diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-06-24 20:38:29 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-06-24 20:38:29 -0700 |
commit | cfcc0ad47f4cbc19ddd057cfb39b144a3518c59e (patch) | |
tree | 35a752e715d42b30eb594b5e2d5ffcc004cddbee | |
parent | a7296b49fb40525a5c42f650617749def3d25bcc (diff) | |
parent | 3c45414527487549f469484337a4c5ae5d84dc80 (diff) |
Merge tag 'for-f2fs-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs
Pull f2fs updates from Jaegeuk Kim:
"New features:
- per-file encryption (e.g., ext4)
- FALLOC_FL_ZERO_RANGE
- FALLOC_FL_COLLAPSE_RANGE
- RENAME_WHITEOUT
Major enhancement/fixes:
- recovery broken superblocks
- enhance f2fs_trim_fs with a discard_map
- fix a race condition on dentry block allocation
- fix a deadlock during summary operation
- fix a missing fiemap result
.. and many minor bug fixes and clean-ups were done"
* tag 'for-f2fs-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (83 commits)
f2fs: do not trim preallocated blocks when truncating after i_size
f2fs crypto: add alloc_bounce_page
f2fs crypto: fix to handle errors likewise ext4
f2fs: drop the volatile_write flag only
f2fs: skip committing valid superblock
f2fs: setting discard option in parse_options()
f2fs: fix to return exact trimmed size
f2fs: support FALLOC_FL_INSERT_RANGE
f2fs: hide common code in f2fs_replace_block
f2fs: disable the discard option when device doesn't support
f2fs crypto: remove alloc_page for bounce_page
f2fs: fix a deadlock for summary page lock vs. sentry_lock
f2fs crypto: clean up error handling in f2fs_fname_setup_filename
f2fs crypto: avoid f2fs_inherit_context for symlink
f2fs crypto: do not set encryption policy for non-directory by ioctl
f2fs crypto: allow setting encryption policy once
f2fs crypto: check context consistent for rename2
f2fs: avoid duplicated code by reusing f2fs_read_end_io
f2fs crypto: use per-inode tfm structure
f2fs: recovering broken superblock during mount
...
-rw-r--r-- | fs/f2fs/Kconfig | 19 | ||||
-rw-r--r-- | fs/f2fs/Makefile | 2 | ||||
-rw-r--r-- | fs/f2fs/acl.c | 46 | ||||
-rw-r--r-- | fs/f2fs/checkpoint.c | 56 | ||||
-rw-r--r-- | fs/f2fs/crypto.c | 491 | ||||
-rw-r--r-- | fs/f2fs/crypto_fname.c | 440 | ||||
-rw-r--r-- | fs/f2fs/crypto_key.c | 255 | ||||
-rw-r--r-- | fs/f2fs/crypto_policy.c | 209 | ||||
-rw-r--r-- | fs/f2fs/data.c | 593 | ||||
-rw-r--r-- | fs/f2fs/debug.c | 11 | ||||
-rw-r--r-- | fs/f2fs/dir.c | 194 | ||||
-rw-r--r-- | fs/f2fs/f2fs.h | 320 | ||||
-rw-r--r-- | fs/f2fs/f2fs_crypto.h | 151 | ||||
-rw-r--r-- | fs/f2fs/file.c | 516 | ||||
-rw-r--r-- | fs/f2fs/gc.c | 115 | ||||
-rw-r--r-- | fs/f2fs/hash.c | 3 | ||||
-rw-r--r-- | fs/f2fs/inline.c | 43 | ||||
-rw-r--r-- | fs/f2fs/inode.c | 9 | ||||
-rw-r--r-- | fs/f2fs/namei.c | 374 | ||||
-rw-r--r-- | fs/f2fs/node.c | 48 | ||||
-rw-r--r-- | fs/f2fs/node.h | 22 | ||||
-rw-r--r-- | fs/f2fs/recovery.c | 28 | ||||
-rw-r--r-- | fs/f2fs/segment.c | 250 | ||||
-rw-r--r-- | fs/f2fs/segment.h | 1 | ||||
-rw-r--r-- | fs/f2fs/super.c | 178 | ||||
-rw-r--r-- | fs/f2fs/trace.c | 6 | ||||
-rw-r--r-- | fs/f2fs/trace.h | 4 | ||||
-rw-r--r-- | fs/f2fs/xattr.c | 3 | ||||
-rw-r--r-- | fs/f2fs/xattr.h | 4 | ||||
-rw-r--r-- | include/linux/f2fs_fs.h | 8 | ||||
-rw-r--r-- | include/trace/events/f2fs.h | 33 |
31 files changed, 3802 insertions, 630 deletions
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig index 05f0f663f14c..c629762005bc 100644 --- a/fs/f2fs/Kconfig +++ b/fs/f2fs/Kconfig @@ -72,6 +72,25 @@ config F2FS_CHECK_FS If you want to improve the performance, say N. +config F2FS_FS_ENCRYPTION + bool "F2FS Encryption" + depends on F2FS_FS + depends on F2FS_FS_XATTR + select CRYPTO_AES + select CRYPTO_CBC + select CRYPTO_ECB + select CRYPTO_XTS + select CRYPTO_CTS + select CRYPTO_CTR + select CRYPTO_SHA256 + select KEYS + select ENCRYPTED_KEYS + help + Enable encryption of f2fs files and directories. This + feature is similar to ecryptfs, but it is more memory + efficient since it avoids caching the encrypted and + decrypted pages in the page cache. + config F2FS_IO_TRACE bool "F2FS IO tracer" depends on F2FS_FS diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile index d92397731db8..396be1a39e55 100644 --- a/fs/f2fs/Makefile +++ b/fs/f2fs/Makefile @@ -6,3 +6,5 @@ f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o +f2fs-$(CONFIG_F2FS_FS_ENCRYPTION) += crypto_policy.o crypto.o \ + crypto_key.o crypto_fname.o diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 4320ffab3495..c8f25f7241f0 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -334,51 +334,45 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode, struct page *dpage) { struct posix_acl *p; + struct posix_acl *clone; int ret; + *acl = NULL; + *default_acl = NULL; + if (S_ISLNK(*mode) || !IS_POSIXACL(dir)) - goto no_acl; + return 0; p = __f2fs_get_acl(dir, ACL_TYPE_DEFAULT, dpage); - if (IS_ERR(p)) { - if (p == ERR_PTR(-EOPNOTSUPP)) - goto apply_umask; - return PTR_ERR(p); + if (!p || p == ERR_PTR(-EOPNOTSUPP)) { + *mode &= ~current_umask(); + return 0; } + if (IS_ERR(p)) + return PTR_ERR(p); - if (!p) - goto apply_umask; - - *acl = f2fs_acl_clone(p, GFP_NOFS); - if (!*acl) + clone = f2fs_acl_clone(p, GFP_NOFS); + if (!clone) goto no_mem; - ret = f2fs_acl_create_masq(*acl, mode); + ret = f2fs_acl_create_masq(clone, mode); if (ret < 0) goto no_mem_clone; - if (ret == 0) { - posix_acl_release(*acl); - *acl = NULL; - } + if (ret == 0) + posix_acl_release(clone); + else + *acl = clone; - if (!S_ISDIR(*mode)) { + if (!S_ISDIR(*mode)) posix_acl_release(p); - *default_acl = NULL; - } else { + else *default_acl = p; - } - return 0; -apply_umask: - *mode &= ~current_umask(); -no_acl: - *default_acl = NULL; - *acl = NULL; return 0; no_mem_clone: - posix_acl_release(*acl); + posix_acl_release(clone); no_mem: posix_acl_release(p); return -ENOMEM; diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index a5e17a2a0781..b70bbe1a6a8c 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -52,9 +52,11 @@ struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) struct address_space *mapping = META_MAPPING(sbi); struct page *page; struct f2fs_io_info fio = { + .sbi = sbi, .type = META, .rw = READ_SYNC | REQ_META | REQ_PRIO, .blk_addr = index, + .encrypted_page = NULL, }; repeat: page = grab_cache_page(mapping, index); @@ -65,7 +67,9 @@ repeat: if (PageUptodate(page)) goto out; - if (f2fs_submit_page_bio(sbi, page, &fio)) + fio.page = page; + + if (f2fs_submit_page_bio(&fio)) goto repeat; lock_page(page); @@ -77,8 +81,7 @@ out: return page; } -static inline bool is_valid_blkaddr(struct f2fs_sb_info *sbi, - block_t blkaddr, int type) +bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { switch (type) { case META_NAT: @@ -118,8 +121,10 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type struct page *page; block_t blkno = start; struct f2fs_io_info fio = { + .sbi = sbi, .type = META, - .rw = READ_SYNC | REQ_META | REQ_PRIO + .rw = READ_SYNC | REQ_META | REQ_PRIO, + .encrypted_page = NULL, }; for (; nrpages-- > 0; blkno++) { @@ -161,7 +166,8 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type continue; } - f2fs_submit_page_mbio(sbi, page, &fio); + fio.page = page; + f2fs_submit_page_mbio(&fio); f2fs_put_page(page, 0); } out: @@ -510,7 +516,12 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) grab_meta_page(sbi, start_blk + index); index = 1; - spin_lock(&im->ino_lock); + + /* + * we don't need to do spin_lock(&im->ino_lock) here, since all the + * orphan inode operations are covered under f2fs_lock_op(). + * And, spin_lock should be avoided due to page operations below. + */ head = &im->ino_list; /* loop for each orphan inode entry and write them in Jornal block */ @@ -550,8 +561,6 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) set_page_dirty(page); f2fs_put_page(page, 1); } - - spin_unlock(&im->ino_lock); } static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, @@ -879,10 +888,8 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num; nid_t last_nid = nm_i->next_scan_nid; block_t start_blk; - struct page *cp_page; unsigned int data_sum_blocks, orphan_blocks; __u32 crc32 = 0; - void *kaddr; int i; int cp_payload_blks = __cp_payload(sbi); @@ -979,19 +986,11 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) start_blk = __start_cp_addr(sbi); /* write out checkpoint buffer at block 0 */ - cp_page = grab_meta_page(sbi, start_blk++); - kaddr = page_address(cp_page); - memcpy(kaddr, ckpt, F2FS_BLKSIZE); - set_page_dirty(cp_page); - f2fs_put_page(cp_page, 1); - - for (i = 1; i < 1 + cp_payload_blks; i++) { - cp_page = grab_meta_page(sbi, start_blk++); - kaddr = page_address(cp_page); - memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE, F2FS_BLKSIZE); - set_page_dirty(cp_page); - f2fs_put_page(cp_page, 1); - } + update_meta_page(sbi, ckpt, start_blk++); + + for (i = 1; i < 1 + cp_payload_blks; i++) + update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE, + start_blk++); if (orphan_num) { write_orphan_inodes(sbi, start_blk); @@ -1006,11 +1005,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) } /* writeout checkpoint block */ - cp_page = grab_meta_page(sbi, start_blk); - kaddr = page_address(cp_page); - memcpy(kaddr, ckpt, F2FS_BLKSIZE); - set_page_dirty(cp_page); - f2fs_put_page(cp_page, 1); + update_meta_page(sbi, ckpt, start_blk); /* wait for previous submitted node/meta pages writeback */ wait_on_all_pages_writeback(sbi); @@ -1036,7 +1031,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (unlikely(f2fs_cp_error(sbi))) return; - clear_prefree_segments(sbi); + clear_prefree_segments(sbi, cpc); clear_sbi_flag(sbi, SBI_IS_DIRTY); } @@ -1051,7 +1046,8 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) mutex_lock(&sbi->cp_mutex); if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) && - (cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC)) + (cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC || + (cpc->reason == CP_DISCARD && !sbi->discard_blks))) goto out; if (unlikely(f2fs_cp_error(sbi))) goto out; diff --git a/fs/f2fs/crypto.c b/fs/f2fs/crypto.c new file mode 100644 index 000000000000..4a62ef14e932 --- /dev/null +++ b/fs/f2fs/crypto.c @@ -0,0 +1,491 @@ +/* + * linux/fs/f2fs/crypto.c + * + * Copied from linux/fs/ext4/crypto.c + * + * Copyright (C) 2015, Google, Inc. + * Copyright (C) 2015, Motorola Mobility + * + * This contains encryption functions for f2fs + * + * Written by Michael Halcrow, 2014. + * + * Filename encryption additions + * Uday Savagaonkar, 2014 + * Encryption policy handling additions + * Ildar Muslukhov, 2014 + * Remove ext4_encrypted_zeroout(), + * add f2fs_restore_and_release_control_page() + * Jaegeuk Kim, 2015. + * + * This has not yet undergone a rigorous security audit. + * + * The usage of AES-XTS should conform to recommendations in NIST + * Special Publication 800-38E and IEEE P1619/D16. + */ +#include <crypto/hash.h> +#include <crypto/sha.h> +#include <keys/user-type.h> +#include <keys/encrypted-type.h> +#include <linux/crypto.h> +#include <linux/ecryptfs.h> +#include <linux/gfp.h> +#include <linux/kernel.h> +#include <linux/key.h> +#include <linux/list.h> +#include <linux/mempool.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/random.h> +#include <linux/scatterlist.h> +#include <linux/spinlock_types.h> +#include <linux/f2fs_fs.h> +#include <linux/ratelimit.h> +#include <linux/bio.h> + +#include "f2fs.h" +#include "xattr.h" + +/* Encryption added and removed here! (L: */ + +static unsigned int num_prealloc_crypto_pages = 32; +static unsigned int num_prealloc_crypto_ctxs = 128; + +module_param(num_prealloc_crypto_pages, uint, 0444); +MODULE_PARM_DESC(num_prealloc_crypto_pages, + "Number of crypto pages to preallocate"); +module_param(num_prealloc_crypto_ctxs, uint, 0444); +MODULE_PARM_DESC(num_prealloc_crypto_ctxs, + "Number of crypto contexts to preallocate"); + +static mempool_t *f2fs_bounce_page_pool; + +static LIST_HEAD(f2fs_free_crypto_ctxs); +static DEFINE_SPINLOCK(f2fs_crypto_ctx_lock); + +static struct workqueue_struct *f2fs_read_workqueue; +static DEFINE_MUTEX(crypto_init); + +static struct kmem_cache *f2fs_crypto_ctx_cachep; +struct kmem_cache *f2fs_crypt_info_cachep; + +/** + * f2fs_release_crypto_ctx() - Releases an encryption context + * @ctx: The encryption context to release. + * + * If the encryption context was allocated from the pre-allocated pool, returns + * it to that pool. Else, frees it. + * + * If there's a bounce page in the context, this frees that. + */ +void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *ctx) +{ + unsigned long flags; + + if (ctx->flags & F2FS_WRITE_PATH_FL && ctx->w.bounce_page) { + mempool_free(ctx->w.bounce_page, f2fs_bounce_page_pool); + ctx->w.bounce_page = NULL; + } + ctx->w.control_page = NULL; + if (ctx->flags & F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL) { + kmem_cache_free(f2fs_crypto_ctx_cachep, ctx); + } else { + spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags); + list_add(&ctx->free_list, &f2fs_free_crypto_ctxs); + spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags); + } +} + +/** + * f2fs_get_crypto_ctx() - Gets an encryption context + * @inode: The inode for which we are doing the crypto + * + * Allocates and initializes an encryption context. + * + * Return: An allocated and initialized encryption context on success; error + * value or NULL otherwise. + */ +struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *inode) +{ + struct f2fs_crypto_ctx *ctx = NULL; + unsigned long flags; + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + + if (ci == NULL) + return ERR_PTR(-ENOKEY); + + /* + * We first try getting the ctx from a free list because in + * the common case the ctx will have an allocated and + * initialized crypto tfm, so it's probably a worthwhile + * optimization. For the bounce page, we first try getting it + * from the kernel allocator because that's just about as fast + * as getting it from a list and because a cache of free pages + * should generally be a "last resort" option for a filesystem + * to be able to do its job. + */ + spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags); + ctx = list_first_entry_or_null(&f2fs_free_crypto_ctxs, + struct f2fs_crypto_ctx, free_list); + if (ctx) + list_del(&ctx->free_list); + spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags); + if (!ctx) { + ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_NOFS); + if (!ctx) + return ERR_PTR(-ENOMEM); + ctx->flags |= F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL; + } else { + ctx->flags &= ~F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL; + } + ctx->flags &= ~F2FS_WRITE_PATH_FL; + return ctx; +} + +/* + * Call f2fs_decrypt on every single page, reusing the encryption + * context. + */ +static void completion_pages(struct work_struct *work) +{ + struct f2fs_crypto_ctx *ctx = + container_of(work, struct f2fs_crypto_ctx, r.work); + struct bio *bio = ctx->r.bio; + struct bio_vec *bv; + int i; + + bio_for_each_segment_all(bv, bio, i) { + struct page *page = bv->bv_page; + int ret = f2fs_decrypt(ctx, page); + + if (ret) { + WARN_ON_ONCE(1); + SetPageError(page); + } else + SetPageUptodate(page); + unlock_page(page); + } + f2fs_release_crypto_ctx(ctx); + bio_put(bio); +} + +void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *ctx, struct bio *bio) +{ + INIT_WORK(&ctx->r.work, completion_pages); + ctx->r.bio = bio; + queue_work(f2fs_read_workqueue, &ctx->r.work); +} + +static void f2fs_crypto_destroy(void) +{ + struct f2fs_crypto_ctx *pos, *n; + + list_for_each_entry_safe(pos, n, &f2fs_free_crypto_ctxs, free_list) + kmem_cache_free(f2fs_crypto_ctx_cachep, pos); + INIT_LIST_HEAD(&f2fs_free_crypto_ctxs); + if (f2fs_bounce_page_pool) + mempool_destroy(f2fs_bounce_page_pool); + f2fs_bounce_page_pool = NULL; +} + +/** + * f2fs_crypto_initialize() - Set up for f2fs encryption. + * + * We only call this when we start accessing encrypted files, since it + * results in memory getting allocated that wouldn't otherwise be used. + * + * Return: Zero on success, non-zero otherwise. + */ +int f2fs_crypto_initialize(void) +{ + int i, res = -ENOMEM; + + if (f2fs_bounce_page_pool) + return 0; + + mutex_lock(&crypto_init); + if (f2fs_bounce_page_pool) + goto already_initialized; + + for (i = 0; i < num_prealloc_crypto_ctxs; i++) { + struct f2fs_crypto_ctx *ctx; + + ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_KERNEL); + if (!ctx) + goto fail; + list_add(&ctx->free_list, &f2fs_free_crypto_ctxs); + } + + /* must be allocated at the last step to avoid race condition above */ + f2fs_bounce_page_pool = + mempool_create_page_pool(num_prealloc_crypto_pages, 0); + if (!f2fs_bounce_page_pool) + goto fail; + +already_initialized: + mutex_unlock(&crypto_init); + return 0; +fail: + f2fs_crypto_destroy(); + mutex_unlock(&crypto_init); + return res; +} + +/** + * f2fs_exit_crypto() - Shutdown the f2fs encryption system + */ +void f2fs_exit_crypto(void) +{ + f2fs_crypto_destroy(); + + if (f2fs_read_workqueue) + destroy_workqueue(f2fs_read_workqueue); + if (f2fs_crypto_ctx_cachep) + kmem_cache_destroy(f2fs_crypto_ctx_cachep); + if (f2fs_crypt_info_cachep) + kmem_cache_destroy(f2fs_crypt_info_cachep); +} + +int __init f2fs_init_crypto(void) +{ + int res = -ENOMEM; + + f2fs_read_workqueue = alloc_workqueue("f2fs_crypto", WQ_HIGHPRI, 0); + if (!f2fs_read_workqueue) + goto fail; + + f2fs_crypto_ctx_cachep = KMEM_CACHE(f2fs_crypto_ctx, + SLAB_RECLAIM_ACCOUNT); + if (!f2fs_crypto_ctx_cachep) + goto fail; + + f2fs_crypt_info_cachep = KMEM_CACHE(f2fs_crypt_info, + SLAB_RECLAIM_ACCOUNT); + if (!f2fs_crypt_info_cachep) + goto fail; + + return 0; +fail: + f2fs_exit_crypto(); + return res; +} + +void f2fs_restore_and_release_control_page(struct page **page) +{ + struct f2fs_crypto_ctx *ctx; + struct page *bounce_page; + + /* The bounce data pages are unmapped. */ + if ((*page)->mapping) + return; + + /* The bounce data page is unmapped. */ + bounce_page = *page; + ctx = (struct f2fs_crypto_ctx *)page_private(bounce_page); + + /* restore control page */ + *page = ctx->w.control_page; + + f2fs_restore_control_page(bounce_page); +} + +void f2fs_restore_control_page(struct page *data_page) +{ + struct f2fs_crypto_ctx *ctx = + (struct f2fs_crypto_ctx *)page_private(data_page); + + set_page_private(data_page, (unsigned long)NULL); + ClearPagePrivate(data_page); + unlock_page(data_page); + f2fs_release_crypto_ctx(ctx); +} + +/** + * f2fs_crypt_complete() - The completion callback for page encryption + * @req: The asynchronous encryption request context + * @res: The result of the encryption operation + */ +static void f2fs_crypt_complete(struct crypto_async_request *req, int res) +{ + struct f2fs_completion_result *ecr = req->data; + + if (res == -EINPROGRESS) + return; + ecr->res = res; + complete(&ecr->completion); +} + +typedef enum { + F2FS_DECRYPT = 0, + F2FS_ENCRYPT, +} f2fs_direction_t; + +static int f2fs_page_crypto(struct f2fs_crypto_ctx *ctx, + struct inode *inode, + f2fs_direction_t rw, + pgoff_t index, + struct page *src_page, + struct page *dest_page) +{ + u8 xts_tweak[F2FS_XTS_TWEAK_SIZE]; + struct ablkcipher_request *req = NULL; + DECLARE_F2FS_COMPLETION_RESULT(ecr); + struct scatterlist dst, src; + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + struct crypto_ablkcipher *tfm = ci->ci_ctfm; + int res = 0; + + req = ablkcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + printk_ratelimited(KERN_ERR + "%s: crypto_request_alloc() failed\n", + __func__); + return -ENOMEM; + } + ablkcipher_request_set_callback( + req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + f2fs_crypt_complete, &ecr); + + BUILD_BUG_ON(F2FS_XTS_TWEAK_SIZE < sizeof(index)); + memcpy(xts_tweak, &index, sizeof(index)); + memset(&xts_tweak[sizeof(index)], 0, + F2FS_XTS_TWEAK_SIZE - sizeof(index)); + + sg_init_table(&dst, 1); + sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0); + sg_init_table(&src, 1); + sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0); + ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE, + xts_tweak); + if (rw == F2FS_DECRYPT) + res = crypto_ablkcipher_decrypt(req); + else + res = crypto_ablkcipher_encrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } + ablkcipher_request_free(req); + if (res) { + printk_ratelimited(KERN_ERR + "%s: crypto_ablkcipher_encrypt() returned %d\n", + __func__, res); + return res; + } + return 0; +} + +static struct page *alloc_bounce_page(struct f2fs_crypto_ctx *ctx) +{ + ctx->w.bounce_page = mempool_alloc(f2fs_bounce_page_pool, GFP_NOWAIT); + if (ctx->w.bounce_page == NULL) + return ERR_PTR(-ENOMEM); + ctx->flags |= F2FS_WRITE_PATH_FL; + return ctx->w.bounce_page; +} + +/** + * f2fs_encrypt() - Encrypts a page + * @inode: The inode for which the encryption should take place + * @plaintext_page: The page to encrypt. Must be locked. + * + * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx + * encryption context. + * + * Called on the page write path. The caller must call + * f2fs_restore_control_page() on the returned ciphertext page to + * release the bounce buffer and the encryption context. + * + * Return: An allocated page with the encrypted content on success. Else, an + * error value or NULL. + */ +struct page *f2fs_encrypt(struct inode *inode, + struct page *plaintext_page) +{ + struct f2fs_crypto_ctx *ctx; + struct page *ciphertext_page = NULL; + int err; + + BUG_ON(!PageLocked(plaintext_page)); + + ctx = f2fs_get_crypto_ctx(inode); + if (IS_ERR(ctx)) + return (struct page *)ctx; + + /* The encryption operation will require a bounce page. */ + ciphertext_page = alloc_bounce_page(ctx); + if (IS_ERR(ciphertext_page)) + goto err_out; + + ctx->w.control_page = plaintext_page; + err = f2fs_page_crypto(ctx, inode, F2FS_ENCRYPT, plaintext_page->index, + plaintext_page, ciphertext_page); + if (err) { + ciphertext_page = ERR_PTR(err); + goto err_out; + } + + SetPagePrivate(ciphertext_page); + set_page_private(ciphertext_page, (unsigned long)ctx); + lock_page(ciphertext_page); + return ciphertext_page; + +err_out: + f2fs_release_crypto_ctx(ctx); + return ciphertext_page; +} + +/** + * f2fs_decrypt() - Decrypts a page in-place + * @ctx: The encryption context. + * @page: The page to decrypt. Must be locked. + * + * Decrypts page in-place using the ctx encryption context. + * + * Called from the read completion callback. + * + * Return: Zero on success, non-zero otherwise. + */ +int f2fs_decrypt(struct f2fs_crypto_ctx *ctx, struct page *page) +{ + BUG_ON(!PageLocked(page)); + + return f2fs_page_crypto(ctx, page->mapping->host, + F2FS_DECRYPT, page->index, page, page); +} + +/* + * Convenience function which takes care of allocating and + * deallocating the encryption context + */ +int f2fs_decrypt_one(struct inode *inode, struct page *page) +{ + struct f2fs_crypto_ctx *ctx = f2fs_get_crypto_ctx(inode); + int ret; + + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + ret = f2fs_decrypt(ctx, page); + f2fs_release_crypto_ctx(ctx); + return ret; +} + +bool f2fs_valid_contents_enc_mode(uint32_t mode) +{ + return (mode == F2FS_ENCRYPTION_MODE_AES_256_XTS); +} + +/** + * f2fs_validate_encryption_key_size() - Validate the encryption key size + * @mode: The key mode. + * @size: The key size to validate. + * + * Return: The validated key size for @mode. Zero if invalid. + */ +uint32_t f2fs_validate_encryption_key_size(uint32_t mode, uint32_t size) +{ + if (size == f2fs_encryption_key_size(mode)) + return size; + return 0; +} diff --git a/fs/f2fs/crypto_fname.c b/fs/f2fs/crypto_fname.c new file mode 100644 index 000000000000..ab377d496a39 --- /dev/null +++ b/fs/f2fs/crypto_fname.c @@ -0,0 +1,440 @@ +/* + * linux/fs/f2fs/crypto_fname.c + * + * Copied from linux/fs/ext4/crypto.c + * + * Copyright (C) 2015, Google, Inc. + * Copyright (C) 2015, Motorola Mobility + * + * This contains functions for filename crypto management in f2fs + * + * Written by Uday Savagaonkar, 2014. + * + * Adjust f2fs dentry structure + * Jaegeuk Kim, 2015. + * + * This has not yet undergone a rigorous security audit. + */ +#include <crypto/hash.h> +#include <crypto/sha.h> +#include <keys/encrypted-type.h> +#include <keys/user-type.h> +#include <linux/crypto.h> +#include <linux/gfp.h> +#include <linux/kernel.h> +#include <linux/key.h> +#include <linux/list.h> +#include <linux/mempool.h> +#include <linux/random.h> +#include <linux/scatterlist.h> +#include <linux/spinlock_types.h> +#include <linux/f2fs_fs.h> +#include <linux/ratelimit.h> + +#include "f2fs.h" +#include "f2fs_crypto.h" +#include "xattr.h" + +/** + * f2fs_dir_crypt_complete() - + */ +static void f2fs_dir_crypt_complete(struct crypto_async_request *req, int res) +{ + struct f2fs_completion_result *ecr = req->data; + + if (res == -EINPROGRESS) + return; + ecr->res = res; + complete(&ecr->completion); +} + +bool f2fs_valid_filenames_enc_mode(uint32_t mode) +{ + return (mode == F2FS_ENCRYPTION_MODE_AES_256_CTS); +} + +static unsigned max_name_len(struct inode *inode) +{ + return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize : + F2FS_NAME_LEN; +} + +/** + * f2fs_fname_encrypt() - + * + * This function encrypts the input filename, and returns the length of the + * ciphertext. Errors are returned as negative numbers. We trust the caller to + * allocate sufficient memory to oname string. + */ +static int f2fs_fname_encrypt(struct inode *inode, + const struct qstr *iname, struct f2fs_str *oname) +{ + u32 ciphertext_len; + struct ablkcipher_request *req = NULL; + DECLARE_F2FS_COMPLETION_RESULT(ecr); + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + struct crypto_ablkcipher *tfm = ci->ci_ctfm; + int res = 0; + char iv[F2FS_CRYPTO_BLOCK_SIZE]; + struct scatterlist src_sg, dst_sg; + int padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK); + char *workbuf, buf[32], *alloc_buf = NULL; + unsigned lim = max_name_len(inode); + + if (iname->len <= 0 || iname->len > lim) + return -EIO; + + ciphertext_len = (iname->len < F2FS_CRYPTO_BLOCK_SIZE) ? + F2FS_CRYPTO_BLOCK_SIZE : iname->len; + ciphertext_len = f2fs_fname_crypto_round_up(ciphertext_len, padding); + ciphertext_len = (ciphertext_len > lim) ? lim : ciphertext_len; + + if (ciphertext_len <= sizeof(buf)) { + workbuf = buf; + } else { + alloc_buf = kmalloc(ciphertext_len, GFP_NOFS); + if (!alloc_buf) + return -ENOMEM; + workbuf = alloc_buf; + } + + /* Allocate request */ + req = ablkcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + printk_ratelimited(KERN_ERR + "%s: crypto_request_alloc() failed\n", __func__); + kfree(alloc_buf); + return -ENOMEM; + } + ablkcipher_request_set_callback(req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + f2fs_dir_crypt_complete, &ecr); + + /* Copy the input */ + memcpy(workbuf, iname->name, iname->len); + if (iname->len < ciphertext_len) + memset(workbuf + iname->len, 0, ciphertext_len - iname->len); + + /* Initialize IV */ + memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE); + + /* Create encryption request */ + sg_init_one(&src_sg, workbuf, ciphertext_len); + sg_init_one(&dst_sg, oname->name, ciphertext_len); + ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv); + res = crypto_ablkcipher_encrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } + kfree(alloc_buf); + ablkcipher_request_free(req); + if (res < 0) { + printk_ratelimited(KERN_ERR + "%s: Error (error code %d)\n", __func__, res); + } + oname->len = ciphertext_len; + return res; +} + +/* + * f2fs_fname_decrypt() + * This function decrypts the input filename, and returns + * the length of the plaintext. + * Errors are returned as negative numbers. + * We trust the caller to allocate sufficient memory to oname string. + */ +static int f2fs_fname_decrypt(struct inode *inode, + const struct f2fs_str *iname, struct f2fs_str *oname) +{ + struct ablkcipher_request *req = NULL; + DECLARE_F2FS_COMPLETION_RESULT(ecr); + struct scatterlist src_sg, dst_sg; + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + struct crypto_ablkcipher *tfm = ci->ci_ctfm; + int res = 0; + char iv[F2FS_CRYPTO_BLOCK_SIZE]; + unsigned lim = max_name_len(inode); + + if (iname->len <= 0 || iname->len > lim) + return -EIO; + + /* Allocate request */ + req = ablkcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + printk_ratelimited(KERN_ERR + "%s: crypto_request_alloc() failed\n", __func__); + return -ENOMEM; + } + ablkcipher_request_set_callback(req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + f2fs_dir_crypt_complete, &ecr); + + /* Initialize IV */ + memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE); + + /* Create decryption request */ + sg_init_one(&src_sg, iname->name, iname->len); + sg_init_one(&dst_sg, oname->name, oname->len); + ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv); + res = crypto_ablkcipher_decrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } + ablkcipher_request_free(req); + if (res < 0) { + printk_ratelimited(KERN_ERR + "%s: Error in f2fs_fname_decrypt (error code %d)\n", + __func__, res); + return res; + } + + oname->len = strnlen(oname->name, iname->len); + return oname->len; +} + +static const char *lookup_table = + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,"; + +/** + * f2fs_fname_encode_digest() - + * + * Encodes the input digest using characters from the set [a-zA-Z0-9_+]. + * The encoded string is roughly 4/3 times the size of the input string. + */ +static int digest_encode(const char *src, int len, char *dst) +{ + int i = 0, bits = 0, ac = 0; + char *cp = dst; + + while (i < len) { + ac += (((unsigned char) src[i]) << bits); + bits += 8; + do { + *cp++ = lookup_table[ac & 0x3f]; + ac >>= 6; + bits -= 6; + } while (bits >= 6); + i++; + } + if (bits) + *cp++ = lookup_table[ac & 0x3f]; + return cp - dst; +} + +static int digest_decode(const char *src, int len, char *dst) +{ + int i = 0, bits = 0, ac = 0; + const char *p; + char *cp = dst; + + while (i < len) { + p = strchr(lookup_table, src[i]); + if (p == NULL || src[i] == 0) + return -2; + ac += (p - lookup_table) << bits; + bits += 6; + if (bits >= 8) { + *cp++ = ac & 0xff; + ac >>= 8; + bits -= 8; + } + i++; + } + if (ac) + return -1; + return cp - dst; +} + +/** + * f2fs_fname_crypto_round_up() - + * + * Return: The next multiple of block size + */ +u32 f2fs_fname_crypto_round_up(u32 size, u32 blksize) +{ + return ((size + blksize - 1) / blksize) * blksize; +} + +/** + * f2fs_fname_crypto_alloc_obuff() - + * + * Allocates an output buffer that is sufficient for the crypto operation + * specified by the context and the direction. + */ +int f2fs_fname_crypto_alloc_buffer(struct inode *inode, + u32 ilen, struct f2fs_str *crypto_str) +{ + unsigned int olen; + int padding = 16; + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + + if (ci) + padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK); + if (padding < F2FS_CRYPTO_BLOCK_SIZE) + padding = F2FS_CRYPTO_BLOCK_SIZE; + olen = f2fs_fname_crypto_round_up(ilen, padding); + crypto_str->len = olen; + if (olen < F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2) + olen = F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2; + /* Allocated buffer can hold one more character to null-terminate the + * string */ + crypto_str->name = kmalloc(olen + 1, GFP_NOFS); + if (!(crypto_str->name)) + return -ENOMEM; + return 0; +} + +/** + * f2fs_fname_crypto_free_buffer() - + * + * Frees the buffer allocated for crypto operation. + */ +void f2fs_fname_crypto_free_buffer(struct f2fs_str *crypto_str) +{ + if (!crypto_str) + return; + kfree(crypto_str->name); + crypto_str->name = NULL; +} + +/** + * f2fs_fname_disk_to_usr() - converts a filename from disk space to user space + */ +int f2fs_fname_disk_to_usr(struct inode *inode, + f2fs_hash_t *hash, + const struct f2fs_str *iname, + struct f2fs_str *oname) +{ + const struct qstr qname = FSTR_TO_QSTR(iname); + char buf[24]; + int ret; + + if (is_dot_dotdot(&qname)) { + oname->name[0] = '.'; + oname->name[iname->len - 1] = '.'; + oname->len = iname->len; + return oname->len; + } + + if (F2FS_I(inode)->i_crypt_info) + return f2fs_fname_decrypt(inode, iname, oname); + + if (iname->len <= F2FS_FNAME_CRYPTO_DIGEST_SIZE) { + ret = digest_encode(iname->name, iname->len, oname->name); + oname->len = ret; + return ret; + } + if (hash) { + memcpy(buf, hash, 4); + memset(buf + 4, 0, 4); + } else + memset(buf, 0, 8); + memcpy(buf + 8, iname->name + iname->len - 16, 16); + oname->name[0] = '_'; + ret = digest_encode(buf, 24, oname->name + 1); + oname->len = ret + 1; + return ret + 1; +} + +/** + * f2fs_fname_usr_to_disk() - converts a filename from user space to disk space + */ +int f2fs_fname_usr_to_disk(struct inode *inode, + const struct qstr *iname, + struct f2fs_str *oname) +{ + int res; + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + + if (is_dot_dotdot(iname)) { + oname->name[0] = '.'; + oname->name[iname->len - 1] = '.'; + oname->len = iname->len; + return oname->len; + } + + if (ci) { + res = f2fs_fname_encrypt(inode, iname, oname); + return res; + } + /* Without a proper key, a user is not allowed to modify the filenames + * in a directory. Consequently, a user space name cannot be mapped to + * a disk-space name */ + return -EACCES; +} + +int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname, + int lookup, struct f2fs_filename *fname) +{ + struct f2fs_crypt_info *ci; + int ret = 0, bigname = 0; + + memset(fname, 0, sizeof(struct f2fs_filename)); + fname->usr_fname = iname; + + if (!f2fs_encrypted_inode(dir) || is_dot_dotdot(iname)) { + fname->disk_name.name = (unsigned char *)iname->name; + fname->disk_name.len = iname->len; + return 0; + } + ret = f2fs_get_encryption_info(dir); + if (ret) + return ret; + ci = F2FS_I(dir)->i_crypt_info; + if (ci) { + ret = f2fs_fname_crypto_alloc_buffer(dir, iname->len, + &fname->crypto_buf); + if (ret < 0) + return ret; + ret = f2fs_fname_encrypt(dir, iname, &fname->crypto_buf); + if (ret < 0) + goto errout; + fname->disk_name.name = fname->crypto_buf.name; + fname->disk_name.len = fname->crypto_buf.len; + return 0; + } + if (!lookup) + return -EACCES; + + /* We don't have the key and we are doing a lookup; decode the + * user-supplied name + */ + if (iname->name[0] == '_') + bigname = 1; + if ((bigname && (iname->len != 33)) || + (!bigname && (iname->len > 43))) + return -ENOENT; + + fname->crypto_buf.name = kmalloc(32, GFP_KERNEL); + if (fname->crypto_buf.name == NULL) + return -ENOMEM; + ret = digest_decode(iname->name + bigname, iname->len - bigname, + fname->crypto_buf.name); + if (ret < 0) { + ret = -ENOENT; + goto errout; + } + fname->crypto_buf.len = ret; + if (bigname) { + memcpy(&fname->hash, fname->crypto_buf.name, 4); + } else { + fname->disk_name.name = fname->crypto_buf.name; + fname->disk_name.len = fname->crypto_buf.len; + } + return 0; +errout: + f2fs_fname_crypto_free_buffer(&fname->crypto_buf); + return ret; +} + +void f2fs_fname_free_filename(struct f2fs_filename *fname) +{ + kfree(fname->crypto_buf.name); + fname->crypto_buf.name = NULL; + fname->usr_fname = NULL; + fname->disk_name.name = NULL; +} diff --git a/fs/f2fs/crypto_key.c b/fs/f2fs/crypto_key.c new file mode 100644 index 000000000000..95b8f936f00b --- /dev/null +++ b/fs/f2fs/crypto_key.c @@ -0,0 +1,255 @@ +/* + * linux/fs/f2fs/crypto_key.c + * + * Copied from linux/fs/f2fs/crypto_key.c + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption key functions for f2fs + * + * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015. + */ +#include <keys/encrypted-type.h> +#include <keys/user-type.h> +#include <linux/random.h> +#include <linux/scatterlist.h> +#include <uapi/linux/keyctl.h> +#include <crypto/hash.h> +#include <linux/f2fs_fs.h> + +#include "f2fs.h" +#include "xattr.h" + +static void derive_crypt_complete(struct crypto_async_request *req, int rc) +{ + struct f2fs_completion_result *ecr = req->data; + + if (rc == -EINPROGRESS) + return; + + ecr->res = rc; + complete(&ecr->completion); +} + +/** + * f2fs_derive_key_aes() - Derive a key using AES-128-ECB + * @deriving_key: Encryption key used for derivatio. + * @source_key: Source key to which to apply derivation. + * @derived_key: Derived key. + * + * Return: Zero on success; non-zero otherwise. + */ +static int f2fs_derive_key_aes(char deriving_key[F2FS_AES_128_ECB_KEY_SIZE], + char source_key[F2FS_AES_256_XTS_KEY_SIZE], + char derived_key[F2FS_AES_256_XTS_KEY_SIZE]) +{ + int res = 0; + struct ablkcipher_request *req = NULL; + DECLARE_F2FS_COMPLETION_RESULT(ecr); + struct scatterlist src_sg, dst_sg; + struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0, + 0); + + if (IS_ERR(tfm)) { + res = PTR_ERR(tfm); + tfm = NULL; + goto out; + } + crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + req = ablkcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + res = -ENOMEM; + goto out; + } + ablkcipher_request_set_callback(req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + derive_crypt_complete, &ecr); + res = crypto_ablkcipher_setkey(tfm, deriving_key, + F2FS_AES_128_ECB_KEY_SIZE); + if (res < 0) + goto out; + + sg_init_one(&src_sg, source_key, F2FS_AES_256_XTS_KEY_SIZE); + sg_init_one(&dst_sg, derived_key, F2FS_AES_256_XTS_KEY_SIZE); + ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, + F2FS_AES_256_XTS_KEY_SIZE, NULL); + res = crypto_ablkcipher_encrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } +out: + if (req) + ablkcipher_request_free(req); + if (tfm) + crypto_free_ablkcipher(tfm); + return res; +} + +static void f2fs_free_crypt_info(struct f2fs_crypt_info *ci) +{ + if (!ci) + return; + + if (ci->ci_keyring_key) + key_put(ci->ci_keyring_key); + crypto_free_ablkcipher(ci->ci_ctfm); + kmem_cache_free(f2fs_crypt_info_cachep, ci); +} + +void f2fs_free_encryption_info(struct inode *inode, struct f2fs_crypt_info *ci) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_crypt_info *prev; + + if (ci == NULL) + ci = ACCESS_ONCE(fi->i_crypt_info); + if (ci == NULL) + return; + prev = cmpxchg(&fi->i_crypt_info, ci, NULL); + if (prev != ci) + return; + + f2fs_free_crypt_info(ci); +} + +int _f2fs_get_encryption_info(struct inode *inode) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_crypt_info *crypt_info; + char full_key_descriptor[F2FS_KEY_DESC_PREFIX_SIZE + + (F2FS_KEY_DESCRIPTOR_SIZE * 2) + 1]; + struct key *keyring_key = NULL; + struct f2fs_encryption_key *master_key; + struct f2fs_encryption_context ctx; + struct user_key_payload *ukp; + struct crypto_ablkcipher *ctfm; + const char *cipher_str; + char raw_key[F2FS_MAX_KEY_SIZE]; + char mode; + int res; + + res = f2fs_crypto_initialize(); + if (res) + return res; +retry: + crypt_info = ACCESS_ONCE(fi->i_crypt_info); + if (crypt_info) { + if (!crypt_info->ci_keyring_key || + key_validate(crypt_info->ci_keyring_key) == 0) + return 0; + f2fs_free_encryption_info(inode, crypt_info); + goto retry; + } + + res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, + &ctx, sizeof(ctx), NULL); + if (res < 0) + return res; + else if (res != sizeof(ctx)) + return -EINVAL; + res = 0; + + crypt_info = kmem_cache_alloc(f2fs_crypt_info_cachep, GFP_NOFS); + if (!crypt_info) + return -ENOMEM; + + crypt_info->ci_flags = ctx.flags; + crypt_info->ci_data_mode = ctx.contents_encryption_mode; + crypt_info->ci_filename_mode = ctx.filenames_encryption_mode; + crypt_info->ci_ctfm = NULL; + crypt_info->ci_keyring_key = NULL; + memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor, + sizeof(crypt_info->ci_master_key)); + if (S_ISREG(inode->i_mode)) + mode = crypt_info->ci_data_mode; + else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) + mode = crypt_info->ci_filename_mode; + else + BUG(); + + switch (mode) { + case F2FS_ENCRYPTION_MODE_AES_256_XTS: + cipher_str = "xts(aes)"; + break; + case F2FS_ENCRYPTION_MODE_AES_256_CTS: + cipher_str = "cts(cbc(aes))"; + break; + default: + printk_once(KERN_WARNING + "f2fs: unsupported key mode %d (ino %u)\n", + mode, (unsigned) inode->i_ino); + res = -ENOKEY; + goto out; + } + + memcpy(full_key_descriptor, F2FS_KEY_DESC_PREFIX, + F2FS_KEY_DESC_PREFIX_SIZE); + sprintf(full_key_descriptor + F2FS_KEY_DESC_PREFIX_SIZE, + "%*phN", F2FS_KEY_DESCRIPTOR_SIZE, + ctx.master_key_descriptor); + full_key_descriptor[F2FS_KEY_DESC_PREFIX_SIZE + + (2 * F2FS_KEY_DESCRIPTOR_SIZE)] = '\0'; + keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL); + if (IS_ERR(keyring_key)) { + res = PTR_ERR(keyring_key); + keyring_key = NULL; + goto out; + } + crypt_info->ci_keyring_key = keyring_key; + BUG_ON(keyring_key->type != &key_type_logon); + ukp = ((struct user_key_payload *)keyring_key->payload.data); + if (ukp->datalen != sizeof(struct f2fs_encryption_key)) { + res = -EINVAL; + goto out; + } + master_key = (struct f2fs_encryption_key *)ukp->data; + BUILD_BUG_ON(F2FS_AES_128_ECB_KEY_SIZE != + F2FS_KEY_DERIVATION_NONCE_SIZE); + BUG_ON(master_key->size != F2FS_AES_256_XTS_KEY_SIZE); + res = f2fs_derive_key_aes(ctx.nonce, master_key->raw, + raw_key); + if (res) + goto out; + + ctfm = crypto_alloc_ablkcipher(cipher_str, 0, 0); + if (!ctfm || IS_ERR(ctfm)) { + res = ctfm ? PTR_ERR(ctfm) : -ENOMEM; + printk(KERN_DEBUG + "%s: error %d (inode %u) allocating crypto tfm\n", + __func__, res, (unsigned) inode->i_ino); + goto out; + } + crypt_info->ci_ctfm = ctfm; + crypto_ablkcipher_clear_flags(ctfm, ~0); + crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctfm), + CRYPTO_TFM_REQ_WEAK_KEY); + res = crypto_ablkcipher_setkey(ctfm, raw_key, + f2fs_encryption_key_size(mode)); + if (res) + goto out; + + memzero_explicit(raw_key, sizeof(raw_key)); + if (cmpxchg(&fi->i_crypt_info, NULL, crypt_info) != NULL) { + f2fs_free_crypt_info(crypt_info); + goto retry; + } + return 0; + +out: + if (res == -ENOKEY && !S_ISREG(inode->i_mode)) + res = 0; + + f2fs_free_crypt_info(crypt_info); + memzero_explicit(raw_key, sizeof(raw_key)); + return res; +} + +int f2fs_has_encryption_key(struct inode *inode) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + + return (fi->i_crypt_info != NULL); +} diff --git a/fs/f2fs/crypto_policy.c b/fs/f2fs/crypto_policy.c new file mode 100644 index 000000000000..d4a96af513c2 --- /dev/null +++ b/fs/f2fs/crypto_policy.c @@ -0,0 +1,209 @@ +/* + * copied from linux/fs/ext4/crypto_policy.c + * + * Copyright (C) 2015, Google, Inc. + * Copyright (C) 2015, Motorola Mobility. + * + * This contains encryption policy functions for f2fs with some modifications + * to support f2fs-specific xattr APIs. + * + * Written by Michael Halcrow, 2015. + * Modified by Jaegeuk Kim, 2015. + */ +#include <linux/random.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/f2fs_fs.h> + +#include "f2fs.h" +#include "xattr.h" + +static int f2fs_inode_has_encryption_context(struct inode *inode) +{ + int res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, NULL, 0, NULL); + return (res > 0); +} + +/* + * check whether the policy is consistent with the encryption context + * for the inode + */ +static int f2fs_is_encryption_context_consistent_with_policy( + struct inode *inode, const struct f2fs_encryption_policy *policy) +{ + struct f2fs_encryption_context ctx; + int res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, + sizeof(ctx), NULL); + + if (res != sizeof(ctx)) + return 0; + + return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor, + F2FS_KEY_DESCRIPTOR_SIZE) == 0 && + (ctx.flags == policy->flags) && + (ctx.contents_encryption_mode == + policy->contents_encryption_mode) && + (ctx.filenames_encryption_mode == + policy->filenames_encryption_mode)); +} + +static int f2fs_create_encryption_context_from_policy( + struct inode *inode, const struct f2fs_encryption_policy *policy) +{ + struct f2fs_encryption_context ctx; + + ctx.format = F2FS_ENCRYPTION_CONTEXT_FORMAT_V1; + memcpy(ctx.master_key_descriptor, policy->master_key_descriptor, + F2FS_KEY_DESCRIPTOR_SIZE); + + if (!f2fs_valid_contents_enc_mode(policy->contents_encryption_mode)) { + printk(KERN_WARNING + "%s: Invalid contents encryption mode %d\n", __func__, + policy->contents_encryption_mode); + return -EINVAL; + } + + if (!f2fs_valid_filenames_enc_mode(policy->filenames_encryption_mode)) { + printk(KERN_WARNING + "%s: Invalid filenames encryption mode %d\n", __func__, + policy->filenames_encryption_mode); + return -EINVAL; + } + + if (policy->flags & ~F2FS_POLICY_FLAGS_VALID) + return -EINVAL; + + ctx.contents_encryption_mode = policy->contents_encryption_mode; + ctx.filenames_encryption_mode = policy->filenames_encryption_mode; + ctx.flags = policy->flags; + BUILD_BUG_ON(sizeof(ctx.nonce) != F2FS_KEY_DERIVATION_NONCE_SIZE); + get_random_bytes(ctx.nonce, F2FS_KEY_DERIVATION_NONCE_SIZE); + + return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, + sizeof(ctx), NULL, XATTR_CREATE); +} + +int f2fs_process_policy(const struct f2fs_encryption_policy *policy, + struct inode *inode) +{ + if (policy->version != 0) + return -EINVAL; + + if (!S_ISDIR(inode->i_mode)) + return -EINVAL; + + if (!f2fs_inode_has_encryption_context(inode)) { + if (!f2fs_empty_dir(inode)) + return -ENOTEMPTY; + return f2fs_create_encryption_context_from_policy(inode, + policy); + } + + if (f2fs_is_encryption_context_consistent_with_policy(inode, policy)) + return 0; + + printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n", + __func__); + return -EINVAL; +} + +int f2fs_get_policy(struct inode *inode, struct f2fs_encryption_policy *policy) +{ + struct f2fs_encryption_context ctx; + int res; + + if (!f2fs_encrypted_inode(inode)) + return -ENODATA; + + res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, + &ctx, sizeof(ctx), NULL); + if (res != sizeof(ctx)) + return -ENODATA; + if (ctx.format != F2FS_ENCRYPTION_CONTEXT_FORMAT_V1) + return -EINVAL; + + policy->version = 0; + policy->contents_encryption_mode = ctx.contents_encryption_mode; + policy->filenames_encryption_mode = ctx.filenames_encryption_mode; + policy->flags = ctx.flags; + memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor, + F2FS_KEY_DESCRIPTOR_SIZE); + return 0; +} + +int f2fs_is_child_context_consistent_with_parent(struct inode *parent, + struct inode *child) +{ + struct f2fs_crypt_info *parent_ci, *child_ci; + int res; + + if ((parent == NULL) || (child == NULL)) { + pr_err("parent %p child %p\n", parent, child); + BUG_ON(1); + } + + /* no restrictions if the parent directory is not encrypted */ + if (!f2fs_encrypted_inode(parent)) + return 1; + /* if the child directory is not encrypted, this is always a problem */ + if (!f2fs_encrypted_inode(child)) + return 0; + res = f2fs_get_encryption_info(parent); + if (res) + return 0; + res = f2fs_get_encryption_info(child); + if (res) + return 0; + parent_ci = F2FS_I(parent)->i_crypt_info; + child_ci = F2FS_I(child)->i_crypt_info; + if (!parent_ci && !child_ci) + return 1; + if (!parent_ci || !child_ci) + return 0; + + return (memcmp(parent_ci->ci_master_key, + child_ci->ci_master_key, + F2FS_KEY_DESCRIPTOR_SIZE) == 0 && + (parent_ci->ci_data_mode == child_ci->ci_data_mode) && + (parent_ci->ci_filename_mode == child_ci->ci_filename_mode) && + (parent_ci->ci_flags == child_ci->ci_flags)); +} + +/** + * f2fs_inherit_context() - Sets a child context from its parent + * @parent: Parent inode from which the context is inherited. + * @child: Child inode that inherits the context from @parent. + * + * Return: Zero on success, non-zero otherwise + */ +int f2fs_inherit_context(struct inode *parent, struct inode *child, + struct page *ipage) +{ + struct f2fs_encryption_context ctx; + struct f2fs_crypt_info *ci; + int res; + + res = f2fs_get_encryption_info(parent); + if (res < 0) + return res; + + ci = F2FS_I(parent)->i_crypt_info; + BUG_ON(ci == NULL); + + ctx.format = F2FS_ENCRYPTION_CONTEXT_FORMAT_V1; + + ctx.contents_encryption_mode = ci->ci_data_mode; + ctx.filenames_encryption_mode = ci->ci_filename_mode; + ctx.flags = ci->ci_flags; + memcpy(ctx.master_key_descriptor, ci->ci_master_key, + F2FS_KEY_DESCRIPTOR_SIZE); + + get_random_bytes(ctx.nonce, F2FS_KEY_DERIVATION_NONCE_SIZE); + return f2fs_setxattr(child, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, + sizeof(ctx), ipage, XATTR_CREATE); +} diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 1e1aae669fa8..9bedfa8dd3a5 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -18,6 +18,7 @@ #include <linux/bio.h> #include <linux/prefetch.h> #include <linux/uio.h> +#include <linux/cleancache.h> #include "f2fs.h" #include "node.h" @@ -33,6 +34,15 @@ static void f2fs_read_end_io(struct bio *bio, int err) struct bio_vec *bvec; int i; + if (f2fs_bio_encrypted(bio)) { + if (err) { + f2fs_release_crypto_ctx(bio->bi_private); + } else { + f2fs_end_io_crypto_work(bio->bi_private, bio); + return; + } + } + bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; @@ -56,6 +66,8 @@ static void f2fs_write_end_io(struct bio *bio, int err) bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; + f2fs_restore_and_release_control_page(&page); + if (unlikely(err)) { set_page_dirty(page); set_bit(AS_EIO, &page->mapping->flags); @@ -86,7 +98,7 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr, bio->bi_bdev = sbi->sb->s_bdev; bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr); bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io; - bio->bi_private = sbi; + bio->bi_private = is_read ? NULL : sbi; return bio; } @@ -133,16 +145,16 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, * Fill the locked page with data located in the block address. * Return unlocked page. */ -int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page, - struct f2fs_io_info *fio) +int f2fs_submit_page_bio(struct f2fs_io_info *fio) { struct bio *bio; + struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page; trace_f2fs_submit_page_bio(page, fio); - f2fs_trace_ios(page, fio, 0); + f2fs_trace_ios(fio, 0); /* Allocate a new bio */ - bio = __bio_alloc(sbi, fio->blk_addr, 1, is_read_io(fio->rw)); + bio = __bio_alloc(fio->sbi, fio->blk_addr, 1, is_read_io(fio->rw)); if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { bio_put(bio); @@ -154,12 +166,13 @@ int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page, return 0; } -void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page, - struct f2fs_io_info *fio) +void f2fs_submit_page_mbio(struct f2fs_io_info *fio) { + struct f2fs_sb_info *sbi = fio->sbi; enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); struct f2fs_bio_info *io; bool is_read = is_read_io(fio->rw); + struct page *bio_page; io = is_read ? &sbi->read_io : &sbi->write_io[btype]; @@ -181,17 +194,19 @@ alloc_new: io->fio = *fio; } - if (bio_add_page(io->bio, page, PAGE_CACHE_SIZE, 0) < + bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; + + if (bio_add_page(io->bio, bio_page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { __submit_merged_bio(io); goto alloc_new; } io->last_block_in_bio = fio->blk_addr; - f2fs_trace_ios(page, fio, 0); + f2fs_trace_ios(fio, 0); up_write(&io->io_rwsem); - trace_f2fs_submit_page_mbio(page, fio); + trace_f2fs_submit_page_mbio(fio->page, fio); } /* @@ -251,19 +266,6 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index) return err; } -static void f2fs_map_bh(struct super_block *sb, pgoff_t pgofs, - struct extent_info *ei, struct buffer_head *bh_result) -{ - unsigned int blkbits = sb->s_blocksize_bits; - size_t max_size = bh_result->b_size; - size_t mapped_size; - - clear_buffer_new(bh_result); - map_bh(bh_result, sb, ei->blk + pgofs - ei->fofs); - mapped_size = (ei->fofs + ei->len - pgofs) << blkbits; - bh_result->b_size = min(max_size, mapped_size); -} - static bool lookup_extent_info(struct inode *inode, pgoff_t pgofs, struct extent_info *ei) { @@ -905,7 +907,7 @@ void f2fs_update_extent_cache(struct dnode_of_data *dn) sync_inode_page(dn); } -struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync) +struct page *get_read_data_page(struct inode *inode, pgoff_t index, int rw) { struct address_space *mapping = inode->i_mapping; struct dnode_of_data dn; @@ -913,83 +915,15 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync) struct extent_info ei; int err; struct f2fs_io_info fio = { + .sbi = F2FS_I_SB(inode), .type = DATA, - .rw = sync ? READ_SYNC : READA, + .rw = rw, + .encrypted_page = NULL, }; - /* - * If sync is false, it needs to check its block allocation. - * This is need and triggered by two flows: - * gc and truncate_partial_data_page. - */ - if (!sync) - goto search; - - page = find_get_page(mapping, index); - if (page && PageUptodate(page)) - return page; - f2fs_put_page(page, 0); -search: - if (f2fs_lookup_extent_cache(inode, index, &ei)) { - dn.data_blkaddr = ei.blk + index - ei.fofs; - goto got_it; - } - - set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, index, LOOKUP_NODE); - if (err) - return ERR_PTR(err); - f2fs_put_dnode(&dn); + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + return read_mapping_page(mapping, index, NULL); - if (dn.data_blkaddr == NULL_ADDR) - return ERR_PTR(-ENOENT); - - /* By fallocate(), there is no cached page, but with NEW_ADDR */ - if (unlikely(dn.data_blkaddr == NEW_ADDR)) - return ERR_PTR(-EINVAL); - -got_it: - page = grab_cache_page(mapping, index); - if (!page) - return ERR_PTR(-ENOMEM); - - if (PageUptodate(page)) { - unlock_page(page); - return page; - } - - fio.blk_addr = dn.data_blkaddr; - err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio); - if (err) - return ERR_PTR(err); - - if (sync) { - wait_on_page_locked(page); - if (unlikely(!PageUptodate(page))) { - f2fs_put_page(page, 0); - return ERR_PTR(-EIO); - } - } - return page; -} - -/* - * If it tries to access a hole, return an error. - * Because, the callers, functions in dir.c and GC, should be able to know - * whether this page exists or not. - */ -struct page *get_lock_data_page(struct inode *inode, pgoff_t index) -{ - struct address_space *mapping = inode->i_mapping; - struct dnode_of_data dn; - struct page *page; - struct extent_info ei; - int err; - struct f2fs_io_info fio = { - .type = DATA, - .rw = READ_SYNC, - }; -repeat: page = grab_cache_page(mapping, index); if (!page) return ERR_PTR(-ENOMEM); @@ -1011,10 +945,11 @@ repeat: f2fs_put_page(page, 1); return ERR_PTR(-ENOENT); } - got_it: - if (PageUptodate(page)) + if (PageUptodate(page)) { + unlock_page(page); return page; + } /* * A new dentry page is allocated but not able to be written, since its @@ -1025,14 +960,58 @@ got_it: if (dn.data_blkaddr == NEW_ADDR) { zero_user_segment(page, 0, PAGE_CACHE_SIZE); SetPageUptodate(page); + unlock_page(page); return page; } fio.blk_addr = dn.data_blkaddr; - err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio); + fio.page = page; + err = f2fs_submit_page_bio(&fio); if (err) return ERR_PTR(err); + return page; +} + +struct page *find_data_page(struct inode *inode, pgoff_t index) +{ + struct address_space *mapping = inode->i_mapping; + struct page *page; + + page = find_get_page(mapping, index); + if (page && PageUptodate(page)) + return page; + f2fs_put_page(page, 0); + page = get_read_data_page(inode, index, READ_SYNC); + if (IS_ERR(page)) + return page; + + if (PageUptodate(page)) + return page; + + wait_on_page_locked(page); + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 0); + return ERR_PTR(-EIO); + } + return page; +} + +/* + * If it tries to access a hole, return an error. + * Because, the callers, functions in dir.c and GC, should be able to know + * whether this page exists or not. + */ +struct page *get_lock_data_page(struct inode *inode, pgoff_t index) +{ + struct address_space *mapping = inode->i_mapping; + struct page *page; +repeat: + page = get_read_data_page(inode, index, READ_SYNC); + if (IS_ERR(page)) + return page; + + /* wait for read completion */ lock_page(page); if (unlikely(!PageUptodate(page))) { f2fs_put_page(page, 1); @@ -1060,46 +1039,37 @@ struct page *get_new_data_page(struct inode *inode, struct page *page; struct dnode_of_data dn; int err; +repeat: + page = grab_cache_page(mapping, index); + if (!page) + return ERR_PTR(-ENOMEM); set_new_dnode(&dn, inode, ipage, NULL, 0); err = f2fs_reserve_block(&dn, index); - if (err) + if (err) { + f2fs_put_page(page, 1); return ERR_PTR(err); -repeat: - page = grab_cache_page(mapping, index); - if (!page) { - err = -ENOMEM; - goto put_err; } + if (!ipage) + f2fs_put_dnode(&dn); if (PageUptodate(page)) - return page; + goto got_it; if (dn.data_blkaddr == NEW_ADDR) { zero_user_segment(page, 0, PAGE_CACHE_SIZE); SetPageUptodate(page); } else { - struct f2fs_io_info fio = { - .type = DATA, - .rw = READ_SYNC, - .blk_addr = dn.data_blkaddr, - }; - err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio); - if (err) - goto put_err; + f2fs_put_page(page, 1); - lock_page(page); - if (unlikely(!PageUptodate(page))) { - f2fs_put_page(page, 1); - err = -EIO; - goto put_err; - } - if (unlikely(page->mapping != mapping)) { - f2fs_put_page(page, 1); + page = get_read_data_page(inode, index, READ_SYNC); + if (IS_ERR(page)) goto repeat; - } - } + /* wait for read completion */ + lock_page(page); + } +got_it: if (new_i_size && i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) { i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT)); @@ -1107,10 +1077,6 @@ repeat: set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR); } return page; - -put_err: - f2fs_put_dnode(&dn); - return ERR_PTR(err); } static int __allocate_data_block(struct dnode_of_data *dn) @@ -1208,18 +1174,18 @@ out: } /* - * get_data_block() now supported readahead/bmap/rw direct_IO with mapped bh. + * f2fs_map_blocks() now supported readahead/bmap/rw direct_IO with + * f2fs_map_blocks structure. * If original data blocks are allocated, then give them to blockdev. * Otherwise, * a. preallocate requested block addresses * b. do not use extent cache for better performance * c. give the block addresses to blockdev */ -static int __get_data_block(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create, bool fiemap) +static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, + int create, bool fiemap) { - unsigned int blkbits = inode->i_sb->s_blocksize_bits; - unsigned maxblocks = bh_result->b_size >> blkbits; + unsigned int maxblocks = map->m_len; struct dnode_of_data dn; int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA; pgoff_t pgofs, end_offset; @@ -1227,11 +1193,16 @@ static int __get_data_block(struct inode *inode, sector_t iblock, struct extent_info ei; bool allocated = false; - /* Get the page offset from the block offset(iblock) */ - pgofs = (pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits)); + map->m_len = 0; + map->m_flags = 0; + + /* it only supports block size == page size */ + pgofs = (pgoff_t)map->m_lblk; if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) { - f2fs_map_bh(inode->i_sb, pgofs, &ei, bh_result); + map->m_pblk = ei.blk + pgofs - ei.fofs; + map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs); + map->m_flags = F2FS_MAP_MAPPED; goto out; } @@ -1250,21 +1221,23 @@ static int __get_data_block(struct inode *inode, sector_t iblock, goto put_out; if (dn.data_blkaddr != NULL_ADDR) { - clear_buffer_new(bh_result); - map_bh(bh_result, inode->i_sb, dn.data_blkaddr); + map->m_flags = F2FS_MAP_MAPPED; + map->m_pblk = dn.data_blkaddr; + if (dn.data_blkaddr == NEW_ADDR) + map->m_flags |= F2FS_MAP_UNWRITTEN; } else if (create) { err = __allocate_data_block(&dn); if (err) goto put_out; allocated = true; - set_buffer_new(bh_result); - map_bh(bh_result, inode->i_sb, dn.data_blkaddr); + map->m_flags = F2FS_MAP_NEW | F2FS_MAP_MAPPED; + map->m_pblk = dn.data_blkaddr; } else { goto put_out; } end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); - bh_result->b_size = (((size_t)1) << blkbits); + map->m_len = 1; dn.ofs_in_node++; pgofs++; @@ -1288,22 +1261,25 @@ get_next: end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); } - if (maxblocks > (bh_result->b_size >> blkbits)) { + if (maxblocks > map->m_len) { block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); if (blkaddr == NULL_ADDR && create) { err = __allocate_data_block(&dn); if (err) goto sync_out; allocated = true; - set_buffer_new(bh_result); + map->m_flags |= F2FS_MAP_NEW; blkaddr = dn.data_blkaddr; } /* Give more consecutive addresses for the readahead */ - if (blkaddr == (bh_result->b_blocknr + ofs)) { + if ((map->m_pblk != NEW_ADDR && + blkaddr == (map->m_pblk + ofs)) || + (map->m_pblk == NEW_ADDR && + blkaddr == NEW_ADDR)) { ofs++; dn.ofs_in_node++; pgofs++; - bh_result->b_size += (((size_t)1) << blkbits); + map->m_len++; goto get_next; } } @@ -1316,10 +1292,28 @@ unlock_out: if (create) f2fs_unlock_op(F2FS_I_SB(inode)); out: - trace_f2fs_get_data_block(inode, iblock, bh_result, err); + trace_f2fs_map_blocks(inode, map, err); return err; } +static int __get_data_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh, int create, bool fiemap) +{ + struct f2fs_map_blocks map; + int ret; + + map.m_lblk = iblock; + map.m_len = bh->b_size >> inode->i_blkbits; + + ret = f2fs_map_blocks(inode, &map, create, fiemap); + if (!ret) { + map_bh(bh, inode->i_sb, map.m_pblk); + bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags; + bh->b_size = map.m_len << inode->i_blkbits; + } + return ret; +} + static int get_data_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { @@ -1332,11 +1326,268 @@ static int get_data_block_fiemap(struct inode *inode, sector_t iblock, return __get_data_block(inode, iblock, bh_result, create, true); } +static inline sector_t logical_to_blk(struct inode *inode, loff_t offset) +{ + return (offset >> inode->i_blkbits); +} + +static inline loff_t blk_to_logical(struct inode *inode, sector_t blk) +{ + return (blk << inode->i_blkbits); +} + int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { - return generic_block_fiemap(inode, fieinfo, - start, len, get_data_block_fiemap); + struct buffer_head map_bh; + sector_t start_blk, last_blk; + loff_t isize = i_size_read(inode); + u64 logical = 0, phys = 0, size = 0; + u32 flags = 0; + bool past_eof = false, whole_file = false; + int ret = 0; + + ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC); + if (ret) + return ret; + + mutex_lock(&inode->i_mutex); + + if (len >= isize) { + whole_file = true; + len = isize; + } + + if (logical_to_blk(inode, len) == 0) + len = blk_to_logical(inode, 1); + + start_blk = logical_to_blk(inode, start); + last_blk = logical_to_blk(inode, start + len - 1); +next: + memset(&map_bh, 0, sizeof(struct buffer_head)); + map_bh.b_size = len; + + ret = get_data_block_fiemap(inode, start_blk, &map_bh, 0); + if (ret) + goto out; + + /* HOLE */ + if (!buffer_mapped(&map_bh)) { + start_blk++; + + if (!past_eof && blk_to_logical(inode, start_blk) >= isize) + past_eof = 1; + + if (past_eof && size) { + flags |= FIEMAP_EXTENT_LAST; + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, flags); + } else if (size) { + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, flags); + size = 0; + } + + /* if we have holes up to/past EOF then we're done */ + if (start_blk > last_blk || past_eof || ret) + goto out; + } else { + if (start_blk > last_blk && !whole_file) { + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, flags); + goto out; + } + + /* + * if size != 0 then we know we already have an extent + * to add, so add it. + */ + if (size) { + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, flags); + if (ret) + goto out; + } + + logical = blk_to_logical(inode, start_blk); + phys = blk_to_logical(inode, map_bh.b_blocknr); + size = map_bh.b_size; + flags = 0; + if (buffer_unwritten(&map_bh)) + flags = FIEMAP_EXTENT_UNWRITTEN; + + start_blk += logical_to_blk(inode, size); + + /* + * If we are past the EOF, then we need to make sure as + * soon as we find a hole that the last extent we found + * is marked with FIEMAP_EXTENT_LAST + */ + if (!past_eof && logical + size >= isize) + past_eof = true; + } + cond_resched(); + if (fatal_signal_pending(current)) + ret = -EINTR; + else + goto next; +out: + if (ret == 1) + ret = 0; + + mutex_unlock(&inode->i_mutex); + return ret; +} + +/* + * This function was originally taken from fs/mpage.c, and customized for f2fs. + * Major change was from block_size == page_size in f2fs by default. + */ +static int f2fs_mpage_readpages(struct address_space *mapping, + struct list_head *pages, struct page *page, + unsigned nr_pages) +{ + struct bio *bio = NULL; + unsigned page_idx; + sector_t last_block_in_bio = 0; + struct inode *inode = mapping->host; + const unsigned blkbits = inode->i_blkbits; + const unsigned blocksize = 1 << blkbits; + sector_t block_in_file; + sector_t last_block; + sector_t last_block_in_file; + sector_t block_nr; + struct block_device *bdev = inode->i_sb->s_bdev; + struct f2fs_map_blocks map; + + map.m_pblk = 0; + map.m_lblk = 0; + map.m_len = 0; + map.m_flags = 0; + + for (page_idx = 0; nr_pages; page_idx++, nr_pages--) { + + prefetchw(&page->flags); + if (pages) { + page = list_entry(pages->prev, struct page, lru); + list_del(&page->lru); + if (add_to_page_cache_lru(page, mapping, + page->index, GFP_KERNEL)) + goto next_page; + } + + block_in_file = (sector_t)page->index; + last_block = block_in_file + nr_pages; + last_block_in_file = (i_size_read(inode) + blocksize - 1) >> + blkbits; + if (last_block > last_block_in_file) + last_block = last_block_in_file; + + /* + * Map blocks using the previous result first. + */ + if ((map.m_flags & F2FS_MAP_MAPPED) && + block_in_file > map.m_lblk && + block_in_file < (map.m_lblk + map.m_len)) + goto got_it; + + /* + * Then do more f2fs_map_blocks() calls until we are + * done with this page. + */ + map.m_flags = 0; + + if (block_in_file < last_block) { + map.m_lblk = block_in_file; + map.m_len = last_block - block_in_file; + + if (f2fs_map_blocks(inode, &map, 0, false)) + goto set_error_page; + } +got_it: + if ((map.m_flags & F2FS_MAP_MAPPED)) { + block_nr = map.m_pblk + block_in_file - map.m_lblk; + SetPageMappedToDisk(page); + + if (!PageUptodate(page) && !cleancache_get_page(page)) { + SetPageUptodate(page); + goto confused; + } + } else { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + SetPageUptodate(page); + unlock_page(page); + goto next_page; + } + + /* + * This page will go to BIO. Do we need to send this + * BIO off first? + */ + if (bio && (last_block_in_bio != block_nr - 1)) { +submit_and_realloc: + submit_bio(READ, bio); + bio = NULL; + } + if (bio == NULL) { + struct f2fs_crypto_ctx *ctx = NULL; + + if (f2fs_encrypted_inode(inode) && + S_ISREG(inode->i_mode)) { + struct page *cpage; + + ctx = f2fs_get_crypto_ctx(inode); + if (IS_ERR(ctx)) + goto set_error_page; + + /* wait the page to be moved by cleaning */ + cpage = find_lock_page( + META_MAPPING(F2FS_I_SB(inode)), + block_nr); + if (cpage) { + f2fs_wait_on_page_writeback(cpage, + DATA); + f2fs_put_page(cpage, 1); + } + } + + bio = bio_alloc(GFP_KERNEL, + min_t(int, nr_pages, bio_get_nr_vecs(bdev))); + if (!bio) { + if (ctx) + f2fs_release_crypto_ctx(ctx); + goto set_error_page; + } + bio->bi_bdev = bdev; + bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(block_nr); + bio->bi_end_io = f2fs_read_end_io; + bio->bi_private = ctx; + } + + if (bio_add_page(bio, page, blocksize, 0) < blocksize) + goto submit_and_realloc; + + last_block_in_bio = block_nr; + goto next_page; +set_error_page: + SetPageError(page); + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + unlock_page(page); + goto next_page; +confused: + if (bio) { + submit_bio(READ, bio); + bio = NULL; + } + unlock_page(page); +next_page: + if (pages) + page_cache_release(page); + } + BUG_ON(pages && !list_empty(pages)); + if (bio) + submit_bio(READ, bio); + return 0; } static int f2fs_read_data_page(struct file *file, struct page *page) @@ -1350,8 +1601,7 @@ static int f2fs_read_data_page(struct file *file, struct page *page) if (f2fs_has_inline_data(inode)) ret = f2fs_read_inline_data(inode, page); if (ret == -EAGAIN) - ret = mpage_readpage(page, get_data_block); - + ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1); return ret; } @@ -1365,11 +1615,12 @@ static int f2fs_read_data_pages(struct file *file, if (f2fs_has_inline_data(inode)) return 0; - return mpage_readpages(mapping, pages, nr_pages, get_data_block); + return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages); } -int do_write_data_page(struct page *page, struct f2fs_io_info *fio) +int do_write_data_page(struct f2fs_io_info *fio) { + struct page *page = fio->page; struct inode *inode = page->mapping->host; struct dnode_of_data dn; int err = 0; @@ -1387,6 +1638,14 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio) goto out_writepage; } + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { + fio->encrypted_page = f2fs_encrypt(inode, fio->page); + if (IS_ERR(fio->encrypted_page)) { + err = PTR_ERR(fio->encrypted_page); + goto out_writepage; + } + } + set_page_writeback(page); /* @@ -1396,11 +1655,11 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio) if (unlikely(fio->blk_addr != NEW_ADDR && !is_cold_data(page) && need_inplace_update(inode))) { - rewrite_data_page(page, fio); + rewrite_data_page(fio); set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE); trace_f2fs_do_write_data_page(page, IPU); } else { - write_data_page(page, &dn, fio); + write_data_page(&dn, fio); set_data_blkaddr(&dn); f2fs_update_extent_cache(&dn); trace_f2fs_do_write_data_page(page, OPU); @@ -1425,8 +1684,11 @@ static int f2fs_write_data_page(struct page *page, bool need_balance_fs = false; int err = 0; struct f2fs_io_info fio = { + .sbi = sbi, .type = DATA, .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE, + .page = page, + .encrypted_page = NULL, }; trace_f2fs_writepage(page, DATA); @@ -1456,7 +1718,7 @@ write: if (S_ISDIR(inode->i_mode)) { if (unlikely(f2fs_cp_error(sbi))) goto redirty_out; - err = do_write_data_page(page, &fio); + err = do_write_data_page(&fio); goto done; } @@ -1476,7 +1738,7 @@ write: if (f2fs_has_inline_data(inode)) err = f2fs_write_inline_data(inode, page); if (err == -EAGAIN) - err = do_write_data_page(page, &fio); + err = do_write_data_page(&fio); f2fs_unlock_op(sbi); done: if (err && err != -ENOENT) @@ -1645,11 +1907,14 @@ put_next: zero_user_segment(page, 0, PAGE_CACHE_SIZE); } else { struct f2fs_io_info fio = { + .sbi = sbi, .type = DATA, .rw = READ_SYNC, .blk_addr = dn.data_blkaddr, + .page = page, + .encrypted_page = NULL, }; - err = f2fs_submit_page_bio(sbi, page, &fio); + err = f2fs_submit_page_bio(&fio); if (err) goto fail; @@ -1663,6 +1928,15 @@ put_next: f2fs_put_page(page, 1); goto repeat; } + + /* avoid symlink page */ + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { + err = f2fs_decrypt_one(inode, page); + if (err) { + f2fs_put_page(page, 1); + goto fail; + } + } } out: SetPageUptodate(page); @@ -1733,6 +2007,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, return err; } + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + return 0; + if (check_direct_IO(inode, iter, offset)) return 0; diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index f5388f37217e..75176e0dd6c8 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -94,7 +94,8 @@ static void update_general_status(struct f2fs_sb_info *sbi) static void update_sit_info(struct f2fs_sb_info *sbi) { struct f2fs_stat_info *si = F2FS_STAT(sbi); - unsigned int blks_per_sec, hblks_per_sec, total_vblocks, bimodal, dist; + unsigned long long blks_per_sec, hblks_per_sec, total_vblocks; + unsigned long long bimodal, dist; unsigned int segno, vblocks; int ndirty = 0; @@ -112,10 +113,10 @@ static void update_sit_info(struct f2fs_sb_info *sbi) ndirty++; } } - dist = MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100; - si->bimodal = bimodal / dist; + dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100); + si->bimodal = div_u64(bimodal, dist); if (si->dirty_count) - si->avg_vblocks = total_vblocks / ndirty; + si->avg_vblocks = div_u64(total_vblocks, ndirty); else si->avg_vblocks = 0; } @@ -143,7 +144,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi) si->base_mem += sizeof(struct sit_info); si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry); si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi)); - si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); + si->base_mem += 3 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); si->base_mem += SIT_VBLOCK_MAP_SIZE; if (sbi->segs_per_sec > 1) si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 3a3302ab7871..a34ebd8312ab 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -76,20 +76,10 @@ static unsigned long dir_block_index(unsigned int level, return bidx; } -static bool early_match_name(size_t namelen, f2fs_hash_t namehash, - struct f2fs_dir_entry *de) -{ - if (le16_to_cpu(de->name_len) != namelen) - return false; - - if (de->hash_code != namehash) - return false; - - return true; -} - static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, - struct qstr *name, int *max_slots, + struct f2fs_filename *fname, + f2fs_hash_t namehash, + int *max_slots, struct page **res_page) { struct f2fs_dentry_block *dentry_blk; @@ -98,9 +88,8 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, dentry_blk = (struct f2fs_dentry_block *)kmap(dentry_page); - make_dentry_ptr(&d, (void *)dentry_blk, 1); - de = find_target_dentry(name, max_slots, &d); - + make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1); + de = find_target_dentry(fname, namehash, max_slots, &d); if (de) *res_page = dentry_page; else @@ -114,13 +103,15 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, return de; } -struct f2fs_dir_entry *find_target_dentry(struct qstr *name, int *max_slots, - struct f2fs_dentry_ptr *d) +struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *fname, + f2fs_hash_t namehash, int *max_slots, + struct f2fs_dentry_ptr *d) { struct f2fs_dir_entry *de; unsigned long bit_pos = 0; - f2fs_hash_t namehash = f2fs_dentry_hash(name); int max_len = 0; + struct f2fs_str de_name = FSTR_INIT(NULL, 0); + struct f2fs_str *name = &fname->disk_name; if (max_slots) *max_slots = 0; @@ -132,8 +123,18 @@ struct f2fs_dir_entry *find_target_dentry(struct qstr *name, int *max_slots, } de = &d->dentry[bit_pos]; - if (early_match_name(name->len, namehash, de) && - !memcmp(d->filename[bit_pos], name->name, name->len)) + + /* encrypted case */ + de_name.name = d->filename[bit_pos]; + de_name.len = le16_to_cpu(de->name_len); + + /* show encrypted name */ + if (fname->hash) { + if (de->hash_code == fname->hash) + goto found; + } else if (de_name.len == name->len && + de->hash_code == namehash && + !memcmp(de_name.name, name->name, name->len)) goto found; if (max_slots && max_len > *max_slots) @@ -155,16 +156,21 @@ found: } static struct f2fs_dir_entry *find_in_level(struct inode *dir, - unsigned int level, struct qstr *name, - f2fs_hash_t namehash, struct page **res_page) + unsigned int level, + struct f2fs_filename *fname, + struct page **res_page) { - int s = GET_DENTRY_SLOTS(name->len); + struct qstr name = FSTR_TO_QSTR(&fname->disk_name); + int s = GET_DENTRY_SLOTS(name.len); unsigned int nbucket, nblock; unsigned int bidx, end_block; struct page *dentry_page; struct f2fs_dir_entry *de = NULL; bool room = false; int max_slots; + f2fs_hash_t namehash; + + namehash = f2fs_dentry_hash(&name); f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH); @@ -177,13 +183,14 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, for (; bidx < end_block; bidx++) { /* no need to allocate new dentry pages to all the indices */ - dentry_page = find_data_page(dir, bidx, true); + dentry_page = find_data_page(dir, bidx); if (IS_ERR(dentry_page)) { room = true; continue; } - de = find_in_block(dentry_page, name, &max_slots, res_page); + de = find_in_block(dentry_page, fname, namehash, &max_slots, + res_page); if (de) break; @@ -211,30 +218,34 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir, { unsigned long npages = dir_blocks(dir); struct f2fs_dir_entry *de = NULL; - f2fs_hash_t name_hash; unsigned int max_depth; unsigned int level; + struct f2fs_filename fname; + int err; *res_page = NULL; - if (f2fs_has_inline_dentry(dir)) - return find_in_inline_dir(dir, child, res_page); + err = f2fs_fname_setup_filename(dir, child, 1, &fname); + if (err) + return NULL; + + if (f2fs_has_inline_dentry(dir)) { + de = find_in_inline_dir(dir, &fname, res_page); + goto out; + } if (npages == 0) - return NULL; + goto out; - name_hash = f2fs_dentry_hash(child); max_depth = F2FS_I(dir)->i_current_depth; for (level = 0; level < max_depth; level++) { - de = find_in_level(dir, level, child, name_hash, res_page); + de = find_in_level(dir, level, &fname, res_page); if (de) break; } - if (!de && F2FS_I(dir)->chash != name_hash) { - F2FS_I(dir)->chash = name_hash; - F2FS_I(dir)->clevel = level - 1; - } +out: + f2fs_fname_free_filename(&fname); return de; } @@ -303,10 +314,14 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage) set_page_dirty(ipage); } -int update_dent_inode(struct inode *inode, const struct qstr *name) +int update_dent_inode(struct inode *inode, struct inode *to, + const struct qstr *name) { struct page *page; + if (file_enc_name(to)) + return 0; + page = get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(page)) return PTR_ERR(page); @@ -356,7 +371,7 @@ static int make_empty_dir(struct inode *inode, dentry_blk = kmap_atomic(dentry_page); - make_dentry_ptr(&d, (void *)dentry_blk, 1); + make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1); do_make_empty_dir(inode, parent, &d); kunmap_atomic(dentry_blk); @@ -390,6 +405,12 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, err = f2fs_init_security(inode, dir, name, page); if (err) goto put_error; + + if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) { + err = f2fs_inherit_context(dir, inode, page); + if (err) + goto put_error; + } } else { page = get_node_page(F2FS_I_SB(dir), inode->i_ino); if (IS_ERR(page)) @@ -501,24 +522,33 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, unsigned long bidx, block; f2fs_hash_t dentry_hash; unsigned int nbucket, nblock; - size_t namelen = name->len; struct page *dentry_page = NULL; struct f2fs_dentry_block *dentry_blk = NULL; struct f2fs_dentry_ptr d; - int slots = GET_DENTRY_SLOTS(namelen); struct page *page = NULL; - int err = 0; + struct f2fs_filename fname; + struct qstr new_name; + int slots, err; + + err = f2fs_fname_setup_filename(dir, name, 0, &fname); + if (err) + return err; + + new_name.name = fname_name(&fname); + new_name.len = fname_len(&fname); if (f2fs_has_inline_dentry(dir)) { - err = f2fs_add_inline_entry(dir, name, inode, ino, mode); + err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode); if (!err || err != -EAGAIN) - return err; + goto out; else err = 0; } - dentry_hash = f2fs_dentry_hash(name); level = 0; + slots = GET_DENTRY_SLOTS(new_name.len); + dentry_hash = f2fs_dentry_hash(&new_name); + current_depth = F2FS_I(dir)->i_current_depth; if (F2FS_I(dir)->chash == dentry_hash) { level = F2FS_I(dir)->clevel; @@ -526,8 +556,10 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, } start: - if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) - return -ENOSPC; + if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) { + err = -ENOSPC; + goto out; + } /* Increase the depth, if required */ if (level == current_depth) @@ -541,8 +573,10 @@ start: for (block = bidx; block <= (bidx + nblock - 1); block++) { dentry_page = get_new_data_page(dir, NULL, block, true); - if (IS_ERR(dentry_page)) - return PTR_ERR(dentry_page); + if (IS_ERR(dentry_page)) { + err = PTR_ERR(dentry_page); + goto out; + } dentry_blk = kmap(dentry_page); bit_pos = room_for_filename(&dentry_blk->dentry_bitmap, @@ -562,15 +596,17 @@ add_dentry: if (inode) { down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, name, NULL); + page = init_inode_metadata(inode, dir, &new_name, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; } + if (f2fs_encrypted_inode(dir)) + file_set_enc_name(inode); } - make_dentry_ptr(&d, (void *)dentry_blk, 1); - f2fs_update_dentry(ino, mode, &d, name, dentry_hash, bit_pos); + make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1); + f2fs_update_dentry(ino, mode, &d, &new_name, dentry_hash, bit_pos); set_page_dirty(dentry_page); @@ -592,6 +628,8 @@ fail: } kunmap(dentry_page); f2fs_put_page(dentry_page, 1); +out: + f2fs_fname_free_filename(&fname); return err; } @@ -729,11 +767,12 @@ bool f2fs_empty_dir(struct inode *dir) } bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, - unsigned int start_pos) + unsigned int start_pos, struct f2fs_str *fstr) { unsigned char d_type = DT_UNKNOWN; unsigned int bit_pos; struct f2fs_dir_entry *de = NULL; + struct f2fs_str de_name = FSTR_INIT(NULL, 0); bit_pos = ((unsigned long)ctx->pos % d->max); @@ -747,8 +786,24 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, d_type = f2fs_filetype_table[de->file_type]; else d_type = DT_UNKNOWN; - if (!dir_emit(ctx, d->filename[bit_pos], - le16_to_cpu(de->name_len), + + /* encrypted case */ + de_name.name = d->filename[bit_pos]; + de_name.len = le16_to_cpu(de->name_len); + + if (f2fs_encrypted_inode(d->inode)) { + int save_len = fstr->len; + int ret; + + ret = f2fs_fname_disk_to_usr(d->inode, &de->hash_code, + &de_name, fstr); + de_name = *fstr; + fstr->len = save_len; + if (ret < 0) + return true; + } + + if (!dir_emit(ctx, de_name.name, de_name.len, le32_to_cpu(de->ino), d_type)) return true; @@ -767,9 +822,24 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) struct file_ra_state *ra = &file->f_ra; unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK); struct f2fs_dentry_ptr d; + struct f2fs_str fstr = FSTR_INIT(NULL, 0); + int err = 0; - if (f2fs_has_inline_dentry(inode)) - return f2fs_read_inline_dir(file, ctx); + if (f2fs_encrypted_inode(inode)) { + err = f2fs_get_encryption_info(inode); + if (err) + return err; + + err = f2fs_fname_crypto_alloc_buffer(inode, F2FS_NAME_LEN, + &fstr); + if (err < 0) + return err; + } + + if (f2fs_has_inline_dentry(inode)) { + err = f2fs_read_inline_dir(file, ctx, &fstr); + goto out; + } /* readahead for multi pages of dir */ if (npages - n > 1 && !ra_has_index(ra, n)) @@ -783,9 +853,9 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) dentry_blk = kmap(dentry_page); - make_dentry_ptr(&d, (void *)dentry_blk, 1); + make_dentry_ptr(inode, &d, (void *)dentry_blk, 1); - if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK)) + if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr)) goto stop; ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK; @@ -798,8 +868,9 @@ stop: kunmap(dentry_page); f2fs_put_page(dentry_page, 1); } - - return 0; +out: + f2fs_fname_crypto_free_buffer(&fstr); + return err; } const struct file_operations f2fs_dir_operations = { @@ -808,4 +879,7 @@ const struct file_operations f2fs_dir_operations = { .iterate = f2fs_readdir, .fsync = f2fs_sync_file, .unlocked_ioctl = f2fs_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = f2fs_compat_ioctl, +#endif }; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 8de34ab6d5b1..a8327ed73898 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -70,6 +70,15 @@ struct f2fs_mount_info { unsigned int opt; }; +#define F2FS_FEATURE_ENCRYPT 0x0001 + +#define F2FS_HAS_FEATURE(sb, mask) \ + ((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0) +#define F2FS_SET_FEATURE(sb, mask) \ + F2FS_SB(sb)->raw_super->feature |= cpu_to_le32(mask) +#define F2FS_CLEAR_FEATURE(sb, mask) \ + F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask) + #define CRCPOLY_LE 0xedb88320 static inline __u32 f2fs_crc32(void *buf, size_t len) @@ -110,6 +119,8 @@ enum { #define DEF_BATCHED_TRIM_SECTIONS 32 #define BATCHED_TRIM_SEGMENTS(sbi) \ (SM_I(sbi)->trim_sections * (sbi)->segs_per_sec) +#define BATCHED_TRIM_BLOCKS(sbi) \ + (BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg) struct cp_control { int reason; @@ -218,6 +229,13 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, #define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4) #define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5) +#define F2FS_IOC_SET_ENCRYPTION_POLICY \ + _IOR('f', 19, struct f2fs_encryption_policy) +#define F2FS_IOC_GET_ENCRYPTION_PWSALT \ + _IOW('f', 20, __u8[16]) +#define F2FS_IOC_GET_ENCRYPTION_POLICY \ + _IOW('f', 21, struct f2fs_encryption_policy) + /* * should be same as XFS_IOC_GOINGDOWN. * Flags for going down operation used by FS_IOC_GOINGDOWN @@ -239,16 +257,38 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, * For INODE and NODE manager */ /* for directory operations */ +struct f2fs_str { + unsigned char *name; + u32 len; +}; + +struct f2fs_filename { + const struct qstr *usr_fname; + struct f2fs_str disk_name; + f2fs_hash_t hash; +#ifdef CONFIG_F2FS_FS_ENCRYPTION + struct f2fs_str crypto_buf; +#endif +}; + +#define FSTR_INIT(n, l) { .name = n, .len = l } +#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len) +#define fname_name(p) ((p)->disk_name.name) +#define fname_len(p) ((p)->disk_name.len) + struct f2fs_dentry_ptr { + struct inode *inode; const void *bitmap; struct f2fs_dir_entry *dentry; __u8 (*filename)[F2FS_SLOT_LEN]; int max; }; -static inline void make_dentry_ptr(struct f2fs_dentry_ptr *d, - void *src, int type) +static inline void make_dentry_ptr(struct inode *inode, + struct f2fs_dentry_ptr *d, void *src, int type) { + d->inode = inode; + if (type == 1) { struct f2fs_dentry_block *t = (struct f2fs_dentry_block *)src; d->max = NR_DENTRY_IN_BLOCK; @@ -315,10 +355,51 @@ struct extent_tree { }; /* + * This structure is taken from ext4_map_blocks. + * + * Note that, however, f2fs uses NEW and MAPPED flags for f2fs_map_blocks(). + */ +#define F2FS_MAP_NEW (1 << BH_New) +#define F2FS_MAP_MAPPED (1 << BH_Mapped) +#define F2FS_MAP_UNWRITTEN (1 << BH_Unwritten) +#define F2FS_MAP_FLAGS (F2FS_MAP_NEW | F2FS_MAP_MAPPED |\ + F2FS_MAP_UNWRITTEN) + +struct f2fs_map_blocks { + block_t m_pblk; + block_t m_lblk; + unsigned int m_len; + unsigned int m_flags; +}; + +/* * i_advise uses FADVISE_XXX_BIT. We can add additional hints later. */ #define FADVISE_COLD_BIT 0x01 #define FADVISE_LOST_PINO_BIT 0x02 +#define FADVISE_ENCRYPT_BIT 0x04 +#define FADVISE_ENC_NAME_BIT 0x08 + +#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT) +#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT) +#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT) +#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT) +#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT) +#define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT) +#define file_is_encrypt(inode) is_file(inode, FADVISE_ENCRYPT_BIT) +#define file_set_encrypt(inode) set_file(inode, FADVISE_ENCRYPT_BIT) +#define file_clear_encrypt(inode) clear_file(inode, FADVISE_ENCRYPT_BIT) +#define file_enc_name(inode) is_file(inode, FADVISE_ENC_NAME_BIT) +#define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT) + +/* Encryption algorithms */ +#define F2FS_ENCRYPTION_MODE_INVALID 0 +#define F2FS_ENCRYPTION_MODE_AES_256_XTS 1 +#define F2FS_ENCRYPTION_MODE_AES_256_GCM 2 +#define F2FS_ENCRYPTION_MODE_AES_256_CBC 3 +#define F2FS_ENCRYPTION_MODE_AES_256_CTS 4 + +#include "f2fs_crypto.h" #define DEF_DIR_LEVEL 0 @@ -346,6 +427,11 @@ struct f2fs_inode_info { struct radix_tree_root inmem_root; /* radix tree for inmem pages */ struct list_head inmem_pages; /* inmemory pages managed by f2fs */ struct mutex inmem_lock; /* lock for inmemory pages */ + +#ifdef CONFIG_F2FS_FS_ENCRYPTION + /* Encryption params */ + struct f2fs_crypt_info *i_crypt_info; +#endif }; static inline void get_extent_info(struct extent_info *ext, @@ -571,9 +657,12 @@ enum page_type { }; struct f2fs_io_info { + struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */ enum page_type type; /* contains DATA/NODE/META/META_FLUSH */ int rw; /* contains R/RS/W/WS with REQ_META/REQ_PRIO */ block_t blk_addr; /* block address to be written */ + struct page *page; /* page to be written */ + struct page *encrypted_page; /* encrypted page */ }; #define is_read_io(rw) (((rw) & 1) == READ) @@ -666,6 +755,7 @@ struct f2fs_sb_info { block_t user_block_count; /* # of user blocks */ block_t total_valid_block_count; /* # of valid blocks */ block_t alloc_valid_block_count; /* # of allocated blocks */ + block_t discard_blks; /* discard command candidats */ block_t last_valid_block_count; /* for recovery */ u32 s_next_generation; /* for NFS support */ atomic_t nr_pages[NR_COUNT_TYPE]; /* # of pages, see count_type */ @@ -1193,6 +1283,24 @@ static inline int f2fs_test_bit(unsigned int nr, char *addr) return mask & *addr; } +static inline void f2fs_set_bit(unsigned int nr, char *addr) +{ + int mask; + + addr += (nr >> 3); + mask = 1 << (7 - (nr & 0x07)); + *addr |= mask; +} + +static inline void f2fs_clear_bit(unsigned int nr, char *addr) +{ + int mask; + + addr += (nr >> 3); + mask = 1 << (7 - (nr & 0x07)); + *addr &= ~mask; +} + static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr) { int mask; @@ -1391,6 +1499,21 @@ static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page) kunmap(page); } +static inline int is_file(struct inode *inode, int type) +{ + return F2FS_I(inode)->i_advise & type; +} + +static inline void set_file(struct inode *inode, int type) +{ + F2FS_I(inode)->i_advise |= type; +} + +static inline void clear_file(struct inode *inode, int type) +{ + F2FS_I(inode)->i_advise &= ~type; +} + static inline int f2fs_readonly(struct super_block *sb) { return sb->s_flags & MS_RDONLY; @@ -1407,6 +1530,17 @@ static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi) sbi->sb->s_flags |= MS_RDONLY; } +static inline bool is_dot_dotdot(const struct qstr *str) +{ + if (str->len == 1 && str->name[0] == '.') + return true; + + if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.') + return true; + + return false; +} + #define get_inode_mode(i) \ ((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \ (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) @@ -1453,10 +1587,11 @@ struct dentry *f2fs_get_parent(struct dentry *child); */ extern unsigned char f2fs_filetype_table[F2FS_FT_MAX]; void set_de_type(struct f2fs_dir_entry *, umode_t); -struct f2fs_dir_entry *find_target_dentry(struct qstr *, int *, - struct f2fs_dentry_ptr *); + +struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *, + f2fs_hash_t, int *, struct f2fs_dentry_ptr *); bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *, - unsigned int); + unsigned int, struct f2fs_str *); void do_make_empty_dir(struct inode *, struct inode *, struct f2fs_dentry_ptr *); struct page *init_inode_metadata(struct inode *, struct inode *, @@ -1470,7 +1605,7 @@ struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **); ino_t f2fs_inode_by_name(struct inode *, struct qstr *); void f2fs_set_link(struct inode *, struct f2fs_dir_entry *, struct page *, struct inode *); -int update_dent_inode(struct inode *, const struct qstr *); +int update_dent_inode(struct inode *, struct inode *, const struct qstr *); void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *, const struct qstr *, f2fs_hash_t , unsigned int); int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t, @@ -1478,7 +1613,6 @@ int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t, void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *, struct inode *); int f2fs_do_tmpfile(struct inode *, struct inode *); -int f2fs_make_empty(struct inode *, struct inode *); bool f2fs_empty_dir(struct inode *); static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) @@ -1490,6 +1624,7 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) /* * super.c */ +int f2fs_commit_super(struct f2fs_sb_info *, bool); int f2fs_sync_fs(struct super_block *, int); extern __printf(3, 4) void f2fs_msg(struct super_block *, const char *, const char *, ...); @@ -1506,8 +1641,8 @@ struct dnode_of_data; struct node_info; bool available_free_memory(struct f2fs_sb_info *, int); +int need_dentry_mark(struct f2fs_sb_info *, nid_t); bool is_checkpointed_node(struct f2fs_sb_info *, nid_t); -bool has_fsynced_inode(struct f2fs_sb_info *, nid_t); bool need_inode_block_update(struct f2fs_sb_info *, nid_t); void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *); int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int); @@ -1548,21 +1683,20 @@ int create_flush_cmd_control(struct f2fs_sb_info *); void destroy_flush_cmd_control(struct f2fs_sb_info *); void invalidate_blocks(struct f2fs_sb_info *, block_t); void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t); -void clear_prefree_segments(struct f2fs_sb_info *); +void clear_prefree_segments(struct f2fs_sb_info *, struct cp_control *); void release_discard_addrs(struct f2fs_sb_info *); void discard_next_dnode(struct f2fs_sb_info *, block_t); int npages_for_summary_flush(struct f2fs_sb_info *, bool); void allocate_new_segments(struct f2fs_sb_info *); int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *); struct page *get_sum_page(struct f2fs_sb_info *, unsigned int); +void update_meta_page(struct f2fs_sb_info *, void *, block_t); void write_meta_page(struct f2fs_sb_info *, struct page *); -void write_node_page(struct f2fs_sb_info *, struct page *, - unsigned int, struct f2fs_io_info *); -void write_data_page(struct page *, struct dnode_of_data *, - struct f2fs_io_info *); -void rewrite_data_page(struct page *, struct f2fs_io_info *); -void recover_data_page(struct f2fs_sb_info *, struct page *, - struct f2fs_summary *, block_t, block_t); +void write_node_page(unsigned int, struct f2fs_io_info *); +void write_data_page(struct dnode_of_data *, struct f2fs_io_info *); +void rewrite_data_page(struct f2fs_io_info *); +void f2fs_replace_block(struct f2fs_sb_info *, struct dnode_of_data *, + block_t, block_t, unsigned char, bool); void allocate_data_block(struct f2fs_sb_info *, struct page *, block_t, block_t *, struct f2fs_summary *, int); void f2fs_wait_on_page_writeback(struct page *, enum page_type); @@ -1581,6 +1715,7 @@ void destroy_segment_manager_caches(void); */ struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t); struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t); +bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int); int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int); void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t); long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long); @@ -1607,10 +1742,8 @@ void destroy_checkpoint_caches(void); * data.c */ void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int); -int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *, - struct f2fs_io_info *); -void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *, - struct f2fs_io_info *); +int f2fs_submit_page_bio(struct f2fs_io_info *); +void f2fs_submit_page_mbio(struct f2fs_io_info *); void set_data_blkaddr(struct dnode_of_data *); int reserve_new_block(struct dnode_of_data *); int f2fs_reserve_block(struct dnode_of_data *, pgoff_t); @@ -1619,10 +1752,11 @@ void f2fs_destroy_extent_tree(struct inode *); void f2fs_init_extent_cache(struct inode *, struct f2fs_extent *); void f2fs_update_extent_cache(struct dnode_of_data *); void f2fs_preserve_extent_tree(struct inode *); -struct page *find_data_page(struct inode *, pgoff_t, bool); +struct page *get_read_data_page(struct inode *, pgoff_t, int); +struct page *find_data_page(struct inode *, pgoff_t); struct page *get_lock_data_page(struct inode *, pgoff_t); struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool); -int do_write_data_page(struct page *, struct f2fs_io_info *); +int do_write_data_page(struct f2fs_io_info *); int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64); void init_extent_cache_info(struct f2fs_sb_info *); int __init create_extent_cache(void); @@ -1787,13 +1921,15 @@ extern const struct address_space_operations f2fs_node_aops; extern const struct address_space_operations f2fs_meta_aops; extern const struct inode_operations f2fs_dir_inode_operations; extern const struct inode_operations f2fs_symlink_inode_operations; +extern const struct inode_operations f2fs_encrypted_symlink_inode_operations; extern const struct inode_operations f2fs_special_inode_operations; extern struct kmem_cache *inode_entry_slab; /* * inline.c */ -bool f2fs_may_inline(struct inode *); +bool f2fs_may_inline_data(struct inode *); +bool f2fs_may_inline_dentry(struct inode *); void read_inline_data(struct page *, struct page *); bool truncate_inline_inode(struct page *, u64); int f2fs_read_inline_data(struct inode *, struct page *); @@ -1801,8 +1937,8 @@ int f2fs_convert_inline_page(struct dnode_of_data *, struct page *); int f2fs_convert_inline_inode(struct inode *); int f2fs_write_inline_data(struct inode *, struct page *); bool recover_inline_data(struct inode *, struct page *); -struct f2fs_dir_entry *find_in_inline_dir(struct inode *, struct qstr *, - struct page **); +struct f2fs_dir_entry *find_in_inline_dir(struct inode *, + struct f2fs_filename *, struct page **); struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *, struct page **); int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *); int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *, @@ -1810,5 +1946,137 @@ int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *, void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *, struct inode *, struct inode *); bool f2fs_empty_inline_dir(struct inode *); -int f2fs_read_inline_dir(struct file *, struct dir_context *); +int f2fs_read_inline_dir(struct file *, struct dir_context *, + struct f2fs_str *); + +/* + * crypto support + */ +static inline int f2fs_encrypted_inode(struct inode *inode) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + return file_is_encrypt(inode); +#else + return 0; +#endif +} + +static inline void f2fs_set_encrypted_inode(struct inode *inode) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + file_set_encrypt(inode); +#endif +} + +static inline bool f2fs_bio_encrypted(struct bio *bio) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + return unlikely(bio->bi_private != NULL); +#else + return false; +#endif +} + +static inline int f2fs_sb_has_crypto(struct super_block *sb) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT); +#else + return 0; +#endif +} + +static inline bool f2fs_may_encrypt(struct inode *inode) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + mode_t mode = inode->i_mode; + + return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)); +#else + return 0; +#endif +} + +/* crypto_policy.c */ +int f2fs_is_child_context_consistent_with_parent(struct inode *, + struct inode *); +int f2fs_inherit_context(struct inode *, struct inode *, struct page *); +int f2fs_process_policy(const struct f2fs_encryption_policy *, struct inode *); +int f2fs_get_policy(struct inode *, struct f2fs_encryption_policy *); + +/* crypt.c */ +extern struct kmem_cache *f2fs_crypt_info_cachep; +bool f2fs_valid_contents_enc_mode(uint32_t); +uint32_t f2fs_validate_encryption_key_size(uint32_t, uint32_t); +struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *); +void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *); +struct page *f2fs_encrypt(struct inode *, struct page *); +int f2fs_decrypt(struct f2fs_crypto_ctx *, struct page *); +int f2fs_decrypt_one(struct inode *, struct page *); +void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *, struct bio *); + +/* crypto_key.c */ +void f2fs_free_encryption_info(struct inode *, struct f2fs_crypt_info *); +int _f2fs_get_encryption_info(struct inode *inode); + +/* crypto_fname.c */ +bool f2fs_valid_filenames_enc_mode(uint32_t); +u32 f2fs_fname_crypto_round_up(u32, u32); +int f2fs_fname_crypto_alloc_buffer(struct inode *, u32, struct f2fs_str *); +int f2fs_fname_disk_to_usr(struct inode *, f2fs_hash_t *, + const struct f2fs_str *, struct f2fs_str *); +int f2fs_fname_usr_to_disk(struct inode *, const struct qstr *, + struct f2fs_str *); + +#ifdef CONFIG_F2FS_FS_ENCRYPTION +void f2fs_restore_and_release_control_page(struct page **); +void f2fs_restore_control_page(struct page *); + +int __init f2fs_init_crypto(void); +int f2fs_crypto_initialize(void); +void f2fs_exit_crypto(void); + +int f2fs_has_encryption_key(struct inode *); + +static inline int f2fs_get_encryption_info(struct inode *inode) +{ + struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + + if (!ci || + (ci->ci_keyring_key && + (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | + (1 << KEY_FLAG_REVOKED) | + (1 << KEY_FLAG_DEAD))))) + return _f2fs_get_encryption_info(inode); + return 0; +} + +void f2fs_fname_crypto_free_buffer(struct f2fs_str *); +int f2fs_fname_setup_filename(struct inode *, const struct qstr *, + int lookup, struct f2fs_filename *); +void f2fs_fname_free_filename(struct f2fs_filename *); +#else +static inline void f2fs_restore_and_release_control_page(struct page **p) { } +static inline void f2fs_restore_control_page(struct page *p) { } + +static inline int __init f2fs_init_crypto(void) { return 0; } +static inline void f2fs_exit_crypto(void) { } + +static inline int f2fs_has_encryption_key(struct inode *i) { return 0; } +static inline int f2fs_get_encryption_info(struct inode *i) { return 0; } +static inline void f2fs_fname_crypto_free_buffer(struct f2fs_str *p) { } + +static inline int f2fs_fname_setup_filename(struct inode *dir, + const struct qstr *iname, + int lookup, struct f2fs_filename *fname) +{ + memset(fname, 0, sizeof(struct f2fs_filename)); + fname->usr_fname = iname; + fname->disk_name.name = (unsigned char *)iname->name; + fname->disk_name.len = iname->len; + return 0; +} + +static inline void f2fs_fname_free_filename(struct f2fs_filename *fname) { } +#endif #endif diff --git a/fs/f2fs/f2fs_crypto.h b/fs/f2fs/f2fs_crypto.h new file mode 100644 index 000000000000..c2c1c2b63b25 --- /dev/null +++ b/fs/f2fs/f2fs_crypto.h @@ -0,0 +1,151 @@ +/* + * linux/fs/f2fs/f2fs_crypto.h + * + * Copied from linux/fs/ext4/ext4_crypto.h + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption header content for f2fs + * + * Written by Michael Halcrow, 2015. + * Modified by Jaegeuk Kim, 2015. + */ +#ifndef _F2FS_CRYPTO_H +#define _F2FS_CRYPTO_H + +#include <linux/fs.h> + +#define F2FS_KEY_DESCRIPTOR_SIZE 8 + +/* Policy provided via an ioctl on the topmost directory */ +struct f2fs_encryption_policy { + char version; + char contents_encryption_mode; + char filenames_encryption_mode; + char flags; + char master_key_descriptor[F2FS_KEY_DESCRIPTOR_SIZE]; +} __attribute__((__packed__)); + +#define F2FS_ENCRYPTION_CONTEXT_FORMAT_V1 1 +#define F2FS_KEY_DERIVATION_NONCE_SIZE 16 + +#define F2FS_POLICY_FLAGS_PAD_4 0x00 +#define F2FS_POLICY_FLAGS_PAD_8 0x01 +#define F2FS_POLICY_FLAGS_PAD_16 0x02 +#define F2FS_POLICY_FLAGS_PAD_32 0x03 +#define F2FS_POLICY_FLAGS_PAD_MASK 0x03 +#define F2FS_POLICY_FLAGS_VALID 0x03 + +/** + * Encryption context for inode + * + * Protector format: + * 1 byte: Protector format (1 = this version) + * 1 byte: File contents encryption mode + * 1 byte: File names encryption mode + * 1 byte: Flags + * 8 bytes: Master Key descriptor + * 16 bytes: Encryption Key derivation nonce + */ +struct f2fs_encryption_context { + char format; + char contents_encryption_mode; + char filenames_encryption_mode; + char flags; + char master_key_descriptor[F2FS_KEY_DESCRIPTOR_SIZE]; + char nonce[F2FS_KEY_DERIVATION_NONCE_SIZE]; +} __attribute__((__packed__)); + +/* Encryption parameters */ +#define F2FS_XTS_TWEAK_SIZE 16 +#define F2FS_AES_128_ECB_KEY_SIZE 16 +#define F2FS_AES_256_GCM_KEY_SIZE 32 +#define F2FS_AES_256_CBC_KEY_SIZE 32 +#define F2FS_AES_256_CTS_KEY_SIZE 32 +#define F2FS_AES_256_XTS_KEY_SIZE 64 +#define F2FS_MAX_KEY_SIZE 64 + +#define F2FS_KEY_DESC_PREFIX "f2fs:" +#define F2FS_KEY_DESC_PREFIX_SIZE 5 + +struct f2fs_encryption_key { + __u32 mode; + char raw[F2FS_MAX_KEY_SIZE]; + __u32 size; +} __attribute__((__packed__)); + +struct f2fs_crypt_info { + char ci_data_mode; + char ci_filename_mode; + char ci_flags; + struct crypto_ablkcipher *ci_ctfm; + struct key *ci_keyring_key; + char ci_master_key[F2FS_KEY_DESCRIPTOR_SIZE]; +}; + +#define F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001 +#define F2FS_WRITE_PATH_FL 0x00000002 + +struct f2fs_crypto_ctx { + union { + struct { + struct page *bounce_page; /* Ciphertext page */ + struct page *control_page; /* Original page */ + } w; + struct { + struct bio *bio; + struct work_struct work; + } r; + struct list_head free_list; /* Free list */ + }; + char flags; /* Flags */ +}; + +struct f2fs_completion_result { + struct completion completion; + int res; +}; + +#define DECLARE_F2FS_COMPLETION_RESULT(ecr) \ + struct f2fs_completion_result ecr = { \ + COMPLETION_INITIALIZER((ecr).completion), 0 } + +static inline int f2fs_encryption_key_size(int mode) +{ + switch (mode) { + case F2FS_ENCRYPTION_MODE_AES_256_XTS: + return F2FS_AES_256_XTS_KEY_SIZE; + case F2FS_ENCRYPTION_MODE_AES_256_GCM: + return F2FS_AES_256_GCM_KEY_SIZE; + case F2FS_ENCRYPTION_MODE_AES_256_CBC: + return F2FS_AES_256_CBC_KEY_SIZE; + case F2FS_ENCRYPTION_MODE_AES_256_CTS: + return F2FS_AES_256_CTS_KEY_SIZE; + default: + BUG(); + } + return 0; +} + +#define F2FS_FNAME_NUM_SCATTER_ENTRIES 4 +#define F2FS_CRYPTO_BLOCK_SIZE 16 +#define F2FS_FNAME_CRYPTO_DIGEST_SIZE 32 + +/** + * For encrypted symlinks, the ciphertext length is stored at the beginning + * of the string in little-endian format. + */ +struct f2fs_encrypted_symlink_data { + __le16 len; + char encrypted_path[1]; +} __attribute__((__packed__)); + +/** + * This function is used to calculate the disk space required to + * store a filename of length l in encrypted symlink format. + */ +static inline u32 encrypted_symlink_data_len(u32 l) +{ + return (l + sizeof(struct f2fs_encrypted_symlink_data) - 1); +} +#endif /* _F2FS_CRYPTO_H */ diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 2b52e48d7482..ada2a3dd701a 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -20,6 +20,7 @@ #include <linux/uaccess.h> #include <linux/mount.h> #include <linux/pagevec.h> +#include <linux/random.h> #include "f2fs.h" #include "node.h" @@ -105,7 +106,7 @@ static int get_parent_ino(struct inode *inode, nid_t *pino) if (!dentry) return 0; - if (update_dent_inode(inode, &dentry->d_name)) { + if (update_dent_inode(inode, inode, &dentry->d_name)) { dput(dentry); return 0; } @@ -122,6 +123,8 @@ static inline bool need_do_checkpoint(struct inode *inode) if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1) need_cp = true; + else if (file_enc_name(inode) && need_dentry_mark(sbi, inode->i_ino)) + need_cp = true; else if (file_wrong_pino(inode)) need_cp = true; else if (!space_for_roll_forward(sbi)) @@ -271,7 +274,7 @@ flush_out: ret = f2fs_issue_flush(sbi); out: trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); - f2fs_trace_ios(NULL, NULL, 1); + f2fs_trace_ios(NULL, 1); return ret; } @@ -407,6 +410,12 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); + if (f2fs_encrypted_inode(inode)) { + int err = f2fs_get_encryption_info(inode); + if (err) + return 0; + } + /* we don't need to use inline_data strictly */ if (f2fs_has_inline_data(inode)) { int err = f2fs_convert_inline_inode(inode); @@ -419,6 +428,18 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) return 0; } +static int f2fs_file_open(struct inode *inode, struct file *filp) +{ + int ret = generic_file_open(inode, filp); + + if (!ret && f2fs_encrypted_inode(inode)) { + ret = f2fs_get_encryption_info(inode); + if (ret) + ret = -EACCES; + } + return ret; +} + int truncate_data_blocks_range(struct dnode_of_data *dn, int count) { int nr_free = 0, ofs = dn->ofs_in_node; @@ -461,28 +482,32 @@ void truncate_data_blocks(struct dnode_of_data *dn) } static int truncate_partial_data_page(struct inode *inode, u64 from, - bool force) + bool cache_only) { unsigned offset = from & (PAGE_CACHE_SIZE - 1); + pgoff_t index = from >> PAGE_CACHE_SHIFT; + struct address_space *mapping = inode->i_mapping; struct page *page; - if (!offset && !force) + if (!offset && !cache_only) return 0; - page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, force); - if (IS_ERR(page)) + if (cache_only) { + page = grab_cache_page(mapping, index); + if (page && PageUptodate(page)) + goto truncate_out; + f2fs_put_page(page, 1); return 0; + } - lock_page(page); - if (unlikely(!PageUptodate(page) || - page->mapping != inode->i_mapping)) - goto out; - + page = get_lock_data_page(inode, index); + if (IS_ERR(page)) + return 0; +truncate_out: f2fs_wait_on_page_writeback(page, DATA); zero_user(page, offset, PAGE_CACHE_SIZE - offset); - if (!force) + if (!cache_only || !f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode)) set_page_dirty(page); -out: f2fs_put_page(page, 1); return 0; } @@ -560,7 +585,7 @@ void f2fs_truncate(struct inode *inode) trace_f2fs_truncate(inode); /* we should check inline_data size */ - if (f2fs_has_inline_data(inode) && !f2fs_may_inline(inode)) { + if (f2fs_has_inline_data(inode) && !f2fs_may_inline_data(inode)) { if (f2fs_convert_inline_inode(inode)) return; } @@ -622,16 +647,20 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) return err; if (attr->ia_valid & ATTR_SIZE) { - if (attr->ia_size != i_size_read(inode)) { + if (f2fs_encrypted_inode(inode) && + f2fs_get_encryption_info(inode)) + return -EACCES; + + if (attr->ia_size <= i_size_read(inode)) { truncate_setsize(inode, attr->ia_size); f2fs_truncate(inode); f2fs_balance_fs(F2FS_I_SB(inode)); } else { /* - * giving a chance to truncate blocks past EOF which - * are fallocated with FALLOC_FL_KEEP_SIZE. + * do not trim all blocks after i_size if target size is + * larger than i_size. */ - f2fs_truncate(inode); + truncate_setsize(inode, attr->ia_size); } } @@ -718,10 +747,6 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) if (!S_ISREG(inode->i_mode)) return -EOPNOTSUPP; - /* skip punching hole beyond i_size */ - if (offset >= inode->i_size) - return ret; - if (f2fs_has_inline_data(inode)) { ret = f2fs_convert_inline_inode(inode); if (ret) @@ -765,6 +790,320 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) return ret; } +static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct dnode_of_data dn; + pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + int ret = 0; + + f2fs_lock_op(sbi); + + for (; end < nrpages; start++, end++) { + block_t new_addr, old_addr; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = get_dnode_of_data(&dn, end, LOOKUP_NODE_RA); + if (ret && ret != -ENOENT) { + goto out; + } else if (ret == -ENOENT) { + new_addr = NULL_ADDR; + } else { + new_addr = dn.data_blkaddr; + truncate_data_blocks_range(&dn, 1); + f2fs_put_dnode(&dn); + } + + if (new_addr == NULL_ADDR) { + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = get_dnode_of_data(&dn, start, LOOKUP_NODE_RA); + if (ret && ret != -ENOENT) + goto out; + else if (ret == -ENOENT) + continue; + + if (dn.data_blkaddr == NULL_ADDR) { + f2fs_put_dnode(&dn); + continue; + } else { + truncate_data_blocks_range(&dn, 1); + } + + f2fs_put_dnode(&dn); + } else { + struct page *ipage; + + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + ret = PTR_ERR(ipage); + goto out; + } + + set_new_dnode(&dn, inode, ipage, NULL, 0); + ret = f2fs_reserve_block(&dn, start); + if (ret) + goto out; + + old_addr = dn.data_blkaddr; + if (old_addr != NEW_ADDR && new_addr == NEW_ADDR) { + dn.data_blkaddr = NULL_ADDR; + f2fs_update_extent_cache(&dn); + invalidate_blocks(sbi, old_addr); + + dn.data_blkaddr = new_addr; + set_data_blkaddr(&dn); + } else if (new_addr != NEW_ADDR) { + struct node_info ni; + + get_node_info(sbi, dn.nid, &ni); + f2fs_replace_block(sbi, &dn, old_addr, new_addr, + ni.version, true); + } + + f2fs_put_dnode(&dn); + } + } + ret = 0; +out: + f2fs_unlock_op(sbi); + return ret; +} + +static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) +{ + pgoff_t pg_start, pg_end; + loff_t new_size; + int ret; + + if (!S_ISREG(inode->i_mode)) + return -EINVAL; + + if (offset + len >= i_size_read(inode)) + return -EINVAL; + + /* collapse range should be aligned to block size of f2fs. */ + if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1)) + return -EINVAL; + + pg_start = offset >> PAGE_CACHE_SHIFT; + pg_end = (offset + len) >> PAGE_CACHE_SHIFT; + + /* write out all dirty pages from offset */ + ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + if (ret) + return ret; + + truncate_pagecache(inode, offset); + + ret = f2fs_do_collapse(inode, pg_start, pg_end); + if (ret) + return ret; + + new_size = i_size_read(inode) - len; + + ret = truncate_blocks(inode, new_size, true); + if (!ret) + i_size_write(inode, new_size); + + return ret; +} + +static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, + int mode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct address_space *mapping = inode->i_mapping; + pgoff_t index, pg_start, pg_end; + loff_t new_size = i_size_read(inode); + loff_t off_start, off_end; + int ret = 0; + + if (!S_ISREG(inode->i_mode)) + return -EINVAL; + + ret = inode_newsize_ok(inode, (len + offset)); + if (ret) + return ret; + + f2fs_balance_fs(sbi); + + if (f2fs_has_inline_data(inode)) { + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; + } + + ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1); + if (ret) + return ret; + + truncate_pagecache_range(inode, offset, offset + len - 1); + + pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; + pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; + + off_start = offset & (PAGE_CACHE_SIZE - 1); + off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + + if (pg_start == pg_end) { + fill_zero(inode, pg_start, off_start, off_end - off_start); + if (offset + len > new_size) + new_size = offset + len; + new_size = max_t(loff_t, new_size, offset + len); + } else { + if (off_start) { + fill_zero(inode, pg_start++, off_start, + PAGE_CACHE_SIZE - off_start); + new_size = max_t(loff_t, new_size, + pg_start << PAGE_CACHE_SHIFT); + } + + for (index = pg_start; index < pg_end; index++) { + struct dnode_of_data dn; + struct page *ipage; + + f2fs_lock_op(sbi); + + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + ret = PTR_ERR(ipage); + f2fs_unlock_op(sbi); + goto out; + } + + set_new_dnode(&dn, inode, ipage, NULL, 0); + ret = f2fs_reserve_block(&dn, index); + if (ret) { + f2fs_unlock_op(sbi); + goto out; + } + + if (dn.data_blkaddr != NEW_ADDR) { + invalidate_blocks(sbi, dn.data_blkaddr); + + dn.data_blkaddr = NEW_ADDR; + set_data_blkaddr(&dn); + + dn.data_blkaddr = NULL_ADDR; + f2fs_update_extent_cache(&dn); + } + f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); + + new_size = max_t(loff_t, new_size, + (index + 1) << PAGE_CACHE_SHIFT); + } + + if (off_end) { + fill_zero(inode, pg_end, 0, off_end); + new_size = max_t(loff_t, new_size, offset + len); + } + } + +out: + if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) { + i_size_write(inode, new_size); + mark_inode_dirty(inode); + update_inode_page(inode); + } + + return ret; +} + +static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + pgoff_t pg_start, pg_end, delta, nrpages, idx; + loff_t new_size; + int ret; + + if (!S_ISREG(inode->i_mode)) + return -EINVAL; + + new_size = i_size_read(inode) + len; + if (new_size > inode->i_sb->s_maxbytes) + return -EFBIG; + + if (offset >= i_size_read(inode)) + return -EINVAL; + + /* insert range should be aligned to block size of f2fs. */ + if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1)) + return -EINVAL; + + f2fs_balance_fs(sbi); + + ret = truncate_blocks(inode, i_size_read(inode), true); + if (ret) + return ret; + + /* write out all dirty pages from offset */ + ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + if (ret) + return ret; + + truncate_pagecache(inode, offset); + + pg_start = offset >> PAGE_CACHE_SHIFT; + pg_end = (offset + len) >> PAGE_CACHE_SHIFT; + delta = pg_end - pg_start; + nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + + for (idx = nrpages - 1; idx >= pg_start && idx != -1; idx--) { + struct dnode_of_data dn; + struct page *ipage; + block_t new_addr, old_addr; + + f2fs_lock_op(sbi); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = get_dnode_of_data(&dn, idx, LOOKUP_NODE_RA); + if (ret && ret != -ENOENT) { + goto out; + } else if (ret == -ENOENT) { + goto next; + } else if (dn.data_blkaddr == NULL_ADDR) { + f2fs_put_dnode(&dn); + goto next; + } else { + new_addr = dn.data_blkaddr; + truncate_data_blocks_range(&dn, 1); + f2fs_put_dnode(&dn); + } + + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + ret = PTR_ERR(ipage); + goto out; + } + + set_new_dnode(&dn, inode, ipage, NULL, 0); + ret = f2fs_reserve_block(&dn, idx + delta); + if (ret) + goto out; + + old_addr = dn.data_blkaddr; + f2fs_bug_on(sbi, old_addr != NEW_ADDR); + + if (new_addr != NEW_ADDR) { + struct node_info ni; + + get_node_info(sbi, dn.nid, &ni); + f2fs_replace_block(sbi, &dn, old_addr, new_addr, + ni.version, true); + } + f2fs_put_dnode(&dn); +next: + f2fs_unlock_op(sbi); + } + + i_size_write(inode, new_size); + return 0; +out: + f2fs_unlock_op(sbi); + return ret; +} + static int expand_inode_data(struct inode *inode, loff_t offset, loff_t len, int mode) { @@ -830,23 +1169,40 @@ static long f2fs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); - long ret; + long ret = 0; + + if (f2fs_encrypted_inode(inode) && + (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) + return -EOPNOTSUPP; - if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | + FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | + FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; mutex_lock(&inode->i_mutex); - if (mode & FALLOC_FL_PUNCH_HOLE) + if (mode & FALLOC_FL_PUNCH_HOLE) { + if (offset >= inode->i_size) + goto out; + ret = punch_hole(inode, offset, len); - else + } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { + ret = f2fs_collapse_range(inode, offset, len); + } else if (mode & FALLOC_FL_ZERO_RANGE) { + ret = f2fs_zero_range(inode, offset, len, mode); + } else if (mode & FALLOC_FL_INSERT_RANGE) { + ret = f2fs_insert_range(inode, offset, len); + } else { ret = expand_inode_data(inode, offset, len, mode); + } if (!ret) { inode->i_mtime = inode->i_ctime = CURRENT_TIME; mark_inode_dirty(inode); } +out: mutex_unlock(&inode->i_mutex); trace_f2fs_fallocate(inode, mode, offset, len, ret); @@ -1035,11 +1391,9 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp) clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); } - if (f2fs_is_volatile_file(inode)) { + if (f2fs_is_volatile_file(inode)) clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); - filemap_fdatawrite(inode->i_mapping); - set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); - } + mnt_drop_write_file(filp); return ret; } @@ -1109,6 +1463,86 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) return 0; } +static bool uuid_is_nonzero(__u8 u[16]) +{ + int i; + + for (i = 0; i < 16; i++) + if (u[i]) + return true; + return false; +} + +static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + struct f2fs_encryption_policy policy; + struct inode *inode = file_inode(filp); + + if (copy_from_user(&policy, (struct f2fs_encryption_policy __user *)arg, + sizeof(policy))) + return -EFAULT; + + return f2fs_process_policy(&policy, inode); +#else + return -EOPNOTSUPP; +#endif +} + +static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg) +{ +#ifdef CONFIG_F2FS_FS_ENCRYPTION + struct f2fs_encryption_policy policy; + struct inode *inode = file_inode(filp); + int err; + + err = f2fs_get_policy(inode, &policy); + if (err) + return err; + + if (copy_to_user((struct f2fs_encryption_policy __user *)arg, &policy, + sizeof(policy))) + return -EFAULT; + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int err; + + if (!f2fs_sb_has_crypto(inode->i_sb)) + return -EOPNOTSUPP; + + if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt)) + goto got_it; + + err = mnt_want_write_file(filp); + if (err) + return err; + + /* update superblock with uuid */ + generate_random_uuid(sbi->raw_super->encrypt_pw_salt); + + err = f2fs_commit_super(sbi, false); + + mnt_drop_write_file(filp); + if (err) { + /* undo new data */ + memset(sbi->raw_super->encrypt_pw_salt, 0, 16); + return err; + } +got_it: + if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt, + 16)) + return -EFAULT; + return 0; +} + long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { switch (cmd) { @@ -1132,11 +1566,29 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_shutdown(filp, arg); case FITRIM: return f2fs_ioc_fitrim(filp, arg); + case F2FS_IOC_SET_ENCRYPTION_POLICY: + return f2fs_ioc_set_encryption_policy(filp, arg); + case F2FS_IOC_GET_ENCRYPTION_POLICY: + return f2fs_ioc_get_encryption_policy(filp, arg); + case F2FS_IOC_GET_ENCRYPTION_PWSALT: + return f2fs_ioc_get_encryption_pwsalt(filp, arg); default: return -ENOTTY; } } +static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct inode *inode = file_inode(iocb->ki_filp); + + if (f2fs_encrypted_inode(inode) && + !f2fs_has_encryption_key(inode) && + f2fs_get_encryption_info(inode)) + return -EACCES; + + return generic_file_write_iter(iocb, from); +} + #ifdef CONFIG_COMPAT long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -1157,8 +1609,8 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) const struct file_operations f2fs_file_operations = { .llseek = f2fs_llseek, .read_iter = generic_file_read_iter, - .write_iter = generic_file_write_iter, - .open = generic_file_open, + .write_iter = f2fs_file_write_iter, + .open = f2fs_file_open, .release = f2fs_release_file, .mmap = f2fs_file_mmap, .fsync = f2fs_sync_file, diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index ed58211fe79b..e1e73617d13b 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -518,12 +518,79 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, return 1; } -static void move_data_page(struct inode *inode, struct page *page, int gc_type) +static void move_encrypted_block(struct inode *inode, block_t bidx) { struct f2fs_io_info fio = { + .sbi = F2FS_I_SB(inode), .type = DATA, - .rw = WRITE_SYNC, + .rw = READ_SYNC, + .encrypted_page = NULL, }; + struct dnode_of_data dn; + struct f2fs_summary sum; + struct node_info ni; + struct page *page; + int err; + + /* do not read out */ + page = grab_cache_page(inode->i_mapping, bidx); + if (!page) + return; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE); + if (err) + goto out; + + if (unlikely(dn.data_blkaddr == NULL_ADDR)) + goto put_out; + + get_node_info(fio.sbi, dn.nid, &ni); + set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); + + /* read page */ + fio.page = page; + fio.blk_addr = dn.data_blkaddr; + + fio.encrypted_page = grab_cache_page(META_MAPPING(fio.sbi), fio.blk_addr); + if (!fio.encrypted_page) + goto put_out; + + f2fs_submit_page_bio(&fio); + + /* allocate block address */ + f2fs_wait_on_page_writeback(dn.node_page, NODE); + + allocate_data_block(fio.sbi, NULL, fio.blk_addr, + &fio.blk_addr, &sum, CURSEG_COLD_DATA); + dn.data_blkaddr = fio.blk_addr; + + /* write page */ + lock_page(fio.encrypted_page); + set_page_writeback(fio.encrypted_page); + fio.rw = WRITE_SYNC; + f2fs_submit_page_mbio(&fio); + + set_data_blkaddr(&dn); + f2fs_update_extent_cache(&dn); + set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE); + if (page->index == 0) + set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); + + f2fs_put_page(fio.encrypted_page, 1); +put_out: + f2fs_put_dnode(&dn); +out: + f2fs_put_page(page, 1); +} + +static void move_data_page(struct inode *inode, block_t bidx, int gc_type) +{ + struct page *page; + + page = get_lock_data_page(inode, bidx); + if (IS_ERR(page)) + return; if (gc_type == BG_GC) { if (PageWriteback(page)) @@ -531,12 +598,19 @@ static void move_data_page(struct inode *inode, struct page *page, int gc_type) set_page_dirty(page); set_cold_data(page); } else { + struct f2fs_io_info fio = { + .sbi = F2FS_I_SB(inode), + .type = DATA, + .rw = WRITE_SYNC, + .page = page, + .encrypted_page = NULL, + }; f2fs_wait_on_page_writeback(page, DATA); if (clear_page_dirty_for_io(page)) inode_dec_dirty_pages(inode); set_cold_data(page); - do_write_data_page(page, &fio); + do_write_data_page(&fio); clear_cold_data(page); } out: @@ -599,10 +673,16 @@ next_step: if (IS_ERR(inode) || is_bad_inode(inode)) continue; - start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)); + /* if encrypted inode, let's go phase 3 */ + if (f2fs_encrypted_inode(inode) && + S_ISREG(inode->i_mode)) { + add_gc_inode(gc_list, inode); + continue; + } - data_page = find_data_page(inode, - start_bidx + ofs_in_node, false); + start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)); + data_page = get_read_data_page(inode, + start_bidx + ofs_in_node, READA); if (IS_ERR(data_page)) { iput(inode); continue; @@ -616,12 +696,12 @@ next_step: /* phase 3 */ inode = find_gc_inode(gc_list, dni.ino); if (inode) { - start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)); - data_page = get_lock_data_page(inode, - start_bidx + ofs_in_node); - if (IS_ERR(data_page)) - continue; - move_data_page(inode, data_page, gc_type); + start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)) + + ofs_in_node; + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + move_encrypted_block(inode, start_bidx); + else + move_data_page(inode, start_bidx, gc_type); stat_inc_data_blk_count(sbi, 1, gc_type); } } @@ -670,6 +750,15 @@ static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, sum = page_address(sum_page); + /* + * this is to avoid deadlock: + * - lock_page(sum_page) - f2fs_replace_block + * - check_valid_map() - mutex_lock(sentry_lock) + * - mutex_lock(sentry_lock) - change_curseg() + * - lock_page(sum_page) + */ + unlock_page(sum_page); + switch (GET_SUM_TYPE((&sum->footer))) { case SUM_TYPE_NODE: gc_node_segment(sbi, sum->entries, segno, gc_type); @@ -683,7 +772,7 @@ static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)), gc_type); stat_inc_call_count(sbi->stat_info); - f2fs_put_page(sum_page, 1); + f2fs_put_page(sum_page, 0); } int f2fs_gc(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c index a844fcfb9a8d..71b7206c431e 100644 --- a/fs/f2fs/hash.c +++ b/fs/f2fs/hash.c @@ -79,8 +79,7 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info) const unsigned char *name = name_info->name; size_t len = name_info->len; - if ((len <= 2) && (name[0] == '.') && - (name[1] == '.' || name[1] == '\0')) + if (is_dot_dotdot(name_info)) return 0; /* Initialize the default seed for the hash checksum functions */ diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 8140e4f0e538..38e75fb1e488 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -13,7 +13,7 @@ #include "f2fs.h" -bool f2fs_may_inline(struct inode *inode) +bool f2fs_may_inline_data(struct inode *inode) { if (!test_opt(F2FS_I_SB(inode), INLINE_DATA)) return false; @@ -27,6 +27,20 @@ bool f2fs_may_inline(struct inode *inode) if (i_size_read(inode) > MAX_INLINE_DATA) return false; + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + return false; + + return true; +} + +bool f2fs_may_inline_dentry(struct inode *inode) +{ + if (!test_opt(F2FS_I_SB(inode), INLINE_DENTRY)) + return false; + + if (!S_ISDIR(inode->i_mode)) + return false; + return true; } @@ -95,8 +109,11 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) { void *src_addr, *dst_addr; struct f2fs_io_info fio = { + .sbi = F2FS_I_SB(dn->inode), .type = DATA, .rw = WRITE_SYNC | REQ_PRIO, + .page = page, + .encrypted_page = NULL, }; int dirty, err; @@ -130,7 +147,7 @@ no_update: /* write data page to try to make data consistent */ set_page_writeback(page); fio.blk_addr = dn->data_blkaddr; - write_data_page(page, dn, &fio); + write_data_page(dn, &fio); set_data_blkaddr(dn); f2fs_update_extent_cache(dn); f2fs_wait_on_page_writeback(page, DATA); @@ -267,23 +284,26 @@ process_inline: } struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, - struct qstr *name, struct page **res_page) + struct f2fs_filename *fname, struct page **res_page) { struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); struct f2fs_inline_dentry *inline_dentry; + struct qstr name = FSTR_TO_QSTR(&fname->disk_name); struct f2fs_dir_entry *de; struct f2fs_dentry_ptr d; struct page *ipage; + f2fs_hash_t namehash; ipage = get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) return NULL; - inline_dentry = inline_data_addr(ipage); + namehash = f2fs_dentry_hash(&name); - make_dentry_ptr(&d, (void *)inline_dentry, 2); - de = find_target_dentry(name, NULL, &d); + inline_dentry = inline_data_addr(ipage); + make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2); + de = find_target_dentry(fname, namehash, NULL, &d); unlock_page(ipage); if (de) *res_page = ipage; @@ -325,7 +345,7 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent, dentry_blk = inline_data_addr(ipage); - make_dentry_ptr(&d, (void *)dentry_blk, 2); + make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2); do_make_empty_dir(inode, parent, &d); set_page_dirty(ipage); @@ -429,7 +449,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name, f2fs_wait_on_page_writeback(ipage, NODE); name_hash = f2fs_dentry_hash(name); - make_dentry_ptr(&d, (void *)dentry_blk, 2); + make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2); f2fs_update_dentry(ino, mode, &d, name, name_hash, bit_pos); set_page_dirty(ipage); @@ -506,7 +526,8 @@ bool f2fs_empty_inline_dir(struct inode *dir) return true; } -int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx) +int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, + struct f2fs_str *fstr) { struct inode *inode = file_inode(file); struct f2fs_inline_dentry *inline_dentry = NULL; @@ -522,9 +543,9 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx) inline_dentry = inline_data_addr(ipage); - make_dentry_ptr(&d, (void *)inline_dentry, 2); + make_dentry_ptr(inode, &d, (void *)inline_dentry, 2); - if (!f2fs_fill_dentries(ctx, &d, 0)) + if (!f2fs_fill_dentries(ctx, &d, 0, fstr)) ctx->pos = NR_INLINE_DENTRY; f2fs_put_page(ipage, 1); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index e622ec95409e..2550868dc651 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -198,7 +198,10 @@ make_now: inode->i_mapping->a_ops = &f2fs_dblock_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO); } else if (S_ISLNK(inode->i_mode)) { - inode->i_op = &f2fs_symlink_inode_operations; + if (f2fs_encrypted_inode(inode)) + inode->i_op = &f2fs_encrypted_symlink_inode_operations; + else + inode->i_op = &f2fs_symlink_inode_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { @@ -359,6 +362,10 @@ no_delete: if (is_inode_flag_set(F2FS_I(inode), FI_UPDATE_WRITE)) add_dirty_inode(sbi, inode->i_ino, UPDATE_INO); out_clear: +#ifdef CONFIG_F2FS_FS_ENCRYPTION + if (F2FS_I(inode)->i_crypt_info) + f2fs_free_encryption_info(inode, F2FS_I(inode)->i_crypt_info); +#endif clear_inode(inode); } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 71765d062914..fdbae21ee8fb 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -56,11 +56,18 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) goto out; } - if (f2fs_may_inline(inode)) + /* If the directory encrypted, then we should encrypt the inode. */ + if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) + f2fs_set_encrypted_inode(inode); + + if (f2fs_may_inline_data(inode)) set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); - if (test_opt(sbi, INLINE_DENTRY) && S_ISDIR(inode->i_mode)) + if (f2fs_may_inline_dentry(inode)) set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY); + stat_inc_inline_inode(inode); + stat_inc_inline_dir(inode); + trace_f2fs_new_inode(inode, 0); mark_inode_dirty(inode); return inode; @@ -136,7 +143,6 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, alloc_nid_done(sbi, ino); - stat_inc_inline_inode(inode); d_instantiate(dentry, inode); unlock_new_inode(inode); @@ -155,6 +161,10 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, struct f2fs_sb_info *sbi = F2FS_I_SB(dir); int err; + if (f2fs_encrypted_inode(dir) && + !f2fs_is_child_context_consistent_with_parent(dir, inode)) + return -EPERM; + f2fs_balance_fs(sbi); inode->i_ctime = CURRENT_TIME; @@ -232,32 +242,34 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, struct inode *inode = NULL; struct f2fs_dir_entry *de; struct page *page; + nid_t ino; + int err = 0; if (dentry->d_name.len > F2FS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); de = f2fs_find_entry(dir, &dentry->d_name, &page); - if (de) { - nid_t ino = le32_to_cpu(de->ino); - f2fs_dentry_kunmap(dir, page); - f2fs_put_page(page, 0); + if (!de) + return d_splice_alias(inode, dentry); - inode = f2fs_iget(dir->i_sb, ino); - if (IS_ERR(inode)) - return ERR_CAST(inode); + ino = le32_to_cpu(de->ino); + f2fs_dentry_kunmap(dir, page); + f2fs_put_page(page, 0); - if (f2fs_has_inline_dots(inode)) { - int err; + inode = f2fs_iget(dir->i_sb, ino); + if (IS_ERR(inode)) + return ERR_CAST(inode); - err = __recover_dot_dentries(inode, dir->i_ino); - if (err) { - iget_failed(inode); - return ERR_PTR(err); - } - } + if (f2fs_has_inline_dots(inode)) { + err = __recover_dot_dentries(inode, dir->i_ino); + if (err) + goto err_out; } - return d_splice_alias(inode, dentry); + +err_out: + iget_failed(inode); + return ERR_PTR(err); } static int f2fs_unlink(struct inode *dir, struct dentry *dentry) @@ -312,16 +324,26 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; - size_t symlen = strlen(symname) + 1; + size_t len = strlen(symname); + size_t p_len; + char *p_str; + struct f2fs_str disk_link = FSTR_INIT(NULL, 0); + struct f2fs_encrypted_symlink_data *sd = NULL; int err; + if (len > dir->i_sb->s_blocksize) + return -ENAMETOOLONG; + f2fs_balance_fs(sbi); inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO); if (IS_ERR(inode)) return PTR_ERR(inode); - inode->i_op = &f2fs_symlink_inode_operations; + if (f2fs_encrypted_inode(inode)) + inode->i_op = &f2fs_encrypted_symlink_inode_operations; + else + inode->i_op = &f2fs_symlink_inode_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; f2fs_lock_op(sbi); @@ -329,10 +351,46 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, if (err) goto out; f2fs_unlock_op(sbi); - - err = page_symlink(inode, symname, symlen); alloc_nid_done(sbi, inode->i_ino); + if (f2fs_encrypted_inode(dir)) { + struct qstr istr = QSTR_INIT(symname, len); + + err = f2fs_get_encryption_info(inode); + if (err) + goto err_out; + + err = f2fs_fname_crypto_alloc_buffer(inode, len, &disk_link); + if (err) + goto err_out; + + err = f2fs_fname_usr_to_disk(inode, &istr, &disk_link); + if (err < 0) + goto err_out; + + p_len = encrypted_symlink_data_len(disk_link.len) + 1; + + if (p_len > dir->i_sb->s_blocksize) { + err = -ENAMETOOLONG; + goto err_out; + } + + sd = kzalloc(p_len, GFP_NOFS); + if (!sd) { + err = -ENOMEM; + goto err_out; + } + memcpy(sd->encrypted_path, disk_link.name, disk_link.len); + sd->len = cpu_to_le16(disk_link.len); + p_str = (char *)sd; + } else { + p_len = len + 1; + p_str = (char *)symname; + } + + err = page_symlink(inode, p_str, p_len); + +err_out: d_instantiate(dentry, inode); unlock_new_inode(inode); @@ -345,10 +403,14 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, * If the symlink path is stored into inline_data, there is no * performance regression. */ - filemap_write_and_wait_range(inode->i_mapping, 0, symlen - 1); + if (!err) + filemap_write_and_wait_range(inode->i_mapping, 0, p_len - 1); if (IS_DIRSYNC(dir)) f2fs_sync_fs(sbi->sb, 1); + + kfree(sd); + f2fs_fname_crypto_free_buffer(&disk_link); return err; out: handle_failed_inode(inode); @@ -379,7 +441,6 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) goto out_fail; f2fs_unlock_op(sbi); - stat_inc_inline_dir(inode); alloc_nid_done(sbi, inode->i_ino); d_instantiate(dentry, inode); @@ -441,19 +502,101 @@ out: return err; } +static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, + umode_t mode, struct inode **whiteout) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct inode *inode; + int err; + + if (!whiteout) + f2fs_balance_fs(sbi); + + inode = f2fs_new_inode(dir, mode); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + if (whiteout) { + init_special_inode(inode, inode->i_mode, WHITEOUT_DEV); + inode->i_op = &f2fs_special_inode_operations; + } else { + inode->i_op = &f2fs_file_inode_operations; + inode->i_fop = &f2fs_file_operations; + inode->i_mapping->a_ops = &f2fs_dblock_aops; + } + + f2fs_lock_op(sbi); + err = acquire_orphan_inode(sbi); + if (err) + goto out; + + err = f2fs_do_tmpfile(inode, dir); + if (err) + goto release_out; + + /* + * add this non-linked tmpfile to orphan list, in this way we could + * remove all unused data of tmpfile after abnormal power-off. + */ + add_orphan_inode(sbi, inode->i_ino); + f2fs_unlock_op(sbi); + + alloc_nid_done(sbi, inode->i_ino); + + if (whiteout) { + inode_dec_link_count(inode); + *whiteout = inode; + } else { + d_tmpfile(dentry, inode); + } + unlock_new_inode(inode); + return 0; + +release_out: + release_orphan_inode(sbi); +out: + handle_failed_inode(inode); + return err; +} + +static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + if (f2fs_encrypted_inode(dir)) { + int err = f2fs_get_encryption_info(dir); + if (err) + return err; + } + + return __f2fs_tmpfile(dir, dentry, mode, NULL); +} + +static int f2fs_create_whiteout(struct inode *dir, struct inode **whiteout) +{ + return __f2fs_tmpfile(dir, NULL, S_IFCHR | WHITEOUT_MODE, whiteout); +} + static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) { struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir); struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); + struct inode *whiteout = NULL; struct page *old_dir_page; - struct page *old_page, *new_page; + struct page *old_page, *new_page = NULL; struct f2fs_dir_entry *old_dir_entry = NULL; struct f2fs_dir_entry *old_entry; struct f2fs_dir_entry *new_entry; int err = -ENOENT; + if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) && + !f2fs_is_child_context_consistent_with_parent(new_dir, + old_inode)) { + err = -EPERM; + goto out; + } + f2fs_balance_fs(sbi); old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); @@ -467,17 +610,23 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out_old; } + if (flags & RENAME_WHITEOUT) { + err = f2fs_create_whiteout(old_dir, &whiteout); + if (err) + goto out_dir; + } + if (new_inode) { err = -ENOTEMPTY; if (old_dir_entry && !f2fs_empty_dir(new_inode)) - goto out_dir; + goto out_whiteout; err = -ENOENT; new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_page); if (!new_entry) - goto out_dir; + goto out_whiteout; f2fs_lock_op(sbi); @@ -485,7 +634,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (err) goto put_out_dir; - if (update_dent_inode(old_inode, &new_dentry->d_name)) { + if (update_dent_inode(old_inode, new_inode, + &new_dentry->d_name)) { release_orphan_inode(sbi); goto put_out_dir; } @@ -514,7 +664,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, err = f2fs_add_link(new_dentry, old_inode); if (err) { f2fs_unlock_op(sbi); - goto out_dir; + goto out_whiteout; } if (old_dir_entry) { @@ -525,6 +675,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, down_write(&F2FS_I(old_inode)->i_sem); file_lost_pino(old_inode); + if (new_inode && file_enc_name(new_inode)) + file_set_enc_name(old_inode); up_write(&F2FS_I(old_inode)->i_sem); old_inode->i_ctime = CURRENT_TIME; @@ -532,8 +684,18 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_delete_entry(old_entry, old_page, old_dir, NULL); + if (whiteout) { + whiteout->i_state |= I_LINKABLE; + set_inode_flag(F2FS_I(whiteout), FI_INC_LINK); + err = f2fs_add_link(old_dentry, whiteout); + if (err) + goto put_out_dir; + whiteout->i_state &= ~I_LINKABLE; + iput(whiteout); + } + if (old_dir_entry) { - if (old_dir != new_dir) { + if (old_dir != new_dir && !whiteout) { f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir); update_inode_page(old_inode); @@ -554,8 +716,13 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, put_out_dir: f2fs_unlock_op(sbi); - f2fs_dentry_kunmap(new_dir, new_page); - f2fs_put_page(new_page, 0); + if (new_page) { + f2fs_dentry_kunmap(new_dir, new_page); + f2fs_put_page(new_page, 0); + } +out_whiteout: + if (whiteout) + iput(whiteout); out_dir: if (old_dir_entry) { f2fs_dentry_kunmap(old_inode, old_dir_page); @@ -581,6 +748,14 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, int old_nlink = 0, new_nlink = 0; int err = -ENOENT; + if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) && + (old_dir != new_dir) && + (!f2fs_is_child_context_consistent_with_parent(new_dir, + old_inode) || + !f2fs_is_child_context_consistent_with_parent(old_dir, + new_inode))) + return -EPERM; + f2fs_balance_fs(sbi); old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); @@ -627,13 +802,17 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_lock_op(sbi); - err = update_dent_inode(old_inode, &new_dentry->d_name); + err = update_dent_inode(old_inode, new_inode, &new_dentry->d_name); if (err) goto out_unlock; + if (file_enc_name(new_inode)) + file_set_enc_name(old_inode); - err = update_dent_inode(new_inode, &old_dentry->d_name); + err = update_dent_inode(new_inode, old_inode, &old_dentry->d_name); if (err) goto out_undo; + if (file_enc_name(old_inode)) + file_set_enc_name(new_inode); /* update ".." directory entry info of old dentry */ if (old_dir_entry) @@ -691,8 +870,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_sync_fs(sbi->sb, 1); return 0; out_undo: - /* Still we may fail to recover name info of f2fs_inode here */ - update_dent_inode(old_inode, &old_dentry->d_name); + /* + * Still we may fail to recover name info of f2fs_inode here + * Drop it, once its name is set as encrypted + */ + update_dent_inode(old_inode, old_inode, &old_dentry->d_name); out_unlock: f2fs_unlock_op(sbi); out_new_dir: @@ -719,7 +901,7 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { - if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; if (flags & RENAME_EXCHANGE) { @@ -730,53 +912,85 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry, * VFS has already handled the new dentry existence case, * here, we just deal with "RENAME_NOREPLACE" as regular rename. */ - return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry); + return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry, flags); } -static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +#ifdef CONFIG_F2FS_FS_ENCRYPTION +static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cookie) { - struct f2fs_sb_info *sbi = F2FS_I_SB(dir); - struct inode *inode; - int err; - - inode = f2fs_new_inode(dir, mode); - if (IS_ERR(inode)) - return PTR_ERR(inode); - - inode->i_op = &f2fs_file_inode_operations; - inode->i_fop = &f2fs_file_operations; - inode->i_mapping->a_ops = &f2fs_dblock_aops; - - f2fs_lock_op(sbi); - err = acquire_orphan_inode(sbi); - if (err) - goto out; - - err = f2fs_do_tmpfile(inode, dir); - if (err) - goto release_out; - - /* - * add this non-linked tmpfile to orphan list, in this way we could - * remove all unused data of tmpfile after abnormal power-off. - */ - add_orphan_inode(sbi, inode->i_ino); - f2fs_unlock_op(sbi); - - alloc_nid_done(sbi, inode->i_ino); - - stat_inc_inline_inode(inode); - d_tmpfile(dentry, inode); - unlock_new_inode(inode); - return 0; + struct page *cpage = NULL; + char *caddr, *paddr = NULL; + struct f2fs_str cstr; + struct f2fs_str pstr = FSTR_INIT(NULL, 0); + struct inode *inode = d_inode(dentry); + struct f2fs_encrypted_symlink_data *sd; + loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1); + u32 max_size = inode->i_sb->s_blocksize; + int res; + + res = f2fs_get_encryption_info(inode); + if (res) + return ERR_PTR(res); + + cpage = read_mapping_page(inode->i_mapping, 0, NULL); + if (IS_ERR(cpage)) + return ERR_CAST(cpage); + caddr = kmap(cpage); + caddr[size] = 0; + + /* Symlink is encrypted */ + sd = (struct f2fs_encrypted_symlink_data *)caddr; + cstr.name = sd->encrypted_path; + cstr.len = le16_to_cpu(sd->len); + + /* this is broken symlink case */ + if (cstr.name[0] == 0 && cstr.len == 0) { + res = -ENOENT; + goto errout; + } -release_out: - release_orphan_inode(sbi); -out: - handle_failed_inode(inode); - return err; + if ((cstr.len + sizeof(struct f2fs_encrypted_symlink_data) - 1) > + max_size) { + /* Symlink data on the disk is corrupted */ + res = -EIO; + goto errout; + } + res = f2fs_fname_crypto_alloc_buffer(inode, cstr.len, &pstr); + if (res) + goto errout; + + res = f2fs_fname_disk_to_usr(inode, NULL, &cstr, &pstr); + if (res < 0) + goto errout; + + paddr = pstr.name; + + /* Null-terminate the name */ + paddr[res] = '\0'; + + kunmap(cpage); + page_cache_release(cpage); + return *cookie = paddr; +errout: + f2fs_fname_crypto_free_buffer(&pstr); + kunmap(cpage); + page_cache_release(cpage); + return ERR_PTR(res); } +const struct inode_operations f2fs_encrypted_symlink_inode_operations = { + .readlink = generic_readlink, + .follow_link = f2fs_encrypted_follow_link, + .put_link = kfree_put_link, + .getattr = f2fs_getattr, + .setattr = f2fs_setattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = f2fs_listxattr, + .removexattr = generic_removexattr, +}; +#endif + const struct inode_operations f2fs_dir_inode_operations = { .create = f2fs_create, .lookup = f2fs_lookup, diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 8ab0cf1930bd..d9c52424bac2 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -195,32 +195,35 @@ static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i, start, nr); } -bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) +int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; - bool is_cp = true; + bool need = false; down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); - if (e && !get_nat_flag(e, IS_CHECKPOINTED)) - is_cp = false; + if (e) { + if (!get_nat_flag(e, IS_CHECKPOINTED) && + !get_nat_flag(e, HAS_FSYNCED_INODE)) + need = true; + } up_read(&nm_i->nat_tree_lock); - return is_cp; + return need; } -bool has_fsynced_inode(struct f2fs_sb_info *sbi, nid_t ino) +bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; - bool fsynced = false; + bool is_cp = true; down_read(&nm_i->nat_tree_lock); - e = __lookup_nat_cache(nm_i, ino); - if (e && get_nat_flag(e, HAS_FSYNCED_INODE)) - fsynced = true; + e = __lookup_nat_cache(nm_i, nid); + if (e && !get_nat_flag(e, IS_CHECKPOINTED)) + is_cp = false; up_read(&nm_i->nat_tree_lock); - return fsynced; + return is_cp; } bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) @@ -312,7 +315,8 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, __set_nat_cache_dirty(nm_i, e); /* update fsync_mark if its inode nat entry is still alive */ - e = __lookup_nat_cache(nm_i, ni->ino); + if (ni->nid != ni->ino) + e = __lookup_nat_cache(nm_i, ni->ino); if (e) { if (fsync_done && ni->nid == ni->ino) set_nat_flag(e, HAS_FSYNCED_INODE, true); @@ -995,8 +999,11 @@ static int read_node_page(struct page *page, int rw) struct f2fs_sb_info *sbi = F2FS_P_SB(page); struct node_info ni; struct f2fs_io_info fio = { + .sbi = sbi, .type = NODE, .rw = rw, + .page = page, + .encrypted_page = NULL, }; get_node_info(sbi, page->index, &ni); @@ -1011,7 +1018,7 @@ static int read_node_page(struct page *page, int rw) return LOCKED_PAGE; fio.blk_addr = ni.blk_addr; - return f2fs_submit_page_bio(sbi, page, &fio); + return f2fs_submit_page_bio(&fio); } /* @@ -1204,13 +1211,9 @@ continue_unlock: /* called by fsync() */ if (ino && IS_DNODE(page)) { set_fsync_mark(page, 1); - if (IS_INODE(page)) { - if (!is_checkpointed_node(sbi, ino) && - !has_fsynced_inode(sbi, ino)) - set_dentry_mark(page, 1); - else - set_dentry_mark(page, 0); - } + if (IS_INODE(page)) + set_dentry_mark(page, + need_dentry_mark(sbi, ino)); nwritten++; } else { set_fsync_mark(page, 0); @@ -1293,8 +1296,11 @@ static int f2fs_write_node_page(struct page *page, nid_t nid; struct node_info ni; struct f2fs_io_info fio = { + .sbi = sbi, .type = NODE, .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE, + .page = page, + .encrypted_page = NULL, }; trace_f2fs_writepage(page, NODE); @@ -1329,7 +1335,7 @@ static int f2fs_write_node_page(struct page *page, set_page_writeback(page); fio.blk_addr = ni.blk_addr; - write_node_page(sbi, page, nid, &fio); + write_node_page(nid, &fio); set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page)); dec_page_count(sbi, F2FS_DIRTY_NODES); up_read(&sbi->node_write); diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index c56026f1725c..7427e956ad81 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -343,28 +343,6 @@ static inline nid_t get_nid(struct page *p, int off, bool i) * - Mark cold node blocks in their node footer * - Mark cold data pages in page cache */ -static inline int is_file(struct inode *inode, int type) -{ - return F2FS_I(inode)->i_advise & type; -} - -static inline void set_file(struct inode *inode, int type) -{ - F2FS_I(inode)->i_advise |= type; -} - -static inline void clear_file(struct inode *inode, int type) -{ - F2FS_I(inode)->i_advise &= ~type; -} - -#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT) -#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT) -#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT) -#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT) -#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT) -#define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT) - static inline int is_cold_data(struct page *page) { return PageChecked(page); diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 8d8ea99f2156..24a8c1d4f45f 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -83,6 +83,11 @@ static int recover_dentry(struct inode *inode, struct page *ipage) goto out; } + if (file_enc_name(inode)) { + iput(dir); + return 0; + } + name.len = le32_to_cpu(raw_inode->i_namelen); name.name = raw_inode->i_name; @@ -143,6 +148,7 @@ out: static void recover_inode(struct inode *inode, struct page *page) { struct f2fs_inode *raw = F2FS_INODE(page); + char *name; inode->i_mode = le16_to_cpu(raw->i_mode); i_size_write(inode, le64_to_cpu(raw->i_size)); @@ -153,8 +159,13 @@ static void recover_inode(struct inode *inode, struct page *page) inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec); inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec); + if (file_enc_name(inode)) + name = "<encrypted>"; + else + name = F2FS_INODE(page)->i_name; + f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s", - ino_of_node(page), F2FS_INODE(page)->i_name); + ino_of_node(page), name); } static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) @@ -174,7 +185,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) while (1) { struct fsync_inode_entry *entry; - if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi)) + if (!is_valid_blkaddr(sbi, blkaddr, META_POR)) return 0; page = get_meta_page(sbi, blkaddr); @@ -349,7 +360,6 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, struct f2fs_inode_info *fi = F2FS_I(inode); unsigned int start, end; struct dnode_of_data dn; - struct f2fs_summary sum; struct node_info ni; int err = 0, recovered = 0; @@ -396,7 +406,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, dest = datablock_addr(page, dn.ofs_in_node); if (src != dest && dest != NEW_ADDR && dest != NULL_ADDR && - dest >= MAIN_BLKADDR(sbi) && dest < MAX_BLKADDR(sbi)) { + is_valid_blkaddr(sbi, dest, META_POR)) { if (src == NULL_ADDR) { err = reserve_new_block(&dn); @@ -409,13 +419,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, if (err) goto err; - set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); - /* write dummy data page */ - recover_data_page(sbi, NULL, &sum, src, dest); - dn.data_blkaddr = dest; - set_data_blkaddr(&dn); - f2fs_update_extent_cache(&dn); + f2fs_replace_block(sbi, &dn, src, dest, + ni.version, false); recovered++; } dn.ofs_in_node++; @@ -454,7 +460,7 @@ static int recover_data(struct f2fs_sb_info *sbi, while (1) { struct fsync_inode_entry *entry; - if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi)) + if (!is_valid_blkaddr(sbi, blkaddr, META_POR)) break; ra_meta_pages_cond(sbi, blkaddr); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index f939660941bb..1eb343768781 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -75,6 +75,14 @@ static inline unsigned long __reverse_ffs(unsigned long word) static unsigned long __find_rev_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { + while (!f2fs_test_bit(offset, (unsigned char *)addr)) + offset++; + + if (offset > size) + offset = size; + + return offset; +#if 0 const unsigned long *p = addr + BIT_WORD(offset); unsigned long result = offset & ~(BITS_PER_LONG - 1); unsigned long tmp; @@ -121,11 +129,20 @@ found_first: return result + size; /* Nope. */ found_middle: return result + __reverse_ffs(tmp); +#endif } static unsigned long __find_rev_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { + while (f2fs_test_bit(offset, (unsigned char *)addr)) + offset++; + + if (offset > size) + offset = size; + + return offset; +#if 0 const unsigned long *p = addr + BIT_WORD(offset); unsigned long result = offset & ~(BITS_PER_LONG - 1); unsigned long tmp; @@ -173,6 +190,7 @@ found_first: return result + size; /* Nope. */ found_middle: return result + __reverse_ffz(tmp); +#endif } void register_inmem_page(struct inode *inode, struct page *page) @@ -216,8 +234,10 @@ void commit_inmem_pages(struct inode *inode, bool abort) struct inmem_pages *cur, *tmp; bool submit_bio = false; struct f2fs_io_info fio = { + .sbi = sbi, .type = DATA, .rw = WRITE_SYNC | REQ_PRIO, + .encrypted_page = NULL, }; /* @@ -241,7 +261,8 @@ void commit_inmem_pages(struct inode *inode, bool abort) if (clear_page_dirty_for_io(cur->page)) inode_dec_dirty_pages(inode); trace_f2fs_commit_inmem_page(cur->page, INMEM); - do_write_data_page(cur->page, &fio); + fio.page = cur->page; + do_write_data_page(&fio); submit_bio = true; } f2fs_put_page(cur->page, 1); @@ -466,22 +487,43 @@ static int f2fs_issue_discard(struct f2fs_sb_info *sbi, { sector_t start = SECTOR_FROM_BLOCK(blkstart); sector_t len = SECTOR_FROM_BLOCK(blklen); + struct seg_entry *se; + unsigned int offset; + block_t i; + + for (i = blkstart; i < blkstart + blklen; i++) { + se = get_seg_entry(sbi, GET_SEGNO(sbi, i)); + offset = GET_BLKOFF_FROM_SEG0(sbi, i); + + if (!f2fs_test_and_set_bit(offset, se->discard_map)) + sbi->discard_blks--; + } trace_f2fs_issue_discard(sbi->sb, blkstart, blklen); return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0); } void discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr) { - if (f2fs_issue_discard(sbi, blkaddr, 1)) { - struct page *page = grab_meta_page(sbi, blkaddr); - /* zero-filled page */ - set_page_dirty(page); - f2fs_put_page(page, 1); + int err = -ENOTSUPP; + + if (test_opt(sbi, DISCARD)) { + struct seg_entry *se = get_seg_entry(sbi, + GET_SEGNO(sbi, blkaddr)); + unsigned int offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); + + if (f2fs_test_bit(offset, se->discard_map)) + return; + + err = f2fs_issue_discard(sbi, blkaddr, 1); } + + if (err) + update_meta_page(sbi, NULL, blkaddr); } static void __add_discard_entry(struct f2fs_sb_info *sbi, - struct cp_control *cpc, unsigned int start, unsigned int end) + struct cp_control *cpc, struct seg_entry *se, + unsigned int start, unsigned int end) { struct list_head *head = &SM_I(sbi)->discard_list; struct discard_entry *new, *last; @@ -502,7 +544,6 @@ static void __add_discard_entry(struct f2fs_sb_info *sbi, list_add_tail(&new->list, head); done: SM_I(sbi)->nr_discards += end - start; - cpc->trimmed += end - start; } static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) @@ -512,41 +553,24 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start); unsigned long *cur_map = (unsigned long *)se->cur_valid_map; unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map; + unsigned long *discard_map = (unsigned long *)se->discard_map; unsigned long *dmap = SIT_I(sbi)->tmp_map; unsigned int start = 0, end = -1; bool force = (cpc->reason == CP_DISCARD); int i; - if (!force && (!test_opt(sbi, DISCARD) || - SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards)) + if (se->valid_blocks == max_blocks) return; - if (force && !se->valid_blocks) { - struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); - /* - * if this segment is registered in the prefree list, then - * we should skip adding a discard candidate, and let the - * checkpoint do that later. - */ - mutex_lock(&dirty_i->seglist_lock); - if (test_bit(cpc->trim_start, dirty_i->dirty_segmap[PRE])) { - mutex_unlock(&dirty_i->seglist_lock); - cpc->trimmed += sbi->blocks_per_seg; + if (!force) { + if (!test_opt(sbi, DISCARD) || !se->valid_blocks || + SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards) return; - } - mutex_unlock(&dirty_i->seglist_lock); - - __add_discard_entry(sbi, cpc, 0, sbi->blocks_per_seg); - return; } - /* zero block will be discarded through the prefree list */ - if (!se->valid_blocks || se->valid_blocks == max_blocks) - return; - /* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */ for (i = 0; i < entries; i++) - dmap[i] = force ? ~ckpt_map[i] : + dmap[i] = force ? ~ckpt_map[i] & ~discard_map[i] : (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i]; while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) { @@ -555,11 +579,7 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) break; end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1); - - if (force && end - start < cpc->trim_minlen) - continue; - - __add_discard_entry(sbi, cpc, start, end); + __add_discard_entry(sbi, cpc, se, start, end); } } @@ -589,7 +609,7 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi) mutex_unlock(&dirty_i->seglist_lock); } -void clear_prefree_segments(struct f2fs_sb_info *sbi) +void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct list_head *head = &(SM_I(sbi)->discard_list); struct discard_entry *entry, *this; @@ -622,7 +642,11 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi) /* send small discards */ list_for_each_entry_safe(entry, this, head, list) { + if (cpc->reason == CP_DISCARD && entry->len < cpc->trim_minlen) + goto skip; f2fs_issue_discard(sbi, entry->blkaddr, entry->len); + cpc->trimmed += entry->len; +skip: list_del(&entry->list); SM_I(sbi)->nr_discards -= entry->len; kmem_cache_free(discard_entry_slab, entry); @@ -673,9 +697,13 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) if (del > 0) { if (f2fs_test_and_set_bit(offset, se->cur_valid_map)) f2fs_bug_on(sbi, 1); + if (!f2fs_test_and_set_bit(offset, se->discard_map)) + sbi->discard_blks--; } else { if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) f2fs_bug_on(sbi, 1); + if (f2fs_test_and_clear_bit(offset, se->discard_map)) + sbi->discard_blks++; } if (!f2fs_test_bit(offset, se->ckpt_valid_map)) se->ckpt_valid_blocks += del; @@ -769,16 +797,25 @@ struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno) return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno)); } -static void write_sum_page(struct f2fs_sb_info *sbi, - struct f2fs_summary_block *sum_blk, block_t blk_addr) +void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr) { struct page *page = grab_meta_page(sbi, blk_addr); - void *kaddr = page_address(page); - memcpy(kaddr, sum_blk, PAGE_CACHE_SIZE); + void *dst = page_address(page); + + if (src) + memcpy(dst, src, PAGE_CACHE_SIZE); + else + memset(dst, 0, PAGE_CACHE_SIZE); set_page_dirty(page); f2fs_put_page(page, 1); } +static void write_sum_page(struct f2fs_sb_info *sbi, + struct f2fs_summary_block *sum_blk, block_t blk_addr) +{ + update_meta_page(sbi, (void *)sum_blk, blk_addr); +} + static int is_next_segment_free(struct f2fs_sb_info *sbi, int type) { struct curseg_info *curseg = CURSEG_I(sbi, type); @@ -1060,8 +1097,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) unsigned int start_segno, end_segno; struct cp_control cpc; - if (range->minlen > SEGMENT_SIZE(sbi) || start >= MAX_BLKADDR(sbi) || - range->len < sbi->blocksize) + if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize) return -EINVAL; cpc.trimmed = 0; @@ -1073,12 +1109,19 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 : GET_SEGNO(sbi, end); cpc.reason = CP_DISCARD; - cpc.trim_minlen = F2FS_BYTES_TO_BLK(range->minlen); + cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen)); /* do checkpoint to issue discard commands safely */ for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) { cpc.trim_start = start_segno; - cpc.trim_end = min_t(unsigned int, rounddown(start_segno + + + if (sbi->discard_blks == 0) + break; + else if (sbi->discard_blks < BATCHED_TRIM_BLOCKS(sbi)) + cpc.trim_end = end_segno; + else + cpc.trim_end = min_t(unsigned int, + rounddown(start_segno + BATCHED_TRIM_SEGMENTS(sbi), sbi->segs_per_sec) - 1, end_segno); @@ -1206,84 +1249,95 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, mutex_unlock(&curseg->curseg_mutex); } -static void do_write_page(struct f2fs_sb_info *sbi, struct page *page, - struct f2fs_summary *sum, - struct f2fs_io_info *fio) +static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) { - int type = __get_segment_type(page, fio->type); + int type = __get_segment_type(fio->page, fio->type); - allocate_data_block(sbi, page, fio->blk_addr, &fio->blk_addr, sum, type); + allocate_data_block(fio->sbi, fio->page, fio->blk_addr, + &fio->blk_addr, sum, type); /* writeout dirty page into bdev */ - f2fs_submit_page_mbio(sbi, page, fio); + f2fs_submit_page_mbio(fio); } void write_meta_page(struct f2fs_sb_info *sbi, struct page *page) { struct f2fs_io_info fio = { + .sbi = sbi, .type = META, .rw = WRITE_SYNC | REQ_META | REQ_PRIO, .blk_addr = page->index, + .page = page, + .encrypted_page = NULL, }; set_page_writeback(page); - f2fs_submit_page_mbio(sbi, page, &fio); + f2fs_submit_page_mbio(&fio); } -void write_node_page(struct f2fs_sb_info *sbi, struct page *page, - unsigned int nid, struct f2fs_io_info *fio) +void write_node_page(unsigned int nid, struct f2fs_io_info *fio) { struct f2fs_summary sum; + set_summary(&sum, nid, 0, 0); - do_write_page(sbi, page, &sum, fio); + do_write_page(&sum, fio); } -void write_data_page(struct page *page, struct dnode_of_data *dn, - struct f2fs_io_info *fio) +void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio) { - struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + struct f2fs_sb_info *sbi = fio->sbi; struct f2fs_summary sum; struct node_info ni; f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR); get_node_info(sbi, dn->nid, &ni); set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); - do_write_page(sbi, page, &sum, fio); + do_write_page(&sum, fio); dn->data_blkaddr = fio->blk_addr; } -void rewrite_data_page(struct page *page, struct f2fs_io_info *fio) +void rewrite_data_page(struct f2fs_io_info *fio) { - stat_inc_inplace_blocks(F2FS_P_SB(page)); - f2fs_submit_page_mbio(F2FS_P_SB(page), page, fio); + stat_inc_inplace_blocks(fio->sbi); + f2fs_submit_page_mbio(fio); } -void recover_data_page(struct f2fs_sb_info *sbi, - struct page *page, struct f2fs_summary *sum, - block_t old_blkaddr, block_t new_blkaddr) +static void __f2fs_replace_block(struct f2fs_sb_info *sbi, + struct f2fs_summary *sum, + block_t old_blkaddr, block_t new_blkaddr, + bool recover_curseg) { struct sit_info *sit_i = SIT_I(sbi); struct curseg_info *curseg; unsigned int segno, old_cursegno; struct seg_entry *se; int type; + unsigned short old_blkoff; segno = GET_SEGNO(sbi, new_blkaddr); se = get_seg_entry(sbi, segno); type = se->type; - if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) { - if (old_blkaddr == NULL_ADDR) - type = CURSEG_COLD_DATA; - else + if (!recover_curseg) { + /* for recovery flow */ + if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) { + if (old_blkaddr == NULL_ADDR) + type = CURSEG_COLD_DATA; + else + type = CURSEG_WARM_DATA; + } + } else { + if (!IS_CURSEG(sbi, segno)) type = CURSEG_WARM_DATA; } + curseg = CURSEG_I(sbi, type); mutex_lock(&curseg->curseg_mutex); mutex_lock(&sit_i->sentry_lock); old_cursegno = curseg->segno; + old_blkoff = curseg->next_blkoff; /* change the current segment */ if (segno != curseg->segno) { @@ -1297,30 +1351,67 @@ void recover_data_page(struct f2fs_sb_info *sbi, refresh_sit_entry(sbi, old_blkaddr, new_blkaddr); locate_dirty_segment(sbi, old_cursegno); + if (recover_curseg) { + if (old_cursegno != curseg->segno) { + curseg->next_segno = old_cursegno; + change_curseg(sbi, type, true); + } + curseg->next_blkoff = old_blkoff; + } + mutex_unlock(&sit_i->sentry_lock); mutex_unlock(&curseg->curseg_mutex); } +void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, + block_t old_addr, block_t new_addr, + unsigned char version, bool recover_curseg) +{ + struct f2fs_summary sum; + + set_summary(&sum, dn->nid, dn->ofs_in_node, version); + + __f2fs_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg); + + dn->data_blkaddr = new_addr; + set_data_blkaddr(dn); + f2fs_update_extent_cache(dn); +} + static inline bool is_merged_page(struct f2fs_sb_info *sbi, struct page *page, enum page_type type) { enum page_type btype = PAGE_TYPE_OF_BIO(type); struct f2fs_bio_info *io = &sbi->write_io[btype]; struct bio_vec *bvec; + struct page *target; int i; down_read(&io->io_rwsem); - if (!io->bio) - goto out; + if (!io->bio) { + up_read(&io->io_rwsem); + return false; + } bio_for_each_segment_all(bvec, io->bio, i) { - if (page == bvec->bv_page) { + + if (bvec->bv_page->mapping) { + target = bvec->bv_page; + } else { + struct f2fs_crypto_ctx *ctx; + + /* encrypted page */ + ctx = (struct f2fs_crypto_ctx *)page_private( + bvec->bv_page); + target = ctx->w.control_page; + } + + if (page == target) { up_read(&io->io_rwsem); return true; } } -out: up_read(&io->io_rwsem); return false; } @@ -1857,8 +1948,11 @@ static int build_sit_info(struct f2fs_sb_info *sbi) = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); sit_i->sentries[start].ckpt_valid_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); - if (!sit_i->sentries[start].cur_valid_map - || !sit_i->sentries[start].ckpt_valid_map) + sit_i->sentries[start].discard_map + = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + if (!sit_i->sentries[start].cur_valid_map || + !sit_i->sentries[start].ckpt_valid_map || + !sit_i->sentries[start].discard_map) return -ENOMEM; } @@ -1996,6 +2090,11 @@ static void build_sit_entries(struct f2fs_sb_info *sbi) got_it: check_block_count(sbi, start, &sit); seg_info_from_raw_sit(se, &sit); + + /* build discard map only one time */ + memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE); + sbi->discard_blks += sbi->blocks_per_seg - se->valid_blocks; + if (sbi->segs_per_sec > 1) { struct sec_entry *e = get_sec_entry(sbi, start); e->valid_blocks += se->valid_blocks; @@ -2245,6 +2344,7 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi) for (start = 0; start < MAIN_SEGS(sbi); start++) { kfree(sit_i->sentries[start].cur_valid_map); kfree(sit_i->sentries[start].ckpt_valid_map); + kfree(sit_i->sentries[start].discard_map); } } kfree(sit_i->tmp_map); diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 85d7fa7514b2..849635778118 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -163,6 +163,7 @@ struct seg_entry { */ unsigned short ckpt_valid_blocks; unsigned char *ckpt_valid_map; + unsigned char *discard_map; unsigned char type; /* segment type like CURSEG_XXX_TYPE */ unsigned long long mtime; /* modification time of the segment */ }; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index b2dd1b01f076..a06b0b46fe69 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -258,6 +258,7 @@ static void init_once(void *foo) static int parse_options(struct super_block *sb, char *options) { struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct request_queue *q; substring_t args[MAX_OPT_ARGS]; char *p, *name; int arg = 0; @@ -302,7 +303,14 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; break; case Opt_discard: - set_opt(sbi, DISCARD); + q = bdev_get_queue(sb->s_bdev); + if (blk_queue_discard(q)) { + set_opt(sbi, DISCARD); + } else { + f2fs_msg(sb, KERN_WARNING, + "mounting with \"discard\" option, but " + "the device does not support discard"); + } break; case Opt_noheap: set_opt(sbi, NOHEAP); @@ -416,6 +424,9 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) /* Will be used by directory only */ fi->i_dir_level = F2FS_SB(sb)->dir_level; +#ifdef CONFIG_F2FS_FS_ENCRYPTION + fi->i_crypt_info = NULL; +#endif return &fi->vfs_inode; } @@ -428,8 +439,31 @@ static int f2fs_drop_inode(struct inode *inode) * - f2fs_gc -> iput -> evict * - inode_wait_for_writeback(inode) */ - if (!inode_unhashed(inode) && inode->i_state & I_SYNC) + if (!inode_unhashed(inode) && inode->i_state & I_SYNC) { + if (!inode->i_nlink && !is_bad_inode(inode)) { + spin_unlock(&inode->i_lock); + + /* some remained atomic pages should discarded */ + if (f2fs_is_atomic_file(inode)) + commit_inmem_pages(inode, true); + + sb_start_intwrite(inode->i_sb); + i_size_write(inode, 0); + + if (F2FS_HAS_BLOCKS(inode)) + f2fs_truncate(inode); + + sb_end_intwrite(inode->i_sb); + +#ifdef CONFIG_F2FS_FS_ENCRYPTION + if (F2FS_I(inode)->i_crypt_info) + f2fs_free_encryption_info(inode, + F2FS_I(inode)->i_crypt_info); +#endif + spin_lock(&inode->i_lock); + } return 0; + } return generic_drop_inode(inode); } @@ -520,7 +554,7 @@ int f2fs_sync_fs(struct super_block *sb, int sync) } else { f2fs_balance_fs(sbi); } - f2fs_trace_ios(NULL, NULL, 1); + f2fs_trace_ios(NULL, 1); return 0; } @@ -658,6 +692,22 @@ static const struct file_operations f2fs_seq_segment_info_fops = { .release = single_release, }; +static void default_options(struct f2fs_sb_info *sbi) +{ + /* init some FS parameters */ + sbi->active_logs = NR_CURSEG_TYPE; + + set_opt(sbi, BG_GC); + set_opt(sbi, INLINE_DATA); + +#ifdef CONFIG_F2FS_FS_XATTR + set_opt(sbi, XATTR_USER); +#endif +#ifdef CONFIG_F2FS_FS_POSIX_ACL + set_opt(sbi, POSIX_ACL); +#endif +} + static int f2fs_remount(struct super_block *sb, int *flags, char *data) { struct f2fs_sb_info *sbi = F2FS_SB(sb); @@ -676,7 +726,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) active_logs = sbi->active_logs; sbi->mount_opt.opt = 0; - sbi->active_logs = NR_CURSEG_TYPE; + default_options(sbi); /* parse mount options */ err = parse_options(sb, data); @@ -929,29 +979,36 @@ static void init_sb_info(struct f2fs_sb_info *sbi) */ static int read_raw_super_block(struct super_block *sb, struct f2fs_super_block **raw_super, - struct buffer_head **raw_super_buf) + struct buffer_head **raw_super_buf, + int *recovery) { int block = 0; + struct buffer_head *buffer; + struct f2fs_super_block *super; + int err = 0; retry: - *raw_super_buf = sb_bread(sb, block); - if (!*raw_super_buf) { + buffer = sb_bread(sb, block); + if (!buffer) { + *recovery = 1; f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock", block + 1); if (block == 0) { block++; goto retry; } else { - return -EIO; + err = -EIO; + goto out; } } - *raw_super = (struct f2fs_super_block *) - ((char *)(*raw_super_buf)->b_data + F2FS_SUPER_OFFSET); + super = (struct f2fs_super_block *) + ((char *)(buffer)->b_data + F2FS_SUPER_OFFSET); /* sanity checking of raw super */ - if (sanity_check_raw_super(sb, *raw_super)) { - brelse(*raw_super_buf); + if (sanity_check_raw_super(sb, super)) { + brelse(buffer); + *recovery = 1; f2fs_msg(sb, KERN_ERR, "Can't find valid F2FS filesystem in %dth superblock", block + 1); @@ -959,25 +1016,76 @@ retry: block++; goto retry; } else { - return -EINVAL; + err = -EINVAL; + goto out; } } + if (!*raw_super) { + *raw_super_buf = buffer; + *raw_super = super; + } else { + /* already have a valid superblock */ + brelse(buffer); + } + + /* check the validity of the second superblock */ + if (block == 0) { + block++; + goto retry; + } + +out: + /* No valid superblock */ + if (!*raw_super) + return err; + return 0; } +int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) +{ + struct buffer_head *sbh = sbi->raw_super_buf; + sector_t block = sbh->b_blocknr; + int err; + + /* write back-up superblock first */ + sbh->b_blocknr = block ? 0 : 1; + mark_buffer_dirty(sbh); + err = sync_dirty_buffer(sbh); + + sbh->b_blocknr = block; + + /* if we are in recovery path, skip writing valid superblock */ + if (recover || err) + goto out; + + /* write current valid superblock */ + mark_buffer_dirty(sbh); + err = sync_dirty_buffer(sbh); +out: + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); + return err; +} + static int f2fs_fill_super(struct super_block *sb, void *data, int silent) { struct f2fs_sb_info *sbi; - struct f2fs_super_block *raw_super = NULL; + struct f2fs_super_block *raw_super; struct buffer_head *raw_super_buf; struct inode *root; - long err = -EINVAL; + long err; bool retry = true, need_fsck = false; char *options = NULL; - int i; + int recovery, i; try_onemore: + err = -EINVAL; + raw_super = NULL; + raw_super_buf = NULL; + recovery = 0; + /* allocate memory for f2fs-specific super block info */ sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL); if (!sbi) @@ -989,23 +1097,12 @@ try_onemore: goto free_sbi; } - err = read_raw_super_block(sb, &raw_super, &raw_super_buf); + err = read_raw_super_block(sb, &raw_super, &raw_super_buf, &recovery); if (err) goto free_sbi; sb->s_fs_info = sbi; - /* init some FS parameters */ - sbi->active_logs = NR_CURSEG_TYPE; - - set_opt(sbi, BG_GC); - set_opt(sbi, INLINE_DATA); - -#ifdef CONFIG_F2FS_FS_XATTR - set_opt(sbi, XATTR_USER); -#endif -#ifdef CONFIG_F2FS_FS_POSIX_ACL - set_opt(sbi, POSIX_ACL); -#endif + default_options(sbi); /* parse mount options */ options = kstrdup((const char *)data, GFP_KERNEL); if (data && !options) { @@ -1148,14 +1245,6 @@ try_onemore: proc_create_data("segment_info", S_IRUGO, sbi->s_proc, &f2fs_seq_segment_info_fops, sb); - if (test_opt(sbi, DISCARD)) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); - if (!blk_queue_discard(q)) - f2fs_msg(sb, KERN_WARNING, - "mounting with \"discard\" option, but " - "the device does not support discard"); - } - sbi->s_kobj.kset = f2fs_kset; init_completion(&sbi->s_kobj_unregister); err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL, @@ -1198,6 +1287,13 @@ try_onemore: goto free_kobj; } kfree(options); + + /* recover broken superblock */ + if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) { + f2fs_msg(sb, KERN_INFO, "Recover invalid superblock"); + f2fs_commit_super(sbi, true); + } + return 0; free_kobj: @@ -1305,13 +1401,18 @@ static int __init init_f2fs_fs(void) err = -ENOMEM; goto free_extent_cache; } - err = register_filesystem(&f2fs_fs_type); + err = f2fs_init_crypto(); if (err) goto free_kset; + err = register_filesystem(&f2fs_fs_type); + if (err) + goto free_crypto; f2fs_create_root_stats(); f2fs_proc_root = proc_mkdir("fs/f2fs", NULL); return 0; +free_crypto: + f2fs_exit_crypto(); free_kset: kset_unregister(f2fs_kset); free_extent_cache: @@ -1333,6 +1434,7 @@ static void __exit exit_f2fs_fs(void) remove_proc_entry("fs/f2fs", NULL); f2fs_destroy_root_stats(); unregister_filesystem(&f2fs_fs_type); + f2fs_exit_crypto(); destroy_extent_cache(); destroy_checkpoint_caches(); destroy_segment_manager_caches(); diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c index 875aa8179bc1..145fb659ad44 100644 --- a/fs/f2fs/trace.c +++ b/fs/f2fs/trace.c @@ -80,7 +80,7 @@ out: radix_tree_preload_end(); } -void f2fs_trace_ios(struct page *page, struct f2fs_io_info *fio, int flush) +void f2fs_trace_ios(struct f2fs_io_info *fio, int flush) { struct inode *inode; pid_t pid; @@ -91,8 +91,8 @@ void f2fs_trace_ios(struct page *page, struct f2fs_io_info *fio, int flush) return; } - inode = page->mapping->host; - pid = page_private(page); + inode = fio->page->mapping->host; + pid = page_private(fio->page); major = MAJOR(inode->i_sb->s_dev); minor = MINOR(inode->i_sb->s_dev); diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h index 1041dbeb52ae..67db24ac1e85 100644 --- a/fs/f2fs/trace.h +++ b/fs/f2fs/trace.h @@ -33,12 +33,12 @@ struct last_io_info { }; extern void f2fs_trace_pid(struct page *); -extern void f2fs_trace_ios(struct page *, struct f2fs_io_info *, int); +extern void f2fs_trace_ios(struct f2fs_io_info *, int); extern void f2fs_build_trace_ios(void); extern void f2fs_destroy_trace_ios(void); #else #define f2fs_trace_pid(p) -#define f2fs_trace_ios(p, i, n) +#define f2fs_trace_ios(i, n) #define f2fs_build_trace_ios() #define f2fs_destroy_trace_ios() diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 9757f65a05bc..07449b980acb 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -584,6 +584,9 @@ static int __f2fs_setxattr(struct inode *inode, int index, inode->i_ctime = CURRENT_TIME; clear_inode_flag(fi, FI_ACL_MODE); } + if (index == F2FS_XATTR_INDEX_ENCRYPTION && + !strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT)) + f2fs_set_encrypted_inode(inode); if (ipage) update_inode(inode, ipage); diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 969d792ca362..71a7100d5492 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -35,6 +35,10 @@ #define F2FS_XATTR_INDEX_LUSTRE 5 #define F2FS_XATTR_INDEX_SECURITY 6 #define F2FS_XATTR_INDEX_ADVISE 7 +/* Should be same as EXT4_XATTR_INDEX_ENCRYPTION */ +#define F2FS_XATTR_INDEX_ENCRYPTION 9 + +#define F2FS_XATTR_NAME_ENCRYPTION_CONTEXT "c" struct f2fs_xattr_header { __le32 h_magic; /* magic number for identification */ diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 591f8c3ef410..920408a21ffd 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -50,6 +50,8 @@ #define MAX_ACTIVE_NODE_LOGS 8 #define MAX_ACTIVE_DATA_LOGS 8 +#define VERSION_LEN 256 + /* * For superblock */ @@ -86,6 +88,12 @@ struct f2fs_super_block { __le32 extension_count; /* # of extensions below */ __u8 extension_list[F2FS_MAX_EXTENSION][8]; /* extension array */ __le32 cp_payload; + __u8 version[VERSION_LEN]; /* the kernel version */ + __u8 init_version[VERSION_LEN]; /* the initial kernel version */ + __le32 feature; /* defined features */ + __u8 encryption_level; /* versioning level for encryption */ + __u8 encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ + __u8 reserved[871]; /* valid reserved region */ } __packed; /* diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index e202dec22e1d..04856a2d8c82 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -13,6 +13,10 @@ TRACE_DEFINE_ENUM(NODE); TRACE_DEFINE_ENUM(DATA); TRACE_DEFINE_ENUM(META); TRACE_DEFINE_ENUM(META_FLUSH); +TRACE_DEFINE_ENUM(INMEM); +TRACE_DEFINE_ENUM(INMEM_DROP); +TRACE_DEFINE_ENUM(IPU); +TRACE_DEFINE_ENUM(OPU); TRACE_DEFINE_ENUM(CURSEG_HOT_DATA); TRACE_DEFINE_ENUM(CURSEG_WARM_DATA); TRACE_DEFINE_ENUM(CURSEG_COLD_DATA); @@ -37,6 +41,7 @@ TRACE_DEFINE_ENUM(__REQ_META); TRACE_DEFINE_ENUM(CP_UMOUNT); TRACE_DEFINE_ENUM(CP_FASTBOOT); TRACE_DEFINE_ENUM(CP_SYNC); +TRACE_DEFINE_ENUM(CP_RECOVERY); TRACE_DEFINE_ENUM(CP_DISCARD); #define show_block_type(type) \ @@ -112,6 +117,7 @@ TRACE_DEFINE_ENUM(CP_DISCARD); { CP_DISCARD, "Discard" }) struct victim_sel_policy; +struct f2fs_map_blocks; DECLARE_EVENT_CLASS(f2fs__inode, @@ -476,36 +482,35 @@ TRACE_EVENT(f2fs_truncate_partial_nodes, __entry->err) ); -TRACE_EVENT(f2fs_get_data_block, - TP_PROTO(struct inode *inode, sector_t iblock, - struct buffer_head *bh, int ret), +TRACE_EVENT(f2fs_map_blocks, + TP_PROTO(struct inode *inode, struct f2fs_map_blocks *map, int ret), - TP_ARGS(inode, iblock, bh, ret), + TP_ARGS(inode, map, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) - __field(sector_t, iblock) - __field(sector_t, bh_start) - __field(size_t, bh_size) + __field(block_t, m_lblk) + __field(block_t, m_pblk) + __field(unsigned int, m_len) __field(int, ret) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; - __entry->iblock = iblock; - __entry->bh_start = bh->b_blocknr; - __entry->bh_size = bh->b_size; + __entry->m_lblk = map->m_lblk; + __entry->m_pblk = map->m_pblk; + __entry->m_len = map->m_len; __entry->ret = ret; ), TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, " - "start blkaddr = 0x%llx, len = 0x%llx bytes, err = %d", + "start blkaddr = 0x%llx, len = 0x%llx, err = %d", show_dev_ino(__entry), - (unsigned long long)__entry->iblock, - (unsigned long long)__entry->bh_start, - (unsigned long long)__entry->bh_size, + (unsigned long long)__entry->m_lblk, + (unsigned long long)__entry->m_pblk, + (unsigned long long)__entry->m_len, __entry->ret) ); |