_007_pos', 'zfs_rename_008_pos', 'zfs_rename_009_neg', 'zfs_rename_010_neg', 'zfs_rename_011_pos', 'zfs_rename_012_neg', 'zfs_rename_013_pos', 'zfs_rename_014_neg', 'zfs_rename_encrypted_child', 'zfs_rename_to_encrypted', 'zfs_rename_mountpoint', 'zfs_rename_nounmount'] tags = ['functional', 'cli_root', 'zfs_rename'] [tests/functional/cli_root/zfs_reservation] tests = ['zfs_reservation_001_pos', 'zfs_reservation_002_pos'] tags = ['functional', 'cli_root', 'zfs_reservation'] [tests/functional/cli_root/zfs_rollback] tests = ['zfs_rollback_001_pos', 'zfs_rollback_002_pos', 'zfs_rollback_003_neg', 'zfs_rollback_004_neg'] tags = ['functional', 'cli_root', 'zfs_rollback'] [tests/functional/cli_root/zfs_send] tests = ['zfs_send_001_pos', 'zfs_send_002_pos', 'zfs_send_003_pos', 'zfs_send_004_neg', 'zfs_send_005_pos', 'zfs_send_006_pos', 'zfs_send_007_pos', 'zfs_send_encrypted', 'zfs_send_raw', 'zfs_send_sparse', 'zfs_send-b', 'zfs_send_skip_missing'] tags = ['functional', 'cli_root', 'zfs_send'] [tests/functional/cli_root/zfs_set] tests = ['cache_001_pos', 'cache_002_neg', 'canmount_001_pos', 'canmount_002_pos', 'canmount_003_pos', 'canmount_004_pos', 'checksum_001_pos', 'compression_001_pos', 'mountpoint_001_pos', 'mountpoint_002_pos', 'reservation_001_neg', 'user_property_002_pos', 'share_mount_001_neg', 'snapdir_001_pos', 'onoffs_001_pos', 'user_property_001_pos', 'user_property_003_neg', 'readonly_001_pos', 'user_property_004_pos', 'version_001_neg', 'zfs_set_001_neg', 'zfs_set_002_neg', 'zfs_set_003_neg', 'property_alias_001_pos', 'mountpoint_003_pos', 'ro_props_001_pos', 'zfs_set_keylocation', 'zfs_set_feature_activation'] tags = ['functional', 'cli_root', 'zfs_set'] [tests/functional/cli_root/zfs_share] tests = ['zfs_share_001_pos', 'zfs_share_002_pos', 'zfs_share_003_pos', 'zfs_share_004_pos', 'zfs_share_006_pos', 'zfs_share_008_neg', 'zfs_share_010_neg', 'zfs_share_011_pos', 'zfs_share_concurrent_shares'] tags = ['functional', 'cli_root', 'zfs_share'] [tests/functional/cli_root/zfs_snapshot] tests = ['zfs_snapshot_001_neg', 'zfs_snapshot_002_neg', 'zfs_snapshot_003_neg', 'zfs_snapshot_004_neg', 'zfs_snapshot_005_neg', 'zfs_snapshot_006_pos', 'zfs_snapshot_007_neg', 'zfs_snapshot_008_neg', 'zfs_snapshot_009_pos'] tags = ['functional', 'cli_root', 'zfs_snapshot'] [tests/functional/cli_root/zfs_unload-key] tests = ['zfs_unload-key', 'zfs_unload-key_all', 'zfs_unload-key_recursive'] tags = ['functional', 'cli_root', 'zfs_unload-key'] [tests/functional/cli_root/zfs_unmount] tests = ['zfs_unmount_001_pos', 'zfs_unmount_002_pos', 'zfs_unmount_003_pos', 'zfs_unmount_004_pos', 'zfs_unmount_005_pos', 'zfs_unmount_006_pos', 'zfs_unmount_007_neg', 'zfs_unmount_008_neg', 'zfs_unmount_009_pos', 'zfs_unmount_all_001_pos', 'zfs_unmount_nested', 'zfs_unmount_unload_keys'] tags = ['functional', 'cli_root', 'zfs_unmount'] [tests/functional/cli_root/zfs_unshare] tests = ['zfs_unshare_001_pos', 'zfs_unshare_002_pos', 'zfs_unshare_003_pos', 'zfs_unshare_004_neg', 'zfs_unshare_005_neg', 'zfs_unshare_006_pos', 'zfs_unshare_007_pos'] tags = ['functional', 'cli_root', 'zfs_unshare'] [tests/functional/cli_root/zfs_upgrade] tests = ['zfs_upgrade_001_pos', 'zfs_upgrade_002_pos', 'zfs_upgrade_003_pos', 'zfs_upgrade_004_pos', 'zfs_upgrade_005_pos', 'zfs_upgrade_006_neg', 'zfs_upgrade_007_neg'] tags = ['functional', 'cli_root', 'zfs_upgrade'] [tests/functional/cli_root/zfs_wait] tests = ['zfs_wait_deleteq'] tags = ['functional', 'cli_root', 'zfs_wait'] [tests/functional/cli_root/zhack] tests = ['zhack_label_checksum'] pre = post = tags = ['functional', 'cli_root', 'zhack'] [tests/functional/cli_root/zpool] tests = ['zpool_001_neg', 'zpool_002_pos', 'zpool_003_pos', 'zpool_colors'] tags = ['functional', 'cli_root', 'zpool'] [tests/functional/cli_root/zpool_add] tests = ['zpool_add_001_pos', 'zpool_add_002_pos', 'zpool_add_003_pos', 'zpool_add_004_pos', 'zpool_add_006_pos', 'zpool_add_007_neg', 'zpool_add_008_neg', 'zpool_add_009_neg', 'zpool_add_010_pos', 'add-o_ashift', 'add_prop_ashift', 'zpool_add_dryrun_output'] tags = ['functional', 'cli_root', 'zpool_add'] [tests/functional/cli_root/zpool_attach] tests = ['zpool_attach_001_neg', 'attach-o_ashift'] tags = ['functional', 'cli_root', 'zpool_attach'] [tests/functional/cli_root/zpool_clear] tests = ['zpool_clear_001_pos', 'zpool_clear_002_neg', 'zpool_clear_003_neg', 'zpool_clear_readonly'] tags = ['functional', 'cli_root', 'zpool_clear'] [tests/functional/cli_root/zpool_create] tests = ['zpool_create_001_pos', 'zpool_create_002_pos', 'zpool_create_003_pos', 'zpool_create_004_pos', 'zpool_create_005_pos', 'zpool_create_006_pos', 'zpool_create_007_neg', 'zpool_create_008_pos', 'zpool_create_009_neg', 'zpool_create_010_neg', 'zpool_create_011_neg', 'zpool_create_012_neg', 'zpool_create_014_neg', 'zpool_create_015_neg', 'zpool_create_017_neg', 'zpool_create_018_pos', 'zpool_create_019_pos', 'zpool_create_020_pos', 'zpool_create_021_pos', 'zpool_create_022_pos', 'zpool_create_023_neg', 'zpool_create_024_pos', 'zpool_create_encrypted', 'zpool_create_crypt_combos', 'zpool_create_draid_001_pos', 'zpool_create_draid_002_pos', 'zpool_create_draid_003_pos', 'zpool_create_draid_004_pos', 'zpool_create_features_001_pos', 'zpool_create_features_002_pos', 'zpool_create_features_003_pos', 'zpool_create_features_004_neg', 'zpool_create_features_005_pos', 'zpool_create_features_006_pos', 'zpool_create_features_007_pos', 'zpool_create_features_008_pos', 'zpool_create_features_009_pos', 'create-o_ashift', 'zpool_create_tempname', 'zpool_create_dryrun_output'] tags = ['functional', 'cli_root', 'zpool_create'] [tests/functional/cli_root/zpool_destroy] tests = ['zpool_destroy_001_pos', 'zpool_destroy_002_pos', 'zpool_destroy_003_neg'] pre = post = tags = ['functional', 'cli_root', 'zpool_destroy'] [tests/functional/cli_root/zpool_detach] tests = ['zpool_detach_001_neg'] tags = ['functional', 'cli_root', 'zpool_detach'] [tests/functional/cli_root/zpool_events] tests = ['zpool_events_clear', 'zpool_events_cliargs', 'zpool_events_follow', 'zpool_events_poolname', 'zpool_events_errors', 'zpool_events_duplicates', 'zpool_events_clear_retained'] tags = ['functional', 'cli_root', 'zpool_events'] [tests/functional/cli_root/zpool_export] tests = ['zpool_export_001_pos', 'zpool_export_002_pos', 'zpool_export_003_neg', 'zpool_export_004_pos'] tags = ['functional', 'cli_root', 'zpool_export'] [tests/functional/cli_root/zpool_get] tests = ['zpool_get_001_pos', 'zpool_get_002_pos', 'zpool_get_003_pos', 'zpool_get_004_neg', 'zpool_get_005_pos'] tags = ['functional', 'cli_root', 'zpool_get'] [tests/functional/cli_root/zpool_history] tests = ['zpool_history_001_neg', 'zpool_history_002_pos'] tags = ['functional', 'cli_root', 'zpool_history'] [tests/functional/cli_root/zpool_import] tests = ['zpool_import_001_pos', 'zpool_import_002_pos', 'zpool_import_003_pos', 'zpool_import_004_pos', 'zpool_import_005_pos', 'zpool_import_006_pos', 'zpool_import_007_pos', 'zpool_import_008_pos', 'zpool_import_009_neg', 'zpool_import_010_pos', 'zpool_import_011_neg', 'zpool_import_012_pos', 'zpool_import_013_neg', 'zpool_import_014_pos', 'zpool_import_015_pos', 'zpool_import_016_pos', 'zpool_import_017_pos', 'zpool_import_features_001_pos', 'zpool_import_features_002_neg', 'zpool_import_features_003_pos', 'zpool_import_missing_001_pos', 'zpool_import_missing_002_pos', 'zpool_import_missing_003_pos', 'zpool_import_rename_001_pos', 'zpool_import_all_001_pos', 'zpool_import_encrypted', 'zpool_import_encrypted_load', 'zpool_import_errata3', 'zpool_import_errata4', 'import_cachefile_device_added', 'import_cachefile_device_removed', 'import_cachefile_device_replaced', 'import_cachefile_mirror_attached', 'import_cachefile_mirror_detached', 'import_cachefile_paths_changed', 'import_cachefile_shared_device', 'import_devices_missing', 'import_paths_changed', 'import_rewind_config_changed', 'import_rewind_device_replaced'] tags = ['functional', 'cli_root', 'zpool_import'] timeout = 1200 [tests/functional/cli_root/zpool_labelclear] tests = ['zpool_labelclear_active', 'zpool_labelclear_exported', 'zpool_labelclear_removed', 'zpool_labelclear_valid'] pre = post = tags = ['functional', 'cli_root', 'zpool_labelclear'] [tests/functional/cli_root/zpool_initialize] tests = ['zpool_initialize_attach_detach_add_remove', 'zpool_initialize_fault_export_import_online', 'zpool_initialize_import_export', 'zpool_initialize_offline_export_import_online', 'zpool_initialize_online_offline', 'zpool_initialize_split', 'zpool_initialize_start_and_cancel_neg', 'zpool_initialize_start_and_cancel_pos', 'zpool_initialize_suspend_resume', 'zpool_initialize_unsupported_vdevs', 'zpool_initialize_verify_checksums', 'zpool_initialize_verify_initialized'] pre = tags = ['functional', 'cli_root', 'zpool_initialize'] [tests/functional/cli_root/zpool_offline] tests = ['zpool_offline_001_pos', 'zpool_offline_002_neg', 'zpool_offline_003_pos'] tags = ['functional', 'cli_root', 'zpool_offline'] [tests/functional/cli_root/zpool_online] tests = ['zpool_online_001_pos', 'zpool_online_002_neg'] tags = ['functional', 'cli_root', 'zpool_online'] [tests/functional/cli_root/zpool_remove] tests = ['zpool_remove_001_neg', 'zpool_remove_002_pos', 'zpool_remove_003_pos'] tags = ['functional', 'cli_root', 'zpool_remove'] [tests/functional/cli_root/zpool_replace] tests = ['zpool_replace_001_neg', 'replace-o_ashift', 'replace_prop_ashift'] tags = ['functional', 'cli_root', 'zpool_replace'] [tests/functional/cli_root/zpool_resilver] tests = ['zpool_resilver_bad_args', 'zpool_resilver_restart'] tags = ['functional', 'cli_root', 'zpool_resilver'] [tests/functional/cli_root/zpool_scrub] tests = ['zpool_scrub_001_neg', 'zpool_scrub_002_pos', 'zpool_scrub_003_pos', 'zpool_scrub_004_pos', 'zpool_scrub_005_pos', 'zpool_scrub_encrypted_unloaded', 'zpool_scrub_print_repairing', 'zpool_scrub_offline_device', 'zpool_scrub_multiple_copies'] tags = ['functional', 'cli_root', 'zpool_scrub'] [tests/functional/cli_root/zpool_set] tests = ['zpool_set_001_pos', 'zpool_set_002_neg', 'zpool_set_003_neg', 'zpool_set_ashift', 'zpool_set_features'] tags = ['functional', 'cli_root', 'zpool_set'] [tests/functional/cli_root/zpool_split] tests = ['zpool_split_cliargs', 'zpool_split_devices', 'zpool_split_encryption', 'zpool_split_props', 'zpool_split_vdevs', 'zpool_split_resilver', 'zpool_split_indirect', 'zpool_split_dryrun_output'] tags = ['functional', 'cli_root', 'zpool_split'] [tests/functional/cli_root/zpool_status] tests = ['zpool_status_001_pos', 'zpool_status_002_pos', 'zpool_status_features_001_pos'] tags = ['functional', 'cli_root', 'zpool_status'] [tests/functional/cli_root/zpool_sync] tests = ['zpool_sync_001_pos', 'zpool_sync_002_neg'] tags = ['functional', 'cli_root', 'zpool_sync'] [tests/functional/cli_root/zpool_trim] tests = ['zpool_trim_attach_detach_add_remove', 'zpool_trim_fault_export_import_online', 'zpool_trim_import_export', 'zpool_trim_multiple', 'zpool_trim_neg', 'zpool_trim_offline_export_import_online', 'zpool_trim_online_offline', 'zpool_trim_partial', 'zpool_trim_rate', 'zpool_trim_rate_neg', 'zpool_trim_secure', 'zpool_trim_split', 'zpool_trim_start_and_cancel_neg', 'zpool_trim_start_and_cancel_pos', 'zpool_trim_suspend_resume', 'zpool_trim_unsupported_vdevs', 'zpool_trim_verify_checksums', 'zpool_trim_verify_trimmed'] tags = ['functional', 'zpool_trim'] [tests/functional/cli_root/zpool_upgrade] tests = ['zpool_upgrade_001_pos', 'zpool_upgrade_002_pos', 'zpool_upgrade_003_pos', 'zpool_upgrade_004_pos', 'zpool_upgrade_005_neg', 'zpool_upgrade_006_neg', 'zpool_upgrade_007_pos', 'zpool_upgrade_008_pos', 'zpool_upgrade_009_neg', 'zpool_upgrade_features_001_pos'] tags = ['functional', 'cli_root', 'zpool_upgrade'] [tests/functional/cli_root/zpool_wait] tests = ['zpool_wait_discard', 'zpool_wait_freeing', 'zpool_wait_initialize_basic', 'zpool_wait_initialize_cancel', 'zpool_wait_initialize_flag', 'zpool_wait_multiple', 'zpool_wait_no_activity', 'zpool_wait_remove', 'zpool_wait_remove_cancel', 'zpool_wait_trim_basic', 'zpool_wait_trim_cancel', 'zpool_wait_trim_flag', 'zpool_wait_usage'] tags = ['functional', 'cli_root', 'zpool_wait'] [tests/functional/cli_root/zpool_wait/scan] tests = ['zpool_wait_replace_cancel', 'zpool_wait_rebuild', 'zpool_wait_resilver', 'zpool_wait_scrub_cancel', 'zpool_wait_replace', 'zpool_wait_scrub_basic', 'zpool_wait_scrub_flag'] tags = ['functional', 'cli_root', 'zpool_wait'] [tests/functional/cli_user/misc] tests = ['zdb_001_neg', 'zfs_001_neg', 'zfs_allow_001_neg', 'zfs_clone_001_neg', 'zfs_create_001_neg', 'zfs_destroy_001_neg', 'zfs_get_001_neg', 'zfs_inherit_001_neg', 'zfs_mount_001_neg', 'zfs_promote_001_neg', 'zfs_receive_001_neg', 'zfs_rename_001_neg', 'zfs_rollback_001_neg', 'zfs_send_001_neg', 'zfs_set_001_neg', 'zfs_share_001_neg', 'zfs_snapshot_001_neg', 'zfs_unallow_001_neg', 'zfs_unmount_001_neg', 'zfs_unshare_001_neg', 'zfs_upgrade_001_neg', 'zpool_001_neg', 'zpool_add_001_neg', 'zpool_attach_001_neg', 'zpool_clear_001_neg', 'zpool_create_001_neg', 'zpool_destroy_001_neg', 'zpool_detach_001_neg', 'zpool_export_001_neg', 'zpool_get_001_neg', 'zpool_history_001_neg', 'zpool_import_001_neg', 'zpool_import_002_neg', 'zpool_offline_001_neg', 'zpool_online_001_neg', 'zpool_remove_001_neg', 'zpool_replace_001_neg', 'zpool_scrub_001_neg', 'zpool_set_001_neg', 'zpool_status_001_neg', 'zpool_upgrade_001_neg', 'arcstat_001_pos', 'arc_summary_001_pos', 'arc_summary_002_neg', 'zpool_wait_privilege'] user = tags = ['functional', 'cli_user', 'misc'] [tests/functional/cli_user/zfs_list] tests = ['zfs_list_001_pos', 'zfs_list_002_pos', 'zfs_list_003_pos', 'zfs_list_004_neg', 'zfs_list_007_pos', 'zfs_list_008_neg'] user = tags = ['functional', 'cli_user', 'zfs_list'] [tests/functional/cli_user/zpool_iostat] tests = ['zpool_iostat_001_neg', 'zpool_iostat_002_pos', 'zpool_iostat_003_neg', 'zpool_iostat_004_pos', 'zpool_iostat_005_pos', 'zpool_iostat_-c_disable', 'zpool_iostat_-c_homedir', 'zpool_iostat_-c_searchpath'] user = tags = ['functional', 'cli_user', 'zpool_iostat'] [tests/functional/cli_user/zpool_list] tests = ['zpool_list_001_pos', 'zpool_list_002_neg'] user = tags = ['functional', 'cli_user', 'zpool_list'] [tests/functional/cli_user/zpool_status] tests = ['zpool_status_003_pos', 'zpool_status_-c_disable', 'zpool_status_-c_homedir', 'zpool_status_-c_searchpath'] user = tags = ['functional', 'cli_user', 'zpool_status'] [tests/functional/compression] tests = ['compress_001_pos', 'compress_002_pos', 'compress_003_pos', 'l2arc_compressed_arc', 'l2arc_compressed_arc_disabled', 'l2arc_encrypted', 'l2arc_encrypted_no_compressed_arc'] tags = ['functional', 'compression'] [tests/functional/cp_files] tests = ['cp_files_001_pos'] tags = ['functional', 'cp_files'] [tests/functional/crtime] tests = ['crtime_001_pos' ] tags = ['functional', 'crtime'] [tests/functional/ctime] tests = ['ctime_001_pos' ] tags = ['functional', 'ctime'] [tests/functional/deadman] tests = ['deadman_ratelimit', 'deadman_sync', 'deadman_zio'] pre = post = tags = ['functional', 'deadman'] [tests/functional/delegate] tests = ['zfs_allow_001_pos', 'zfs_allow_002_pos', 'zfs_allow_003_pos', 'zfs_allow_004_pos', 'zfs_allow_005_pos', 'zfs_allow_006_pos', 'zfs_allow_007_pos', 'zfs_allow_008_pos', 'zfs_allow_009_neg', 'zfs_allow_010_pos', 'zfs_allow_011_neg', 'zfs_allow_012_neg', 'zfs_unallow_001_pos', 'zfs_unallow_002_pos', 'zfs_unallow_003_pos', 'zfs_unallow_004_pos', 'zfs_unallow_005_pos', 'zfs_unallow_006_pos', 'zfs_unallow_007_neg', 'zfs_unallow_008_neg'] tags = ['functional', 'delegate'] [tests/functional/exec] tests = ['exec_001_pos', 'exec_002_neg'] tags = ['functional', 'exec'] [tests/functional/fallocate] tests = ['fallocate_punch-hole'] tags = ['functional', 'fallocate'] [tests/functional/features/async_destroy] tests = ['async_destroy_001_pos'] tags = ['functional', 'features', 'async_destroy'] [tests/functional/features/large_dnode] tests = ['large_dnode_001_pos', 'large_dnode_003_pos', 'large_dnode_004_neg', 'large_dnode_005_pos', 'large_dnode_007_neg', 'large_dnode_009_pos'] tags = ['functional', 'features', 'large_dnode'] [tests/functional/grow] pre = post = tests = ['grow_pool_001_pos', 'grow_replicas_001_pos'] tags = ['functional', 'grow'] [tests/functional/history] tests = ['history_001_pos', 'history_002_pos', 'history_003_pos', 'history_004_pos', 'history_005_neg', 'history_006_neg', 'history_007_pos', 'history_008_pos', 'history_009_pos', 'history_010_pos'] tags = ['functional', 'history'] [tests/functional/hkdf] tests = ['run_hkdf_test'] tags = ['functional', 'hkdf'] [tests/functional/inheritance] tests = ['inherit_001_pos'] pre = tags = ['functional', 'inheritance'] [tests/functional/io] tests = ['sync', 'psync', 'posixaio', 'mmap'] tags = ['functional', 'io'] [tests/functional/inuse] tests = ['inuse_004_pos', 'inuse_005_pos', 'inuse_008_pos', 'inuse_009_pos'] post = tags = ['functional', 'inuse'] [tests/functional/large_files] tests = ['large_files_001_pos', 'large_files_002_pos'] tags = ['functional', 'large_files'] [tests/functional/largest_pool] tests = ['largest_pool_001_pos'] pre = post = tags = ['functional', 'largest_pool'] [tests/functional/limits] tests = ['filesystem_count', 'filesystem_limit', 'snapshot_count', 'snapshot_limit'] tags = ['functional', 'limits'] [tests/functional/link_count] tests = ['link_count_001', 'link_count_root_inode'] tags = ['functional', 'link_count'] [tests/functional/migration] tests = ['migration_001_pos', 'migration_002_pos', 'migration_003_pos', 'migration_004_pos', 'migration_005_pos', 'migration_006_pos', 'migration_007_pos', 'migration_008_pos', 'migration_009_pos', 'migration_010_pos', 'migration_011_pos', 'migration_012_pos'] tags = ['functional', 'migration'] [tests/functional/mmap] tests = ['mmap_write_001_pos', 'mmap_read_001_pos', 'mmap_seek_001_pos'] tags = ['functional', 'mmap'] [tests/functional/mount] tests = ['umount_001', 'umountall_001'] tags = ['functional', 'mount'] [tests/functional/mv_files] tests = ['mv_files_001_pos', 'mv_files_002_pos', 'random_creation'] tags = ['functional', 'mv_files'] [tests/functional/nestedfs] tests = ['nestedfs_001_pos'] tags = ['functional', 'nestedfs'] [tests/functional/no_space] tests = ['enospc_001_pos', 'enospc_002_pos', 'enospc_003_pos', 'enospc_df'] tags = ['functional', 'no_space'] [tests/functional/nopwrite] tests = ['nopwrite_copies', 'nopwrite_mtime', 'nopwrite_negative', 'nopwrite_promoted_clone', 'nopwrite_recsize', 'nopwrite_sync', 'nopwrite_varying_compression', 'nopwrite_volume'] tags = ['functional', 'nopwrite'] [tests/functional/online_offline] tests = ['online_offline_001_pos', 'online_offline_002_neg', 'online_offline_003_neg'] tags = ['functional', 'online_offline'] [tests/functional/pool_checkpoint] tests = ['checkpoint_after_rewind', 'checkpoint_big_rewind', 'checkpoint_capacity', 'checkpoint_conf_change', 'checkpoint_discard', 'checkpoint_discard_busy', 'checkpoint_discard_many', 'checkpoint_indirect', 'checkpoint_invalid', 'checkpoint_lun_expsz', 'checkpoint_open', 'checkpoint_removal', 'checkpoint_rewind', 'checkpoint_ro_rewind', 'checkpoint_sm_scale', 'checkpoint_twice', 'checkpoint_vdev_add', 'checkpoint_zdb', 'checkpoint_zhack_feat'] tags = ['functional', 'pool_checkpoint'] timeout = 1800 [tests/functional/pool_names] tests = ['pool_names_001_pos', 'pool_names_002_neg'] pre = post = tags = ['functional', 'pool_names'] [tests/functional/poolversion] tests = ['poolversion_001_pos', 'poolversion_002_pos'] tags = ['functional', 'poolversion'] [tests/functional/pyzfs] tests = ['pyzfs_unittest'] pre = post = tags = ['functional', 'pyzfs'] [tests/functional/quota] tests = ['quota_001_pos', 'quota_002_pos', 'quota_003_pos', 'quota_004_pos', 'quota_005_pos', 'quota_006_neg'] tags = ['functional', 'quota'] [tests/functional/redacted_send] tests = ['redacted_compressed', 'redacted_contents', 'redacted_deleted', 'redacted_disabled_feature', 'redacted_embedded', 'redacted_holes', 'redacted_incrementals', 'redacted_largeblocks', 'redacted_many_clones', 'redacted_mixed_recsize', 'redacted_mounts', 'redacted_negative', 'redacted_origin', 'redacted_panic', 'redacted_props', 'redacted_resume', 'redacted_size', 'redacted_volume'] tags = ['functional', 'redacted_send'] [tests/functional/raidz] tests = ['raidz_001_neg', 'raidz_002_pos', 'raidz_003_pos', 'raidz_004_pos'] tags = ['functional', 'raidz'] [tests/functional/redundancy] tests = ['redundancy_draid', 'redundancy_draid1', 'redundancy_draid2', 'redundancy_draid3', 'redundancy_draid_damaged', 'redundancy_draid_spare1', 'redundancy_draid_spare2', 'redundancy_draid_spare3', 'redundancy_mirror', 'redundancy_raidz', 'redundancy_raidz1', 'redundancy_raidz2', 'redundancy_raidz3', 'redundancy_stripe'] tags = ['functional', 'redundancy'] timeout = 1200 [tests/functional/refquota] tests = ['refquota_001_pos', 'refquota_002_pos', 'refquota_003_pos', 'refquota_004_pos', 'refquota_005_pos', 'refquota_006_neg', 'refquota_007_neg', 'refquota_008_neg'] tags = ['functional', 'refquota'] [tests/functional/refreserv] tests = ['refreserv_001_pos', 'refreserv_002_pos', 'refreserv_003_pos', 'refreserv_004_pos', 'refreserv_005_pos', 'refreserv_multi_raidz', 'refreserv_raidz'] tags = ['functional', 'refreserv'] [tests/functional/removal] pre = tests = ['removal_all_vdev', 'removal_cancel', 'removal_check_space', 'removal_condense_export', 'removal_multiple_indirection', 'removal_nopwrite', 'removal_remap_deadlists', 'removal_resume_export', 'removal_sanity', 'removal_with_add', 'removal_with_create_fs', 'removal_with_dedup', 'removal_with_errors', 'removal_with_export', 'removal_with_ganging', 'removal_with_faulted', 'removal_with_remove', 'removal_with_scrub', 'removal_with_send', 'removal_with_send_recv', 'removal_with_snapshot', 'removal_with_write', 'removal_with_zdb', 'remove_expanded', 'remove_mirror', 'remove_mirror_sanity', 'remove_raidz', 'remove_indirect', 'remove_attach_mirror'] tags = ['functional', 'removal'] [tests/functional/rename_dirs] tests = ['rename_dirs_001_pos'] tags = ['functional', 'rename_dirs'] [tests/functional/replacement] tests = ['attach_import', 'attach_multiple', 'attach_rebuild', 'attach_resilver', 'detach', 'rebuild_disabled_feature', 'rebuild_multiple', 'rebuild_raidz', 'replace_import', 'replace_rebuild', 'replace_resilver', 'resilver_restart_001', 'resilver_restart_002', 'scrub_cancel'] tags = ['functional', 'replacement'] [tests/functional/reservation] tests = ['reservation_001_pos', 'reservation_002_pos', 'reservation_003_pos', 'reservation_004_pos', 'reservation_005_pos', 'reservation_006_pos', 'reservation_007_pos', 'reservation_008_pos', 'reservation_009_pos', 'reservation_010_pos', 'reservation_011_pos', 'reservation_012_pos', 'reservation_013_pos', 'reservation_014_pos', 'reservation_015_pos', 'reservation_016_pos', 'reservation_017_pos', 'reservation_018_pos', 'reservation_019_pos', 'reservation_020_pos', 'reservation_021_neg', 'reservation_022_pos'] tags = ['functional', 'reservation'] [tests/functional/rootpool] tests = ['rootpool_002_neg', 'rootpool_003_neg', 'rootpool_007_pos'] tags = ['functional', 'rootpool'] [tests/functional/rsend] tests = ['recv_dedup', 'recv_dedup_encrypted_zvol', 'rsend_001_pos', 'rsend_002_pos', 'rsend_003_pos', 'rsend_004_pos', 'rsend_005_pos', 'rsend_006_pos', 'rsend_007_pos', 'rsend_008_pos', 'rsend_009_pos', 'rsend_010_pos', 'rsend_011_pos', 'rsend_012_pos', 'rsend_013_pos', 'rsend_014_pos', 'rsend_016_neg', 'rsend_019_pos', 'rsend_020_pos', 'rsend_021_pos', 'rsend_022_pos', 'rsend_024_pos', 'send-c_verify_ratio', 'send-c_verify_contents', 'send-c_props', 'send-c_incremental', 'send-c_volume', 'send-c_zstreamdump', 'send-c_lz4_disabled', 'send-c_recv_lz4_disabled', 'send-c_mixed_compression', 'send-c_stream_size_estimate', 'send-c_embedded_blocks', 'send-c_resume', 'send-cpL_varied_recsize', 'send-c_recv_dedup', 'send-L_toggle', 'send_encrypted_hierarchy', 'send_encrypted_props', 'send_encrypted_truncated_files', 'send_freeobjects', 'send_realloc_files', 'send_realloc_encrypted_files', 'send_spill_block', 'send_holds', 'send_hole_birth', 'send_mixed_raw', 'send-wR_encrypted_zvol', 'send_partial_dataset', 'send_invalid', 'send_doall', 'send_raw_spill_block', 'send_raw_ashift'] tags = ['functional', 'rsend'] [tests/functional/scrub_mirror] tests = ['scrub_mirror_001_pos', 'scrub_mirror_002_pos', 'scrub_mirror_003_pos', 'scrub_mirror_004_pos'] tags = ['functional', 'scrub_mirror'] [tests/functional/slog] tests = ['slog_001_pos', 'slog_002_pos', 'slog_003_pos', 'slog_004_pos', 'slog_005_pos', 'slog_006_pos', 'slog_007_pos', 'slog_008_neg', 'slog_009_neg', 'slog_010_neg', 'slog_011_neg', 'slog_012_neg', 'slog_013_pos', 'slog_014_pos', 'slog_015_neg', 'slog_replay_fs_001', - 'slog_replay_fs_002', 'slog_replay_volume'] + 'slog_replay_fs_002', 'slog_replay_volume', 'slog_016_pos'] tags = ['functional', 'slog'] [tests/functional/snapshot] tests = ['clone_001_pos', 'rollback_001_pos', 'rollback_002_pos', 'rollback_003_pos', 'snapshot_001_pos', 'snapshot_002_pos', 'snapshot_003_pos', 'snapshot_004_pos', 'snapshot_005_pos', 'snapshot_006_pos', 'snapshot_007_pos', 'snapshot_008_pos', 'snapshot_009_pos', 'snapshot_010_pos', 'snapshot_011_pos', 'snapshot_012_pos', 'snapshot_013_pos', 'snapshot_014_pos', 'snapshot_017_pos'] tags = ['functional', 'snapshot'] [tests/functional/snapused] tests = ['snapused_001_pos', 'snapused_002_pos', 'snapused_003_pos', 'snapused_004_pos', 'snapused_005_pos'] tags = ['functional', 'snapused'] [tests/functional/sparse] tests = ['sparse_001_pos'] tags = ['functional', 'sparse'] [tests/functional/stat] tests = ['stat_001_pos'] tags = ['functional', 'stat'] [tests/functional/suid] tests = ['suid_write_to_suid', 'suid_write_to_sgid', 'suid_write_to_suid_sgid', 'suid_write_to_none', 'suid_write_zil_replay'] tags = ['functional', 'suid'] [tests/functional/threadsappend] tests = ['threadsappend_001_pos'] tags = ['functional', 'threadsappend'] [tests/functional/trim] tests = ['autotrim_integrity', 'autotrim_config', 'autotrim_trim_integrity', 'trim_integrity', 'trim_config', 'trim_l2arc'] tags = ['functional', 'trim'] [tests/functional/truncate] tests = ['truncate_001_pos', 'truncate_002_pos', 'truncate_timestamps'] tags = ['functional', 'truncate'] [tests/functional/upgrade] tests = ['upgrade_userobj_001_pos', 'upgrade_readonly_pool'] tags = ['functional', 'upgrade'] [tests/functional/userquota] tests = [ 'userquota_001_pos', 'userquota_002_pos', 'userquota_003_pos', 'userquota_004_pos', 'userquota_005_neg', 'userquota_006_pos', 'userquota_007_pos', 'userquota_008_pos', 'userquota_009_pos', 'userquota_010_pos', 'userquota_011_pos', 'userquota_012_neg', 'userspace_001_pos', 'userspace_002_pos', 'userspace_encrypted', 'userspace_send_encrypted'] tags = ['functional', 'userquota'] [tests/functional/vdev_zaps] tests = ['vdev_zaps_001_pos', 'vdev_zaps_002_pos', 'vdev_zaps_003_pos', 'vdev_zaps_004_pos', 'vdev_zaps_005_pos', 'vdev_zaps_006_pos', 'vdev_zaps_007_pos'] tags = ['functional', 'vdev_zaps'] [tests/functional/write_dirs] tests = ['write_dirs_001_pos', 'write_dirs_002_pos'] tags = ['functional', 'write_dirs'] [tests/functional/xattr] tests = ['xattr_001_pos', 'xattr_002_neg', 'xattr_003_neg', 'xattr_004_pos', 'xattr_005_pos', 'xattr_006_pos', 'xattr_007_neg', 'xattr_011_pos', 'xattr_012_pos', 'xattr_013_pos', 'xattr_compat'] tags = ['functional', 'xattr'] [tests/functional/zvol/zvol_ENOSPC] tests = ['zvol_ENOSPC_001_pos'] tags = ['functional', 'zvol', 'zvol_ENOSPC'] [tests/functional/zvol/zvol_cli] tests = ['zvol_cli_001_pos', 'zvol_cli_002_pos', 'zvol_cli_003_neg'] tags = ['functional', 'zvol', 'zvol_cli'] [tests/functional/zvol/zvol_misc] tests = ['zvol_misc_002_pos', 'zvol_misc_hierarchy', 'zvol_misc_rename_inuse', 'zvol_misc_snapdev', 'zvol_misc_volmode', 'zvol_misc_zil'] tags = ['functional', 'zvol', 'zvol_misc'] [tests/functional/zvol/zvol_swap] tests = ['zvol_swap_001_pos', 'zvol_swap_002_pos', 'zvol_swap_004_pos'] tags = ['functional', 'zvol', 'zvol_swap'] [tests/functional/libzfs] tests = ['many_fds', 'libzfs_input'] tags = ['functional', 'libzfs'] [tests/functional/log_spacemap] tests = ['log_spacemap_import_logs'] pre = post = tags = ['functional', 'log_spacemap'] [tests/functional/l2arc] tests = ['l2arc_arcstats_pos', 'l2arc_mfuonly_pos', 'l2arc_l2miss_pos', 'persist_l2arc_001_pos', 'persist_l2arc_002_pos', 'persist_l2arc_003_neg', 'persist_l2arc_004_pos', 'persist_l2arc_005_pos'] tags = ['functional', 'l2arc'] [tests/functional/zpool_influxdb] tests = ['zpool_influxdb'] tags = ['functional', 'zpool_influxdb'] diff --git a/tests/zfs-tests/include/tunables.cfg b/tests/zfs-tests/include/tunables.cfg index eea2af2edcf0..d3838cb7c8ed 100644 --- a/tests/zfs-tests/include/tunables.cfg +++ b/tests/zfs-tests/include/tunables.cfg @@ -1,97 +1,98 @@ # This file exports variables for each tunable used in the test suite. # # Different platforms use different names for most tunables. To avoid littering # the tests with conditional logic for deciding how to set each tunable, the # logic is instead consolidated to this one file. # # Any use of tunables in tests must use a name defined here. New entries # should be added to the table as needed. Please keep the table sorted # alphabetically for ease of maintenance. # # Platform-specific tunables should still use a NAME from this table for # consistency. Enter UNSUPPORTED in the column for platforms on which the # tunable is not implemented. UNAME=$(uname) # NAME FreeBSD tunable Linux tunable cat <<%%%% | ADMIN_SNAPSHOT UNSUPPORTED zfs_admin_snapshot ALLOW_REDACTED_DATASET_MOUNT allow_redacted_dataset_mount zfs_allow_redacted_dataset_mount ARC_MAX arc.max zfs_arc_max ARC_MIN arc.min zfs_arc_min ASYNC_BLOCK_MAX_BLOCKS async_block_max_blocks zfs_async_block_max_blocks CHECKSUM_EVENTS_PER_SECOND checksum_events_per_second zfs_checksum_events_per_second COMMIT_TIMEOUT_PCT commit_timeout_pct zfs_commit_timeout_pct COMPRESSED_ARC_ENABLED compressed_arc_enabled zfs_compressed_arc_enabled CONDENSE_INDIRECT_COMMIT_ENTRY_DELAY_MS condense.indirect_commit_entry_delay_ms zfs_condense_indirect_commit_entry_delay_ms CONDENSE_INDIRECT_OBSOLETE_PCT condense.indirect_obsolete_pct zfs_condense_indirect_obsolete_pct CONDENSE_MIN_MAPPING_BYTES condense.min_mapping_bytes zfs_condense_min_mapping_bytes DBUF_CACHE_SHIFT dbuf.cache_shift dbuf_cache_shift DEADMAN_CHECKTIME_MS deadman.checktime_ms zfs_deadman_checktime_ms DEADMAN_FAILMODE deadman.failmode zfs_deadman_failmode DEADMAN_SYNCTIME_MS deadman.synctime_ms zfs_deadman_synctime_ms DEADMAN_ZIOTIME_MS deadman.ziotime_ms zfs_deadman_ziotime_ms DISABLE_IVSET_GUID_CHECK disable_ivset_guid_check zfs_disable_ivset_guid_check DMU_OFFSET_NEXT_SYNC dmu_offset_next_sync zfs_dmu_offset_next_sync INITIALIZE_CHUNK_SIZE initialize_chunk_size zfs_initialize_chunk_size INITIALIZE_VALUE initialize_value zfs_initialize_value KEEP_LOG_SPACEMAPS_AT_EXPORT keep_log_spacemaps_at_export zfs_keep_log_spacemaps_at_export LUA_MAX_MEMLIMIT lua.max_memlimit zfs_lua_max_memlimit L2ARC_MFUONLY l2arc.mfuonly l2arc_mfuonly L2ARC_NOPREFETCH l2arc.noprefetch l2arc_noprefetch L2ARC_REBUILD_BLOCKS_MIN_L2SIZE l2arc.rebuild_blocks_min_l2size l2arc_rebuild_blocks_min_l2size L2ARC_REBUILD_ENABLED l2arc.rebuild_enabled l2arc_rebuild_enabled L2ARC_TRIM_AHEAD l2arc.trim_ahead l2arc_trim_ahead L2ARC_WRITE_BOOST l2arc.write_boost l2arc_write_boost L2ARC_WRITE_MAX l2arc.write_max l2arc_write_max LIVELIST_CONDENSE_NEW_ALLOC livelist.condense.new_alloc zfs_livelist_condense_new_alloc LIVELIST_CONDENSE_SYNC_CANCEL livelist.condense.sync_cancel zfs_livelist_condense_sync_cancel LIVELIST_CONDENSE_SYNC_PAUSE livelist.condense.sync_pause zfs_livelist_condense_sync_pause LIVELIST_CONDENSE_ZTHR_CANCEL livelist.condense.zthr_cancel zfs_livelist_condense_zthr_cancel LIVELIST_CONDENSE_ZTHR_PAUSE livelist.condense.zthr_pause zfs_livelist_condense_zthr_pause LIVELIST_MAX_ENTRIES livelist.max_entries zfs_livelist_max_entries LIVELIST_MIN_PERCENT_SHARED livelist.min_percent_shared zfs_livelist_min_percent_shared MAX_DATASET_NESTING max_dataset_nesting zfs_max_dataset_nesting MAX_MISSING_TVDS max_missing_tvds zfs_max_missing_tvds METASLAB_DEBUG_LOAD metaslab.debug_load metaslab_debug_load METASLAB_FORCE_GANGING metaslab.force_ganging metaslab_force_ganging MULTIHOST_FAIL_INTERVALS multihost.fail_intervals zfs_multihost_fail_intervals MULTIHOST_HISTORY multihost.history zfs_multihost_history MULTIHOST_IMPORT_INTERVALS multihost.import_intervals zfs_multihost_import_intervals MULTIHOST_INTERVAL multihost.interval zfs_multihost_interval OVERRIDE_ESTIMATE_RECORDSIZE send.override_estimate_recordsize zfs_override_estimate_recordsize PREFETCH_DISABLE prefetch.disable zfs_prefetch_disable REBUILD_SCRUB_ENABLED rebuild_scrub_enabled zfs_rebuild_scrub_enabled REMOVAL_SUSPEND_PROGRESS removal_suspend_progress zfs_removal_suspend_progress REMOVE_MAX_SEGMENT remove_max_segment zfs_remove_max_segment RESILVER_MIN_TIME_MS resilver_min_time_ms zfs_resilver_min_time_ms SCAN_LEGACY scan_legacy zfs_scan_legacy SCAN_SUSPEND_PROGRESS scan_suspend_progress zfs_scan_suspend_progress SCAN_VDEV_LIMIT scan_vdev_limit zfs_scan_vdev_limit SEND_HOLES_WITHOUT_BIRTH_TIME send_holes_without_birth_time send_holes_without_birth_time SLOW_IO_EVENTS_PER_SECOND slow_io_events_per_second zfs_slow_io_events_per_second SPA_ASIZE_INFLATION spa.asize_inflation spa_asize_inflation SPA_DISCARD_MEMORY_LIMIT spa.discard_memory_limit zfs_spa_discard_memory_limit SPA_LOAD_VERIFY_DATA spa.load_verify_data spa_load_verify_data SPA_LOAD_VERIFY_METADATA spa.load_verify_metadata spa_load_verify_metadata TRIM_EXTENT_BYTES_MIN trim.extent_bytes_min zfs_trim_extent_bytes_min TRIM_METASLAB_SKIP trim.metaslab_skip zfs_trim_metaslab_skip TRIM_TXG_BATCH trim.txg_batch zfs_trim_txg_batch TXG_HISTORY txg.history zfs_txg_history TXG_TIMEOUT txg.timeout zfs_txg_timeout UNLINK_SUSPEND_PROGRESS UNSUPPORTED zfs_unlink_suspend_progress VDEV_FILE_PHYSICAL_ASHIFT vdev.file.physical_ashift vdev_file_physical_ashift VDEV_MIN_MS_COUNT vdev.min_ms_count zfs_vdev_min_ms_count VDEV_VALIDATE_SKIP vdev.validate_skip vdev_validate_skip VOL_INHIBIT_DEV UNSUPPORTED zvol_inhibit_dev VOL_MODE vol.mode zvol_volmode VOL_RECURSIVE vol.recursive UNSUPPORTED XATTR_COMPAT xattr_compat zfs_xattr_compat ZEVENT_LEN_MAX zevent.len_max zfs_zevent_len_max ZEVENT_RETAIN_MAX zevent.retain_max zfs_zevent_retain_max ZIO_SLOW_IO_MS zio.slow_io_ms zio_slow_io_ms +ZIL_SAXATTR zil_saxattr zfs_zil_saxattr %%%% while read name FreeBSD Linux; do eval "export ${name}=\$${UNAME}" done diff --git a/tests/zfs-tests/tests/functional/cli_root/zpool_get/zpool_get.cfg b/tests/zfs-tests/tests/functional/cli_root/zpool_get/zpool_get.cfg index accbf69cf9c8..fac96e26e460 100644 --- a/tests/zfs-tests/tests/functional/cli_root/zpool_get/zpool_get.cfg +++ b/tests/zfs-tests/tests/functional/cli_root/zpool_get/zpool_get.cfg @@ -1,101 +1,102 @@ # # 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 2009 Sun Microsystems, Inc. All rights reserved. # Use is subject to license terms. # # # Copyright (c) 2013, 2014 by Delphix. All rights reserved. # Copyright 2016 Nexenta Systems, Inc. All rights reserved. # # Set the expected properties of zpool typeset -a properties=( "size" "capacity" "altroot" "health" "guid" "load_guid" "version" "bootfs" "delegation" "autoreplace" "cachefile" "checkpoint" "failmode" "listsnapshots" "autoexpand" "dedupratio" "free" "allocated" "readonly" "comment" "expandsize" "freeing" "fragmentation" "leaked" "multihost" "autotrim" "compatibility" "feature@async_destroy" "feature@empty_bpobj" "feature@lz4_compress" "feature@multi_vdev_crash_dump" "feature@spacemap_histogram" "feature@enabled_txg" "feature@hole_birth" "feature@extensible_dataset" "feature@embedded_data" "feature@bookmarks" "feature@filesystem_limits" "feature@large_blocks" "feature@sha512" "feature@skein" "feature@edonr" "feature@device_removal" "feature@obsolete_counts" "feature@zpool_checkpoint" "feature@spacemap_v2" "feature@redaction_bookmarks" "feature@redacted_datasets" "feature@bookmark_written" "feature@log_spacemap" "feature@device_rebuild" "feature@draid" ) if is_linux || is_freebsd; then properties+=( "ashift" "feature@large_dnode" "feature@userobj_accounting" "feature@encryption" "feature@project_quota" "feature@allocation_classes" "feature@resilver_defer" "feature@bookmark_v2" "feature@livelist" "feature@zstd_compress" + "feature@zilsaxattr" ) fi \ No newline at end of file diff --git a/tests/zfs-tests/tests/functional/slog/Makefile.am b/tests/zfs-tests/tests/functional/slog/Makefile.am index 33e3a6d3a496..92c3fd6c8e75 100644 --- a/tests/zfs-tests/tests/functional/slog/Makefile.am +++ b/tests/zfs-tests/tests/functional/slog/Makefile.am @@ -1,26 +1,27 @@ pkgdatadir = $(datadir)/@PACKAGE@/zfs-tests/tests/functional/slog dist_pkgdata_SCRIPTS = \ setup.ksh \ cleanup.ksh \ slog_001_pos.ksh \ slog_002_pos.ksh \ slog_003_pos.ksh \ slog_004_pos.ksh \ slog_005_pos.ksh \ slog_006_pos.ksh \ slog_007_pos.ksh \ slog_008_neg.ksh \ slog_009_neg.ksh \ slog_010_neg.ksh \ slog_011_neg.ksh \ slog_012_neg.ksh \ slog_013_pos.ksh \ slog_014_pos.ksh \ slog_015_neg.ksh \ slog_replay_fs_001.ksh \ slog_replay_fs_002.ksh \ - slog_replay_volume.ksh + slog_replay_volume.ksh \ + slog_016_pos.ksh dist_pkgdata_DATA = \ slog.cfg \ slog.kshlib diff --git a/tests/zfs-tests/tests/functional/slog/slog_016_pos.ksh b/tests/zfs-tests/tests/functional/slog/slog_016_pos.ksh new file mode 100755 index 000000000000..75f78c800a7c --- /dev/null +++ b/tests/zfs-tests/tests/functional/slog/slog_016_pos.ksh @@ -0,0 +1,157 @@ +#!/bin/ksh -p +# +# 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) 2021 by Nutanix. All rights reserved. +# + +. $STF_SUITE/tests/functional/slog/slog.kshlib + +# +# DESCRIPTION: +# Verify saxattr logging in to ZIL works +# +# STRATEGY: +# 1. Create an empty file system (TESTFS) +# 2. Freeze TESTFS +# 3. Create Xattrs. +# 4. Unmount filesystem +# +# 5. Remount TESTFS +# 6. Check xattrs. +# + +verify_runnable "global" + +function cleanup_testenv +{ + cleanup + log_must set_tunable32 ZIL_SAXATTR $orig_zil_saxattr +} + +log_assert "Verify saxattr logging in to ZIL works" + +orig_zil_saxattr=$(get_tunable ZIL_SAXATTR) + +log_onexit cleanup_testenv +log_must setup + +NFILES=10 +function validate_zil_saxattr +{ + saxattrzil=$1 + if [ "$2" == "disabled" ]; then + zilsaxattr_feature_disabled=1 + zpoolcreateflags="-ofeature@zilsaxattr=disabled" + else + zilsaxattr_feature_disabled=0 + zpoolcreateflags="" + fi + + log_must set_tunable32 ZIL_SAXATTR $saxattrzil + + # + # 1. Create an empty file system (TESTFS) + # + log_must zpool create $zpoolcreateflags $TESTPOOL $VDEV log mirror $LDEV + log_must zfs set compression=on $TESTPOOL + log_must zfs create -o xattr=sa $TESTPOOL/$TESTFS + log_must mkdir -p $TESTDIR + + # + # This dd command works around an issue where ZIL records aren't created + # after freezing the pool unless a ZIL header already exists. Create a + # file synchronously to force ZFS to write one out. + # + log_must dd if=/dev/zero of=/$TESTPOOL/$TESTFS/sync \ + conv=fdatasync,fsync bs=1 count=1 + + # + # 2. Freeze TESTFS + # + log_must zpool freeze $TESTPOOL + + rm /$TESTPOOL/$TESTFS/sync + # + # 3. Create xattrs + # + for i in $(seq $NFILES); do + log_must mkdir /$TESTPOOL/$TESTFS/xattr.d.$i + log_must set_xattr test test /$TESTPOOL/$TESTFS/xattr.d.$i + + log_must touch /$TESTPOOL/$TESTFS/xattr.f.$i + log_must set_xattr test test /$TESTPOOL/$TESTFS/xattr.f.$i + done + + # + # 4. Unmount filesystem and export the pool + # + # At this stage TESTFS is empty again and unfrozen, and the + # intent log contains a complete set of deltas to replay it. + # + log_must zfs unmount /$TESTPOOL/$TESTFS + + log_note "Verify transactions to replay:" + log_must zdb -iv $TESTPOOL/$TESTFS + + log_must zpool export $TESTPOOL + + # + # 5. Remount TESTFS + # + # Import the pool to unfreeze it and claim log blocks. It has to be + # `zpool import -f` because we can't write a frozen pool's labels! + # + log_must zpool import -f -d $VDIR $TESTPOOL + + # + # 6. Verify Xattr + # If zilsaxattr_feature_disabled=1 or saxattrzil=0, then xattr=sa + # logging in ZIL is not enabled, So, xattrs would be lost. + # If zilsaxattr_feature_disabled=0 and saxattrzil=1, then xattr=sa + # logging in ZIL is enabled, So, xattrs shouldn't be lost. + # + for i in $(seq $NFILES); do + if [ $zilsaxattr_feature_disabled -eq 1 -o \ + $saxattrzil -eq 0 ]; then + log_mustnot get_xattr test /$TESTPOOL/$TESTFS/xattr.d.$i + log_mustnot get_xattr test /$TESTPOOL/$TESTFS/xattr.f.$i + else + log_must get_xattr test /$TESTPOOL/$TESTFS/xattr.d.$i + log_must get_xattr test /$TESTPOOL/$TESTFS/xattr.f.$i + fi + done + + cleanup + log_must setup +} + + +#Validate zilsaxattr feature enabled. +validate_zil_saxattr 0 +validate_zil_saxattr 1 +#Validate zilsaxattr feature disabled. +validate_zil_saxattr 0 disabled +validate_zil_saxattr 1 disabled + +log_pass "Verify saxattr logging in to ZIL works"