diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst index f200d7874495..57c6ae23b3fc 100644 --- a/Documentation/filesystems/erofs.rst +++ b/Documentation/filesystems/erofs.rst @@ -199,7 +199,7 @@ may not. All metadatas can be now observed in two different spaces (views): | | |__________________| 64 bytes - Xattrs, extents, data inline are followed by the corresponding inode with + Xattrs, extents, data inline are placed after the corresponding inode with proper alignment, and they could be optional for different data mappings. _currently_ total 5 data layouts are supported: diff --git a/MAINTAINERS b/MAINTAINERS index 802bb655a431..004a673fbb06 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6172,11 +6172,11 @@ F: drivers/video/fbdev/udlfb.c F: include/video/udlfb.h DISTRIBUTED LOCK MANAGER (DLM) -M: Christine Caulfield +M: Alexander Aring M: David Teigland L: gfs2@lists.linux.dev S: Supported -W: http://sources.redhat.com/cluster/ +W: https://pagure.io/dlm T: git git://git.kernel.org/pub/scm/linux/kernel/git/teigland/linux-dlm.git F: fs/dlm/ diff --git a/certs/Kconfig b/certs/Kconfig index 1f109b070877..62036974367c 100644 --- a/certs/Kconfig +++ b/certs/Kconfig @@ -88,7 +88,21 @@ config SECONDARY_TRUSTED_KEYRING help If set, provide a keyring to which extra keys may be added, provided those keys are not blacklisted and are vouched for by a key built - into the kernel or already in the secondary trusted keyring. + into the kernel, machine keyring (if configured), or already in the + secondary trusted keyring. + +config SECONDARY_TRUSTED_KEYRING_SIGNED_BY_BUILTIN + bool "Only allow additional certs signed by keys on the builtin trusted keyring" + depends on SECONDARY_TRUSTED_KEYRING + help + If set, only certificates signed by keys on the builtin trusted + keyring may be loaded onto the secondary trusted keyring. + + Note: The machine keyring, if configured, will be linked to the + secondary keyring. When enabling this option, it is recommended + to also configure INTEGRITY_CA_MACHINE_KEYRING_MAX to prevent + linking code signing keys with imputed trust to the secondary + trusted keyring. config SYSTEM_BLACKLIST_KEYRING bool "Provide system-wide ring of blacklisted keys" diff --git a/crypto/asymmetric_keys/restrict.c b/crypto/asymmetric_keys/restrict.c index 6b69ea40da23..afcd4d101ac5 100644 --- a/crypto/asymmetric_keys/restrict.c +++ b/crypto/asymmetric_keys/restrict.c @@ -102,6 +102,10 @@ int restrict_link_by_signature(struct key *dest_keyring, if (use_builtin_keys && !test_bit(KEY_FLAG_BUILTIN, &key->flags)) ret = -ENOKEY; + else if (IS_BUILTIN(CONFIG_SECONDARY_TRUSTED_KEYRING_SIGNED_BY_BUILTIN) && + !strcmp(dest_keyring->description, ".secondary_trusted_keys") && + !test_bit(KEY_FLAG_BUILTIN, &key->flags)) + ret = -ENOKEY; else ret = verify_signature(key, sig); key_put(key); diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index 5aabcb6f0f15..42f332f46359 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -973,7 +973,8 @@ void dlm_delete_debug_comms_file(void *ctx) void dlm_create_debug_file(struct dlm_ls *ls) { - char name[DLM_LOCKSPACE_LEN + 8]; + /* Reserve enough space for the longest file name */ + char name[DLM_LOCKSPACE_LEN + sizeof("_queued_asts")]; /* format 1 */ @@ -985,8 +986,7 @@ void dlm_create_debug_file(struct dlm_ls *ls) /* format 2 */ - memset(name, 0, sizeof(name)); - snprintf(name, DLM_LOCKSPACE_LEN + 8, "%s_locks", ls->ls_name); + snprintf(name, sizeof(name), "%s_locks", ls->ls_name); ls->ls_debug_locks_dentry = debugfs_create_file(name, 0644, @@ -996,8 +996,7 @@ void dlm_create_debug_file(struct dlm_ls *ls) /* format 3 */ - memset(name, 0, sizeof(name)); - snprintf(name, DLM_LOCKSPACE_LEN + 8, "%s_all", ls->ls_name); + snprintf(name, sizeof(name), "%s_all", ls->ls_name); ls->ls_debug_all_dentry = debugfs_create_file(name, S_IFREG | S_IRUGO, @@ -1007,8 +1006,7 @@ void dlm_create_debug_file(struct dlm_ls *ls) /* format 4 */ - memset(name, 0, sizeof(name)); - snprintf(name, DLM_LOCKSPACE_LEN + 8, "%s_toss", ls->ls_name); + snprintf(name, sizeof(name), "%s_toss", ls->ls_name); ls->ls_debug_toss_dentry = debugfs_create_file(name, S_IFREG | S_IRUGO, @@ -1016,8 +1014,7 @@ void dlm_create_debug_file(struct dlm_ls *ls) ls, &format4_fops); - memset(name, 0, sizeof(name)); - snprintf(name, DLM_LOCKSPACE_LEN + 8, "%s_waiters", ls->ls_name); + snprintf(name, sizeof(name), "%s_waiters", ls->ls_name); ls->ls_debug_waiters_dentry = debugfs_create_file(name, 0644, @@ -1027,8 +1024,7 @@ void dlm_create_debug_file(struct dlm_ls *ls) /* format 5 */ - memset(name, 0, sizeof(name)); - snprintf(name, DLM_LOCKSPACE_LEN + 8, "%s_queued_asts", ls->ls_name); + snprintf(name, sizeof(name), "%s_queued_asts", ls->ls_name); ls->ls_debug_queued_asts_dentry = debugfs_create_file(name, 0644, diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index f7bc22e74db2..67f8dd8a05ef 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -63,6 +63,7 @@ #include "config.h" #define DLM_SHUTDOWN_WAIT_TIMEOUT msecs_to_jiffies(5000) +#define DLM_MAX_PROCESS_BUFFERS 24 #define NEEDED_RMEM (4*1024*1024) struct connection { @@ -194,6 +195,7 @@ static const struct dlm_proto_ops *dlm_proto_ops; #define DLM_IO_END 1 #define DLM_IO_EOF 2 #define DLM_IO_RESCHED 3 +#define DLM_IO_FLUSH 4 static void process_recv_sockets(struct work_struct *work); static void process_send_sockets(struct work_struct *work); @@ -202,6 +204,7 @@ static void process_dlm_messages(struct work_struct *work); static DECLARE_WORK(process_work, process_dlm_messages); static DEFINE_SPINLOCK(processqueue_lock); static bool process_dlm_messages_pending; +static atomic_t processqueue_count; static LIST_HEAD(processqueue); bool dlm_lowcomms_is_running(void) @@ -874,6 +877,7 @@ static void process_dlm_messages(struct work_struct *work) } list_del(&pentry->list); + atomic_dec(&processqueue_count); spin_unlock(&processqueue_lock); for (;;) { @@ -891,6 +895,7 @@ static void process_dlm_messages(struct work_struct *work) } list_del(&pentry->list); + atomic_dec(&processqueue_count); spin_unlock(&processqueue_lock); } } @@ -962,6 +967,7 @@ again: con->rx_leftover); spin_lock(&processqueue_lock); + ret = atomic_inc_return(&processqueue_count); list_add_tail(&pentry->list, &processqueue); if (!process_dlm_messages_pending) { process_dlm_messages_pending = true; @@ -969,6 +975,9 @@ again: } spin_unlock(&processqueue_lock); + if (ret > DLM_MAX_PROCESS_BUFFERS) + return DLM_IO_FLUSH; + return DLM_IO_SUCCESS; } @@ -1503,6 +1512,9 @@ static void process_recv_sockets(struct work_struct *work) wake_up(&con->shutdown_wait); /* CF_RECV_PENDING cleared */ break; + case DLM_IO_FLUSH: + flush_workqueue(process_workqueue); + fallthrough; case DLM_IO_RESCHED: cond_resched(); queue_work(io_workqueue, &con->rwork); diff --git a/fs/dlm/midcomms.c b/fs/dlm/midcomms.c index f641b36a36db..2247ebb61be1 100644 --- a/fs/dlm/midcomms.c +++ b/fs/dlm/midcomms.c @@ -337,13 +337,21 @@ static struct midcomms_node *nodeid2node(int nodeid) int dlm_midcomms_addr(int nodeid, struct sockaddr_storage *addr, int len) { - int ret, r = nodeid_hash(nodeid); + int ret, idx, r = nodeid_hash(nodeid); struct midcomms_node *node; ret = dlm_lowcomms_addr(nodeid, addr, len); if (ret) return ret; + idx = srcu_read_lock(&nodes_srcu); + node = __find_node(nodeid, r); + if (node) { + srcu_read_unlock(&nodes_srcu, idx); + return 0; + } + srcu_read_unlock(&nodes_srcu, idx); + node = kmalloc(sizeof(*node), GFP_NOFS); if (!node) return -ENOMEM; @@ -1030,15 +1038,15 @@ struct dlm_mhandle *dlm_midcomms_get_mhandle(int nodeid, int len, break; case DLM_VERSION_3_2: + /* send ack back if necessary */ + dlm_send_ack_threshold(node, DLM_SEND_ACK_BACK_MSG_THRESHOLD); + msg = dlm_midcomms_get_msg_3_2(mh, nodeid, len, allocation, ppc); if (!msg) { dlm_free_mhandle(mh); goto err; } - - /* send ack back if necessary */ - dlm_send_ack_threshold(node, DLM_SEND_ACK_BACK_MSG_THRESHOLD); break; default: dlm_free_mhandle(mh); @@ -1260,12 +1268,23 @@ void dlm_midcomms_remove_member(int nodeid) idx = srcu_read_lock(&nodes_srcu); node = nodeid2node(nodeid); - if (WARN_ON_ONCE(!node)) { + /* in case of dlm_midcomms_close() removes node */ + if (!node) { srcu_read_unlock(&nodes_srcu, idx); return; } spin_lock(&node->state_lock); + /* case of dlm_midcomms_addr() created node but + * was not added before because dlm_midcomms_close() + * removed the node + */ + if (!node->users) { + spin_unlock(&node->state_lock); + srcu_read_unlock(&nodes_srcu, idx); + return; + } + node->users--; pr_debug("node %d users dec count %d\n", nodeid, node->users); @@ -1386,10 +1405,16 @@ void dlm_midcomms_shutdown(void) midcomms_shutdown(node); } } - srcu_read_unlock(&nodes_srcu, idx); - mutex_unlock(&close_lock); dlm_lowcomms_shutdown(); + + for (i = 0; i < CONN_HASH_SIZE; i++) { + hlist_for_each_entry_rcu(node, &node_hash[i], hlist) { + midcomms_node_reset(node); + } + } + srcu_read_unlock(&nodes_srcu, idx); + mutex_unlock(&close_lock); } int dlm_midcomms_close(int nodeid) diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index f6dc961e6c2b..e540648dedc2 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -91,13 +91,10 @@ config EROFS_FS_ZIP_LZMA select XZ_DEC_MICROLZMA help Saying Y here includes support for reading EROFS file systems - containing LZMA compressed data, specifically called microLZMA. it - gives better compression ratios than the LZ4 algorithm, at the + containing LZMA compressed data, specifically called microLZMA. It + gives better compression ratios than the default LZ4 format, at the expense of more CPU overhead. - LZMA support is an experimental feature for now and so most file - systems will be readable without selecting this option. - If unsure, say N. config EROFS_FS_ZIP_DEFLATE diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h index 349c3316ae6b..279933e007d2 100644 --- a/fs/erofs/compress.h +++ b/fs/erofs/compress.h @@ -21,6 +21,8 @@ struct z_erofs_decompress_req { }; struct z_erofs_decompressor { + int (*config)(struct super_block *sb, struct erofs_super_block *dsb, + void *data, int size); int (*decompress)(struct z_erofs_decompress_req *rq, struct page **pagepool); char *name; @@ -92,6 +94,10 @@ int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf, extern const struct z_erofs_decompressor erofs_decompressors[]; /* prototypes for specific algorithms */ +int z_erofs_load_lzma_config(struct super_block *sb, + struct erofs_super_block *dsb, void *data, int size); +int z_erofs_load_deflate_config(struct super_block *sb, + struct erofs_super_block *dsb, void *data, int size); int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool); int z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq, diff --git a/fs/erofs/data.c b/fs/erofs/data.c index f6a0a1748521..029c761670bf 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -5,9 +5,7 @@ * Copyright (C) 2021, Alibaba Cloud */ #include "internal.h" -#include #include -#include #include void erofs_unmap_metabuf(struct erofs_buf *buf) diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 332ec5f74002..021be5feb1bc 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -4,7 +4,6 @@ * https://www.huawei.com/ */ #include "compress.h" -#include #include #ifndef LZ4_DISTANCE_MAX /* history window size */ @@ -24,11 +23,11 @@ struct z_erofs_lz4_decompress_ctx { unsigned int oend; }; -int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int size) +static int z_erofs_load_lz4_config(struct super_block *sb, + struct erofs_super_block *dsb, void *data, int size) { struct erofs_sb_info *sbi = EROFS_SB(sb); + struct z_erofs_lz4_cfgs *lz4 = data; u16 distance; if (lz4) { @@ -370,19 +369,75 @@ const struct z_erofs_decompressor erofs_decompressors[] = { .name = "interlaced" }, [Z_EROFS_COMPRESSION_LZ4] = { + .config = z_erofs_load_lz4_config, .decompress = z_erofs_lz4_decompress, .name = "lz4" }, #ifdef CONFIG_EROFS_FS_ZIP_LZMA [Z_EROFS_COMPRESSION_LZMA] = { + .config = z_erofs_load_lzma_config, .decompress = z_erofs_lzma_decompress, .name = "lzma" }, #endif #ifdef CONFIG_EROFS_FS_ZIP_DEFLATE [Z_EROFS_COMPRESSION_DEFLATE] = { + .config = z_erofs_load_deflate_config, .decompress = z_erofs_deflate_decompress, .name = "deflate" }, #endif }; + +int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + unsigned int algs, alg; + erofs_off_t offset; + int size, ret = 0; + + if (!erofs_sb_has_compr_cfgs(sbi)) { + sbi->available_compr_algs = Z_EROFS_COMPRESSION_LZ4; + return z_erofs_load_lz4_config(sb, dsb, NULL, 0); + } + + sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs); + if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) { + erofs_err(sb, "unidentified algorithms %x, please upgrade kernel", + sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS); + return -EOPNOTSUPP; + } + + erofs_init_metabuf(&buf, sb); + offset = EROFS_SUPER_OFFSET + sbi->sb_size; + alg = 0; + for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) { + void *data; + + if (!(algs & 1)) + continue; + + data = erofs_read_metadata(sb, &buf, &offset, &size); + if (IS_ERR(data)) { + ret = PTR_ERR(data); + break; + } + + if (alg >= ARRAY_SIZE(erofs_decompressors) || + !erofs_decompressors[alg].config) { + erofs_err(sb, "algorithm %d isn't enabled on this kernel", + alg); + ret = -EOPNOTSUPP; + } else { + ret = erofs_decompressors[alg].config(sb, + dsb, data, size); + } + + kfree(data); + if (ret) + break; + } + erofs_put_metabuf(&buf); + return ret; +} diff --git a/fs/erofs/decompressor_deflate.c b/fs/erofs/decompressor_deflate.c index 19e5bdeb30b6..daf3c1bdeab8 100644 --- a/fs/erofs/decompressor_deflate.c +++ b/fs/erofs/decompressor_deflate.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0-or-later -#include #include #include "compress.h" @@ -77,9 +76,10 @@ out_failed: } int z_erofs_load_deflate_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_deflate_cfgs *dfl, int size) + struct erofs_super_block *dsb, void *data, int size) { + struct z_erofs_deflate_cfgs *dfl = data; + if (!dfl || size < sizeof(struct z_erofs_deflate_cfgs)) { erofs_err(sb, "invalid deflate cfgs, size=%u", size); return -EINVAL; diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index dee10d22ada9..2dd14f99c1dc 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later #include -#include #include "compress.h" struct z_erofs_lzma { @@ -72,10 +71,10 @@ int __init z_erofs_lzma_init(void) } int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size) + struct erofs_super_block *dsb, void *data, int size) { static DEFINE_MUTEX(lzma_resize_mutex); + struct z_erofs_lzma_cfgs *lzma = data; unsigned int dict_size, i; struct z_erofs_lzma *strm, *head = NULL; int err; @@ -96,8 +95,6 @@ int z_erofs_load_lzma_config(struct super_block *sb, return -EINVAL; } - erofs_info(sb, "EXPERIMENTAL MicroLZMA in use. Use at your own risk!"); - /* in case 2 z_erofs_load_lzma_config() race to avoid deadlock */ mutex_lock(&lzma_resize_mutex); diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index cf04e21bfda2..b0409badb017 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -8,8 +8,10 @@ #define __EROFS_INTERNAL_H #include +#include #include #include +#include #include #include #include @@ -228,8 +230,6 @@ struct erofs_buf { }; #define __EROFS_BUF_INITIALIZER ((struct erofs_buf){ .page = NULL }) -#define ROOT_NID(sb) ((sb)->root_nid) - #define erofs_blknr(sb, addr) ((addr) >> (sb)->s_blocksize_bits) #define erofs_blkoff(sb, addr) ((addr) & ((sb)->s_blocksize - 1)) #define erofs_pos(sb, blk) ((erofs_off_t)(blk) << (sb)->s_blocksize_bits) @@ -469,9 +469,6 @@ int __init z_erofs_init_zip_subsystem(void); void z_erofs_exit_zip_subsystem(void); int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi, struct erofs_workgroup *egrp); -int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int len); int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, int flags); void *erofs_get_pcpubuf(unsigned int requiredpages); @@ -480,6 +477,7 @@ int erofs_pcpubuf_growsize(unsigned int nrpages); void __init erofs_pcpubuf_init(void); void erofs_pcpubuf_exit(void); int erofs_init_managed_cache(struct super_block *sb); +int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb); #else static inline void erofs_shrinker_register(struct super_block *sb) {} static inline void erofs_shrinker_unregister(struct super_block *sb) {} @@ -487,16 +485,6 @@ static inline int erofs_init_shrinker(void) { return 0; } static inline void erofs_exit_shrinker(void) {} static inline int z_erofs_init_zip_subsystem(void) { return 0; } static inline void z_erofs_exit_zip_subsystem(void) {} -static inline int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int len) -{ - if (lz4 || dsb->u1.lz4_max_distance) { - erofs_err(sb, "lz4 algorithm isn't enabled"); - return -EINVAL; - } - return 0; -} static inline void erofs_pcpubuf_init(void) {} static inline void erofs_pcpubuf_exit(void) {} static inline int erofs_init_managed_cache(struct super_block *sb) { return 0; } @@ -505,41 +493,17 @@ static inline int erofs_init_managed_cache(struct super_block *sb) { return 0; } #ifdef CONFIG_EROFS_FS_ZIP_LZMA int __init z_erofs_lzma_init(void); void z_erofs_lzma_exit(void); -int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size); #else static inline int z_erofs_lzma_init(void) { return 0; } static inline int z_erofs_lzma_exit(void) { return 0; } -static inline int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size) { - if (lzma) { - erofs_err(sb, "lzma algorithm isn't enabled"); - return -EINVAL; - } - return 0; -} #endif /* !CONFIG_EROFS_FS_ZIP_LZMA */ #ifdef CONFIG_EROFS_FS_ZIP_DEFLATE int __init z_erofs_deflate_init(void); void z_erofs_deflate_exit(void); -int z_erofs_load_deflate_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_deflate_cfgs *dfl, int size); #else static inline int z_erofs_deflate_init(void) { return 0; } static inline int z_erofs_deflate_exit(void) { return 0; } -static inline int z_erofs_load_deflate_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_deflate_cfgs *dfl, int size) { - if (dfl) { - erofs_err(sb, "deflate algorithm isn't enabled"); - return -EINVAL; - } - return 0; -} #endif /* !CONFIG_EROFS_FS_ZIP_DEFLATE */ #ifdef CONFIG_EROFS_FS_ONDEMAND diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 6fd04781fec5..976dc39a88f7 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -4,14 +4,11 @@ * https://www.huawei.com/ * Copyright (C) 2021, Alibaba Cloud */ -#include #include -#include #include #include #include #include -#include #include #include "xattr.h" @@ -156,68 +153,15 @@ void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, return buffer; } -#ifdef CONFIG_EROFS_FS_ZIP -static int erofs_load_compr_cfgs(struct super_block *sb, - struct erofs_super_block *dsb) +#ifndef CONFIG_EROFS_FS_ZIP +static int z_erofs_parse_cfgs(struct super_block *sb, + struct erofs_super_block *dsb) { - struct erofs_sb_info *sbi = EROFS_SB(sb); - struct erofs_buf buf = __EROFS_BUF_INITIALIZER; - unsigned int algs, alg; - erofs_off_t offset; - int size, ret = 0; + if (!dsb->u1.available_compr_algs) + return 0; - sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs); - if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) { - erofs_err(sb, "try to load compressed fs with unsupported algorithms %x", - sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS); - return -EINVAL; - } - - erofs_init_metabuf(&buf, sb); - offset = EROFS_SUPER_OFFSET + sbi->sb_size; - alg = 0; - for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) { - void *data; - - if (!(algs & 1)) - continue; - - data = erofs_read_metadata(sb, &buf, &offset, &size); - if (IS_ERR(data)) { - ret = PTR_ERR(data); - break; - } - - switch (alg) { - case Z_EROFS_COMPRESSION_LZ4: - ret = z_erofs_load_lz4_config(sb, dsb, data, size); - break; - case Z_EROFS_COMPRESSION_LZMA: - ret = z_erofs_load_lzma_config(sb, dsb, data, size); - break; - case Z_EROFS_COMPRESSION_DEFLATE: - ret = z_erofs_load_deflate_config(sb, dsb, data, size); - break; - default: - DBG_BUGON(1); - ret = -EFAULT; - } - kfree(data); - if (ret) - break; - } - erofs_put_metabuf(&buf); - return ret; -} -#else -static int erofs_load_compr_cfgs(struct super_block *sb, - struct erofs_super_block *dsb) -{ - if (dsb->u1.available_compr_algs) { - erofs_err(sb, "try to load compressed fs when compression is disabled"); - return -EINVAL; - } - return 0; + erofs_err(sb, "compression disabled, unable to mount compressed EROFS"); + return -EOPNOTSUPP; } #endif @@ -406,10 +350,7 @@ static int erofs_read_superblock(struct super_block *sb) } /* parse on-disk compression configurations */ - if (erofs_sb_has_compr_cfgs(sbi)) - ret = erofs_load_compr_cfgs(sb, dsb); - else - ret = z_erofs_load_lz4_config(sb, dsb, NULL, 0); + ret = z_erofs_parse_cfgs(sb, dsb); if (ret < 0) goto out; @@ -724,13 +665,13 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) xa_init(&sbi->managed_pslots); #endif - inode = erofs_iget(sb, ROOT_NID(sbi)); + inode = erofs_iget(sb, sbi->root_nid); if (IS_ERR(inode)) return PTR_ERR(inode); if (!S_ISDIR(inode->i_mode)) { erofs_err(sb, "rootino(nid %llu) is not a directory(i_mode %o)", - ROOT_NID(sbi), inode->i_mode); + sbi->root_nid, inode->i_mode); iput(inode); return -EINVAL; } @@ -760,7 +701,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) if (err) return err; - erofs_info(sb, "mounted with root inode @ nid %llu.", ROOT_NID(sbi)); + erofs_info(sb, "mounted with root inode @ nid %llu.", sbi->root_nid); return 0; } diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c index cc6fb9e98899..4256a85719a1 100644 --- a/fs/erofs/utils.c +++ b/fs/erofs/utils.c @@ -77,12 +77,7 @@ struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb, struct erofs_sb_info *const sbi = EROFS_SB(sb); struct erofs_workgroup *pre; - /* - * Bump up before making this visible to others for the XArray in order - * to avoid potential UAF without serialized by xa_lock. - */ - lockref_get(&grp->lockref); - + DBG_BUGON(grp->lockref.count < 1); repeat: xa_lock(&sbi->managed_pslots); pre = __xa_cmpxchg(&sbi->managed_pslots, grp->index, @@ -96,7 +91,6 @@ repeat: cond_resched(); goto repeat; } - lockref_put_return(&grp->lockref); grp = pre; } xa_unlock(&sbi->managed_pslots); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 036f610e044b..a7e6847f6f8f 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -796,6 +796,7 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe) return PTR_ERR(pcl); spin_lock_init(&pcl->obj.lockref.lock); + pcl->obj.lockref.count = 1; /* one ref for this request */ pcl->algorithmformat = map->m_algorithmformat; pcl->length = 0; pcl->partial = true; diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index e1586bba6d86..9f9295847a4e 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -287,7 +287,7 @@ get_new: mutex_unlock(&EXFAT_SB(sb)->s_lock); if (!dir_emit(ctx, nb->lfn, strlen(nb->lfn), inum, - (de.attr & ATTR_SUBDIR) ? DT_DIR : DT_REG)) + (de.attr & EXFAT_ATTR_SUBDIR) ? DT_DIR : DT_REG)) goto out; ctx->pos = cpos; goto get_new; @@ -359,7 +359,7 @@ unsigned int exfat_get_entry_type(struct exfat_dentry *ep) if (ep->type == EXFAT_VOLUME) return TYPE_VOLUME; if (ep->type == EXFAT_FILE) { - if (le16_to_cpu(ep->dentry.file.attr) & ATTR_SUBDIR) + if (le16_to_cpu(ep->dentry.file.attr) & EXFAT_ATTR_SUBDIR) return TYPE_DIR; return TYPE_FILE; } @@ -410,19 +410,21 @@ static void exfat_set_entry_type(struct exfat_dentry *ep, unsigned int type) ep->type = EXFAT_VOLUME; } else if (type == TYPE_DIR) { ep->type = EXFAT_FILE; - ep->dentry.file.attr = cpu_to_le16(ATTR_SUBDIR); + ep->dentry.file.attr = cpu_to_le16(EXFAT_ATTR_SUBDIR); } else if (type == TYPE_FILE) { ep->type = EXFAT_FILE; - ep->dentry.file.attr = cpu_to_le16(ATTR_ARCHIVE); + ep->dentry.file.attr = cpu_to_le16(EXFAT_ATTR_ARCHIVE); } } static void exfat_init_stream_entry(struct exfat_dentry *ep, - unsigned char flags, unsigned int start_clu, - unsigned long long size) + unsigned int start_clu, unsigned long long size) { exfat_set_entry_type(ep, TYPE_STREAM); - ep->dentry.stream.flags = flags; + if (size == 0) + ep->dentry.stream.flags = ALLOC_FAT_CHAIN; + else + ep->dentry.stream.flags = ALLOC_NO_FAT_CHAIN; ep->dentry.stream.start_clu = cpu_to_le32(start_clu); ep->dentry.stream.valid_size = cpu_to_le64(size); ep->dentry.stream.size = cpu_to_le64(size); @@ -488,9 +490,7 @@ int exfat_init_dir_entry(struct inode *inode, struct exfat_chain *p_dir, if (!ep) return -EIO; - exfat_init_stream_entry(ep, - (type == TYPE_FILE) ? ALLOC_FAT_CHAIN : ALLOC_NO_FAT_CHAIN, - start_clu, size); + exfat_init_stream_entry(ep, start_clu, size); exfat_update_bh(bh, IS_DIRSYNC(inode)); brelse(bh); diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index f78b614f44dc..a7a2c35d74fb 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -234,6 +234,8 @@ struct exfat_mount_options { discard:1, /* Issue discard requests on deletions */ keep_last_dots:1; /* Keep trailing periods in paths */ int time_offset; /* Offset of timestamps from UTC (in minutes) */ + /* Support creating zero-size directory, default: false */ + bool zero_size_dir; }; /* @@ -357,10 +359,10 @@ static inline int exfat_mode_can_hold_ro(struct inode *inode) static inline mode_t exfat_make_mode(struct exfat_sb_info *sbi, unsigned short attr, mode_t mode) { - if ((attr & ATTR_READONLY) && !(attr & ATTR_SUBDIR)) + if ((attr & EXFAT_ATTR_READONLY) && !(attr & EXFAT_ATTR_SUBDIR)) mode &= ~0222; - if (attr & ATTR_SUBDIR) + if (attr & EXFAT_ATTR_SUBDIR) return (mode & ~sbi->options.fs_dmask) | S_IFDIR; return (mode & ~sbi->options.fs_fmask) | S_IFREG; @@ -372,18 +374,18 @@ static inline unsigned short exfat_make_attr(struct inode *inode) unsigned short attr = EXFAT_I(inode)->attr; if (S_ISDIR(inode->i_mode)) - attr |= ATTR_SUBDIR; + attr |= EXFAT_ATTR_SUBDIR; if (exfat_mode_can_hold_ro(inode) && !(inode->i_mode & 0222)) - attr |= ATTR_READONLY; + attr |= EXFAT_ATTR_READONLY; return attr; } static inline void exfat_save_attr(struct inode *inode, unsigned short attr) { if (exfat_mode_can_hold_ro(inode)) - EXFAT_I(inode)->attr = attr & (ATTR_RWMASK | ATTR_READONLY); + EXFAT_I(inode)->attr = attr & (EXFAT_ATTR_RWMASK | EXFAT_ATTR_READONLY); else - EXFAT_I(inode)->attr = attr & ATTR_RWMASK; + EXFAT_I(inode)->attr = attr & EXFAT_ATTR_RWMASK; } static inline bool exfat_is_last_sector_in_cluster(struct exfat_sb_info *sbi, diff --git a/fs/exfat/exfat_raw.h b/fs/exfat/exfat_raw.h index 0ece2e43cf49..971a1ccd0e89 100644 --- a/fs/exfat/exfat_raw.h +++ b/fs/exfat/exfat_raw.h @@ -64,15 +64,16 @@ #define CS_DEFAULT 2 /* file attributes */ -#define ATTR_READONLY 0x0001 -#define ATTR_HIDDEN 0x0002 -#define ATTR_SYSTEM 0x0004 -#define ATTR_VOLUME 0x0008 -#define ATTR_SUBDIR 0x0010 -#define ATTR_ARCHIVE 0x0020 +#define EXFAT_ATTR_READONLY 0x0001 +#define EXFAT_ATTR_HIDDEN 0x0002 +#define EXFAT_ATTR_SYSTEM 0x0004 +#define EXFAT_ATTR_VOLUME 0x0008 +#define EXFAT_ATTR_SUBDIR 0x0010 +#define EXFAT_ATTR_ARCHIVE 0x0020 -#define ATTR_RWMASK (ATTR_HIDDEN | ATTR_SYSTEM | ATTR_VOLUME | \ - ATTR_SUBDIR | ATTR_ARCHIVE) +#define EXFAT_ATTR_RWMASK (EXFAT_ATTR_HIDDEN | EXFAT_ATTR_SYSTEM | \ + EXFAT_ATTR_VOLUME | EXFAT_ATTR_SUBDIR | \ + EXFAT_ATTR_ARCHIVE) #define BOOTSEC_JUMP_BOOT_LEN 3 #define BOOTSEC_FS_NAME_LEN 8 diff --git a/fs/exfat/file.c b/fs/exfat/file.c index 30ee2c8d36a5..02c4e2937879 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -8,6 +8,9 @@ #include #include #include +#include +#include +#include #include "exfat_raw.h" #include "exfat_fs.h" @@ -144,7 +147,7 @@ int __exfat_truncate(struct inode *inode) } if (ei->type == TYPE_FILE) - ei->attr |= ATTR_ARCHIVE; + ei->attr |= EXFAT_ATTR_ARCHIVE; /* * update the directory entry @@ -315,6 +318,93 @@ out: return error; } +/* + * modified ioctls from fat/file.c by Welmer Almesberger + */ +static int exfat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr) +{ + u32 attr; + + inode_lock_shared(inode); + attr = exfat_make_attr(inode); + inode_unlock_shared(inode); + + return put_user(attr, user_attr); +} + +static int exfat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) +{ + struct inode *inode = file_inode(file); + struct exfat_sb_info *sbi = EXFAT_SB(inode->i_sb); + int is_dir = S_ISDIR(inode->i_mode); + u32 attr, oldattr; + struct iattr ia; + int err; + + err = get_user(attr, user_attr); + if (err) + goto out; + + err = mnt_want_write_file(file); + if (err) + goto out; + inode_lock(inode); + + oldattr = exfat_make_attr(inode); + + /* + * Mask attributes so we don't set reserved fields. + */ + attr &= (EXFAT_ATTR_READONLY | EXFAT_ATTR_HIDDEN | EXFAT_ATTR_SYSTEM | + EXFAT_ATTR_ARCHIVE); + attr |= (is_dir ? EXFAT_ATTR_SUBDIR : 0); + + /* Equivalent to a chmod() */ + ia.ia_valid = ATTR_MODE | ATTR_CTIME; + ia.ia_ctime = current_time(inode); + if (is_dir) + ia.ia_mode = exfat_make_mode(sbi, attr, 0777); + else + ia.ia_mode = exfat_make_mode(sbi, attr, 0666 | (inode->i_mode & 0111)); + + /* The root directory has no attributes */ + if (inode->i_ino == EXFAT_ROOT_INO && attr != EXFAT_ATTR_SUBDIR) { + err = -EINVAL; + goto out_unlock_inode; + } + + if (((attr | oldattr) & EXFAT_ATTR_SYSTEM) && + !capable(CAP_LINUX_IMMUTABLE)) { + err = -EPERM; + goto out_unlock_inode; + } + + /* + * The security check is questionable... We single + * out the RO attribute for checking by the security + * module, just because it maps to a file mode. + */ + err = security_inode_setattr(file_mnt_idmap(file), + file->f_path.dentry, &ia); + if (err) + goto out_unlock_inode; + + /* This MUST be done before doing anything irreversible... */ + err = exfat_setattr(file_mnt_idmap(file), file->f_path.dentry, &ia); + if (err) + goto out_unlock_inode; + + fsnotify_change(file->f_path.dentry, ia.ia_valid); + + exfat_save_attr(inode, attr); + mark_inode_dirty(inode); +out_unlock_inode: + inode_unlock(inode); + mnt_drop_write_file(file); +out: + return err; +} + static int exfat_ioctl_fitrim(struct inode *inode, unsigned long arg) { struct fstrim_range range; @@ -345,8 +435,13 @@ static int exfat_ioctl_fitrim(struct inode *inode, unsigned long arg) long exfat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); + u32 __user *user_attr = (u32 __user *)arg; switch (cmd) { + case FAT_IOCTL_GET_ATTRIBUTES: + return exfat_ioctl_get_attributes(inode, user_attr); + case FAT_IOCTL_SET_ATTRIBUTES: + return exfat_ioctl_set_attributes(filp, user_attr); case FITRIM: return exfat_ioctl_fitrim(inode, arg); default: diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index a2185e6f0548..875234179d1f 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -400,9 +400,9 @@ static int exfat_write_end(struct file *file, struct address_space *mapping, if (err < len) exfat_write_failed(mapping, pos+len); - if (!(err < 0) && !(ei->attr & ATTR_ARCHIVE)) { + if (!(err < 0) && !(ei->attr & EXFAT_ATTR_ARCHIVE)) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); - ei->attr |= ATTR_ARCHIVE; + ei->attr |= EXFAT_ATTR_ARCHIVE; mark_inode_dirty(inode); } @@ -550,7 +550,7 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info) inode_inc_iversion(inode); inode->i_generation = get_random_u32(); - if (info->attr & ATTR_SUBDIR) { /* directory */ + if (info->attr & EXFAT_ATTR_SUBDIR) { /* directory */ inode->i_generation &= ~1; inode->i_mode = exfat_make_mode(sbi, info->attr, 0777); inode->i_op = &exfat_dir_inode_operations; diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index b92e46916dea..5d737e0b639a 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -351,14 +351,20 @@ static int exfat_find_empty_entry(struct inode *inode, if (exfat_check_max_dentries(inode)) return -ENOSPC; - /* we trust p_dir->size regardless of FAT type */ - if (exfat_find_last_cluster(sb, p_dir, &last_clu)) - return -EIO; - /* * Allocate new cluster to this directory */ - exfat_chain_set(&clu, last_clu + 1, 0, p_dir->flags); + if (ei->start_clu != EXFAT_EOF_CLUSTER) { + /* we trust p_dir->size regardless of FAT type */ + if (exfat_find_last_cluster(sb, p_dir, &last_clu)) + return -EIO; + + exfat_chain_set(&clu, last_clu + 1, 0, p_dir->flags); + } else { + /* This directory is empty */ + exfat_chain_set(&clu, EXFAT_EOF_CLUSTER, 0, + ALLOC_NO_FAT_CHAIN); + } /* allocate a cluster */ ret = exfat_alloc_cluster(inode, 1, &clu, IS_DIRSYNC(inode)); @@ -368,6 +374,11 @@ static int exfat_find_empty_entry(struct inode *inode, if (exfat_zeroed_cluster(inode, clu.dir)) return -EIO; + if (ei->start_clu == EXFAT_EOF_CLUSTER) { + ei->start_clu = clu.dir; + p_dir->dir = clu.dir; + } + /* append to the FAT chain */ if (clu.flags != p_dir->flags) { /* no-fat-chain bit is disabled, @@ -507,7 +518,7 @@ static int exfat_add_entry(struct inode *inode, const char *path, goto out; } - if (type == TYPE_DIR) { + if (type == TYPE_DIR && !sbi->options.zero_size_dir) { ret = exfat_alloc_new_dir(inode, &clu); if (ret) goto out; @@ -534,13 +545,16 @@ static int exfat_add_entry(struct inode *inode, const char *path, info->type = type; if (type == TYPE_FILE) { - info->attr = ATTR_ARCHIVE; + info->attr = EXFAT_ATTR_ARCHIVE; info->start_clu = EXFAT_EOF_CLUSTER; info->size = 0; info->num_subdirs = 0; } else { - info->attr = ATTR_SUBDIR; - info->start_clu = start_clu; + info->attr = EXFAT_ATTR_SUBDIR; + if (sbi->options.zero_size_dir) + info->start_clu = EXFAT_EOF_CLUSTER; + else + info->start_clu = start_clu; info->size = clu_size; info->num_subdirs = EXFAT_MIN_SUBDIR; } @@ -646,7 +660,7 @@ static int exfat_find(struct inode *dir, struct qstr *qname, info->type = exfat_get_entry_type(ep); info->attr = le16_to_cpu(ep->dentry.file.attr); info->size = le64_to_cpu(ep2->dentry.stream.valid_size); - if ((info->type == TYPE_FILE) && (info->size == 0)) { + if (info->size == 0) { info->flags = ALLOC_NO_FAT_CHAIN; info->start_clu = EXFAT_EOF_CLUSTER; } else { @@ -889,6 +903,9 @@ static int exfat_check_dir_empty(struct super_block *sb, dentries_per_clu = sbi->dentries_per_clu; + if (p_dir->dir == EXFAT_EOF_CLUSTER) + return 0; + exfat_chain_dup(&clu, p_dir); while (clu.dir != EXFAT_EOF_CLUSTER) { @@ -1033,8 +1050,8 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir, *epnew = *epold; if (exfat_get_entry_type(epnew) == TYPE_FILE) { - epnew->dentry.file.attr |= cpu_to_le16(ATTR_ARCHIVE); - ei->attr |= ATTR_ARCHIVE; + epnew->dentry.file.attr |= cpu_to_le16(EXFAT_ATTR_ARCHIVE); + ei->attr |= EXFAT_ATTR_ARCHIVE; } exfat_update_bh(new_bh, sync); brelse(old_bh); @@ -1065,8 +1082,8 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir, ei->entry = newentry; } else { if (exfat_get_entry_type(epold) == TYPE_FILE) { - epold->dentry.file.attr |= cpu_to_le16(ATTR_ARCHIVE); - ei->attr |= ATTR_ARCHIVE; + epold->dentry.file.attr |= cpu_to_le16(EXFAT_ATTR_ARCHIVE); + ei->attr |= EXFAT_ATTR_ARCHIVE; } exfat_update_bh(old_bh, sync); brelse(old_bh); @@ -1114,8 +1131,8 @@ static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir, *epnew = *epmov; if (exfat_get_entry_type(epnew) == TYPE_FILE) { - epnew->dentry.file.attr |= cpu_to_le16(ATTR_ARCHIVE); - ei->attr |= ATTR_ARCHIVE; + epnew->dentry.file.attr |= cpu_to_le16(EXFAT_ATTR_ARCHIVE); + ei->attr |= EXFAT_ATTR_ARCHIVE; } exfat_update_bh(new_bh, IS_DIRSYNC(inode)); brelse(mov_bh); @@ -1256,7 +1273,8 @@ static int __exfat_rename(struct inode *old_parent_inode, } /* Free the clusters if new_inode is a dir(as if exfat_rmdir) */ - if (new_entry_type == TYPE_DIR) { + if (new_entry_type == TYPE_DIR && + new_ei->start_clu != EXFAT_EOF_CLUSTER) { /* new_ei, new_clu_to_free */ struct exfat_chain new_clu_to_free; diff --git a/fs/exfat/super.c b/fs/exfat/super.c index e919a68bf4a1..d9d4fa91010b 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -165,6 +165,8 @@ static int exfat_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",sys_tz"); else if (opts->time_offset) seq_printf(m, ",time_offset=%d", opts->time_offset); + if (opts->zero_size_dir) + seq_puts(m, ",zero_size_dir"); return 0; } @@ -209,6 +211,7 @@ enum { Opt_keep_last_dots, Opt_sys_tz, Opt_time_offset, + Opt_zero_size_dir, /* Deprecated options */ Opt_utf8, @@ -237,6 +240,7 @@ static const struct fs_parameter_spec exfat_parameters[] = { fsparam_flag("keep_last_dots", Opt_keep_last_dots), fsparam_flag("sys_tz", Opt_sys_tz), fsparam_s32("time_offset", Opt_time_offset), + fsparam_flag("zero_size_dir", Opt_zero_size_dir), __fsparam(NULL, "utf8", Opt_utf8, fs_param_deprecated, NULL), __fsparam(NULL, "debug", Opt_debug, fs_param_deprecated, @@ -305,6 +309,9 @@ static int exfat_parse_param(struct fs_context *fc, struct fs_parameter *param) return -EINVAL; opts->time_offset = result.int_32; break; + case Opt_zero_size_dir: + opts->zero_size_dir = true; + break; case Opt_utf8: case Opt_debug: case Opt_namecase: @@ -360,7 +367,7 @@ static int exfat_read_root(struct inode *inode) inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); inode->i_generation = 0; - inode->i_mode = exfat_make_mode(sbi, ATTR_SUBDIR, 0777); + inode->i_mode = exfat_make_mode(sbi, EXFAT_ATTR_SUBDIR, 0777); inode->i_op = &exfat_dir_inode_operations; inode->i_fop = &exfat_dir_operations; @@ -369,7 +376,7 @@ static int exfat_read_root(struct inode *inode) ei->i_size_aligned = i_size_read(inode); ei->i_size_ondisk = i_size_read(inode); - exfat_save_attr(inode, ATTR_SUBDIR); + exfat_save_attr(inode, EXFAT_ATTR_SUBDIR); ei->i_crtime = simple_inode_init_ts(inode); exfat_truncate_inode_atime(inode); return 0; diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h index 0c5a79c3b5d4..ef4c19e5f570 100644 --- a/fs/ext4/acl.h +++ b/fs/ext4/acl.h @@ -68,6 +68,11 @@ extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); static inline int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) { + /* usually, the umask is applied by posix_acl_create(), but if + ext4 ACL support is disabled at compile time, we need to do + it here, because posix_acl_create() will never be called */ + inode->i_mode &= ~current_umask(); + return 0; } #endif /* CONFIG_EXT4_FS_POSIX_ACL */ diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 79b20d6ae39e..591fb3f710be 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -22,6 +22,7 @@ #include "mballoc.h" #include +#include static unsigned ext4_num_base_meta_clusters(struct super_block *sb, ext4_group_t block_group); @@ -111,10 +112,8 @@ static unsigned ext4_num_overhead_clusters(struct super_block *sb, itbl_blk_start = ext4_inode_table(sb, gdp); itbl_blk_end = itbl_blk_start + sbi->s_itb_per_group - 1; if (itbl_blk_start <= end && itbl_blk_end >= start) { - itbl_blk_start = itbl_blk_start >= start ? - itbl_blk_start : start; - itbl_blk_end = itbl_blk_end <= end ? - itbl_blk_end : end; + itbl_blk_start = max(itbl_blk_start, start); + itbl_blk_end = min(itbl_blk_end, end); itbl_cluster_start = EXT4_B2C(sbi, itbl_blk_start - start); itbl_cluster_end = EXT4_B2C(sbi, itbl_blk_end - start); @@ -274,6 +273,9 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bh_p; + KUNIT_STATIC_STUB_REDIRECT(ext4_get_group_desc, + sb, block_group, bh); + if (block_group >= ngroups) { ext4_error(sb, "block_group >= groups_count - block_group = %u," " groups_count = %u", block_group, ngroups); @@ -468,6 +470,9 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group, ext4_fsblk_t bitmap_blk; int err; + KUNIT_STATIC_STUB_REDIRECT(ext4_read_block_bitmap_nowait, + sb, block_group, ignore_locked); + desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) return ERR_PTR(-EFSCORRUPTED); @@ -563,6 +568,9 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, { struct ext4_group_desc *desc; + KUNIT_STATIC_STUB_REDIRECT(ext4_wait_block_bitmap, + sb, block_group, bh); + if (!buffer_new(bh)) return 0; desc = ext4_get_group_desc(sb, block_group, NULL); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 8da5fb680210..f16aa375c02b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1504,6 +1504,7 @@ struct ext4_sb_info { loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ struct buffer_head * s_sbh; /* Buffer containing the super block */ struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ + /* Array of bh's for the block group descriptors */ struct buffer_head * __rcu *s_group_desc; unsigned int s_mount_opt; unsigned int s_mount_opt2; @@ -1574,7 +1575,7 @@ struct ext4_sb_info { unsigned int *s_mb_maxs; unsigned int s_group_info_size; unsigned int s_mb_free_pending; - struct list_head s_freed_data_list; /* List of blocks to be freed + struct list_head s_freed_data_list[2]; /* List of blocks to be freed after commit completed */ struct list_head s_discard_list; struct work_struct s_discard_work; @@ -1686,7 +1687,8 @@ struct ext4_sb_info { /* * Barrier between writepages ops and changing any inode's JOURNAL_DATA - * or EXTENTS flag. + * or EXTENTS flag or between writepages ops and changing DELALLOC or + * DIOREAD_NOLOCK mount options on remount. */ struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; @@ -2934,7 +2936,7 @@ extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid); extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, - int len, int state); + int len, bool state); static inline bool ext4_mb_cr_expensive(enum criteria cr) { return cr >= CR_GOAL_LEN_SLOW; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 4c4176ee1749..d5efe076d3d3 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1010,6 +1010,11 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, ix = curp->p_idx; } + if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { + EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); + return -EFSCORRUPTED; + } + len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1; BUG_ON(len < 0); if (len > 0) { @@ -1019,11 +1024,6 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx)); } - if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { - EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); - return -EFSCORRUPTED; - } - ix->ei_block = cpu_to_le32(logical); ext4_idx_store_pblock(ix, ptr); le16_add_cpu(&curp->p_hdr->eh_entries, 1); @@ -6081,13 +6081,13 @@ int ext4_ext_clear_bb(struct inode *inode) for (j = 0; j < path->p_depth; j++) { ext4_mb_mark_bb(inode->i_sb, - path[j].p_block, 1, 0); + path[j].p_block, 1, false); ext4_fc_record_regions(inode->i_sb, inode->i_ino, 0, path[j].p_block, 1, 1); } ext4_free_ext_path(path); } - ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); + ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, false); ext4_fc_record_regions(inode->i_sb, inode->i_ino, map.m_lblk, map.m_pblk, map.m_len, 1); } diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 6f7de14c0fa8..f4b50652f0cc 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -152,8 +152,9 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); -static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len); +static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, + struct pending_reservation **prealloc); int __init ext4_init_es(void) { @@ -448,6 +449,19 @@ static void ext4_es_list_del(struct inode *inode) spin_unlock(&sbi->s_es_lock); } +static inline struct pending_reservation *__alloc_pending(bool nofail) +{ + if (!nofail) + return kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); + + return kmem_cache_zalloc(ext4_pending_cachep, GFP_KERNEL | __GFP_NOFAIL); +} + +static inline void __free_pending(struct pending_reservation *pr) +{ + kmem_cache_free(ext4_pending_cachep, pr); +} + /* * Returns true if we cannot fail to allocate memory for this extent_status * entry and cannot reclaim it until its status changes. @@ -836,11 +850,12 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; - int err1 = 0; - int err2 = 0; + int err1 = 0, err2 = 0, err3 = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; + struct pending_reservation *pr = NULL; + bool revise_pending = false; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; @@ -868,11 +883,17 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_es_insert_extent_check(inode, &newes); + revise_pending = sbi->s_cluster_ratio > 1 && + test_opt(inode->i_sb, DELALLOC) && + (status & (EXTENT_STATUS_WRITTEN | + EXTENT_STATUS_UNWRITTEN)); retry: if (err1 && !es1) es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); + if ((err1 || err2 || err3) && revise_pending && !pr) + pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, end, NULL, es1); @@ -897,13 +918,18 @@ retry: es2 = NULL; } - if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) && - (status & EXTENT_STATUS_WRITTEN || - status & EXTENT_STATUS_UNWRITTEN)) - __revise_pending(inode, lblk, len); + if (revise_pending) { + err3 = __revise_pending(inode, lblk, len, &pr); + if (err3 != 0) + goto error; + if (pr) { + __free_pending(pr); + pr = NULL; + } + } error: write_unlock(&EXT4_I(inode)->i_es_lock); - if (err1 || err2) + if (err1 || err2 || err3) goto retry; ext4_es_print_tree(inode); @@ -1311,7 +1337,7 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end, rc->ndelonly--; node = rb_next(&pr->rb_node); rb_erase(&pr->rb_node, &tree->root); - kmem_cache_free(ext4_pending_cachep, pr); + __free_pending(pr); if (!node) break; pr = rb_entry(node, struct pending_reservation, @@ -1405,8 +1431,8 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, } } if (count_reserved) - count_rsvd(inode, lblk, orig_es.es_len - len1 - len2, - &orig_es, &rc); + count_rsvd(inode, orig_es.es_lblk + len1, + orig_es.es_len - len1 - len2, &orig_es, &rc); goto out_get_reserved; } @@ -1907,11 +1933,13 @@ static struct pending_reservation *__get_pending(struct inode *inode, * * @inode - file containing the cluster * @lblk - logical block in the cluster to be added + * @prealloc - preallocated pending entry * * Returns 0 on successful insertion and -ENOMEM on failure. If the * pending reservation is already in the set, returns successfully. */ -static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) +static int __insert_pending(struct inode *inode, ext4_lblk_t lblk, + struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; @@ -1937,10 +1965,15 @@ static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) } } - pr = kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); - if (pr == NULL) { - ret = -ENOMEM; - goto out; + if (likely(*prealloc == NULL)) { + pr = __alloc_pending(false); + if (!pr) { + ret = -ENOMEM; + goto out; + } + } else { + pr = *prealloc; + *prealloc = NULL; } pr->lclu = lclu; @@ -1970,7 +2003,7 @@ static void __remove_pending(struct inode *inode, ext4_lblk_t lblk) if (pr != NULL) { tree = &EXT4_I(inode)->i_pending_tree; rb_erase(&pr->rb_node, &tree->root); - kmem_cache_free(ext4_pending_cachep, pr); + __free_pending(pr); } } @@ -2029,10 +2062,10 @@ void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, bool allocated) { struct extent_status newes; - int err1 = 0; - int err2 = 0; + int err1 = 0, err2 = 0, err3 = 0; struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; + struct pending_reservation *pr = NULL; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; @@ -2052,6 +2085,8 @@ retry: es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); + if ((err1 || err2 || err3) && allocated && !pr) + pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1); @@ -2074,11 +2109,18 @@ retry: es2 = NULL; } - if (allocated) - __insert_pending(inode, lblk); + if (allocated) { + err3 = __insert_pending(inode, lblk, &pr); + if (err3 != 0) + goto error; + if (pr) { + __free_pending(pr); + pr = NULL; + } + } error: write_unlock(&EXT4_I(inode)->i_es_lock); - if (err1 || err2) + if (err1 || err2 || err3) goto retry; ext4_es_print_tree(inode); @@ -2184,21 +2226,24 @@ unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk, * @inode - file containing the range * @lblk - logical block defining the start of range * @len - length of range in blocks + * @prealloc - preallocated pending entry * * Used after a newly allocated extent is added to the extents status tree. * Requires that the extents in the range have either written or unwritten * status. Must be called while holding i_es_lock. */ -static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len) +static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, + struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t end = lblk + len - 1; ext4_lblk_t first, last; bool f_del = false, l_del = false; + int ret = 0; if (len == 0) - return; + return 0; /* * Two cases - block range within single cluster and block range @@ -2219,7 +2264,9 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); if (f_del) { - __insert_pending(inode, first); + ret = __insert_pending(inode, first, prealloc); + if (ret < 0) + goto out; } else { last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; @@ -2227,9 +2274,11 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); - if (l_del) - __insert_pending(inode, last); - else + if (l_del) { + ret = __insert_pending(inode, last, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, last); } } else { @@ -2237,18 +2286,24 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); - if (f_del) - __insert_pending(inode, first); - else + if (f_del) { + ret = __insert_pending(inode, first, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, first); last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); - if (l_del) - __insert_pending(inode, last); - else + if (l_del) { + ret = __insert_pending(inode, last, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, last); } +out: + return ret; } diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index b06de728b3b6..87c009e0c59a 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1806,7 +1806,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb, * at the end of the FC replay using our array of * modified inodes. */ - ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); + ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, false); goto next; } @@ -1875,7 +1875,7 @@ ext4_fc_replay_del_range(struct super_block *sb, if (ret > 0) { remaining -= ret; cur += ret; - ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); + ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, false); } else { remaining -= map.m_len; cur += map.m_len; @@ -1934,12 +1934,12 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) if (!IS_ERR(path)) { for (j = 0; j < path->p_depth; j++) ext4_mb_mark_bb(inode->i_sb, - path[j].p_block, 1, 1); + path[j].p_block, 1, true); ext4_free_ext_path(path); } cur += ret; ext4_mb_mark_bb(inode->i_sb, map.m_pblk, - map.m_len, 1); + map.m_len, true); } else { cur = cur + (map.m_len ? map.m_len : 1); } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 6830ea3a6c59..0166bb9ca160 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -306,80 +306,38 @@ out: } static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset, - ssize_t written, size_t count) + ssize_t count) { handle_t *handle; - bool truncate = false; - u8 blkbits = inode->i_blkbits; - ext4_lblk_t written_blk, end_blk; - int ret; - - /* - * Note that EXT4_I(inode)->i_disksize can get extended up to - * inode->i_size while the I/O was running due to writeback of delalloc - * blocks. But, the code in ext4_iomap_alloc() is careful to use - * zeroed/unwritten extents if this is possible; thus we won't leave - * uninitialized blocks in a file even if we didn't succeed in writing - * as much as we intended. - */ - WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize); - if (offset + count <= EXT4_I(inode)->i_disksize) { - /* - * We need to ensure that the inode is removed from the orphan - * list if it has been added prematurely, due to writeback of - * delalloc blocks. - */ - if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) { - handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); - - if (IS_ERR(handle)) { - ext4_orphan_del(NULL, inode); - return PTR_ERR(handle); - } - - ext4_orphan_del(handle, inode); - ext4_journal_stop(handle); - } - - return written; - } - - if (written < 0) - goto truncate; + lockdep_assert_held_write(&inode->i_rwsem); handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); - if (IS_ERR(handle)) { - written = PTR_ERR(handle); - goto truncate; - } + if (IS_ERR(handle)) + return PTR_ERR(handle); - if (ext4_update_inode_size(inode, offset + written)) { - ret = ext4_mark_inode_dirty(handle, inode); + if (ext4_update_inode_size(inode, offset + count)) { + int ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) { - written = ret; ext4_journal_stop(handle); - goto truncate; + return ret; } } - /* - * We may need to truncate allocated but not written blocks beyond EOF. - */ - written_blk = ALIGN(offset + written, 1 << blkbits); - end_blk = ALIGN(offset + count, 1 << blkbits); - if (written_blk < end_blk && ext4_can_truncate(inode)) - truncate = true; - - /* - * Remove the inode from the orphan list if it has been extended and - * everything went OK. - */ - if (!truncate && inode->i_nlink) + if (inode->i_nlink) ext4_orphan_del(handle, inode); ext4_journal_stop(handle); - if (truncate) { -truncate: + return count; +} + +/* + * Clean up the inode after DIO or DAX extending write has completed and the + * inode size has been updated using ext4_handle_inode_extension(). + */ +static void ext4_inode_extension_cleanup(struct inode *inode, ssize_t count) +{ + lockdep_assert_held_write(&inode->i_rwsem); + if (count < 0) { ext4_truncate_failed_write(inode); /* * If the truncate operation failed early, then the inode may @@ -388,9 +346,28 @@ truncate: */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); + return; } + /* + * If i_disksize got extended due to writeback of delalloc blocks while + * the DIO was running we could fail to cleanup the orphan list in + * ext4_handle_inode_extension(). Do it now. + */ + if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) { + handle_t *handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); - return written; + if (IS_ERR(handle)) { + /* + * The write has successfully completed. Not much to + * do with the error here so just cleanup the orphan + * list and hope for the best. + */ + ext4_orphan_del(NULL, inode); + return; + } + ext4_orphan_del(handle, inode); + ext4_journal_stop(handle); + } } static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size, @@ -399,31 +376,22 @@ static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size, loff_t pos = iocb->ki_pos; struct inode *inode = file_inode(iocb->ki_filp); + if (!error && size && flags & IOMAP_DIO_UNWRITTEN) + error = ext4_convert_unwritten_extents(NULL, inode, pos, size); if (error) return error; - - if (size && flags & IOMAP_DIO_UNWRITTEN) { - error = ext4_convert_unwritten_extents(NULL, inode, pos, size); - if (error < 0) - return error; - } /* - * If we are extending the file, we have to update i_size here before - * page cache gets invalidated in iomap_dio_rw(). Otherwise racing - * buffered reads could zero out too much from page cache pages. Update - * of on-disk size will happen later in ext4_dio_write_iter() where - * we have enough information to also perform orphan list handling etc. - * Note that we perform all extending writes synchronously under - * i_rwsem held exclusively so i_size update is safe here in that case. - * If the write was not extending, we cannot see pos > i_size here - * because operations reducing i_size like truncate wait for all - * outstanding DIO before updating i_size. + * Note that EXT4_I(inode)->i_disksize can get extended up to + * inode->i_size while the I/O was running due to writeback of delalloc + * blocks. But the code in ext4_iomap_alloc() is careful to use + * zeroed/unwritten extents if this is possible; thus we won't leave + * uninitialized blocks in a file even if we didn't succeed in writing + * as much as we intended. */ - pos += size; - if (pos > i_size_read(inode)) - i_size_write(inode, pos); - - return 0; + WARN_ON_ONCE(i_size_read(inode) < READ_ONCE(EXT4_I(inode)->i_disksize)); + if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize)) + return size; + return ext4_handle_inode_extension(inode, pos, size); } static const struct iomap_dio_ops ext4_dio_write_ops = { @@ -569,18 +537,20 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) return ext4_buffered_write_iter(iocb, from); } + /* + * Prevent inline data from being created since we are going to allocate + * blocks for DIO. We know the inode does not currently have inline data + * because ext4_should_use_dio() checked for it, but we have to clear + * the state flag before the write checks because a lock cycle could + * introduce races with other writers. + */ + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend, &unwritten, &dio_flags); if (ret <= 0) return ret; - /* - * Make sure inline data cannot be created anymore since we are going - * to allocate blocks for DIO. We know the inode does not have any - * inline data now because ext4_dio_supported() checked for that. - */ - ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); - offset = iocb->ki_pos; count = ret; @@ -606,9 +576,16 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) dio_flags, NULL, 0); if (ret == -ENOTBLK) ret = 0; - - if (extend) - ret = ext4_handle_inode_extension(inode, offset, ret, count); + if (extend) { + /* + * We always perform extending DIO write synchronously so by + * now the IO is completed and ext4_handle_inode_extension() + * was called. Cleanup the inode in case of error or race with + * writeback of delalloc blocks. + */ + WARN_ON_ONCE(ret == -EIOCBQUEUED); + ext4_inode_extension_cleanup(inode, ret); + } out: if (ilock_shared) @@ -689,8 +666,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from) ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops); - if (extend) - ret = ext4_handle_inode_extension(inode, offset, ret, count); + if (extend) { + ret = ext4_handle_inode_extension(inode, offset, ret); + ext4_inode_extension_cleanup(inode, ret); + } out: inode_unlock(inode); if (ret > 0) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 08cb5c0e0d51..a6838f54ae91 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -789,10 +789,22 @@ int ext4_get_block(struct inode *inode, sector_t iblock, int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { + int ret = 0; + ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n", inode->i_ino, create); - return _ext4_get_block(inode, iblock, bh_result, + ret = _ext4_get_block(inode, iblock, bh_result, EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT); + + /* + * If the buffer is marked unwritten, mark it as new to make sure it is + * zeroed out correctly in case of partial writes. Otherwise, there is + * a chance of stale data getting exposed. + */ + if (ret == 0 && buffer_unwritten(bh_result)) + set_buffer_new(bh_result); + + return ret; } /* Maximum number of blocks we map for direct IO at once. */ diff --git a/fs/ext4/mballoc-test.c b/fs/ext4/mballoc-test.c new file mode 100644 index 000000000000..f94901fd3835 --- /dev/null +++ b/fs/ext4/mballoc-test.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit test of ext4 multiblocks allocation. + */ + +#include +#include + +#include "ext4.h" + +struct mbt_grp_ctx { + struct buffer_head bitmap_bh; + /* desc and gd_bh are just the place holders for now */ + struct ext4_group_desc desc; + struct buffer_head gd_bh; +}; + +struct mbt_ctx { + struct mbt_grp_ctx *grp_ctx; +}; + +struct mbt_ext4_super_block { + struct super_block sb; + struct mbt_ctx mbt_ctx; +}; + +#define MBT_CTX(_sb) (&(container_of((_sb), struct mbt_ext4_super_block, sb)->mbt_ctx)) +#define MBT_GRP_CTX(_sb, _group) (&MBT_CTX(_sb)->grp_ctx[_group]) + +static struct super_block *mbt_ext4_alloc_super_block(void) +{ + struct ext4_super_block *es = kzalloc(sizeof(*es), GFP_KERNEL); + struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + struct mbt_ext4_super_block *fsb = kzalloc(sizeof(*fsb), GFP_KERNEL); + + if (fsb == NULL || sbi == NULL || es == NULL) + goto out; + + sbi->s_es = es; + fsb->sb.s_fs_info = sbi; + return &fsb->sb; + +out: + kfree(fsb); + kfree(sbi); + kfree(es); + return NULL; +} + +static void mbt_ext4_free_super_block(struct super_block *sb) +{ + struct mbt_ext4_super_block *fsb = + container_of(sb, struct mbt_ext4_super_block, sb); + struct ext4_sb_info *sbi = EXT4_SB(sb); + + kfree(sbi->s_es); + kfree(sbi); + kfree(fsb); +} + +struct mbt_ext4_block_layout { + unsigned char blocksize_bits; + unsigned int cluster_bits; + uint32_t blocks_per_group; + ext4_group_t group_count; + uint16_t desc_size; +}; + +static void mbt_init_sb_layout(struct super_block *sb, + struct mbt_ext4_block_layout *layout) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + + sb->s_blocksize = 1UL << layout->blocksize_bits; + sb->s_blocksize_bits = layout->blocksize_bits; + + sbi->s_groups_count = layout->group_count; + sbi->s_blocks_per_group = layout->blocks_per_group; + sbi->s_cluster_bits = layout->cluster_bits; + sbi->s_cluster_ratio = 1U << layout->cluster_bits; + sbi->s_clusters_per_group = layout->blocks_per_group >> + layout->cluster_bits; + sbi->s_desc_size = layout->desc_size; + + es->s_first_data_block = cpu_to_le32(0); + es->s_blocks_count_lo = cpu_to_le32(layout->blocks_per_group * + layout->group_count); +} + +static int mbt_grp_ctx_init(struct super_block *sb, + struct mbt_grp_ctx *grp_ctx) +{ + grp_ctx->bitmap_bh.b_data = kzalloc(EXT4_BLOCK_SIZE(sb), GFP_KERNEL); + if (grp_ctx->bitmap_bh.b_data == NULL) + return -ENOMEM; + + return 0; +} + +static void mbt_grp_ctx_release(struct mbt_grp_ctx *grp_ctx) +{ + kfree(grp_ctx->bitmap_bh.b_data); + grp_ctx->bitmap_bh.b_data = NULL; +} + +static void mbt_ctx_mark_used(struct super_block *sb, ext4_group_t group, + unsigned int start, unsigned int len) +{ + struct mbt_grp_ctx *grp_ctx = MBT_GRP_CTX(sb, group); + + mb_set_bits(grp_ctx->bitmap_bh.b_data, start, len); +} + +/* called after mbt_init_sb_layout */ +static int mbt_ctx_init(struct super_block *sb) +{ + struct mbt_ctx *ctx = MBT_CTX(sb); + ext4_group_t i, ngroups = ext4_get_groups_count(sb); + + ctx->grp_ctx = kcalloc(ngroups, sizeof(struct mbt_grp_ctx), + GFP_KERNEL); + if (ctx->grp_ctx == NULL) + return -ENOMEM; + + for (i = 0; i < ngroups; i++) + if (mbt_grp_ctx_init(sb, &ctx->grp_ctx[i])) + goto out; + + /* + * first data block(first cluster in first group) is used by + * metadata, mark it used to avoid to alloc data block at first + * block which will fail ext4_sb_block_valid check. + */ + mb_set_bits(ctx->grp_ctx[0].bitmap_bh.b_data, 0, 1); + + return 0; +out: + while (i-- > 0) + mbt_grp_ctx_release(&ctx->grp_ctx[i]); + kfree(ctx->grp_ctx); + return -ENOMEM; +} + +static void mbt_ctx_release(struct super_block *sb) +{ + struct mbt_ctx *ctx = MBT_CTX(sb); + ext4_group_t i, ngroups = ext4_get_groups_count(sb); + + for (i = 0; i < ngroups; i++) + mbt_grp_ctx_release(&ctx->grp_ctx[i]); + kfree(ctx->grp_ctx); +} + +static struct buffer_head * +ext4_read_block_bitmap_nowait_stub(struct super_block *sb, ext4_group_t block_group, + bool ignore_locked) +{ + struct mbt_grp_ctx *grp_ctx = MBT_GRP_CTX(sb, block_group); + + /* paired with brelse from caller of ext4_read_block_bitmap_nowait */ + get_bh(&grp_ctx->bitmap_bh); + return &grp_ctx->bitmap_bh; +} + +static int ext4_wait_block_bitmap_stub(struct super_block *sb, + ext4_group_t block_group, + struct buffer_head *bh) +{ + return 0; +} + +static struct ext4_group_desc * +ext4_get_group_desc_stub(struct super_block *sb, ext4_group_t block_group, + struct buffer_head **bh) +{ + struct mbt_grp_ctx *grp_ctx = MBT_GRP_CTX(sb, block_group); + + if (bh != NULL) + *bh = &grp_ctx->gd_bh; + + return &grp_ctx->desc; +} + +static int +ext4_mb_mark_context_stub(handle_t *handle, struct super_block *sb, bool state, + ext4_group_t group, ext4_grpblk_t blkoff, + ext4_grpblk_t len, int flags, + ext4_grpblk_t *ret_changed) +{ + struct mbt_grp_ctx *grp_ctx = MBT_GRP_CTX(sb, group); + struct buffer_head *bitmap_bh = &grp_ctx->bitmap_bh; + + if (state) + mb_set_bits(bitmap_bh->b_data, blkoff, len); + else + mb_clear_bits(bitmap_bh->b_data, blkoff, len); + + return 0; +} + +#define TEST_GOAL_GROUP 1 +static int mbt_kunit_init(struct kunit *test) +{ + struct mbt_ext4_block_layout *layout = + (struct mbt_ext4_block_layout *)(test->param_value); + struct super_block *sb; + int ret; + + sb = mbt_ext4_alloc_super_block(); + if (sb == NULL) + return -ENOMEM; + + mbt_init_sb_layout(sb, layout); + + ret = mbt_ctx_init(sb); + if (ret != 0) { + mbt_ext4_free_super_block(sb); + return ret; + } + + test->priv = sb; + kunit_activate_static_stub(test, + ext4_read_block_bitmap_nowait, + ext4_read_block_bitmap_nowait_stub); + kunit_activate_static_stub(test, + ext4_wait_block_bitmap, + ext4_wait_block_bitmap_stub); + kunit_activate_static_stub(test, + ext4_get_group_desc, + ext4_get_group_desc_stub); + kunit_activate_static_stub(test, + ext4_mb_mark_context, + ext4_mb_mark_context_stub); + return 0; +} + +static void mbt_kunit_exit(struct kunit *test) +{ + struct super_block *sb = (struct super_block *)test->priv; + + mbt_ctx_release(sb); + mbt_ext4_free_super_block(sb); +} + +static void test_new_blocks_simple(struct kunit *test) +{ + struct super_block *sb = (struct super_block *)test->priv; + struct inode inode = { .i_sb = sb, }; + struct ext4_allocation_request ar; + ext4_group_t i, goal_group = TEST_GOAL_GROUP; + int err = 0; + ext4_fsblk_t found; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + ar.inode = &inode; + + /* get block at goal */ + ar.goal = ext4_group_first_block_no(sb, goal_group); + found = ext4_mb_new_blocks_simple(&ar, &err); + KUNIT_ASSERT_EQ_MSG(test, ar.goal, found, + "failed to alloc block at goal, expected %llu found %llu", + ar.goal, found); + + /* get block after goal in goal group */ + ar.goal = ext4_group_first_block_no(sb, goal_group); + found = ext4_mb_new_blocks_simple(&ar, &err); + KUNIT_ASSERT_EQ_MSG(test, ar.goal + EXT4_C2B(sbi, 1), found, + "failed to alloc block after goal in goal group, expected %llu found %llu", + ar.goal + 1, found); + + /* get block after goal group */ + mbt_ctx_mark_used(sb, goal_group, 0, EXT4_CLUSTERS_PER_GROUP(sb)); + ar.goal = ext4_group_first_block_no(sb, goal_group); + found = ext4_mb_new_blocks_simple(&ar, &err); + KUNIT_ASSERT_EQ_MSG(test, + ext4_group_first_block_no(sb, goal_group + 1), found, + "failed to alloc block after goal group, expected %llu found %llu", + ext4_group_first_block_no(sb, goal_group + 1), found); + + /* get block before goal group */ + for (i = goal_group; i < ext4_get_groups_count(sb); i++) + mbt_ctx_mark_used(sb, i, 0, EXT4_CLUSTERS_PER_GROUP(sb)); + ar.goal = ext4_group_first_block_no(sb, goal_group); + found = ext4_mb_new_blocks_simple(&ar, &err); + KUNIT_ASSERT_EQ_MSG(test, + ext4_group_first_block_no(sb, 0) + EXT4_C2B(sbi, 1), found, + "failed to alloc block before goal group, expected %llu found %llu", + ext4_group_first_block_no(sb, 0 + EXT4_C2B(sbi, 1)), found); + + /* no block available, fail to allocate block */ + for (i = 0; i < ext4_get_groups_count(sb); i++) + mbt_ctx_mark_used(sb, i, 0, EXT4_CLUSTERS_PER_GROUP(sb)); + ar.goal = ext4_group_first_block_no(sb, goal_group); + found = ext4_mb_new_blocks_simple(&ar, &err); + KUNIT_ASSERT_NE_MSG(test, err, 0, + "unexpectedly get block when no block is available"); +} + +static const struct mbt_ext4_block_layout mbt_test_layouts[] = { + { + .blocksize_bits = 10, + .cluster_bits = 3, + .blocks_per_group = 8192, + .group_count = 4, + .desc_size = 64, + }, + { + .blocksize_bits = 12, + .cluster_bits = 3, + .blocks_per_group = 8192, + .group_count = 4, + .desc_size = 64, + }, + { + .blocksize_bits = 16, + .cluster_bits = 3, + .blocks_per_group = 8192, + .group_count = 4, + .desc_size = 64, + }, +}; + +static void mbt_show_layout(const struct mbt_ext4_block_layout *layout, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "block_bits=%d cluster_bits=%d " + "blocks_per_group=%d group_count=%d desc_size=%d\n", + layout->blocksize_bits, layout->cluster_bits, + layout->blocks_per_group, layout->group_count, + layout->desc_size); +} +KUNIT_ARRAY_PARAM(mbt_layouts, mbt_test_layouts, mbt_show_layout); + +static struct kunit_case mbt_test_cases[] = { + KUNIT_CASE_PARAM(test_new_blocks_simple, mbt_layouts_gen_params), + {} +}; + +static struct kunit_suite mbt_test_suite = { + .name = "ext4_mballoc_test", + .init = mbt_kunit_init, + .exit = mbt_kunit_exit, + .test_cases = mbt_test_cases, +}; + +kunit_test_suites(&mbt_test_suite); + +MODULE_LICENSE("GPL"); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 1e599305d85f..454d5612641e 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -18,6 +18,7 @@ #include #include #include +#include /* * MUSTDO: @@ -417,8 +418,6 @@ static const char * const ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = { static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); -static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, - ext4_group_t group); static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac); static bool ext4_mb_good_group(struct ext4_allocation_context *ac, @@ -1361,17 +1360,17 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) * We place the buddy block and bitmap block * close together */ + grinfo = ext4_get_group_info(sb, group); + if (!grinfo) { + err = -EFSCORRUPTED; + goto out; + } if ((first_block + i) & 1) { /* this is block of buddy */ BUG_ON(incore == NULL); mb_debug(sb, "put buddy for group %u in page %lu/%x\n", group, page->index, i * blocksize); trace_ext4_mb_buddy_bitmap_load(sb, group); - grinfo = ext4_get_group_info(sb, group); - if (!grinfo) { - err = -EFSCORRUPTED; - goto out; - } grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, sizeof(*grinfo->bb_counters) * @@ -1398,7 +1397,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) /* mark all preallocated blks used in in-core bitmap */ ext4_mb_generate_from_pa(sb, data, group); - ext4_mb_generate_from_freelist(sb, data, group); + WARN_ON_ONCE(!RB_EMPTY_ROOT(&grinfo->bb_free_root)); ext4_unlock_group(sb, group); /* set incore so that the buddy information can be @@ -3631,7 +3630,8 @@ int ext4_mb_init(struct super_block *sb) spin_lock_init(&sbi->s_md_lock); sbi->s_mb_free_pending = 0; - INIT_LIST_HEAD(&sbi->s_freed_data_list); + INIT_LIST_HEAD(&sbi->s_freed_data_list[0]); + INIT_LIST_HEAD(&sbi->s_freed_data_list[1]); INIT_LIST_HEAD(&sbi->s_discard_list); INIT_WORK(&sbi->s_discard_work, ext4_discard_work); atomic_set(&sbi->s_retry_alloc_pending, 0); @@ -3883,19 +3883,10 @@ void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid) struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_free_data *entry, *tmp; LIST_HEAD(freed_data_list); - struct list_head *cut_pos = NULL; + struct list_head *s_freed_head = &sbi->s_freed_data_list[commit_tid & 1]; bool wake; - spin_lock(&sbi->s_md_lock); - list_for_each_entry(entry, &sbi->s_freed_data_list, efd_list) { - if (entry->efd_tid != commit_tid) - break; - cut_pos = &entry->efd_list; - } - if (cut_pos) - list_cut_position(&freed_data_list, &sbi->s_freed_data_list, - cut_pos); - spin_unlock(&sbi->s_md_lock); + list_replace_init(s_freed_head, &freed_data_list); list_for_each_entry(entry, &freed_data_list, efd_list) ext4_free_data_in_buddy(sb, entry); @@ -3953,6 +3944,111 @@ void ext4_exit_mballoc(void) ext4_groupinfo_destroy_slabs(); } +#define EXT4_MB_BITMAP_MARKED_CHECK 0x0001 +#define EXT4_MB_SYNC_UPDATE 0x0002 +static int +ext4_mb_mark_context(handle_t *handle, struct super_block *sb, bool state, + ext4_group_t group, ext4_grpblk_t blkoff, + ext4_grpblk_t len, int flags, ext4_grpblk_t *ret_changed) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct buffer_head *bitmap_bh = NULL; + struct ext4_group_desc *gdp; + struct buffer_head *gdp_bh; + int err; + unsigned int i, already, changed = len; + + KUNIT_STATIC_STUB_REDIRECT(ext4_mb_mark_context, + handle, sb, state, group, blkoff, len, + flags, ret_changed); + + if (ret_changed) + *ret_changed = 0; + bitmap_bh = ext4_read_block_bitmap(sb, group); + if (IS_ERR(bitmap_bh)) + return PTR_ERR(bitmap_bh); + + if (handle) { + BUFFER_TRACE(bitmap_bh, "getting write access"); + err = ext4_journal_get_write_access(handle, sb, bitmap_bh, + EXT4_JTR_NONE); + if (err) + goto out_err; + } + + err = -EIO; + gdp = ext4_get_group_desc(sb, group, &gdp_bh); + if (!gdp) + goto out_err; + + if (handle) { + BUFFER_TRACE(gdp_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, gdp_bh, + EXT4_JTR_NONE); + if (err) + goto out_err; + } + + ext4_lock_group(sb, group); + if (ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { + gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); + ext4_free_group_clusters_set(sb, gdp, + ext4_free_clusters_after_init(sb, group, gdp)); + } + + if (flags & EXT4_MB_BITMAP_MARKED_CHECK) { + already = 0; + for (i = 0; i < len; i++) + if (mb_test_bit(blkoff + i, bitmap_bh->b_data) == + state) + already++; + changed = len - already; + } + + if (state) { + mb_set_bits(bitmap_bh->b_data, blkoff, len); + ext4_free_group_clusters_set(sb, gdp, + ext4_free_group_clusters(sb, gdp) - changed); + } else { + mb_clear_bits(bitmap_bh->b_data, blkoff, len); + ext4_free_group_clusters_set(sb, gdp, + ext4_free_group_clusters(sb, gdp) + changed); + } + + ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); + ext4_group_desc_csum_set(sb, group, gdp); + ext4_unlock_group(sb, group); + if (ret_changed) + *ret_changed = changed; + + if (sbi->s_log_groups_per_flex) { + ext4_group_t flex_group = ext4_flex_group(sbi, group); + struct flex_groups *fg = sbi_array_rcu_deref(sbi, + s_flex_groups, flex_group); + + if (state) + atomic64_sub(changed, &fg->free_clusters); + else + atomic64_add(changed, &fg->free_clusters); + } + + err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); + if (err) + goto out_err; + err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh); + if (err) + goto out_err; + + if (flags & EXT4_MB_SYNC_UPDATE) { + sync_dirty_buffer(bitmap_bh); + sync_dirty_buffer(gdp_bh); + } + +out_err: + brelse(bitmap_bh); + return err; +} /* * Check quota and mark chosen space (ac->ac_b_ex) non-free in bitmaps @@ -3962,13 +4058,13 @@ static noinline_for_stack int ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, handle_t *handle, unsigned int reserv_clstrs) { - struct buffer_head *bitmap_bh = NULL; struct ext4_group_desc *gdp; - struct buffer_head *gdp_bh; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block; int err, len; + int flags = 0; + ext4_grpblk_t changed; BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(ac->ac_b_ex.fe_len <= 0); @@ -3976,32 +4072,13 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, sb = ac->ac_sb; sbi = EXT4_SB(sb); - bitmap_bh = ext4_read_block_bitmap(sb, ac->ac_b_ex.fe_group); - if (IS_ERR(bitmap_bh)) { - return PTR_ERR(bitmap_bh); - } - - BUFFER_TRACE(bitmap_bh, "getting write access"); - err = ext4_journal_get_write_access(handle, sb, bitmap_bh, - EXT4_JTR_NONE); - if (err) - goto out_err; - - err = -EIO; - gdp = ext4_get_group_desc(sb, ac->ac_b_ex.fe_group, &gdp_bh); + gdp = ext4_get_group_desc(sb, ac->ac_b_ex.fe_group, NULL); if (!gdp) - goto out_err; - + return -EIO; ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group, ext4_free_group_clusters(sb, gdp)); - BUFFER_TRACE(gdp_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, sb, gdp_bh, EXT4_JTR_NONE); - if (err) - goto out_err; - block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); - len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len); if (!ext4_inode_block_valid(ac->ac_inode, block, len)) { ext4_error(sb, "Allocating blocks %llu-%llu which overlap " @@ -4010,41 +4087,29 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, * Fix the bitmap and return EFSCORRUPTED * We leak some of the blocks here. */ - ext4_lock_group(sb, ac->ac_b_ex.fe_group); - mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, - ac->ac_b_ex.fe_len); - ext4_unlock_group(sb, ac->ac_b_ex.fe_group); - err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); + err = ext4_mb_mark_context(handle, sb, true, + ac->ac_b_ex.fe_group, + ac->ac_b_ex.fe_start, + ac->ac_b_ex.fe_len, + 0, NULL); if (!err) err = -EFSCORRUPTED; - goto out_err; + return err; } - ext4_lock_group(sb, ac->ac_b_ex.fe_group); #ifdef AGGRESSIVE_CHECK - { - int i; - for (i = 0; i < ac->ac_b_ex.fe_len; i++) { - BUG_ON(mb_test_bit(ac->ac_b_ex.fe_start + i, - bitmap_bh->b_data)); - } - } + flags |= EXT4_MB_BITMAP_MARKED_CHECK; #endif - mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, - ac->ac_b_ex.fe_len); - if (ext4_has_group_desc_csum(sb) && - (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { - gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); - ext4_free_group_clusters_set(sb, gdp, - ext4_free_clusters_after_init(sb, - ac->ac_b_ex.fe_group, gdp)); - } - len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len; - ext4_free_group_clusters_set(sb, gdp, len); - ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); - ext4_group_desc_csum_set(sb, ac->ac_b_ex.fe_group, gdp); + err = ext4_mb_mark_context(handle, sb, true, ac->ac_b_ex.fe_group, + ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, + flags, &changed); - ext4_unlock_group(sb, ac->ac_b_ex.fe_group); + if (err && changed == 0) + return err; + +#ifdef AGGRESSIVE_CHECK + BUG_ON(changed != ac->ac_b_ex.fe_len); +#endif percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len); /* * Now reduce the dirty block count also. Should not go negative @@ -4054,21 +4119,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); - if (sbi->s_log_groups_per_flex) { - ext4_group_t flex_group = ext4_flex_group(sbi, - ac->ac_b_ex.fe_group); - atomic64_sub(ac->ac_b_ex.fe_len, - &sbi_array_rcu_deref(sbi, s_flex_groups, - flex_group)->free_clusters); - } - - err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); - if (err) - goto out_err; - err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh); - -out_err: - brelse(bitmap_bh); return err; } @@ -4077,17 +4127,13 @@ out_err: * blocks in bitmaps and update counters. */ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, - int len, int state) + int len, bool state) { - struct buffer_head *bitmap_bh = NULL; - struct ext4_group_desc *gdp; - struct buffer_head *gdp_bh; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; ext4_grpblk_t blkoff; - int i, err = 0; - int already; - unsigned int clen, clen_changed, thisgrp_len; + int err = 0; + unsigned int clen, thisgrp_len; while (len > 0) { ext4_get_group_no_and_offset(sb, block, &group, &blkoff); @@ -4108,80 +4154,21 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, ext4_error(sb, "Marking blocks in system zone - " "Block = %llu, len = %u", block, thisgrp_len); - bitmap_bh = NULL; break; } - bitmap_bh = ext4_read_block_bitmap(sb, group); - if (IS_ERR(bitmap_bh)) { - err = PTR_ERR(bitmap_bh); - bitmap_bh = NULL; - break; - } - - err = -EIO; - gdp = ext4_get_group_desc(sb, group, &gdp_bh); - if (!gdp) - break; - - ext4_lock_group(sb, group); - already = 0; - for (i = 0; i < clen; i++) - if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == - !state) - already++; - - clen_changed = clen - already; - if (state) - mb_set_bits(bitmap_bh->b_data, blkoff, clen); - else - mb_clear_bits(bitmap_bh->b_data, blkoff, clen); - if (ext4_has_group_desc_csum(sb) && - (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { - gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); - ext4_free_group_clusters_set(sb, gdp, - ext4_free_clusters_after_init(sb, group, gdp)); - } - if (state) - clen = ext4_free_group_clusters(sb, gdp) - clen_changed; - else - clen = ext4_free_group_clusters(sb, gdp) + clen_changed; - - ext4_free_group_clusters_set(sb, gdp, clen); - ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); - ext4_group_desc_csum_set(sb, group, gdp); - - ext4_unlock_group(sb, group); - - if (sbi->s_log_groups_per_flex) { - ext4_group_t flex_group = ext4_flex_group(sbi, group); - struct flex_groups *fg = sbi_array_rcu_deref(sbi, - s_flex_groups, flex_group); - - if (state) - atomic64_sub(clen_changed, &fg->free_clusters); - else - atomic64_add(clen_changed, &fg->free_clusters); - - } - - err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); - if (err) - break; - sync_dirty_buffer(bitmap_bh); - err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); - sync_dirty_buffer(gdp_bh); + err = ext4_mb_mark_context(NULL, sb, state, + group, blkoff, clen, + EXT4_MB_BITMAP_MARKED_CHECK | + EXT4_MB_SYNC_UPDATE, + NULL); if (err) break; block += thisgrp_len; len -= thisgrp_len; - brelse(bitmap_bh); BUG_ON(len < 0); } - - if (err) - brelse(bitmap_bh); } /* @@ -4958,31 +4945,6 @@ try_group_pa: return false; } -/* - * the function goes through all block freed in the group - * but not yet committed and marks them used in in-core bitmap. - * buddy must be generated from this bitmap - * Need to be called with the ext4 group lock held - */ -static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, - ext4_group_t group) -{ - struct rb_node *n; - struct ext4_group_info *grp; - struct ext4_free_data *entry; - - grp = ext4_get_group_info(sb, group); - if (!grp) - return; - n = rb_first(&(grp->bb_free_root)); - - while (n) { - entry = rb_entry(n, struct ext4_free_data, efd_node); - mb_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count); - n = rb_next(n); - } -} - /* * the function goes through all preallocation in this group and marks them * used in in-core bitmap. buddy must be generated from this bitmap @@ -6130,7 +6092,7 @@ ext4_mb_new_blocks_simple(struct ext4_allocation_request *ar, int *errp) } block = ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, i); - ext4_mb_mark_bb(sb, block, 1, 1); + ext4_mb_mark_bb(sb, block, 1, true); ar->len = 1; return block; @@ -6378,7 +6340,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, } spin_lock(&sbi->s_md_lock); - list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list); + list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list[new_entry->efd_tid & 1]); sbi->s_mb_free_pending += clusters; spin_unlock(&sbi->s_md_lock); } @@ -6386,43 +6348,15 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, unsigned long count) { - struct buffer_head *bitmap_bh; struct super_block *sb = inode->i_sb; - struct ext4_group_desc *gdp; - struct buffer_head *gdp_bh; ext4_group_t group; ext4_grpblk_t blkoff; - int already_freed = 0, err, i; ext4_get_group_no_and_offset(sb, block, &group, &blkoff); - bitmap_bh = ext4_read_block_bitmap(sb, group); - if (IS_ERR(bitmap_bh)) { - pr_warn("Failed to read block bitmap\n"); - return; - } - gdp = ext4_get_group_desc(sb, group, &gdp_bh); - if (!gdp) - goto err_out; - - for (i = 0; i < count; i++) { - if (!mb_test_bit(blkoff + i, bitmap_bh->b_data)) - already_freed++; - } - mb_clear_bits(bitmap_bh->b_data, blkoff, count); - err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); - if (err) - goto err_out; - ext4_free_group_clusters_set( - sb, gdp, ext4_free_group_clusters(sb, gdp) + - count - already_freed); - ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); - ext4_group_desc_csum_set(sb, group, gdp); - ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); - sync_dirty_buffer(bitmap_bh); - sync_dirty_buffer(gdp_bh); - -err_out: - brelse(bitmap_bh); + ext4_mb_mark_context(NULL, sb, false, group, blkoff, count, + EXT4_MB_BITMAP_MARKED_CHECK | + EXT4_MB_SYNC_UPDATE, + NULL); } /** @@ -6438,19 +6372,17 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, ext4_fsblk_t block, unsigned long count, int flags) { - struct buffer_head *bitmap_bh = NULL; struct super_block *sb = inode->i_sb; - struct ext4_group_desc *gdp; struct ext4_group_info *grp; unsigned int overflow; ext4_grpblk_t bit; - struct buffer_head *gd_bh; ext4_group_t block_group; struct ext4_sb_info *sbi; struct ext4_buddy e4b; unsigned int count_clusters; int err = 0; - int ret; + int mark_flags = 0; + ext4_grpblk_t changed; sbi = EXT4_SB(sb); @@ -6459,7 +6391,7 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ - goto error_return; + goto error_out; } flags |= EXT4_FREE_BLOCKS_VALIDATED; @@ -6483,55 +6415,35 @@ do_more: flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } count_clusters = EXT4_NUM_B2C(sbi, count); - bitmap_bh = ext4_read_block_bitmap(sb, block_group); - if (IS_ERR(bitmap_bh)) { - err = PTR_ERR(bitmap_bh); - bitmap_bh = NULL; - goto error_return; - } - gdp = ext4_get_group_desc(sb, block_group, &gd_bh); - if (!gdp) { - err = -EIO; - goto error_return; - } - - if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && - !ext4_inode_block_valid(inode, block, count)) { - ext4_error(sb, "Freeing blocks in system zone - " - "Block = %llu, count = %lu", block, count); - /* err = 0. ext4_std_error should be a no op */ - goto error_return; - } - - BUFFER_TRACE(bitmap_bh, "getting write access"); - err = ext4_journal_get_write_access(handle, sb, bitmap_bh, - EXT4_JTR_NONE); - if (err) - goto error_return; - - /* - * We are about to modify some metadata. Call the journal APIs - * to unshare ->b_data if a currently-committing transaction is - * using it - */ - BUFFER_TRACE(gd_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, sb, gd_bh, EXT4_JTR_NONE); - if (err) - goto error_return; -#ifdef AGGRESSIVE_CHECK - { - int i; - for (i = 0; i < count_clusters; i++) - BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data)); - } -#endif trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters); /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */ err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) - goto error_return; + goto error_out; + + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && + !ext4_inode_block_valid(inode, block, count)) { + ext4_error(sb, "Freeing blocks in system zone - " + "Block = %llu, count = %lu", block, count); + /* err = 0. ext4_std_error should be a no op */ + goto error_clean; + } + +#ifdef AGGRESSIVE_CHECK + mark_flags |= EXT4_MB_BITMAP_MARKED_CHECK; +#endif + err = ext4_mb_mark_context(handle, sb, false, block_group, bit, + count_clusters, mark_flags, &changed); + + + if (err && changed == 0) + goto error_clean; + +#ifdef AGGRESSIVE_CHECK + BUG_ON(changed != count_clusters); +#endif /* * We need to make sure we don't reuse the freed block until after the @@ -6555,13 +6467,8 @@ do_more: new_entry->efd_tid = handle->h_transaction->t_tid; ext4_lock_group(sb, block_group); - mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); ext4_mb_free_metadata(handle, &e4b, new_entry); } else { - /* need to update group_info->bb_free and bitmap - * with group lock held. generate_buddy look at - * them with group lock_held - */ if (test_opt(sb, DISCARD)) { err = ext4_issue_discard(sb, block_group, bit, count_clusters, NULL); @@ -6574,23 +6481,11 @@ do_more: EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info); ext4_lock_group(sb, block_group); - mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); mb_free_blocks(inode, &e4b, bit, count_clusters); } - ret = ext4_free_group_clusters(sb, gdp) + count_clusters; - ext4_free_group_clusters_set(sb, gdp, ret); - ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); - ext4_group_desc_csum_set(sb, block_group, gdp); ext4_unlock_group(sb, block_group); - if (sbi->s_log_groups_per_flex) { - ext4_group_t flex_group = ext4_flex_group(sbi, block_group); - atomic64_add(count_clusters, - &sbi_array_rcu_deref(sbi, s_flex_groups, - flex_group)->free_clusters); - } - /* * on a bigalloc file system, defer the s_freeclusters_counter * update to the caller (ext4_remove_space and friends) so they @@ -6603,28 +6498,18 @@ do_more: count_clusters); } - ext4_mb_unload_buddy(&e4b); - - /* We dirtied the bitmap block */ - BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); - err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); - - /* And the group descriptor block */ - BUFFER_TRACE(gd_bh, "dirtied group descriptor block"); - ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh); - if (!err) - err = ret; - if (overflow && !err) { block += count; count = overflow; - put_bh(bitmap_bh); + ext4_mb_unload_buddy(&e4b); /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; goto do_more; } -error_return: - brelse(bitmap_bh); + +error_clean: + ext4_mb_unload_buddy(&e4b); +error_out: ext4_std_error(sb, err); } @@ -6742,23 +6627,19 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count) { - struct buffer_head *bitmap_bh = NULL; - struct buffer_head *gd_bh; ext4_group_t block_group; ext4_grpblk_t bit; - unsigned int i; - struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_buddy e4b; - int err = 0, ret, free_clusters_count; - ext4_grpblk_t clusters_freed; + int err = 0; ext4_fsblk_t first_cluster = EXT4_B2C(sbi, block); ext4_fsblk_t last_cluster = EXT4_B2C(sbi, block + count - 1); unsigned long cluster_count = last_cluster - first_cluster + 1; + ext4_grpblk_t changed; ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1); - if (count == 0) + if (cluster_count == 0) return 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); @@ -6770,99 +6651,39 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_warning(sb, "too many blocks added to group %u", block_group); err = -EINVAL; - goto error_return; + goto error_out; } - bitmap_bh = ext4_read_block_bitmap(sb, block_group); - if (IS_ERR(bitmap_bh)) { - err = PTR_ERR(bitmap_bh); - bitmap_bh = NULL; - goto error_return; - } - - desc = ext4_get_group_desc(sb, block_group, &gd_bh); - if (!desc) { - err = -EIO; - goto error_return; - } + err = ext4_mb_load_buddy(sb, block_group, &e4b); + if (err) + goto error_out; if (!ext4_sb_block_valid(sb, NULL, block, count)) { ext4_error(sb, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); err = -EINVAL; - goto error_return; + goto error_clean; } - BUFFER_TRACE(bitmap_bh, "getting write access"); - err = ext4_journal_get_write_access(handle, sb, bitmap_bh, - EXT4_JTR_NONE); - if (err) - goto error_return; + err = ext4_mb_mark_context(handle, sb, false, block_group, bit, + cluster_count, EXT4_MB_BITMAP_MARKED_CHECK, + &changed); + if (err && changed == 0) + goto error_clean; - /* - * We are about to modify some metadata. Call the journal APIs - * to unshare ->b_data if a currently-committing transaction is - * using it - */ - BUFFER_TRACE(gd_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, sb, gd_bh, EXT4_JTR_NONE); - if (err) - goto error_return; + if (changed != cluster_count) + ext4_error(sb, "bit already cleared in group %u", block_group); - for (i = 0, clusters_freed = 0; i < cluster_count; i++) { - BUFFER_TRACE(bitmap_bh, "clear bit"); - if (!mb_test_bit(bit + i, bitmap_bh->b_data)) { - ext4_error(sb, "bit already cleared for block %llu", - (ext4_fsblk_t)(block + i)); - BUFFER_TRACE(bitmap_bh, "bit already cleared"); - } else { - clusters_freed++; - } - } - - err = ext4_mb_load_buddy(sb, block_group, &e4b); - if (err) - goto error_return; - - /* - * need to update group_info->bb_free and bitmap - * with group lock held. generate_buddy look at - * them with group lock_held - */ ext4_lock_group(sb, block_group); - mb_clear_bits(bitmap_bh->b_data, bit, cluster_count); mb_free_blocks(NULL, &e4b, bit, cluster_count); - free_clusters_count = clusters_freed + - ext4_free_group_clusters(sb, desc); - ext4_free_group_clusters_set(sb, desc, free_clusters_count); - ext4_block_bitmap_csum_set(sb, desc, bitmap_bh); - ext4_group_desc_csum_set(sb, block_group, desc); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, - clusters_freed); - - if (sbi->s_log_groups_per_flex) { - ext4_group_t flex_group = ext4_flex_group(sbi, block_group); - atomic64_add(clusters_freed, - &sbi_array_rcu_deref(sbi, s_flex_groups, - flex_group)->free_clusters); - } + changed); +error_clean: ext4_mb_unload_buddy(&e4b); - - /* We dirtied the bitmap block */ - BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); - err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); - - /* And the group descriptor block */ - BUFFER_TRACE(gd_bh, "dirtied group descriptor block"); - ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh); - if (!err) - err = ret; - -error_return: - brelse(bitmap_bh); +error_out: ext4_std_error(sb, err); return err; } @@ -7170,3 +6991,7 @@ out_unload: return error; } + +#ifdef CONFIG_EXT4_KUNIT_TESTS +#include "mballoc-test.c" +#endif diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 057d74467293..d252935f9c8a 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2280,8 +2280,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, top = data2 + len; while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) { if (ext4_check_dir_entry(dir, NULL, de, bh2, data2, len, - (data2 + (blocksize - csum_size) - - (char *) de))) { + (char *)de - data2)) { brelse(bh2); brelse(bh); return -EFSCORRUPTED; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 0361c20910de..4fe061edefdd 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -10,8 +10,6 @@ */ -#define EXT4FS_DEBUG - #include #include #include @@ -57,7 +55,7 @@ int ext4_resize_begin(struct super_block *sb) * If the reserved GDT blocks is non-zero, the resize_inode feature * should always be set. */ - if (EXT4_SB(sb)->s_es->s_reserved_gdt_blocks && + if (sbi->s_es->s_reserved_gdt_blocks && !ext4_has_feature_resize_inode(sb)) { ext4_error(sb, "resize_inode disabled but reserved GDT blocks non-zero"); return -EFSCORRUPTED; @@ -69,9 +67,9 @@ int ext4_resize_begin(struct super_block *sb) * bad time to do it anyways. */ if (EXT4_B2C(sbi, sbi->s_sbh->b_blocknr) != - le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) { + le32_to_cpu(sbi->s_es->s_first_data_block)) { ext4_warning(sb, "won't resize using backup superblock at %llu", - (unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr); + (unsigned long long)sbi->s_sbh->b_blocknr); return -EPERM; } @@ -79,7 +77,7 @@ int ext4_resize_begin(struct super_block *sb) * We are not allowed to do online-resizing on a filesystem mounted * with error, because it can destroy the filesystem easily. */ - if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { + if (sbi->s_mount_state & EXT4_ERROR_FS) { ext4_warning(sb, "There are errors in the filesystem, " "so online resizing is not allowed"); return -EPERM; @@ -91,7 +89,7 @@ int ext4_resize_begin(struct super_block *sb) } if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING, - &EXT4_SB(sb)->s_ext4_flags)) + &sbi->s_ext4_flags)) ret = -EBUSY; return ret; @@ -106,18 +104,6 @@ int ext4_resize_end(struct super_block *sb, bool update_backups) return 0; } -static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb, - ext4_group_t group) { - return (group >> EXT4_DESC_PER_BLOCK_BITS(sb)) << - EXT4_DESC_PER_BLOCK_BITS(sb); -} - -static ext4_fsblk_t ext4_meta_bg_first_block_no(struct super_block *sb, - ext4_group_t group) { - group = ext4_meta_bg_first_group(sb, group); - return ext4_group_first_block_no(sb, group); -} - static ext4_grpblk_t ext4_group_overhead_blocks(struct super_block *sb, ext4_group_t group) { ext4_grpblk_t overhead; @@ -154,8 +140,9 @@ static int verify_group_input(struct super_block *sb, overhead = ext4_group_overhead_blocks(sb, group); metaend = start + overhead; - input->free_clusters_count = free_blocks_count = - input->blocks_count - 2 - overhead - sbi->s_itb_per_group; + free_blocks_count = input->blocks_count - 2 - overhead - + sbi->s_itb_per_group; + input->free_clusters_count = EXT4_B2C(sbi, free_blocks_count); if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: adding %s group %u: %u blocks " @@ -460,8 +447,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, ext4_debug("mark clusters [%llu-%llu] used\n", first_cluster, last_cluster); - for (count2 = count; count > 0; - count -= count2, first_cluster += count2) { + for (; count > 0; count -= count2, first_cluster += count2) { ext4_fsblk_t start; struct buffer_head *bh; ext4_group_t group; @@ -560,13 +546,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb, if (meta_bg == 0 && !ext4_bg_has_super(sb, group)) goto handle_itb; - if (meta_bg == 1) { - ext4_group_t first_group; - first_group = ext4_meta_bg_first_group(sb, group); - if (first_group != group + 1 && - first_group != group + EXT4_DESC_PER_BLOCK(sb) - 1) - goto handle_itb; - } + if (meta_bg == 1) + goto handle_itb; block = start + ext4_bg_has_super(sb, group); /* Copy all of the GDT blocks into the backup in this group */ @@ -614,7 +595,7 @@ static int setup_new_flex_group_blocks(struct super_block *sb, } handle_itb: - /* Initialize group tables of the grop @group */ + /* Initialize group tables of the group @group */ if (!(bg_flags[i] & EXT4_BG_INODE_ZEROED)) goto handle_bb; @@ -704,16 +685,14 @@ handle_ib: block = start; } - if (count) { - err = set_flexbg_block_bitmap(sb, handle, - flex_gd, - EXT4_B2C(sbi, start), - EXT4_B2C(sbi, - start + count - - 1)); - if (err) - goto out; - } + err = set_flexbg_block_bitmap(sb, handle, + flex_gd, + EXT4_B2C(sbi, start), + EXT4_B2C(sbi, + start + count + - 1)); + if (err) + goto out; } out: @@ -952,7 +931,13 @@ errout: } /* - * add_new_gdb_meta_bg is the sister of add_new_gdb. + * If there is no available space in the existing block group descriptors for + * the new block group and there are no reserved block group descriptors, then + * the meta_bg feature will get enabled, and es->s_first_meta_bg will get set + * to the first block group that is managed using meta_bg and s_first_meta_bg + * must be a multiple of EXT4_DESC_PER_BLOCK(sb). + * This function will be called when first group of meta_bg is added to bring + * new group descriptors block of new added meta_bg. */ static int add_new_gdb_meta_bg(struct super_block *sb, handle_t *handle, ext4_group_t group) { @@ -962,8 +947,8 @@ static int add_new_gdb_meta_bg(struct super_block *sb, unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb); int err; - gdblock = ext4_meta_bg_first_block_no(sb, group) + - ext4_bg_has_super(sb, group); + gdblock = ext4_group_first_block_no(sb, group) + + ext4_bg_has_super(sb, group); gdb_bh = ext4_sb_bread(sb, gdblock, 0); if (IS_ERR(gdb_bh)) return PTR_ERR(gdb_bh); @@ -1087,9 +1072,6 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, for (i = 0; i < reserved_gdb; i++) { int err2; data = (__le32 *)primary[i]->b_data; - /* printk("reserving backup %lu[%u] = %lu\n", - primary[i]->b_blocknr, gdbackups, - blk + primary[i]->b_blocknr); */ data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr); err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]); if (!err) @@ -1191,8 +1173,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, ext4_group_first_block_no(sb, group)); BUFFER_TRACE(bh, "get_write_access"); if ((err = ext4_journal_get_write_access(handle, sb, bh, - EXT4_JTR_NONE))) + EXT4_JTR_NONE))) { + brelse(bh); break; + } lock_buffer(bh); memcpy(bh->b_data, data, size); if (rest) @@ -1601,7 +1585,8 @@ exit_journal: int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); int meta_bg = ext4_has_feature_meta_bg(sb); - sector_t old_gdb = 0; + sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - + ext4_group_first_block_no(sb, 0); update_backups(sb, ext4_group_first_block_no(sb, 0), (char *)es, sizeof(struct ext4_super_block), 0); @@ -1610,11 +1595,8 @@ exit_journal: gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, gdb_num); - if (old_gdb == gdb_bh->b_blocknr) - continue; - update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data, - gdb_bh->b_size, meta_bg); - old_gdb = gdb_bh->b_blocknr; + update_backups(sb, gdb_bh->b_blocknr - padding_blocks, + gdb_bh->b_data, gdb_bh->b_size, meta_bg); } } exit: @@ -1980,9 +1962,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) errout: ret = ext4_journal_stop(handle); - if (!err) - err = ret; - return ret; + return err ? err : ret; invalid_resize_inode: ext4_error(sb, "corrupted/inconsistent resize inode"); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 42a44990d99c..77e2b694c7d5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -768,7 +768,8 @@ static void update_super_work(struct work_struct *work) */ if (!sb_rdonly(sbi->s_sb) && journal) { struct buffer_head *sbh = sbi->s_sbh; - bool call_notify_err; + bool call_notify_err = false; + handle = jbd2_journal_start(journal, 1); if (IS_ERR(handle)) goto write_directly; @@ -6444,6 +6445,7 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) struct ext4_mount_options old_opts; ext4_group_t g; int err = 0; + int alloc_ctx; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; @@ -6484,7 +6486,16 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) } + /* + * Changing the DIOREAD_NOLOCK or DELALLOC mount options may cause + * two calls to ext4_should_dioread_nolock() to return inconsistent + * values, triggering WARN_ON in ext4_add_complete_io(). we grab + * here s_writepages_rwsem to avoid race between writepages ops and + * remount. + */ + alloc_ctx = ext4_writepages_down_write(sb); ext4_apply_options(fc, sb); + ext4_writepages_up_write(sb, alloc_ctx); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { @@ -6702,6 +6713,8 @@ restore_opts: if (sb_rdonly(sb) && !(old_sb_flags & SB_RDONLY) && sb_any_quota_suspended(sb)) dquot_resume(sb, -1); + + alloc_ctx = ext4_writepages_down_write(sb); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -6710,6 +6723,8 @@ restore_opts: sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; + ext4_writepages_up_write(sb, alloc_ctx); + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index c269a7d29a46..01f744cb97a4 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -289,6 +289,8 @@ int jbd2_journal_recover(journal_t *journal) journal_superblock_t * sb; struct recovery_info info; + errseq_t wb_err; + struct address_space *mapping; memset(&info, 0, sizeof(info)); sb = journal->j_superblock; @@ -306,6 +308,9 @@ int jbd2_journal_recover(journal_t *journal) return 0; } + wb_err = 0; + mapping = journal->j_fs_dev->bd_inode->i_mapping; + errseq_check_and_advance(&mapping->wb_err, &wb_err); err = do_one_pass(journal, &info, PASS_SCAN); if (!err) err = do_one_pass(journal, &info, PASS_REVOKE); @@ -327,6 +332,9 @@ int jbd2_journal_recover(journal_t *journal) jbd2_journal_clear_revoke(journal); err2 = sync_blockdev(journal->j_fs_dev); + if (!err) + err = err2; + err2 = errseq_check_and_advance(&mapping->wb_err, &wb_err); if (!err) err = err2; /* Make sure all replayed data is on permanent storage */ @@ -632,7 +640,7 @@ static int do_one_pass(journal_t *journal, success = err; printk(KERN_ERR "JBD2: IO error %d recovering " - "block %ld in log\n", + "block %lu in log\n", err, io_block); } else { unsigned long long blocknr; @@ -661,7 +669,8 @@ static int do_one_pass(journal_t *journal, printk(KERN_ERR "JBD2: Invalid " "checksum recovering " "data block %llu in " - "log\n", blocknr); + "journal block %lu\n", + blocknr, io_block); block_error = 1; goto skip_write; } diff --git a/fs/jfs/jfs_dinode.h b/fs/jfs/jfs_dinode.h index 6b231d0d0071..603aae17a693 100644 --- a/fs/jfs/jfs_dinode.h +++ b/fs/jfs/jfs_dinode.h @@ -96,7 +96,7 @@ struct dinode { #define di_gengen u._file._u1._imap._gengen union { - xtpage_t _xtroot; + xtroot_t _xtroot; struct { u8 unused[16]; /* 16: */ dxd_t _dxd; /* 16: */ diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 88afd108c2dd..11c77757ead9 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -87,7 +87,7 @@ static int dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, static int dbExtend(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks); static int dbFindBits(u32 word, int l2nb); static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno); -static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx); +static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl); static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, @@ -180,7 +180,8 @@ int dbMount(struct inode *ipbmap) bmp->db_nfree = le64_to_cpu(dbmp_le->dn_nfree); bmp->db_l2nbperpage = le32_to_cpu(dbmp_le->dn_l2nbperpage); - if (bmp->db_l2nbperpage > L2PSIZE - L2MINBLOCKSIZE) { + if (bmp->db_l2nbperpage > L2PSIZE - L2MINBLOCKSIZE || + bmp->db_l2nbperpage < 0) { err = -EINVAL; goto err_release_metapage; } @@ -194,6 +195,12 @@ int dbMount(struct inode *ipbmap) bmp->db_maxlevel = le32_to_cpu(dbmp_le->dn_maxlevel); bmp->db_maxag = le32_to_cpu(dbmp_le->dn_maxag); bmp->db_agpref = le32_to_cpu(dbmp_le->dn_agpref); + if (bmp->db_maxag >= MAXAG || bmp->db_maxag < 0 || + bmp->db_agpref >= MAXAG || bmp->db_agpref < 0) { + err = -EINVAL; + goto err_release_metapage; + } + bmp->db_aglevel = le32_to_cpu(dbmp_le->dn_aglevel); bmp->db_agheight = le32_to_cpu(dbmp_le->dn_agheight); bmp->db_agwidth = le32_to_cpu(dbmp_le->dn_agwidth); @@ -1710,7 +1717,7 @@ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno) * dbFindLeaf() returns the index of the leaf at which * free space was found. */ - rc = dbFindLeaf((dmtree_t *) dcp, l2nb, &leafidx); + rc = dbFindLeaf((dmtree_t *) dcp, l2nb, &leafidx, true); /* release the buffer. */ @@ -1957,7 +1964,7 @@ dbAllocDmapLev(struct bmap * bmp, * free space. if sufficient free space is found, dbFindLeaf() * returns the index of the leaf at which free space was found. */ - if (dbFindLeaf((dmtree_t *) & dp->tree, l2nb, &leafidx)) + if (dbFindLeaf((dmtree_t *) &dp->tree, l2nb, &leafidx, false)) return -ENOSPC; if (leafidx < 0) @@ -2921,14 +2928,18 @@ static void dbAdjTree(dmtree_t * tp, int leafno, int newval) * leafidx - return pointer to be set to the index of the leaf * describing at least l2nb free blocks if sufficient * free blocks are found. + * is_ctl - determines if the tree is of type ctl * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient free blocks. */ -static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx) +static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl) { int ti, n = 0, k, x = 0; + int max_size; + + max_size = is_ctl ? CTLTREESIZE : TREESIZE; /* first check the root of the tree to see if there is * sufficient free space. @@ -2949,6 +2960,8 @@ static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx) /* sufficient free space found. move to the next * level (or quit if this is the last level). */ + if (x + n > max_size) + return -ENOSPC; if (l2nb <= tp->dmt_stree[x + n]) break; } diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 8e87264e56ce..a037ee59e398 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -670,7 +670,7 @@ int diWrite(tid_t tid, struct inode *ip) * This is the special xtree inside the directory for storing * the directory table */ - xtpage_t *p, *xp; + xtroot_t *p, *xp; xad_t *xad; jfs_ip->xtlid = 0; @@ -684,7 +684,7 @@ int diWrite(tid_t tid, struct inode *ip) * copy xtree root from inode to dinode: */ p = &jfs_ip->i_xtroot; - xp = (xtpage_t *) &dp->di_dirtable; + xp = (xtroot_t *) &dp->di_dirtable; lv = ilinelock->lv; for (n = 0; n < ilinelock->index; n++, lv++) { memcpy(&xp->xad[lv->offset], &p->xad[lv->offset], @@ -713,7 +713,7 @@ int diWrite(tid_t tid, struct inode *ip) * regular file: 16 byte (XAD slot) granularity */ if (type & tlckXTREE) { - xtpage_t *p, *xp; + xtroot_t *p, *xp; xad_t *xad; /* @@ -1320,7 +1320,7 @@ diInitInode(struct inode *ip, int iagno, int ino, int extno, struct iag * iagp) int diAlloc(struct inode *pip, bool dir, struct inode *ip) { int rc, ino, iagno, addext, extno, bitno, sword; - int nwords, rem, i, agno; + int nwords, rem, i, agno, dn_numag; u32 mask, inosmap, extsmap; struct inode *ipimap; struct metapage *mp; @@ -1356,6 +1356,9 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip) /* get the ag number of this iag */ agno = BLKTOAG(JFS_IP(pip)->agstart, JFS_SBI(pip->i_sb)); + dn_numag = JFS_SBI(pip->i_sb)->bmap->db_numag; + if (agno < 0 || agno > dn_numag) + return -EIO; if (atomic_read(&JFS_SBI(pip->i_sb)->bmap->db_active[agno])) { /* diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 721def69e732..dd4264aa9bed 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -66,7 +66,7 @@ struct jfs_inode_info { lid_t xtlid; /* lid of xtree lock on directory */ union { struct { - xtpage_t _xtroot; /* 288: xtree root */ + xtroot_t _xtroot; /* 288: xtree root */ struct inomap *_imap; /* 4: inode map header */ } file; struct { diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index ce4b4760fcb1..dccc8b3f1045 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -783,7 +783,7 @@ struct tlock *txLock(tid_t tid, struct inode *ip, struct metapage * mp, if (mp->xflag & COMMIT_PAGE) p = (xtpage_t *) mp->data; else - p = &jfs_ip->i_xtroot; + p = (xtpage_t *) &jfs_ip->i_xtroot; xtlck->lwm.offset = le16_to_cpu(p->header.nextindex); } @@ -1676,7 +1676,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, if (tlck->type & tlckBTROOT) { lrd->log.redopage.type |= cpu_to_le16(LOG_BTROOT); - p = &JFS_IP(ip)->i_xtroot; + p = (xtpage_t *) &JFS_IP(ip)->i_xtroot; if (S_ISDIR(ip->i_mode)) lrd->log.redopage.type |= cpu_to_le16(LOG_DIR_XTREE); diff --git a/fs/jfs/jfs_xtree.c b/fs/jfs/jfs_xtree.c index 2d304cee884c..5ee618d17e77 100644 --- a/fs/jfs/jfs_xtree.c +++ b/fs/jfs/jfs_xtree.c @@ -1213,7 +1213,7 @@ xtSplitRoot(tid_t tid, struct xtlock *xtlck; int rc; - sp = &JFS_IP(ip)->i_xtroot; + sp = (xtpage_t *) &JFS_IP(ip)->i_xtroot; INCREMENT(xtStat.split); @@ -2098,7 +2098,7 @@ int xtAppend(tid_t tid, /* transaction id */ */ void xtInitRoot(tid_t tid, struct inode *ip) { - xtpage_t *p; + xtroot_t *p; /* * acquire a transaction lock on the root diff --git a/fs/jfs/jfs_xtree.h b/fs/jfs/jfs_xtree.h index ad7592191d76..0f6cf5a1ce75 100644 --- a/fs/jfs/jfs_xtree.h +++ b/fs/jfs/jfs_xtree.h @@ -65,24 +65,33 @@ struct xadlist { #define XTPAGEMAXSLOT 256 #define XTENTRYSTART 2 +struct xtheader { + __le64 next; /* 8: */ + __le64 prev; /* 8: */ + + u8 flag; /* 1: */ + u8 rsrvd1; /* 1: */ + __le16 nextindex; /* 2: next index = number of entries */ + __le16 maxentry; /* 2: max number of entries */ + __le16 rsrvd2; /* 2: */ + + pxd_t self; /* 8: self */ +}; + +/* + * xtree root (in inode): + */ +typedef union { + struct xtheader header; + xad_t xad[XTROOTMAXSLOT]; /* 16 * maxentry: xad array */ +} xtroot_t; + /* * xtree page: */ typedef union { - struct xtheader { - __le64 next; /* 8: */ - __le64 prev; /* 8: */ - - u8 flag; /* 1: */ - u8 rsrvd1; /* 1: */ - __le16 nextindex; /* 2: next index = number of entries */ - __le16 maxentry; /* 2: max number of entries */ - __le16 rsrvd2; /* 2: */ - - pxd_t self; /* 8: self */ - } header; /* (32) */ - - xad_t xad[XTROOTMAXSLOT]; /* 16 * maxentry: xad array */ + struct xtheader header; + xad_t xad[XTPAGEMAXSLOT]; /* 16 * maxentry: xad array */ } xtpage_t; /* diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 6cd949c59fed..17864a8d2b85 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1499,7 +1499,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) #ifdef CONFIG_FS_POSIX_ACL sb->s_flags |= SB_POSIXACL; #endif - sb->s_iflags |= SB_I_SKIP_SYNC | SB_I_IMA_UNVERIFIABLE_SIGNATURE; + sb->s_iflags |= SB_I_SKIP_SYNC; /* * Ensure that umask handling is done by the filesystems used * for the the upper layer instead of overlayfs as that would diff --git a/kernel/module/decompress.c b/kernel/module/decompress.c index 4156d59be440..474e68f0f063 100644 --- a/kernel/module/decompress.c +++ b/kernel/module/decompress.c @@ -100,7 +100,7 @@ static ssize_t module_gzip_decompress(struct load_info *info, s.next_in = buf + gzip_hdr_len; s.avail_in = size - gzip_hdr_len; - s.workspace = vmalloc(zlib_inflate_workspacesize()); + s.workspace = kvmalloc(zlib_inflate_workspacesize(), GFP_KERNEL); if (!s.workspace) return -ENOMEM; @@ -138,7 +138,7 @@ static ssize_t module_gzip_decompress(struct load_info *info, out_inflate_end: zlib_inflateEnd(&s); out: - vfree(s.workspace); + kvfree(s.workspace); return retval; } #elif defined(CONFIG_MODULE_COMPRESS_XZ) @@ -241,7 +241,7 @@ static ssize_t module_zstd_decompress(struct load_info *info, } wksp_size = zstd_dstream_workspace_bound(header.windowSize); - wksp = vmalloc(wksp_size); + wksp = kvmalloc(wksp_size, GFP_KERNEL); if (!wksp) { retval = -ENOMEM; goto out; @@ -284,7 +284,7 @@ static ssize_t module_zstd_decompress(struct load_info *info, retval = new_size; out: - vfree(wksp); + kvfree(wksp); return retval; } #else diff --git a/security/integrity/Kconfig b/security/integrity/Kconfig index b6e074ac0227..3c45f4f3455f 100644 --- a/security/integrity/Kconfig +++ b/security/integrity/Kconfig @@ -34,10 +34,10 @@ config INTEGRITY_ASYMMETRIC_KEYS bool "Enable asymmetric keys support" depends on INTEGRITY_SIGNATURE default n - select ASYMMETRIC_KEY_TYPE - select ASYMMETRIC_PUBLIC_KEY_SUBTYPE - select CRYPTO_RSA - select X509_CERTIFICATE_PARSER + select ASYMMETRIC_KEY_TYPE + select ASYMMETRIC_PUBLIC_KEY_SUBTYPE + select CRYPTO_RSA + select X509_CERTIFICATE_PARSER help This option enables digital signature verification using asymmetric keys. @@ -53,14 +53,14 @@ config INTEGRITY_TRUSTED_KEYRING keyring. config INTEGRITY_PLATFORM_KEYRING - bool "Provide keyring for platform/firmware trusted keys" - depends on INTEGRITY_ASYMMETRIC_KEYS - depends on SYSTEM_BLACKLIST_KEYRING - help - Provide a separate, distinct keyring for platform trusted keys, which - the kernel automatically populates during initialization from values - provided by the platform for verifying the kexec'ed kerned image - and, possibly, the initramfs signature. + bool "Provide keyring for platform/firmware trusted keys" + depends on INTEGRITY_ASYMMETRIC_KEYS + depends on SYSTEM_BLACKLIST_KEYRING + help + Provide a separate, distinct keyring for platform trusted keys, which + the kernel automatically populates during initialization from values + provided by the platform for verifying the kexec'ed kerned image + and, possibly, the initramfs signature. config INTEGRITY_MACHINE_KEYRING bool "Provide a keyring to which Machine Owner Keys may be added" @@ -69,10 +69,10 @@ config INTEGRITY_MACHINE_KEYRING depends on SYSTEM_BLACKLIST_KEYRING depends on LOAD_UEFI_KEYS || LOAD_PPC_KEYS help - If set, provide a keyring to which Machine Owner Keys (MOK) may - be added. This keyring shall contain just MOK keys. Unlike keys - in the platform keyring, keys contained in the .machine keyring will - be trusted within the kernel. + If set, provide a keyring to which Machine Owner Keys (MOK) may + be added. This keyring shall contain just MOK keys. Unlike keys + in the platform keyring, keys contained in the .machine keyring will + be trusted within the kernel. config INTEGRITY_CA_MACHINE_KEYRING bool "Enforce Machine Keyring CA Restrictions" @@ -97,14 +97,14 @@ config INTEGRITY_CA_MACHINE_KEYRING_MAX .platform keyring. config LOAD_UEFI_KEYS - depends on INTEGRITY_PLATFORM_KEYRING - depends on EFI - def_bool y + depends on INTEGRITY_PLATFORM_KEYRING + depends on EFI + def_bool y config LOAD_IPL_KEYS - depends on INTEGRITY_PLATFORM_KEYRING - depends on S390 - def_bool y + depends on INTEGRITY_PLATFORM_KEYRING + depends on S390 + def_bool y config LOAD_PPC_KEYS bool "Enable loading of platform and blacklisted keys for POWER" diff --git a/security/integrity/iint.c b/security/integrity/iint.c index a462df827de2..27ea19fb1f54 100644 --- a/security/integrity/iint.c +++ b/security/integrity/iint.c @@ -66,9 +66,32 @@ struct integrity_iint_cache *integrity_iint_find(struct inode *inode) return iint; } -static void iint_free(struct integrity_iint_cache *iint) +#define IMA_MAX_NESTING (FILESYSTEM_MAX_STACK_DEPTH+1) + +/* + * It is not clear that IMA should be nested at all, but as long is it measures + * files both on overlayfs and on underlying fs, we need to annotate the iint + * mutex to avoid lockdep false positives related to IMA + overlayfs. + * See ovl_lockdep_annotate_inode_mutex_key() for more details. + */ +static inline void iint_lockdep_annotate(struct integrity_iint_cache *iint, + struct inode *inode) +{ +#ifdef CONFIG_LOCKDEP + static struct lock_class_key iint_mutex_key[IMA_MAX_NESTING]; + + int depth = inode->i_sb->s_stack_depth; + + if (WARN_ON_ONCE(depth < 0 || depth >= IMA_MAX_NESTING)) + depth = 0; + + lockdep_set_class(&iint->mutex, &iint_mutex_key[depth]); +#endif +} + +static void iint_init_always(struct integrity_iint_cache *iint, + struct inode *inode) { - kfree(iint->ima_hash); iint->ima_hash = NULL; iint->version = 0; iint->flags = 0UL; @@ -80,6 +103,14 @@ static void iint_free(struct integrity_iint_cache *iint) iint->ima_creds_status = INTEGRITY_UNKNOWN; iint->evm_status = INTEGRITY_UNKNOWN; iint->measured_pcrs = 0; + mutex_init(&iint->mutex); + iint_lockdep_annotate(iint, inode); +} + +static void iint_free(struct integrity_iint_cache *iint) +{ + kfree(iint->ima_hash); + mutex_destroy(&iint->mutex); kmem_cache_free(iint_cache, iint); } @@ -104,6 +135,8 @@ struct integrity_iint_cache *integrity_inode_get(struct inode *inode) if (!iint) return NULL; + iint_init_always(iint, inode); + write_lock(&integrity_iint_lock); p = &integrity_iint_tree.rb_node; @@ -153,25 +186,18 @@ void integrity_inode_free(struct inode *inode) iint_free(iint); } -static void init_once(void *foo) +static void iint_init_once(void *foo) { struct integrity_iint_cache *iint = (struct integrity_iint_cache *) foo; memset(iint, 0, sizeof(*iint)); - iint->ima_file_status = INTEGRITY_UNKNOWN; - iint->ima_mmap_status = INTEGRITY_UNKNOWN; - iint->ima_bprm_status = INTEGRITY_UNKNOWN; - iint->ima_read_status = INTEGRITY_UNKNOWN; - iint->ima_creds_status = INTEGRITY_UNKNOWN; - iint->evm_status = INTEGRITY_UNKNOWN; - mutex_init(&iint->mutex); } static int __init integrity_iintcache_init(void) { iint_cache = kmem_cache_create("iint_cache", sizeof(struct integrity_iint_cache), - 0, SLAB_PANIC, init_once); + 0, SLAB_PANIC, iint_init_once); return 0; } DEFINE_LSM(integrity) = { diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index 452e80b541e5..597ea0c4d72f 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -243,6 +243,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, { const char *audit_cause = "failed"; struct inode *inode = file_inode(file); + struct inode *real_inode = d_real_inode(file_dentry(file)); const char *filename = file->f_path.dentry->d_name.name; struct ima_max_digest_data hash; struct kstat stat; @@ -302,6 +303,10 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, iint->ima_hash = tmpbuf; memcpy(iint->ima_hash, &hash, length); iint->version = i_version; + if (real_inode != inode) { + iint->real_ino = real_inode->i_ino; + iint->real_dev = real_inode->i_sb->s_dev; + } /* Possibly temporary failure due to type of read (eg. O_DIRECT) */ if (!result) diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 365db0e43d7c..cc1217ac2c6f 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "ima.h" @@ -207,7 +208,7 @@ static int process_measurement(struct file *file, const struct cred *cred, u32 secid, char *buf, loff_t size, int mask, enum ima_hooks func) { - struct inode *inode = file_inode(file); + struct inode *backing_inode, *inode = file_inode(file); struct integrity_iint_cache *iint = NULL; struct ima_template_desc *template_desc = NULL; char *pathbuf = NULL; @@ -284,6 +285,19 @@ static int process_measurement(struct file *file, const struct cred *cred, iint->measured_pcrs = 0; } + /* Detect and re-evaluate changes made to the backing file. */ + backing_inode = d_real_inode(file_dentry(file)); + if (backing_inode != inode && + (action & IMA_DO_MASK) && (iint->flags & IMA_DONE_MASK)) { + if (!IS_I_VERSION(backing_inode) || + backing_inode->i_sb->s_dev != iint->real_dev || + backing_inode->i_ino != iint->real_ino || + !inode_eq_iversion(backing_inode, iint->version)) { + iint->flags &= ~IMA_DONE_MASK; + iint->measured_pcrs = 0; + } + } + /* Determine if already appraised/measured based on bitmask * (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED, * IMA_AUDIT, IMA_AUDITED) diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index d7553c93f5c0..9561db7cf6b4 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -164,6 +164,8 @@ struct integrity_iint_cache { unsigned long flags; unsigned long measured_pcrs; unsigned long atomic_flags; + unsigned long real_ino; + dev_t real_dev; enum integrity_status ima_file_status:4; enum integrity_status ima_mmap_status:4; enum integrity_status ima_bprm_status:4;