diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-19 21:26:31 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-19 21:26:31 (GMT) |
commit | 6162e4b0bedeb3dac2ba0a5e1b1f56db107d97ec (patch) | |
tree | b4ee364c3819f19acd8a63b06d455b11cd91b9ae /fs/ext4 | |
parent | 17974c054db3030b714b7108566bf5208d965a19 (diff) | |
parent | 6ddb2447846a8ece111e316a2863c2355023682d (diff) | |
download | linux-6162e4b0bedeb3dac2ba0a5e1b1f56db107d97ec.tar.xz |
Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 updates from Ted Ts'o:
"A few bug fixes and add support for file-system level encryption in
ext4"
* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (31 commits)
ext4 crypto: enable encryption feature flag
ext4 crypto: add symlink encryption
ext4 crypto: enable filename encryption
ext4 crypto: filename encryption modifications
ext4 crypto: partial update to namei.c for fname crypto
ext4 crypto: insert encrypted filenames into a leaf directory block
ext4 crypto: teach ext4_htree_store_dirent() to store decrypted filenames
ext4 crypto: filename encryption facilities
ext4 crypto: implement the ext4 decryption read path
ext4 crypto: implement the ext4 encryption write path
ext4 crypto: inherit encryption policies on inode and directory create
ext4 crypto: enforce context consistency
ext4 crypto: add encryption key management facilities
ext4 crypto: add ext4 encryption facilities
ext4 crypto: add encryption policy and password salt support
ext4 crypto: add encryption xattr support
ext4 crypto: export ext4_empty_dir()
ext4 crypto: add ext4 encryption Kconfig
ext4 crypto: reserve codepoints used by the ext4 encryption feature
ext4 crypto: add ext4_mpage_readpages()
...
Diffstat (limited to 'fs/ext4')
-rw-r--r-- | fs/ext4/Kconfig | 17 | ||||
-rw-r--r-- | fs/ext4/Makefile | 4 | ||||
-rw-r--r-- | fs/ext4/acl.c | 5 | ||||
-rw-r--r-- | fs/ext4/balloc.c | 3 | ||||
-rw-r--r-- | fs/ext4/bitmap.c | 1 | ||||
-rw-r--r-- | fs/ext4/block_validity.c | 1 | ||||
-rw-r--r-- | fs/ext4/crypto.c | 558 | ||||
-rw-r--r-- | fs/ext4/crypto_fname.c | 709 | ||||
-rw-r--r-- | fs/ext4/crypto_key.c | 165 | ||||
-rw-r--r-- | fs/ext4/crypto_policy.c | 194 | ||||
-rw-r--r-- | fs/ext4/dir.c | 81 | ||||
-rw-r--r-- | fs/ext4/ext4.h | 169 | ||||
-rw-r--r-- | fs/ext4/ext4_crypto.h | 147 | ||||
-rw-r--r-- | fs/ext4/extents.c | 81 | ||||
-rw-r--r-- | fs/ext4/extents_status.c | 2 | ||||
-rw-r--r-- | fs/ext4/file.c | 19 | ||||
-rw-r--r-- | fs/ext4/fsync.c | 1 | ||||
-rw-r--r-- | fs/ext4/hash.c | 1 | ||||
-rw-r--r-- | fs/ext4/ialloc.c | 28 | ||||
-rw-r--r-- | fs/ext4/inline.c | 16 | ||||
-rw-r--r-- | fs/ext4/inode.c | 130 | ||||
-rw-r--r-- | fs/ext4/ioctl.c | 86 | ||||
-rw-r--r-- | fs/ext4/namei.c | 637 | ||||
-rw-r--r-- | fs/ext4/page-io.c | 47 | ||||
-rw-r--r-- | fs/ext4/readpage.c | 328 | ||||
-rw-r--r-- | fs/ext4/super.c | 56 | ||||
-rw-r--r-- | fs/ext4/symlink.c | 97 | ||||
-rw-r--r-- | fs/ext4/xattr.c | 4 | ||||
-rw-r--r-- | fs/ext4/xattr.h | 3 |
29 files changed, 3344 insertions, 246 deletions
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index efea5d5..18228c2 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -64,6 +64,23 @@ config EXT4_FS_SECURITY If you are not using a security module that requires using extended attributes for file security labels, say N. +config EXT4_FS_ENCRYPTION + bool "Ext4 Encryption" + depends on EXT4_FS + select CRYPTO_AES + select CRYPTO_CBC + select CRYPTO_ECB + select CRYPTO_XTS + select CRYPTO_CTS + select CRYPTO_SHA256 + select KEYS + select ENCRYPTED_KEYS + help + Enable encryption of ext4 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 EXT4_DEBUG bool "EXT4 debugging support" depends on EXT4_FS diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 0310fec..75285ea 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -8,7 +8,9 @@ ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \ ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \ mmp.o indirect.o extents_status.o xattr.o xattr_user.o \ - xattr_trusted.o inline.o + xattr_trusted.o inline.o readpage.o ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o +ext4-$(CONFIG_EXT4_FS_ENCRYPTION) += crypto_policy.o crypto.o \ + crypto_key.o crypto_fname.o diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index d40c8db..69b1e73 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -4,11 +4,6 @@ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> */ -#include <linux/init.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/capability.h> -#include <linux/fs.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 83a6f49..955bf49 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -14,7 +14,6 @@ #include <linux/time.h> #include <linux/capability.h> #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/quotaops.h> #include <linux/buffer_head.h> #include "ext4.h" @@ -641,8 +640,6 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, * fail EDQUOT for metdata, but we do account for it. */ if (!(*errp) && (flags & EXT4_MB_DELALLOC_RESERVED)) { - spin_lock(&EXT4_I(inode)->i_block_reservation_lock); - spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); dquot_alloc_block_nofail(inode, EXT4_C2B(EXT4_SB(inode->i_sb), ar.len)); } diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index b610779..4a606afb 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -8,7 +8,6 @@ */ #include <linux/buffer_head.h> -#include <linux/jbd2.h> #include "ext4.h" unsigned int ext4_count_free(char *bitmap, unsigned int numchars) diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 41eb9dc..3522340 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -16,7 +16,6 @@ #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/blkdev.h> -#include <linux/mutex.h> #include <linux/slab.h> #include "ext4.h" diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c new file mode 100644 index 0000000..8ff1527 --- /dev/null +++ b/fs/ext4/crypto.c @@ -0,0 +1,558 @@ +/* + * linux/fs/ext4/crypto.c + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption functions for ext4 + * + * Written by Michael Halcrow, 2014. + * + * Filename encryption additions + * Uday Savagaonkar, 2014 + * Encryption policy handling additions + * Ildar Muslukhov, 2014 + * + * 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 "ext4_extents.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 *ext4_bounce_page_pool; + +static LIST_HEAD(ext4_free_crypto_ctxs); +static DEFINE_SPINLOCK(ext4_crypto_ctx_lock); + +/** + * ext4_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 ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx) +{ + unsigned long flags; + + if (ctx->bounce_page) { + if (ctx->flags & EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL) + __free_page(ctx->bounce_page); + else + mempool_free(ctx->bounce_page, ext4_bounce_page_pool); + ctx->bounce_page = NULL; + } + ctx->control_page = NULL; + if (ctx->flags & EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL) { + if (ctx->tfm) + crypto_free_tfm(ctx->tfm); + kfree(ctx); + } else { + spin_lock_irqsave(&ext4_crypto_ctx_lock, flags); + list_add(&ctx->free_list, &ext4_free_crypto_ctxs); + spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags); + } +} + +/** + * ext4_alloc_and_init_crypto_ctx() - Allocates and inits an encryption context + * @mask: The allocation mask. + * + * Return: An allocated and initialized encryption context on success. An error + * value or NULL otherwise. + */ +static struct ext4_crypto_ctx *ext4_alloc_and_init_crypto_ctx(gfp_t mask) +{ + struct ext4_crypto_ctx *ctx = kzalloc(sizeof(struct ext4_crypto_ctx), + mask); + + if (!ctx) + return ERR_PTR(-ENOMEM); + return ctx; +} + +/** + * ext4_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 ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode) +{ + struct ext4_crypto_ctx *ctx = NULL; + int res = 0; + unsigned long flags; + struct ext4_encryption_key *key = &EXT4_I(inode)->i_encryption_key; + + if (!ext4_read_workqueue) + ext4_init_crypto(); + + /* + * 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(&ext4_crypto_ctx_lock, flags); + ctx = list_first_entry_or_null(&ext4_free_crypto_ctxs, + struct ext4_crypto_ctx, free_list); + if (ctx) + list_del(&ctx->free_list); + spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags); + if (!ctx) { + ctx = ext4_alloc_and_init_crypto_ctx(GFP_NOFS); + if (IS_ERR(ctx)) { + res = PTR_ERR(ctx); + goto out; + } + ctx->flags |= EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL; + } else { + ctx->flags &= ~EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL; + } + + /* Allocate a new Crypto API context if we don't already have + * one or if it isn't the right mode. */ + BUG_ON(key->mode == EXT4_ENCRYPTION_MODE_INVALID); + if (ctx->tfm && (ctx->mode != key->mode)) { + crypto_free_tfm(ctx->tfm); + ctx->tfm = NULL; + ctx->mode = EXT4_ENCRYPTION_MODE_INVALID; + } + if (!ctx->tfm) { + switch (key->mode) { + case EXT4_ENCRYPTION_MODE_AES_256_XTS: + ctx->tfm = crypto_ablkcipher_tfm( + crypto_alloc_ablkcipher("xts(aes)", 0, 0)); + break; + case EXT4_ENCRYPTION_MODE_AES_256_GCM: + /* TODO(mhalcrow): AEAD w/ gcm(aes); + * crypto_aead_setauthsize() */ + ctx->tfm = ERR_PTR(-ENOTSUPP); + break; + default: + BUG(); + } + if (IS_ERR_OR_NULL(ctx->tfm)) { + res = PTR_ERR(ctx->tfm); + ctx->tfm = NULL; + goto out; + } + ctx->mode = key->mode; + } + BUG_ON(key->size != ext4_encryption_key_size(key->mode)); + + /* There shouldn't be a bounce page attached to the crypto + * context at this point. */ + BUG_ON(ctx->bounce_page); + +out: + if (res) { + if (!IS_ERR_OR_NULL(ctx)) + ext4_release_crypto_ctx(ctx); + ctx = ERR_PTR(res); + } + return ctx; +} + +struct workqueue_struct *ext4_read_workqueue; +static DEFINE_MUTEX(crypto_init); + +/** + * ext4_exit_crypto() - Shutdown the ext4 encryption system + */ +void ext4_exit_crypto(void) +{ + struct ext4_crypto_ctx *pos, *n; + + list_for_each_entry_safe(pos, n, &ext4_free_crypto_ctxs, free_list) { + if (pos->bounce_page) { + if (pos->flags & + EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL) { + __free_page(pos->bounce_page); + } else { + mempool_free(pos->bounce_page, + ext4_bounce_page_pool); + } + } + if (pos->tfm) + crypto_free_tfm(pos->tfm); + kfree(pos); + } + INIT_LIST_HEAD(&ext4_free_crypto_ctxs); + if (ext4_bounce_page_pool) + mempool_destroy(ext4_bounce_page_pool); + ext4_bounce_page_pool = NULL; + if (ext4_read_workqueue) + destroy_workqueue(ext4_read_workqueue); + ext4_read_workqueue = NULL; +} + +/** + * ext4_init_crypto() - Set up for ext4 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 ext4_init_crypto(void) +{ + int i, res; + + mutex_lock(&crypto_init); + if (ext4_read_workqueue) + goto already_initialized; + ext4_read_workqueue = alloc_workqueue("ext4_crypto", WQ_HIGHPRI, 0); + if (!ext4_read_workqueue) { + res = -ENOMEM; + goto fail; + } + + for (i = 0; i < num_prealloc_crypto_ctxs; i++) { + struct ext4_crypto_ctx *ctx; + + ctx = ext4_alloc_and_init_crypto_ctx(GFP_KERNEL); + if (IS_ERR(ctx)) { + res = PTR_ERR(ctx); + goto fail; + } + list_add(&ctx->free_list, &ext4_free_crypto_ctxs); + } + + ext4_bounce_page_pool = + mempool_create_page_pool(num_prealloc_crypto_pages, 0); + if (!ext4_bounce_page_pool) { + res = -ENOMEM; + goto fail; + } +already_initialized: + mutex_unlock(&crypto_init); + return 0; +fail: + ext4_exit_crypto(); + mutex_unlock(&crypto_init); + return res; +} + +void ext4_restore_control_page(struct page *data_page) +{ + struct ext4_crypto_ctx *ctx = + (struct ext4_crypto_ctx *)page_private(data_page); + + set_page_private(data_page, (unsigned long)NULL); + ClearPagePrivate(data_page); + unlock_page(data_page); + ext4_release_crypto_ctx(ctx); +} + +/** + * ext4_crypt_complete() - The completion callback for page encryption + * @req: The asynchronous encryption request context + * @res: The result of the encryption operation + */ +static void ext4_crypt_complete(struct crypto_async_request *req, int res) +{ + struct ext4_completion_result *ecr = req->data; + + if (res == -EINPROGRESS) + return; + ecr->res = res; + complete(&ecr->completion); +} + +typedef enum { + EXT4_DECRYPT = 0, + EXT4_ENCRYPT, +} ext4_direction_t; + +static int ext4_page_crypto(struct ext4_crypto_ctx *ctx, + struct inode *inode, + ext4_direction_t rw, + pgoff_t index, + struct page *src_page, + struct page *dest_page) + +{ + u8 xts_tweak[EXT4_XTS_TWEAK_SIZE]; + struct ablkcipher_request *req = NULL; + DECLARE_EXT4_COMPLETION_RESULT(ecr); + struct scatterlist dst, src; + struct ext4_inode_info *ei = EXT4_I(inode); + struct crypto_ablkcipher *atfm = __crypto_ablkcipher_cast(ctx->tfm); + int res = 0; + + BUG_ON(!ctx->tfm); + BUG_ON(ctx->mode != ei->i_encryption_key.mode); + + if (ctx->mode != EXT4_ENCRYPTION_MODE_AES_256_XTS) { + printk_ratelimited(KERN_ERR + "%s: unsupported crypto algorithm: %d\n", + __func__, ctx->mode); + return -ENOTSUPP; + } + + crypto_ablkcipher_clear_flags(atfm, ~0); + crypto_tfm_set_flags(ctx->tfm, CRYPTO_TFM_REQ_WEAK_KEY); + + res = crypto_ablkcipher_setkey(atfm, ei->i_encryption_key.raw, + ei->i_encryption_key.size); + if (res) { + printk_ratelimited(KERN_ERR + "%s: crypto_ablkcipher_setkey() failed\n", + __func__); + return res; + } + req = ablkcipher_request_alloc(atfm, 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, + ext4_crypt_complete, &ecr); + + BUILD_BUG_ON(EXT4_XTS_TWEAK_SIZE < sizeof(index)); + memcpy(xts_tweak, &index, sizeof(index)); + memset(&xts_tweak[sizeof(index)], 0, + EXT4_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 == EXT4_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; +} + +/** + * ext4_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 + * ext4_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 *ext4_encrypt(struct inode *inode, + struct page *plaintext_page) +{ + struct ext4_crypto_ctx *ctx; + struct page *ciphertext_page = NULL; + int err; + + BUG_ON(!PageLocked(plaintext_page)); + + ctx = ext4_get_crypto_ctx(inode); + if (IS_ERR(ctx)) + return (struct page *) ctx; + + /* The encryption operation will require a bounce page. */ + ciphertext_page = alloc_page(GFP_NOFS); + if (!ciphertext_page) { + /* This is a potential bottleneck, but at least we'll have + * forward progress. */ + ciphertext_page = mempool_alloc(ext4_bounce_page_pool, + GFP_NOFS); + if (WARN_ON_ONCE(!ciphertext_page)) { + ciphertext_page = mempool_alloc(ext4_bounce_page_pool, + GFP_NOFS | __GFP_WAIT); + } + ctx->flags &= ~EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL; + } else { + ctx->flags |= EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL; + } + ctx->bounce_page = ciphertext_page; + ctx->control_page = plaintext_page; + err = ext4_page_crypto(ctx, inode, EXT4_ENCRYPT, plaintext_page->index, + plaintext_page, ciphertext_page); + if (err) { + ext4_release_crypto_ctx(ctx); + return ERR_PTR(err); + } + SetPagePrivate(ciphertext_page); + set_page_private(ciphertext_page, (unsigned long)ctx); + lock_page(ciphertext_page); + return ciphertext_page; +} + +/** + * ext4_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 ext4_decrypt(struct ext4_crypto_ctx *ctx, struct page *page) +{ + BUG_ON(!PageLocked(page)); + + return ext4_page_crypto(ctx, page->mapping->host, + EXT4_DECRYPT, page->index, page, page); +} + +/* + * Convenience function which takes care of allocating and + * deallocating the encryption context + */ +int ext4_decrypt_one(struct inode *inode, struct page *page) +{ + int ret; + + struct ext4_crypto_ctx *ctx = ext4_get_crypto_ctx(inode); + + if (!ctx) + return -ENOMEM; + ret = ext4_decrypt(ctx, page); + ext4_release_crypto_ctx(ctx); + return ret; +} + +int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) +{ + struct ext4_crypto_ctx *ctx; + struct page *ciphertext_page = NULL; + struct bio *bio; + ext4_lblk_t lblk = ex->ee_block; + ext4_fsblk_t pblk = ext4_ext_pblock(ex); + unsigned int len = ext4_ext_get_actual_len(ex); + int err = 0; + + BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE); + + ctx = ext4_get_crypto_ctx(inode); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ciphertext_page = alloc_page(GFP_NOFS); + if (!ciphertext_page) { + /* This is a potential bottleneck, but at least we'll have + * forward progress. */ + ciphertext_page = mempool_alloc(ext4_bounce_page_pool, + GFP_NOFS); + if (WARN_ON_ONCE(!ciphertext_page)) { + ciphertext_page = mempool_alloc(ext4_bounce_page_pool, + GFP_NOFS | __GFP_WAIT); + } + ctx->flags &= ~EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL; + } else { + ctx->flags |= EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL; + } + ctx->bounce_page = ciphertext_page; + + while (len--) { + err = ext4_page_crypto(ctx, inode, EXT4_ENCRYPT, lblk, + ZERO_PAGE(0), ciphertext_page); + if (err) + goto errout; + + bio = bio_alloc(GFP_KERNEL, 1); + if (!bio) { + err = -ENOMEM; + goto errout; + } + bio->bi_bdev = inode->i_sb->s_bdev; + bio->bi_iter.bi_sector = pblk; + err = bio_add_page(bio, ciphertext_page, + inode->i_sb->s_blocksize, 0); + if (err) { + bio_put(bio); + goto errout; + } + err = submit_bio_wait(WRITE, bio); + if (err) + goto errout; + } + err = 0; +errout: + ext4_release_crypto_ctx(ctx); + return err; +} + +bool ext4_valid_contents_enc_mode(uint32_t mode) +{ + return (mode == EXT4_ENCRYPTION_MODE_AES_256_XTS); +} + +/** + * ext4_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 ext4_validate_encryption_key_size(uint32_t mode, uint32_t size) +{ + if (size == ext4_encryption_key_size(mode)) + return size; + return 0; +} diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c new file mode 100644 index 0000000..ca2f594 --- /dev/null +++ b/fs/ext4/crypto_fname.c @@ -0,0 +1,709 @@ +/* + * linux/fs/ext4/crypto_fname.c + * + * Copyright (C) 2015, Google, Inc. + * + * This contains functions for filename crypto management in ext4 + * + * Written by Uday Savagaonkar, 2014. + * + * 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/key.h> +#include <linux/list.h> +#include <linux/mempool.h> +#include <linux/random.h> +#include <linux/scatterlist.h> +#include <linux/spinlock_types.h> + +#include "ext4.h" +#include "ext4_crypto.h" +#include "xattr.h" + +/** + * ext4_dir_crypt_complete() - + */ +static void ext4_dir_crypt_complete(struct crypto_async_request *req, int res) +{ + struct ext4_completion_result *ecr = req->data; + + if (res == -EINPROGRESS) + return; + ecr->res = res; + complete(&ecr->completion); +} + +bool ext4_valid_filenames_enc_mode(uint32_t mode) +{ + return (mode == EXT4_ENCRYPTION_MODE_AES_256_CTS); +} + +/** + * ext4_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 ext4_fname_encrypt(struct ext4_fname_crypto_ctx *ctx, + const struct qstr *iname, + struct ext4_str *oname) +{ + u32 ciphertext_len; + struct ablkcipher_request *req = NULL; + DECLARE_EXT4_COMPLETION_RESULT(ecr); + struct crypto_ablkcipher *tfm = ctx->ctfm; + int res = 0; + char iv[EXT4_CRYPTO_BLOCK_SIZE]; + struct scatterlist sg[1]; + char *workbuf; + + if (iname->len <= 0 || iname->len > ctx->lim) + return -EIO; + + ciphertext_len = (iname->len < EXT4_CRYPTO_BLOCK_SIZE) ? + EXT4_CRYPTO_BLOCK_SIZE : iname->len; + ciphertext_len = (ciphertext_len > ctx->lim) + ? ctx->lim : ciphertext_len; + + /* 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, + ext4_dir_crypt_complete, &ecr); + + /* Map the workpage */ + workbuf = kmap(ctx->workpage); + + /* 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, EXT4_CRYPTO_BLOCK_SIZE); + + /* Create encryption request */ + sg_init_table(sg, 1); + sg_set_page(sg, ctx->workpage, PAGE_SIZE, 0); + ablkcipher_request_set_crypt(req, sg, sg, iname->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; + } + if (res >= 0) { + /* Copy the result to output */ + memcpy(oname->name, workbuf, ciphertext_len); + res = ciphertext_len; + } + kunmap(ctx->workpage); + 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; +} + +/* + * ext4_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 ext4_fname_decrypt(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_str *iname, + struct ext4_str *oname) +{ + struct ext4_str tmp_in[2], tmp_out[1]; + struct ablkcipher_request *req = NULL; + DECLARE_EXT4_COMPLETION_RESULT(ecr); + struct scatterlist sg[1]; + struct crypto_ablkcipher *tfm = ctx->ctfm; + int res = 0; + char iv[EXT4_CRYPTO_BLOCK_SIZE]; + char *workbuf; + + if (iname->len <= 0 || iname->len > ctx->lim) + return -EIO; + + tmp_in[0].name = iname->name; + tmp_in[0].len = iname->len; + tmp_out[0].name = oname->name; + + /* 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, + ext4_dir_crypt_complete, &ecr); + + /* Map the workpage */ + workbuf = kmap(ctx->workpage); + + /* Copy the input */ + memcpy(workbuf, iname->name, iname->len); + + /* Initialize IV */ + memset(iv, 0, EXT4_CRYPTO_BLOCK_SIZE); + + /* Create encryption request */ + sg_init_table(sg, 1); + sg_set_page(sg, ctx->workpage, PAGE_SIZE, 0); + ablkcipher_request_set_crypt(req, sg, 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; + } + if (res >= 0) { + /* Copy the result to output */ + memcpy(oname->name, workbuf, iname->len); + res = iname->len; + } + kunmap(ctx->workpage); + ablkcipher_request_free(req); + if (res < 0) { + printk_ratelimited( + KERN_ERR "%s: Error in ext4_fname_encrypt (error code %d)\n", + __func__, res); + return res; + } + + oname->len = strnlen(oname->name, iname->len); + return oname->len; +} + +/** + * ext4_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. + */ +int ext4_fname_encode_digest(char *dst, char *src, u32 len) +{ + static const char *lookup_table = + "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_+"; + u32 current_chunk, num_chunks, i; + char tmp_buf[3]; + u32 c0, c1, c2, c3; + + current_chunk = 0; + num_chunks = len/3; + for (i = 0; i < num_chunks; i++) { + c0 = src[3*i] & 0x3f; + c1 = (((src[3*i]>>6)&0x3) | ((src[3*i+1] & 0xf)<<2)) & 0x3f; + c2 = (((src[3*i+1]>>4)&0xf) | ((src[3*i+2] & 0x3)<<4)) & 0x3f; + c3 = (src[3*i+2]>>2) & 0x3f; + dst[4*i] = lookup_table[c0]; + dst[4*i+1] = lookup_table[c1]; + dst[4*i+2] = lookup_table[c2]; + dst[4*i+3] = lookup_table[c3]; + } + if (i*3 < len) { + memset(tmp_buf, 0, 3); + memcpy(tmp_buf, &src[3*i], len-3*i); + c0 = tmp_buf[0] & 0x3f; + c1 = (((tmp_buf[0]>>6)&0x3) | ((tmp_buf[1] & 0xf)<<2)) & 0x3f; + c2 = (((tmp_buf[1]>>4)&0xf) | ((tmp_buf[2] & 0x3)<<4)) & 0x3f; + c3 = (tmp_buf[2]>>2) & 0x3f; + dst[4*i] = lookup_table[c0]; + dst[4*i+1] = lookup_table[c1]; + dst[4*i+2] = lookup_table[c2]; + dst[4*i+3] = lookup_table[c3]; + i++; + } + return (i * 4); +} + +/** + * ext4_fname_hash() - + * + * This function computes the hash of the input filename, and sets the output + * buffer to the *encoded* digest. It returns the length of the digest as its + * return value. Errors are returned as negative numbers. We trust the caller + * to allocate sufficient memory to oname string. + */ +static int ext4_fname_hash(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_str *iname, + struct ext4_str *oname) +{ + struct scatterlist sg; + struct hash_desc desc = { + .tfm = (struct crypto_hash *)ctx->htfm, + .flags = CRYPTO_TFM_REQ_MAY_SLEEP + }; + int res = 0; + + if (iname->len <= EXT4_FNAME_CRYPTO_DIGEST_SIZE) { + res = ext4_fname_encode_digest(oname->name, iname->name, + iname->len); + oname->len = res; + return res; + } + + sg_init_one(&sg, iname->name, iname->len); + res = crypto_hash_init(&desc); + if (res) { + printk(KERN_ERR + "%s: Error initializing crypto hash; res = [%d]\n", + __func__, res); + goto out; + } + res = crypto_hash_update(&desc, &sg, iname->len); + if (res) { + printk(KERN_ERR + "%s: Error updating crypto hash; res = [%d]\n", + __func__, res); + goto out; + } + res = crypto_hash_final(&desc, + &oname->name[EXT4_FNAME_CRYPTO_DIGEST_SIZE]); + if (res) { + printk(KERN_ERR + "%s: Error finalizing crypto hash; res = [%d]\n", + __func__, res); + goto out; + } + /* Encode the digest as a printable string--this will increase the + * size of the digest */ + oname->name[0] = 'I'; + res = ext4_fname_encode_digest(oname->name+1, + &oname->name[EXT4_FNAME_CRYPTO_DIGEST_SIZE], + EXT4_FNAME_CRYPTO_DIGEST_SIZE) + 1; + oname->len = res; +out: + return res; +} + +/** + * ext4_free_fname_crypto_ctx() - + * + * Frees up a crypto context. + */ +void ext4_free_fname_crypto_ctx(struct ext4_fname_crypto_ctx *ctx) +{ + if (ctx == NULL || IS_ERR(ctx)) + return; + + if (ctx->ctfm && !IS_ERR(ctx->ctfm)) + crypto_free_ablkcipher(ctx->ctfm); + if (ctx->htfm && !IS_ERR(ctx->htfm)) + crypto_free_hash(ctx->htfm); + if (ctx->workpage && !IS_ERR(ctx->workpage)) + __free_page(ctx->workpage); + kfree(ctx); +} + +/** + * ext4_put_fname_crypto_ctx() - + * + * Return: The crypto context onto free list. If the free list is above a + * threshold, completely frees up the context, and returns the memory. + * + * TODO: Currently we directly free the crypto context. Eventually we should + * add code it to return to free list. Such an approach will increase + * efficiency of directory lookup. + */ +void ext4_put_fname_crypto_ctx(struct ext4_fname_crypto_ctx **ctx) +{ + if (*ctx == NULL || IS_ERR(*ctx)) + return; + ext4_free_fname_crypto_ctx(*ctx); + *ctx = NULL; +} + +/** + * ext4_search_fname_crypto_ctx() - + */ +static struct ext4_fname_crypto_ctx *ext4_search_fname_crypto_ctx( + const struct ext4_encryption_key *key) +{ + return NULL; +} + +/** + * ext4_alloc_fname_crypto_ctx() - + */ +struct ext4_fname_crypto_ctx *ext4_alloc_fname_crypto_ctx( + const struct ext4_encryption_key *key) +{ + struct ext4_fname_crypto_ctx *ctx; + + ctx = kmalloc(sizeof(struct ext4_fname_crypto_ctx), GFP_NOFS); + if (ctx == NULL) + return ERR_PTR(-ENOMEM); + if (key->mode == EXT4_ENCRYPTION_MODE_INVALID) { + /* This will automatically set key mode to invalid + * As enum for ENCRYPTION_MODE_INVALID is zero */ + memset(&ctx->key, 0, sizeof(ctx->key)); + } else { + memcpy(&ctx->key, key, sizeof(struct ext4_encryption_key)); + } + ctx->has_valid_key = (EXT4_ENCRYPTION_MODE_INVALID == key->mode) + ? 0 : 1; + ctx->ctfm_key_is_ready = 0; + ctx->ctfm = NULL; + ctx->htfm = NULL; + ctx->workpage = NULL; + return ctx; +} + +/** + * ext4_get_fname_crypto_ctx() - + * + * Allocates a free crypto context and initializes it to hold + * the crypto material for the inode. + * + * Return: NULL if not encrypted. Error value on error. Valid pointer otherwise. + */ +struct ext4_fname_crypto_ctx *ext4_get_fname_crypto_ctx( + struct inode *inode, u32 max_ciphertext_len) +{ + struct ext4_fname_crypto_ctx *ctx; + struct ext4_inode_info *ei = EXT4_I(inode); + int res; + + /* Check if the crypto policy is set on the inode */ + res = ext4_encrypted_inode(inode); + if (res == 0) + return NULL; + + if (!ext4_has_encryption_key(inode)) + ext4_generate_encryption_key(inode); + + /* Get a crypto context based on the key. + * A new context is allocated if no context matches the requested key. + */ + ctx = ext4_search_fname_crypto_ctx(&(ei->i_encryption_key)); + if (ctx == NULL) + ctx = ext4_alloc_fname_crypto_ctx(&(ei->i_encryption_key)); + if (IS_ERR(ctx)) + return ctx; + + if (ctx->has_valid_key) { + if (ctx->key.mode != EXT4_ENCRYPTION_MODE_AES_256_CTS) { + printk_once(KERN_WARNING + "ext4: unsupported key mode %d\n", + ctx->key.mode); + return ERR_PTR(-ENOKEY); + } + + /* As a first cut, we will allocate new tfm in every call. + * later, we will keep the tfm around, in case the key gets + * re-used */ + if (ctx->ctfm == NULL) { + ctx->ctfm = crypto_alloc_ablkcipher("cts(cbc(aes))", + 0, 0); + } + if (IS_ERR(ctx->ctfm)) { + res = PTR_ERR(ctx->ctfm); + printk( + KERN_DEBUG "%s: error (%d) allocating crypto tfm\n", + __func__, res); + ctx->ctfm = NULL; + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(res); + } + if (ctx->ctfm == NULL) { + printk( + KERN_DEBUG "%s: could not allocate crypto tfm\n", + __func__); + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(-ENOMEM); + } + if (ctx->workpage == NULL) + ctx->workpage = alloc_page(GFP_NOFS); + if (IS_ERR(ctx->workpage)) { + res = PTR_ERR(ctx->workpage); + printk( + KERN_DEBUG "%s: error (%d) allocating work page\n", + __func__, res); + ctx->workpage = NULL; + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(res); + } + if (ctx->workpage == NULL) { + printk( + KERN_DEBUG "%s: could not allocate work page\n", + __func__); + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(-ENOMEM); + } + ctx->lim = max_ciphertext_len; + crypto_ablkcipher_clear_flags(ctx->ctfm, ~0); + crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctx->ctfm), + CRYPTO_TFM_REQ_WEAK_KEY); + + /* If we are lucky, we will get a context that is already + * set up with the right key. Else, we will have to + * set the key */ + if (!ctx->ctfm_key_is_ready) { + /* Since our crypto objectives for filename encryption + * are pretty weak, + * we directly use the inode master key */ + res = crypto_ablkcipher_setkey(ctx->ctfm, + ctx->key.raw, ctx->key.size); + if (res) { + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(-EIO); + } + ctx->ctfm_key_is_ready = 1; + } else { + /* In the current implementation, key should never be + * marked "ready" for a context that has just been + * allocated. So we should never reach here */ + BUG(); + } + } + if (ctx->htfm == NULL) + ctx->htfm = crypto_alloc_hash("sha256", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(ctx->htfm)) { + res = PTR_ERR(ctx->htfm); + printk(KERN_DEBUG "%s: error (%d) allocating hash tfm\n", + __func__, res); + ctx->htfm = NULL; + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(res); + } + if (ctx->htfm == NULL) { + printk(KERN_DEBUG "%s: could not allocate hash tfm\n", + __func__); + ext4_put_fname_crypto_ctx(&ctx); + return ERR_PTR(-ENOMEM); + } + + return ctx; +} + +/** + * ext4_fname_crypto_round_up() - + * + * Return: The next multiple of block size + */ +u32 ext4_fname_crypto_round_up(u32 size, u32 blksize) +{ + return ((size+blksize-1)/blksize)*blksize; +} + +/** + * ext4_fname_crypto_namelen_on_disk() - + */ +int ext4_fname_crypto_namelen_on_disk(struct ext4_fname_crypto_ctx *ctx, + u32 namelen) +{ + u32 ciphertext_len; + + if (ctx == NULL) + return -EIO; + if (!(ctx->has_valid_key)) + return -EACCES; + ciphertext_len = (namelen < EXT4_CRYPTO_BLOCK_SIZE) ? + EXT4_CRYPTO_BLOCK_SIZE : namelen; + ciphertext_len = (ciphertext_len > ctx->lim) + ? ctx->lim : ciphertext_len; + return (int) ciphertext_len; +} + +/** + * ext4_fname_crypto_alloc_obuff() - + * + * Allocates an output buffer that is sufficient for the crypto operation + * specified by the context and the direction. + */ +int ext4_fname_crypto_alloc_buffer(struct ext4_fname_crypto_ctx *ctx, + u32 ilen, struct ext4_str *crypto_str) +{ + unsigned int olen; + + if (!ctx) + return -EIO; + olen = ext4_fname_crypto_round_up(ilen, EXT4_CRYPTO_BLOCK_SIZE); + crypto_str->len = olen; + if (olen < EXT4_FNAME_CRYPTO_DIGEST_SIZE*2) + olen = EXT4_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; +} + +/** + * ext4_fname_crypto_free_buffer() - + * + * Frees the buffer allocated for crypto operation. + */ +void ext4_fname_crypto_free_buffer(struct ext4_str *crypto_str) +{ + if (!crypto_str) + return; + kfree(crypto_str->name); + crypto_str->name = NULL; +} + +/** + * ext4_fname_disk_to_usr() - converts a filename from disk space to user space + */ +int _ext4_fname_disk_to_usr(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_str *iname, + struct ext4_str *oname) +{ + if (ctx == NULL) + return -EIO; + if (iname->len < 3) { + /*Check for . and .. */ + if (iname->name[0] == '.' && iname->name[iname->len-1] == '.') { + oname->name[0] = '.'; + oname->name[iname->len-1] = '.'; + oname->len = iname->len; + return oname->len; + } + } + if (ctx->has_valid_key) + return ext4_fname_decrypt(ctx, iname, oname); + else + return ext4_fname_hash(ctx, iname, oname); +} + +int ext4_fname_disk_to_usr(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_dir_entry_2 *de, + struct ext4_str *oname) +{ + struct ext4_str iname = {.name = (unsigned char *) de->name, + .len = de->name_len }; + + return _ext4_fname_disk_to_usr(ctx, &iname, oname); +} + + +/** + * ext4_fname_usr_to_disk() - converts a filename from user space to disk space + */ +int ext4_fname_usr_to_disk(struct ext4_fname_crypto_ctx *ctx, + const struct qstr *iname, + struct ext4_str *oname) +{ + int res; + + if (ctx == NULL) + return -EIO; + if (iname->len < 3) { + /*Check for . and .. */ + if (iname->name[0] == '.' && + iname->name[iname->len-1] == '.') { + oname->name[0] = '.'; + oname->name[iname->len-1] = '.'; + oname->len = iname->len; + return oname->len; + } + } + if (ctx->has_valid_key) { + res = ext4_fname_encrypt(ctx, 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; +} + +/* + * Calculate the htree hash from a filename from user space + */ +int ext4_fname_usr_to_hash(struct ext4_fname_crypto_ctx *ctx, + const struct qstr *iname, + struct dx_hash_info *hinfo) +{ + struct ext4_str tmp, tmp2; + int ret = 0; + + if (!ctx || !ctx->has_valid_key || + ((iname->name[0] == '.') && + ((iname->len == 1) || + ((iname->name[1] == '.') && (iname->len == 2))))) { + ext4fs_dirhash(iname->name, iname->len, hinfo); + return 0; + } + + /* First encrypt the plaintext name */ + ret = ext4_fname_crypto_alloc_buffer(ctx, iname->len, &tmp); + if (ret < 0) + return ret; + + ret = ext4_fname_encrypt(ctx, iname, &tmp); + if (ret < 0) + goto out; + + tmp2.len = (4 * ((EXT4_FNAME_CRYPTO_DIGEST_SIZE + 2) / 3)) + 1; + tmp2.name = kmalloc(tmp2.len + 1, GFP_KERNEL); + if (tmp2.name == NULL) { + ret = -ENOMEM; + goto out; + } + + ret = ext4_fname_hash(ctx, &tmp, &tmp2); + if (ret > 0) + ext4fs_dirhash(tmp2.name, tmp2.len, hinfo); + ext4_fname_crypto_free_buffer(&tmp2); +out: + ext4_fname_crypto_free_buffer(&tmp); + return ret; +} + +/** + * ext4_fname_disk_to_htree() - converts a filename from disk space to htree-access string + */ +int ext4_fname_disk_to_hash(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_dir_entry_2 *de, + struct dx_hash_info *hinfo) +{ + struct ext4_str iname = {.name = (unsigned char *) de->name, + .len = de->name_len}; + struct ext4_str tmp; + int ret; + + if (!ctx || + ((iname.name[0] == '.') && + ((iname.len == 1) || + ((iname.name[1] == '.') && (iname.len == 2))))) { + ext4fs_dirhash(iname.name, iname.len, hinfo); + return 0; + } + + tmp.len = (4 * ((EXT4_FNAME_CRYPTO_DIGEST_SIZE + 2) / 3)) + 1; + tmp.name = kmalloc(tmp.len + 1, GFP_KERNEL); + if (tmp.name == NULL) + return -ENOMEM; + + ret = ext4_fname_hash(ctx, &iname, &tmp); + if (ret > 0) + ext4fs_dirhash(tmp.name, tmp.len, hinfo); + ext4_fname_crypto_free_buffer(&tmp); + return ret; +} diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c new file mode 100644 index 0000000..c8392af --- /dev/null +++ b/fs/ext4/crypto_key.c @@ -0,0 +1,165 @@ +/* + * linux/fs/ext4/crypto_key.c + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption key functions for ext4 + * + * 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 "ext4.h" +#include "xattr.h" + +static void derive_crypt_complete(struct crypto_async_request *req, int rc) +{ + struct ext4_completion_result *ecr = req->data; + + if (rc == -EINPROGRESS) + return; + + ecr->res = rc; + complete(&ecr->completion); +} + +/** + * ext4_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 ext4_derive_key_aes(char deriving_key[EXT4_AES_128_ECB_KEY_SIZE], + char source_key[EXT4_AES_256_XTS_KEY_SIZE], + char derived_key[EXT4_AES_256_XTS_KEY_SIZE]) +{ + int res = 0; + struct ablkcipher_request *req = NULL; + DECLARE_EXT4_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, + EXT4_AES_128_ECB_KEY_SIZE); + if (res < 0) + goto out; + sg_init_one(&src_sg, source_key, EXT4_AES_256_XTS_KEY_SIZE); + sg_init_one(&dst_sg, derived_key, EXT4_AES_256_XTS_KEY_SIZE); + ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, + EXT4_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; +} + +/** + * ext4_generate_encryption_key() - generates an encryption key + * @inode: The inode to generate the encryption key for. + */ +int ext4_generate_encryption_key(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_encryption_key *crypt_key = &ei->i_encryption_key; + char full_key_descriptor[EXT4_KEY_DESC_PREFIX_SIZE + + (EXT4_KEY_DESCRIPTOR_SIZE * 2) + 1]; + struct key *keyring_key = NULL; + struct ext4_encryption_key *master_key; + struct ext4_encryption_context ctx; + struct user_key_payload *ukp; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + &ctx, sizeof(ctx)); + + if (res != sizeof(ctx)) { + if (res > 0) + res = -EINVAL; + goto out; + } + res = 0; + + if (S_ISREG(inode->i_mode)) + crypt_key->mode = ctx.contents_encryption_mode; + else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) + crypt_key->mode = ctx.filenames_encryption_mode; + else { + printk(KERN_ERR "ext4 crypto: Unsupported inode type.\n"); + BUG(); + } + crypt_key->size = ext4_encryption_key_size(crypt_key->mode); + BUG_ON(!crypt_key->size); + if (DUMMY_ENCRYPTION_ENABLED(sbi)) { + memset(crypt_key->raw, 0x42, EXT4_AES_256_XTS_KEY_SIZE); + goto out; + } + memcpy(full_key_descriptor, EXT4_KEY_DESC_PREFIX, + EXT4_KEY_DESC_PREFIX_SIZE); + sprintf(full_key_descriptor + EXT4_KEY_DESC_PREFIX_SIZE, + "%*phN", EXT4_KEY_DESCRIPTOR_SIZE, + ctx.master_key_descriptor); + full_key_descriptor[EXT4_KEY_DESC_PREFIX_SIZE + + (2 * EXT4_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; + } + BUG_ON(keyring_key->type != &key_type_logon); + ukp = ((struct user_key_payload *)keyring_key->payload.data); + if (ukp->datalen != sizeof(struct ext4_encryption_key)) { + res = -EINVAL; + goto out; + } + master_key = (struct ext4_encryption_key *)ukp->data; + BUILD_BUG_ON(EXT4_AES_128_ECB_KEY_SIZE != + EXT4_KEY_DERIVATION_NONCE_SIZE); + BUG_ON(master_key->size != EXT4_AES_256_XTS_KEY_SIZE); + res = ext4_derive_key_aes(ctx.nonce, master_key->raw, crypt_key->raw); +out: + if (keyring_key) + key_put(keyring_key); + if (res < 0) + crypt_key->mode = EXT4_ENCRYPTION_MODE_INVALID; + return res; +} + +int ext4_has_encryption_key(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_encryption_key *crypt_key = &ei->i_encryption_key; + + return (crypt_key->mode != EXT4_ENCRYPTION_MODE_INVALID); +} diff --git a/fs/ext4/crypto_policy.c b/fs/ext4/crypto_policy.c new file mode 100644 index 0000000..30eaf9e --- /dev/null +++ b/fs/ext4/crypto_policy.c @@ -0,0 +1,194 @@ +/* + * linux/fs/ext4/crypto_policy.c + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption policy functions for ext4 + * + * Written by Michael Halcrow, 2015. + */ + +#include <linux/random.h> +#include <linux/string.h> +#include <linux/types.h> + +#include "ext4.h" +#include "xattr.h" + +static int ext4_inode_has_encryption_context(struct inode *inode) +{ + int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, NULL, 0); + return (res > 0); +} + +/* + * check whether the policy is consistent with the encryption context + * for the inode + */ +static int ext4_is_encryption_context_consistent_with_policy( + struct inode *inode, const struct ext4_encryption_policy *policy) +{ + struct ext4_encryption_context ctx; + int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, + sizeof(ctx)); + if (res != sizeof(ctx)) + return 0; + return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor, + EXT4_KEY_DESCRIPTOR_SIZE) == 0 && + (ctx.contents_encryption_mode == + policy->contents_encryption_mode) && + (ctx.filenames_encryption_mode == + policy->filenames_encryption_mode)); +} + +static int ext4_create_encryption_context_from_policy( + struct inode *inode, const struct ext4_encryption_policy *policy) +{ + struct ext4_encryption_context ctx; + int res = 0; + + ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1; + memcpy(ctx.master_key_descriptor, policy->master_key_descriptor, + EXT4_KEY_DESCRIPTOR_SIZE); + if (!ext4_valid_contents_enc_mode(policy->contents_encryption_mode)) { + printk(KERN_WARNING + "%s: Invalid contents encryption mode %d\n", __func__, + policy->contents_encryption_mode); + res = -EINVAL; + goto out; + } + if (!ext4_valid_filenames_enc_mode(policy->filenames_encryption_mode)) { + printk(KERN_WARNING + "%s: Invalid filenames encryption mode %d\n", __func__, + policy->filenames_encryption_mode); + res = -EINVAL; + goto out; + } + ctx.contents_encryption_mode = policy->contents_encryption_mode; + ctx.filenames_encryption_mode = policy->filenames_encryption_mode; + BUILD_BUG_ON(sizeof(ctx.nonce) != EXT4_KEY_DERIVATION_NONCE_SIZE); + get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE); + + res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, + sizeof(ctx), 0); +out: + if (!res) + ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); + return res; +} + +int ext4_process_policy(const struct ext4_encryption_policy *policy, + struct inode *inode) +{ + if (policy->version != 0) + return -EINVAL; + + if (!ext4_inode_has_encryption_context(inode)) { + if (!ext4_empty_dir(inode)) + return -ENOTEMPTY; + return ext4_create_encryption_context_from_policy(inode, + policy); + } + + if (ext4_is_encryption_context_consistent_with_policy(inode, policy)) + return 0; + + printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n", + __func__); + return -EINVAL; +} + +int ext4_get_policy(struct inode *inode, struct ext4_encryption_policy *policy) +{ + struct ext4_encryption_context ctx; + + int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + &ctx, sizeof(ctx)); + if (res != sizeof(ctx)) + return -ENOENT; + if (ctx.format != EXT4_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; + memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor, + EXT4_KEY_DESCRIPTOR_SIZE); + return 0; +} + +int ext4_is_child_context_consistent_with_parent(struct inode *parent, + struct inode *child) +{ + struct ext4_encryption_context parent_ctx, child_ctx; + 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 (!ext4_encrypted_inode(parent)) + return 1; + res = ext4_xattr_get(parent, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + &parent_ctx, sizeof(parent_ctx)); + if (res != sizeof(parent_ctx)) + return 0; + /* if the child directory is not encrypted, this is always a problem */ + if (!ext4_encrypted_inode(child)) + return 0; + res = ext4_xattr_get(child, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + &child_ctx, sizeof(child_ctx)); + if (res != sizeof(child_ctx)) + return 0; + return (memcmp(parent_ctx.master_key_descriptor, + child_ctx.master_key_descriptor, + EXT4_KEY_DESCRIPTOR_SIZE) == 0 && + (parent_ctx.contents_encryption_mode == + child_ctx.contents_encryption_mode) && + (parent_ctx.filenames_encryption_mode == + child_ctx.filenames_encryption_mode)); +} + +/** + * ext4_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 ext4_inherit_context(struct inode *parent, struct inode *child) +{ + struct ext4_encryption_context ctx; + int res = ext4_xattr_get(parent, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + &ctx, sizeof(ctx)); + + if (res != sizeof(ctx)) { + if (DUMMY_ENCRYPTION_ENABLED(EXT4_SB(parent->i_sb))) { + ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1; + ctx.contents_encryption_mode = + EXT4_ENCRYPTION_MODE_AES_256_XTS; + ctx.filenames_encryption_mode = + EXT4_ENCRYPTION_MODE_AES_256_CTS; + memset(ctx.master_key_descriptor, 0x42, + EXT4_KEY_DESCRIPTOR_SIZE); + res = 0; + } else { + goto out; + } + } + get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE); + res = ext4_xattr_set(child, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, + sizeof(ctx), 0); +out: + if (!res) + ext4_set_inode_flag(child, EXT4_INODE_ENCRYPT); + return res; +} diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index c24143e..61db51a5 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -22,10 +22,8 @@ */ #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/buffer_head.h> #include <linux/slab.h> -#include <linux/rbtree.h> #include "ext4.h" #include "xattr.h" @@ -110,7 +108,10 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) int err; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; + struct buffer_head *bh = NULL; int dir_has_error = 0; + struct ext4_fname_crypto_ctx *enc_ctx = NULL; + struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}; if (is_dx_dir(inode)) { err = ext4_dx_readdir(file, ctx); @@ -127,17 +128,28 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) if (ext4_has_inline_data(inode)) { int has_inline_data = 1; - int ret = ext4_read_inline_dir(file, ctx, + err = ext4_read_inline_dir(file, ctx, &has_inline_data); if (has_inline_data) - return ret; + return err; + } + + enc_ctx = ext4_get_fname_crypto_ctx(inode, EXT4_NAME_LEN); + if (IS_ERR(enc_ctx)) + return PTR_ERR(enc_ctx); + if (enc_ctx) { + err = ext4_fname_crypto_alloc_buffer(enc_ctx, EXT4_NAME_LEN, + &fname_crypto_str); + if (err < 0) { + ext4_put_fname_crypto_ctx(&enc_ctx); + return err; + } } offset = ctx->pos & (sb->s_blocksize - 1); while (ctx->pos < inode->i_size) { struct ext4_map_blocks map; - struct buffer_head *bh = NULL; map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb); map.m_len = 1; @@ -180,6 +192,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) (unsigned long long)ctx->pos); ctx->pos += sb->s_blocksize - offset; brelse(bh); + bh = NULL; continue; } set_buffer_verified(bh); @@ -226,25 +239,44 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); if (le32_to_cpu(de->inode)) { - if (!dir_emit(ctx, de->name, - de->name_len, - le32_to_cpu(de->inode), - get_dtype(sb, de->file_type))) { - brelse(bh); - return 0; + if (enc_ctx == NULL) { + /* Directory is not encrypted */ + if (!dir_emit(ctx, de->name, + de->name_len, + le32_to_cpu(de->inode), + get_dtype(sb, de->file_type))) + goto done; + } else { + /* Directory is encrypted */ + err = ext4_fname_disk_to_usr(enc_ctx, + de, &fname_crypto_str); + if (err < 0) + goto errout; + if (!dir_emit(ctx, + fname_crypto_str.name, err, + le32_to_cpu(de->inode), + get_dtype(sb, de->file_type))) + goto done; } } ctx->pos += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); } - offset = 0; + if ((ctx->pos < inode->i_size) && !dir_relax(inode)) + goto done; brelse(bh); - if (ctx->pos < inode->i_size) { - if (!dir_relax(inode)) - return 0; - } + bh = NULL; + offset = 0; } - return 0; +done: + err = 0; +errout: +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ext4_put_fname_crypto_ctx(&enc_ctx); + ext4_fname_crypto_free_buffer(&fname_crypto_str); +#endif + brelse(bh); + return err; } static inline int is_32bit_api(void) @@ -384,10 +416,15 @@ void ext4_htree_free_dir_info(struct dir_private_info *p) /* * Given a directory entry, enter it into the fname rb tree. + * + * When filename encryption is enabled, the dirent will hold the + * encrypted filename, while the htree will hold decrypted filename. + * The decrypted filename is passed in via ent_name. parameter. */ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, __u32 minor_hash, - struct ext4_dir_entry_2 *dirent) + struct ext4_dir_entry_2 *dirent, + struct ext4_str *ent_name) { struct rb_node **p, *parent = NULL; struct fname *fname, *new_fn; @@ -398,17 +435,17 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, p = &info->root.rb_node; /* Create and allocate the fname structure */ - len = sizeof(struct fname) + dirent->name_len + 1; + len = sizeof(struct fname) + ent_name->len + 1; new_fn = kzalloc(len, GFP_KERNEL); if (!new_fn) return -ENOMEM; new_fn->hash = hash; new_fn->minor_hash = minor_hash; new_fn->inode = le32_to_cpu(dirent->inode); - new_fn->name_len = dirent->name_len; + new_fn->name_len = ent_name->len; new_fn->file_type = dirent->file_type; - memcpy(new_fn->name, dirent->name, dirent->name_len); - new_fn->name[dirent->name_len] = 0; + memcpy(new_fn->name, ent_name->name, ent_name->len); + new_fn->name[ent_name->len] = 0; while (*p) { parent = *p; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index c8eb32e..ef267ad 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -422,7 +422,7 @@ enum { EXT4_INODE_DIRTY = 8, EXT4_INODE_COMPRBLK = 9, /* One or more compressed clusters */ EXT4_INODE_NOCOMPR = 10, /* Don't compress */ - EXT4_INODE_ENCRYPT = 11, /* Compression error */ + EXT4_INODE_ENCRYPT = 11, /* Encrypted file */ /* End compression flags --- maybe not all used */ EXT4_INODE_INDEX = 12, /* hash-indexed directory */ EXT4_INODE_IMAGIC = 13, /* AFS directory */ @@ -582,6 +582,15 @@ enum { #define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010 #define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020 +/* Encryption algorithms */ +#define EXT4_ENCRYPTION_MODE_INVALID 0 +#define EXT4_ENCRYPTION_MODE_AES_256_XTS 1 +#define EXT4_ENCRYPTION_MODE_AES_256_GCM 2 +#define EXT4_ENCRYPTION_MODE_AES_256_CBC 3 +#define EXT4_ENCRYPTION_MODE_AES_256_CTS 4 + +#include "ext4_crypto.h" + /* * ioctl commands */ @@ -603,6 +612,9 @@ enum { #define EXT4_IOC_RESIZE_FS _IOW('f', 16, __u64) #define EXT4_IOC_SWAP_BOOT _IO('f', 17) #define EXT4_IOC_PRECACHE_EXTENTS _IO('f', 18) +#define EXT4_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct ext4_encryption_policy) +#define EXT4_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16]) +#define EXT4_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct ext4_encryption_policy) #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* @@ -939,6 +951,11 @@ struct ext4_inode_info { /* Precomputed uuid+inum+igen checksum for seeding inode checksums */ __u32 i_csum_seed; + +#ifdef CONFIG_EXT4_FS_ENCRYPTION + /* Encryption params */ + struct ext4_encryption_key i_encryption_key; +#endif }; /* @@ -1142,7 +1159,8 @@ struct ext4_super_block { __le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/ __u8 s_log_groups_per_flex; /* FLEX_BG group size */ __u8 s_checksum_type; /* metadata checksum algorithm used */ - __le16 s_reserved_pad; + __u8 s_encryption_level; /* versioning level for encryption */ + __u8 s_reserved_pad; /* Padding to next 32bits */ __le64 s_kbytes_written; /* nr of lifetime kilobytes written */ __le32 s_snapshot_inum; /* Inode number of active snapshot */ __le32 s_snapshot_id; /* sequential ID of active snapshot */ @@ -1169,7 +1187,9 @@ struct ext4_super_block { __le32 s_overhead_clusters; /* overhead blocks/clusters in fs */ __le32 s_backup_bgs[2]; /* groups with sparse_super2 SBs */ __u8 s_encrypt_algos[4]; /* Encryption algorithms in use */ - __le32 s_reserved[105]; /* Padding to the end of the block */ + __u8 s_encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ + __le32 s_lpf_ino; /* Location of the lost+found inode */ + __le32 s_reserved[100]; /* Padding to the end of the block */ __le32 s_checksum; /* crc32c(superblock) */ }; @@ -1180,8 +1200,16 @@ struct ext4_super_block { /* * run-time mount flags */ -#define EXT4_MF_MNTDIR_SAMPLED 0x0001 -#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */ +#define EXT4_MF_MNTDIR_SAMPLED 0x0001 +#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */ +#define EXT4_MF_TEST_DUMMY_ENCRYPTION 0x0004 + +#ifdef CONFIG_EXT4_FS_ENCRYPTION +#define DUMMY_ENCRYPTION_ENABLED(sbi) (unlikely((sbi)->s_mount_flags & \ + EXT4_MF_TEST_DUMMY_ENCRYPTION)) +#else +#define DUMMY_ENCRYPTION_ENABLED(sbi) (0) +#endif /* Number of quota types we support */ #define EXT4_MAXQUOTAS 2 @@ -1351,6 +1379,12 @@ struct ext4_sb_info { struct ratelimit_state s_err_ratelimit_state; struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; + +#ifdef CONFIG_EXT4_FS_ENCRYPTION + /* Encryption */ + uint32_t s_file_encryption_mode; + uint32_t s_dir_encryption_mode; +#endif }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -1466,6 +1500,18 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_SB(sb) (sb) #endif +/* + * Returns true if the inode is inode is encrypted + */ +static inline int ext4_encrypted_inode(struct inode *inode) +{ +#ifdef CONFIG_EXT4_FS_ENCRYPTION + return ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT); +#else + return 0; +#endif +} + #define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime /* @@ -1575,8 +1621,9 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) EXT4_FEATURE_INCOMPAT_EXTENTS| \ EXT4_FEATURE_INCOMPAT_64BIT| \ EXT4_FEATURE_INCOMPAT_FLEX_BG| \ - EXT4_FEATURE_INCOMPAT_MMP | \ - EXT4_FEATURE_INCOMPAT_INLINE_DATA) + EXT4_FEATURE_INCOMPAT_MMP | \ + EXT4_FEATURE_INCOMPAT_INLINE_DATA | \ + EXT4_FEATURE_INCOMPAT_ENCRYPT) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \ @@ -2001,6 +2048,99 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); +/* crypto_policy.c */ +int ext4_is_child_context_consistent_with_parent(struct inode *parent, + struct inode *child); +int ext4_inherit_context(struct inode *parent, struct inode *child); +void ext4_to_hex(char *dst, char *src, size_t src_size); +int ext4_process_policy(const struct ext4_encryption_policy *policy, + struct inode *inode); +int ext4_get_policy(struct inode *inode, + struct ext4_encryption_policy *policy); + +/* crypto.c */ +bool ext4_valid_contents_enc_mode(uint32_t mode); +uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size); +extern struct workqueue_struct *ext4_read_workqueue; +struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode); +void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx); +void ext4_restore_control_page(struct page *data_page); +struct page *ext4_encrypt(struct inode *inode, + struct page *plaintext_page); +int ext4_decrypt(struct ext4_crypto_ctx *ctx, struct page *page); +int ext4_decrypt_one(struct inode *inode, struct page *page); +int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex); + +#ifdef CONFIG_EXT4_FS_ENCRYPTION +int ext4_init_crypto(void); +void ext4_exit_crypto(void); +static inline int ext4_sb_has_crypto(struct super_block *sb) +{ + return EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT); +} +#else +static inline int ext4_init_crypto(void) { return 0; } +static inline void ext4_exit_crypto(void) { } +static inline int ext4_sb_has_crypto(struct super_block *sb) +{ + return 0; +} +#endif + +/* crypto_fname.c */ +bool ext4_valid_filenames_enc_mode(uint32_t mode); +u32 ext4_fname_crypto_round_up(u32 size, u32 blksize); +int ext4_fname_crypto_alloc_buffer(struct ext4_fname_crypto_ctx *ctx, + u32 ilen, struct ext4_str *crypto_str); +int _ext4_fname_disk_to_usr(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_str *iname, + struct ext4_str *oname); +int ext4_fname_disk_to_usr(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_dir_entry_2 *de, + struct ext4_str *oname); +int ext4_fname_usr_to_disk(struct ext4_fname_crypto_ctx *ctx, + const struct qstr *iname, + struct ext4_str *oname); +int ext4_fname_usr_to_hash(struct ext4_fname_crypto_ctx *ctx, + const struct qstr *iname, + struct dx_hash_info *hinfo); +int ext4_fname_disk_to_hash(struct ext4_fname_crypto_ctx *ctx, + const struct ext4_dir_entry_2 *de, + struct dx_hash_info *hinfo); +int ext4_fname_crypto_namelen_on_disk(struct ext4_fname_crypto_ctx *ctx, + u32 namelen); + +#ifdef CONFIG_EXT4_FS_ENCRYPTION +void ext4_put_fname_crypto_ctx(struct ext4_fname_crypto_ctx **ctx); +struct ext4_fname_crypto_ctx *ext4_get_fname_crypto_ctx(struct inode *inode, + u32 max_len); +void ext4_fname_crypto_free_buffer(struct ext4_str *crypto_str); +#else +static inline +void ext4_put_fname_crypto_ctx(struct ext4_fname_crypto_ctx **ctx) { } +static inline +struct ext4_fname_crypto_ctx *ext4_get_fname_crypto_ctx(struct inode *inode, + u32 max_len) +{ + return NULL; +} +static inline void ext4_fname_crypto_free_buffer(struct ext4_str *p) { } +#endif + + +/* crypto_key.c */ +int ext4_generate_encryption_key(struct inode *inode); + +#ifdef CONFIG_EXT4_FS_ENCRYPTION +int ext4_has_encryption_key(struct inode *inode); +#else +static inline int ext4_has_encryption_key(struct inode *inode) +{ + return 0; +} +#endif + + /* dir.c */ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, struct file *, @@ -2011,17 +2151,20 @@ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \ (de), (bh), (buf), (size), (offset))) extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, - __u32 minor_hash, - struct ext4_dir_entry_2 *dirent); + __u32 minor_hash, + struct ext4_dir_entry_2 *dirent, + struct ext4_str *ent_name); extern void ext4_htree_free_dir_info(struct dir_private_info *p); extern int ext4_find_dest_de(struct inode *dir, struct inode *inode, struct buffer_head *bh, void *buf, int buf_size, const char *name, int namelen, struct ext4_dir_entry_2 **dest_de); -void ext4_insert_dentry(struct inode *inode, +int ext4_insert_dentry(struct inode *dir, + struct inode *inode, struct ext4_dir_entry_2 *de, int buf_size, + const struct qstr *iname, const char *name, int namelen); static inline void ext4_update_dx_flag(struct inode *inode) { @@ -2099,6 +2242,7 @@ extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); /* inode.c */ +int ext4_inode_is_fast_symlink(struct inode *inode); struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int); struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int); int ext4_get_block_write(struct inode *inode, sector_t iblock, @@ -2189,6 +2333,7 @@ extern int ext4_generic_delete_entry(handle_t *handle, void *entry_buf, int buf_size, int csum_size); +extern int ext4_empty_dir(struct inode *inode); /* resize.c */ extern int ext4_group_add(struct super_block *sb, @@ -2698,6 +2843,10 @@ static inline void ext4_set_de_type(struct super_block *sb, de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; } +/* readpages.c */ +extern int ext4_mpage_readpages(struct address_space *mapping, + struct list_head *pages, struct page *page, + unsigned nr_pages); /* symlink.c */ extern const struct inode_operations ext4_symlink_inode_operations; diff --git a/fs/ext4/ext4_crypto.h b/fs/ext4/ext4_crypto.h new file mode 100644 index 0000000..c2ba35a --- /dev/null +++ b/fs/ext4/ext4_crypto.h @@ -0,0 +1,147 @@ +/* + * linux/fs/ext4/ext4_crypto.h + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption header content for ext4 + * + * Written by Michael Halcrow, 2015. + */ + +#ifndef _EXT4_CRYPTO_H +#define _EXT4_CRYPTO_H + +#include <linux/fs.h> + +#define EXT4_KEY_DESCRIPTOR_SIZE 8 + +/* Policy provided via an ioctl on the topmost directory */ +struct ext4_encryption_policy { + char version; + char contents_encryption_mode; + char filenames_encryption_mode; + char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE]; +} __attribute__((__packed__)); + +#define EXT4_ENCRYPTION_CONTEXT_FORMAT_V1 1 +#define EXT4_KEY_DERIVATION_NONCE_SIZE 16 + +/** + * 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: Reserved + * 8 bytes: Master Key descriptor + * 16 bytes: Encryption Key derivation nonce + */ +struct ext4_encryption_context { + char format; + char contents_encryption_mode; + char filenames_encryption_mode; + char reserved; + char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE]; + char nonce[EXT4_KEY_DERIVATION_NONCE_SIZE]; +} __attribute__((__packed__)); + +/* Encryption parameters */ +#define EXT4_XTS_TWEAK_SIZE 16 +#define EXT4_AES_128_ECB_KEY_SIZE 16 +#define EXT4_AES_256_GCM_KEY_SIZE 32 +#define EXT4_AES_256_CBC_KEY_SIZE 32 +#define EXT4_AES_256_CTS_KEY_SIZE 32 +#define EXT4_AES_256_XTS_KEY_SIZE 64 +#define EXT4_MAX_KEY_SIZE 64 + +#define EXT4_KEY_DESC_PREFIX "ext4:" +#define EXT4_KEY_DESC_PREFIX_SIZE 5 + +struct ext4_encryption_key { + uint32_t mode; + char raw[EXT4_MAX_KEY_SIZE]; + uint32_t size; +}; + +#define EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001 +#define EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL 0x00000002 + +struct ext4_crypto_ctx { + struct crypto_tfm *tfm; /* Crypto API context */ + struct page *bounce_page; /* Ciphertext page on write path */ + struct page *control_page; /* Original page on write path */ + struct bio *bio; /* The bio for this context */ + struct work_struct work; /* Work queue for read complete path */ + struct list_head free_list; /* Free list */ + int flags; /* Flags */ + int mode; /* Encryption mode for tfm */ +}; + +struct ext4_completion_result { + struct completion completion; + int res; +}; + +#define DECLARE_EXT4_COMPLETION_RESULT(ecr) \ + struct ext4_completion_result ecr = { \ + COMPLETION_INITIALIZER((ecr).completion), 0 } + +static inline int ext4_encryption_key_size(int mode) +{ + switch (mode) { + case EXT4_ENCRYPTION_MODE_AES_256_XTS: + return EXT4_AES_256_XTS_KEY_SIZE; + case EXT4_ENCRYPTION_MODE_AES_256_GCM: + return EXT4_AES_256_GCM_KEY_SIZE; + case EXT4_ENCRYPTION_MODE_AES_256_CBC: + return EXT4_AES_256_CBC_KEY_SIZE; + case EXT4_ENCRYPTION_MODE_AES_256_CTS: + return EXT4_AES_256_CTS_KEY_SIZE; + default: + BUG(); + } + return 0; +} + +#define EXT4_FNAME_NUM_SCATTER_ENTRIES 4 +#define EXT4_CRYPTO_BLOCK_SIZE 16 +#define EXT4_FNAME_CRYPTO_DIGEST_SIZE 32 + +struct ext4_str { + unsigned char *name; + u32 len; +}; + +struct ext4_fname_crypto_ctx { + u32 lim; + char tmp_buf[EXT4_CRYPTO_BLOCK_SIZE]; + struct crypto_ablkcipher *ctfm; + struct crypto_hash *htfm; + struct page *workpage; + struct ext4_encryption_key key; + unsigned has_valid_key : 1; + unsigned ctfm_key_is_ready : 1; +}; + +/** + * For encrypted symlinks, the ciphertext length is stored at the beginning + * of the string in little-endian format. + */ +struct ext4_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) +{ + if (l < EXT4_CRYPTO_BLOCK_SIZE) + l = EXT4_CRYPTO_BLOCK_SIZE; + return (l + sizeof(struct ext4_encrypted_symlink_data) - 1); +} + +#endif /* _EXT4_CRYPTO_H */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index bed4308..973816b 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1717,12 +1717,6 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, { unsigned short ext1_ee_len, ext2_ee_len; - /* - * Make sure that both extents are initialized. We don't merge - * unwritten extents so that we can be sure that end_io code has - * the extent that was written properly split out and conversion to - * initialized is trivial. - */ if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2)) return 0; @@ -3128,6 +3122,9 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) ee_len = ext4_ext_get_actual_len(ex); ee_pblock = ext4_ext_pblock(ex); + if (ext4_encrypted_inode(inode)) + return ext4_encrypted_zeroout(inode, ex); + ret = sb_issue_zeroout(inode->i_sb, ee_pblock, ee_len, GFP_NOFS); if (ret > 0) ret = 0; @@ -4535,19 +4532,7 @@ got_allocated_blocks: */ reserved_clusters = get_reserved_cluster_alloc(inode, map->m_lblk, allocated); - if (map_from_cluster) { - if (reserved_clusters) { - /* - * We have clusters reserved for this range. - * But since we are not doing actual allocation - * and are simply using blocks from previously - * allocated cluster, we should release the - * reservation and not claim quota. - */ - ext4_da_update_reserve_space(inode, - reserved_clusters, 0); - } - } else { + if (!map_from_cluster) { BUG_ON(allocated_clusters < reserved_clusters); if (reserved_clusters < allocated_clusters) { struct ext4_inode_info *ei = EXT4_I(inode); @@ -4803,12 +4788,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, else max_blocks -= lblk; - flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT | - EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | - EXT4_EX_NOCACHE; - if (mode & FALLOC_FL_KEEP_SIZE) - flags |= EXT4_GET_BLOCKS_KEEP_SIZE; - mutex_lock(&inode->i_mutex); /* @@ -4825,15 +4804,28 @@ static long ext4_zero_range(struct file *file, loff_t offset, ret = inode_newsize_ok(inode, new_size); if (ret) goto out_mutex; - /* - * If we have a partial block after EOF we have to allocate - * the entire block. - */ - if (partial_end) - max_blocks += 1; } + flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; + if (mode & FALLOC_FL_KEEP_SIZE) + flags |= EXT4_GET_BLOCKS_KEEP_SIZE; + + /* Preallocate the range including the unaligned edges */ + if (partial_begin || partial_end) { + ret = ext4_alloc_file_blocks(file, + round_down(offset, 1 << blkbits) >> blkbits, + (round_up((offset + len), 1 << blkbits) - + round_down(offset, 1 << blkbits)) >> blkbits, + new_size, flags, mode); + if (ret) + goto out_mutex; + + } + + /* Zero range excluding the unaligned edges */ if (max_blocks > 0) { + flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | + EXT4_EX_NOCACHE); /* Now release the pages and zero block aligned part of pages*/ truncate_pagecache_range(inode, start, end - 1); @@ -4847,19 +4839,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, flags, mode); if (ret) goto out_dio; - /* - * Remove entire range from the extent status tree. - * - * ext4_es_remove_extent(inode, lblk, max_blocks) is - * NOT sufficient. I'm not sure why this is the case, - * but let's be conservative and remove the extent - * status tree for the entire inode. There should be - * no outstanding delalloc extents thanks to the - * filemap_write_and_wait_range() call above. - */ - ret = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); - if (ret) - goto out_dio; } if (!partial_begin && !partial_end) goto out_dio; @@ -4922,6 +4901,20 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) ext4_lblk_t lblk; unsigned int blkbits = inode->i_blkbits; + /* + * Encrypted inodes can't handle collapse range or insert + * range since we would need to re-encrypt blocks with a + * different IV or XTS tweak (which are based on the logical + * block number). + * + * XXX It's not clear why zero range isn't working, but we'll + * leave it disabled for encrypted inodes for now. This is a + * bug we should fix.... + */ + if (ext4_encrypted_inode(inode) && + (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))) + return -EOPNOTSUPP; + /* Return error if mode is not supported */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE)) diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index e04d457..d33d5a6 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -9,12 +9,10 @@ * * Ext4 extents status tree core functions. */ -#include <linux/rbtree.h> #include <linux/list_sort.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include "ext4.h" -#include "extents_status.h" #include <trace/events/ext4.h> diff --git a/fs/ext4/file.c b/fs/ext4/file.c index e576d68..0613c25 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -20,7 +20,6 @@ #include <linux/time.h> #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/mount.h> #include <linux/path.h> #include <linux/quotaops.h> @@ -221,6 +220,13 @@ static const struct vm_operations_struct ext4_file_vm_ops = { static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) { + struct inode *inode = file->f_mapping->host; + + if (ext4_encrypted_inode(inode)) { + int err = ext4_generate_encryption_key(inode); + if (err) + return 0; + } file_accessed(file); if (IS_DAX(file_inode(file))) { vma->vm_ops = &ext4_dax_vm_ops; @@ -238,6 +244,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp) struct vfsmount *mnt = filp->f_path.mnt; struct path path; char buf[64], *cp; + int ret; if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) && !(sb->s_flags & MS_RDONLY))) { @@ -276,11 +283,17 @@ static int ext4_file_open(struct inode * inode, struct file * filp) * writing and the journal is present */ if (filp->f_mode & FMODE_WRITE) { - int ret = ext4_inode_attach_jinode(inode); + ret = ext4_inode_attach_jinode(inode); if (ret < 0) return ret; } - return dquot_file_open(inode, filp); + ret = dquot_file_open(inode, filp); + if (!ret && ext4_encrypted_inode(inode)) { + ret = ext4_generate_encryption_key(inode); + if (ret) + ret = -EACCES; + } + return ret; } /* diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index a8bc47f..e9d632e 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -26,7 +26,6 @@ #include <linux/fs.h> #include <linux/sched.h> #include <linux/writeback.h> -#include <linux/jbd2.h> #include <linux/blkdev.h> #include "ext4.h" diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index 3d586f0..e026aa9 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -10,7 +10,6 @@ */ #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/cryptohash.h> #include "ext4.h" diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index ac644c3..2cf18a2 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -14,7 +14,6 @@ #include <linux/time.h> #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/quotaops.h> @@ -997,6 +996,12 @@ got: ei->i_block_group = group; ei->i_last_alloc_group = ~0; + /* If the directory encrypted, then we should encrypt the inode. */ + if ((S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) && + (ext4_encrypted_inode(dir) || + DUMMY_ENCRYPTION_ENABLED(sbi))) + ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); + ext4_set_inode_flags(inode); if (IS_DIRSYNC(inode)) ext4_handle_sync(handle); @@ -1029,11 +1034,28 @@ got: ext4_set_inode_state(inode, EXT4_STATE_NEW); ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize; - +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if ((sbi->s_file_encryption_mode == EXT4_ENCRYPTION_MODE_INVALID) && + (sbi->s_dir_encryption_mode == EXT4_ENCRYPTION_MODE_INVALID)) { + ei->i_inline_off = 0; + if (EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_INLINE_DATA)) + ext4_set_inode_state(inode, + EXT4_STATE_MAY_INLINE_DATA); + } else { + /* Inline data and encryption are incompatible + * We turn off inline data since encryption is enabled */ + ei->i_inline_off = 1; + if (EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_INLINE_DATA)) + ext4_clear_inode_state(inode, + EXT4_STATE_MAY_INLINE_DATA); + } +#else ei->i_inline_off = 0; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_INLINE_DATA)) ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); - +#endif ret = inode; err = dquot_alloc_inode(inode); if (err) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 4b143fe..feb2caf 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -11,11 +11,13 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ + +#include <linux/fiemap.h> + #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" #include "truncate.h" -#include <linux/fiemap.h> #define EXT4_XATTR_SYSTEM_DATA "data" #define EXT4_MIN_INLINE_DATA_SIZE ((sizeof(__le32) * EXT4_N_BLOCKS)) @@ -972,7 +974,7 @@ void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh, offset = 0; while ((void *)de < dlimit) { de_len = ext4_rec_len_from_disk(de->rec_len, inline_size); - trace_printk("de: off %u rlen %u name %*.s nlen %u ino %u\n", + trace_printk("de: off %u rlen %u name %.*s nlen %u ino %u\n", offset, de_len, de->name_len, de->name, de->name_len, le32_to_cpu(de->inode)); if (ext4_check_dir_entry(dir, NULL, de, bh, @@ -1014,7 +1016,8 @@ static int ext4_add_dirent_to_inline(handle_t *handle, err = ext4_journal_get_write_access(handle, iloc->bh); if (err) return err; - ext4_insert_dentry(inode, de, inline_size, name, namelen); + ext4_insert_dentry(dir, inode, de, inline_size, &dentry->d_name, + name, namelen); ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size); @@ -1327,6 +1330,7 @@ int htree_inlinedir_to_tree(struct file *dir_file, struct ext4_iloc iloc; void *dir_buf = NULL; struct ext4_dir_entry_2 fake; + struct ext4_str tmp_str; ret = ext4_get_inode_loc(inode, &iloc); if (ret) @@ -1398,8 +1402,10 @@ int htree_inlinedir_to_tree(struct file *dir_file, continue; if (de->inode == 0) continue; - err = ext4_htree_store_dirent(dir_file, - hinfo->hash, hinfo->minor_hash, de); + tmp_str.name = de->name; + tmp_str.len = de->name_len; + err = ext4_htree_store_dirent(dir_file, hinfo->hash, + hinfo->minor_hash, de, &tmp_str); if (err) { count = err; goto out; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b49cf6e..366476e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -20,7 +20,6 @@ #include <linux/fs.h> #include <linux/time.h> -#include <linux/jbd2.h> #include <linux/highuid.h> #include <linux/pagemap.h> #include <linux/quotaops.h> @@ -36,7 +35,6 @@ #include <linux/kernel.h> #include <linux/printk.h> #include <linux/slab.h> -#include <linux/ratelimit.h> #include <linux/bitops.h> #include "ext4_jbd2.h" @@ -140,7 +138,7 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, /* * Test whether an inode is a fast symlink. */ -static int ext4_inode_is_fast_symlink(struct inode *inode) +int ext4_inode_is_fast_symlink(struct inode *inode) { int ea_blocks = EXT4_I(inode)->i_file_acl ? EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; @@ -887,6 +885,95 @@ int do_journal_get_write_access(handle_t *handle, static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); + +#ifdef CONFIG_EXT4_FS_ENCRYPTION +static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, + get_block_t *get_block) +{ + unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned to = from + len; + struct inode *inode = page->mapping->host; + unsigned block_start, block_end; + sector_t block; + int err = 0; + unsigned blocksize = inode->i_sb->s_blocksize; + unsigned bbits; + struct buffer_head *bh, *head, *wait[2], **wait_bh = wait; + bool decrypt = false; + + BUG_ON(!PageLocked(page)); + BUG_ON(from > PAGE_CACHE_SIZE); + BUG_ON(to > PAGE_CACHE_SIZE); + BUG_ON(from > to); + + if (!page_has_buffers(page)) + create_empty_buffers(page, blocksize, 0); + head = page_buffers(page); + bbits = ilog2(blocksize); + block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); + + for (bh = head, block_start = 0; bh != head || !block_start; + block++, block_start = block_end, bh = bh->b_this_page) { + block_end = block_start + blocksize; + if (block_end <= from || block_start >= to) { + if (PageUptodate(page)) { + if (!buffer_uptodate(bh)) + set_buffer_uptodate(bh); + } + continue; + } + if (buffer_new(bh)) + clear_buffer_new(bh); + if (!buffer_mapped(bh)) { + WARN_ON(bh->b_size != blocksize); + err = get_block(inode, block, bh, 1); + if (err) + break; + if (buffer_new(bh)) { + unmap_underlying_metadata(bh->b_bdev, + bh->b_blocknr); + if (PageUptodate(page)) { + clear_buffer_new(bh); + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + continue; + } + if (block_end > to || block_start < from) + zero_user_segments(page, to, block_end, + block_start, from); + continue; + } + } + if (PageUptodate(page)) { + if (!buffer_uptodate(bh)) + set_buffer_uptodate(bh); + continue; + } + if (!buffer_uptodate(bh) && !buffer_delay(bh) && + !buffer_unwritten(bh) && + (block_start < from || block_end > to)) { + ll_rw_block(READ, 1, &bh); + *wait_bh++ = bh; + decrypt = ext4_encrypted_inode(inode) && + S_ISREG(inode->i_mode); + } + } + /* + * If we issued read requests, let them complete. + */ + while (wait_bh > wait) { + wait_on_buffer(*--wait_bh); + if (!buffer_uptodate(*wait_bh)) + err = -EIO; + } + if (unlikely(err)) + page_zero_new_buffers(page, from, to); + else if (decrypt) + err = ext4_decrypt_one(inode, page); + return err; +} +#endif + static int ext4_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -949,11 +1036,19 @@ retry_journal: /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (ext4_should_dioread_nolock(inode)) + ret = ext4_block_write_begin(page, pos, len, + ext4_get_block_write); + else + ret = ext4_block_write_begin(page, pos, len, + ext4_get_block); +#else if (ext4_should_dioread_nolock(inode)) ret = __block_write_begin(page, pos, len, ext4_get_block_write); else ret = __block_write_begin(page, pos, len, ext4_get_block); - +#endif if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, page_buffers(page), from, to, NULL, @@ -2575,7 +2670,12 @@ retry_journal: /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ret = ext4_block_write_begin(page, pos, len, + ext4_da_get_block_prep); +#else ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep); +#endif if (ret < 0) { unlock_page(page); ext4_journal_stop(handle); @@ -2821,7 +2921,7 @@ static int ext4_readpage(struct file *file, struct page *page) ret = ext4_readpage_inline(inode, page); if (ret == -EAGAIN) - return mpage_readpage(page, ext4_get_block); + return ext4_mpage_readpages(page->mapping, NULL, page, 1); return ret; } @@ -2836,7 +2936,7 @@ ext4_readpages(struct file *file, struct address_space *mapping, if (ext4_has_inline_data(inode)) return 0; - return mpage_readpages(mapping, pages, nr_pages, ext4_get_block); + return ext4_mpage_readpages(mapping, pages, NULL, nr_pages); } static void ext4_invalidatepage(struct page *page, unsigned int offset, @@ -3033,6 +3133,9 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, get_block_func = ext4_get_block_write; dio_flags = DIO_LOCKING; } +#ifdef CONFIG_EXT4_FS_ENCRYPTION + BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)); +#endif if (IS_DAX(inode)) ret = dax_do_io(iocb, inode, iter, offset, get_block_func, ext4_end_io_dio, dio_flags); @@ -3097,6 +3200,11 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); ssize_t ret; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + return 0; +#endif + /* * If we are doing data journalling we don't support O_DIRECT */ @@ -3261,6 +3369,13 @@ static int __ext4_block_zero_page_range(handle_t *handle, /* Uhhuh. Read error. Complain and punt. */ if (!buffer_uptodate(bh)) goto unlock; + if (S_ISREG(inode->i_mode) && + ext4_encrypted_inode(inode)) { + /* We expect the key to be set. */ + BUG_ON(!ext4_has_encryption_key(inode)); + BUG_ON(blocksize != PAGE_CACHE_SIZE); + WARN_ON_ONCE(ext4_decrypt_one(inode, page)); + } } if (ext4_should_journal_data(inode)) { BUFFER_TRACE(bh, "get write access"); @@ -4096,7 +4211,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_op = &ext4_dir_inode_operations; inode->i_fop = &ext4_dir_operations; } else if (S_ISLNK(inode->i_mode)) { - if (ext4_inode_is_fast_symlink(inode)) { + if (ext4_inode_is_fast_symlink(inode) && + !ext4_encrypted_inode(inode)) { inode->i_op = &ext4_fast_symlink_inode_operations; nd_terminate_link(ei->i_data, inode->i_size, sizeof(ei->i_data) - 1); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index f58a0d1..2cb9e17 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -8,12 +8,12 @@ */ #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/capability.h> #include <linux/time.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/file.h> +#include <linux/random.h> #include <asm/uaccess.h> #include "ext4_jbd2.h" #include "ext4.h" @@ -196,6 +196,16 @@ journal_err_out: return err; } +static int uuid_is_zero(__u8 u[16]) +{ + int i; + + for (i = 0; i < 16; i++) + if (u[i]) + return 0; + return 1; +} + long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -615,7 +625,78 @@ resizefs_out: } case EXT4_IOC_PRECACHE_EXTENTS: return ext4_ext_precache(inode); + case EXT4_IOC_SET_ENCRYPTION_POLICY: { +#ifdef CONFIG_EXT4_FS_ENCRYPTION + struct ext4_encryption_policy policy; + int err = 0; + + if (copy_from_user(&policy, + (struct ext4_encryption_policy __user *)arg, + sizeof(policy))) { + err = -EFAULT; + goto encryption_policy_out; + } + err = ext4_process_policy(&policy, inode); +encryption_policy_out: + return err; +#else + return -EOPNOTSUPP; +#endif + } + case EXT4_IOC_GET_ENCRYPTION_PWSALT: { + int err, err2; + struct ext4_sb_info *sbi = EXT4_SB(sb); + handle_t *handle; + + if (!ext4_sb_has_crypto(sb)) + return -EOPNOTSUPP; + if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) { + err = mnt_want_write_file(filp); + if (err) + return err; + handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto pwsalt_err_exit; + } + err = ext4_journal_get_write_access(handle, sbi->s_sbh); + if (err) + goto pwsalt_err_journal; + generate_random_uuid(sbi->s_es->s_encrypt_pw_salt); + err = ext4_handle_dirty_metadata(handle, NULL, + sbi->s_sbh); + pwsalt_err_journal: + err2 = ext4_journal_stop(handle); + if (err2 && !err) + err = err2; + pwsalt_err_exit: + mnt_drop_write_file(filp); + if (err) + return err; + } + if (copy_to_user((void *) arg, sbi->s_es->s_encrypt_pw_salt, + 16)) + return -EFAULT; + return 0; + } + case EXT4_IOC_GET_ENCRYPTION_POLICY: { +#ifdef CONFIG_EXT4_FS_ENCRYPTION + struct ext4_encryption_policy policy; + int err = 0; + + if (!ext4_encrypted_inode(inode)) + return -ENOENT; + err = ext4_get_policy(inode, &policy); + if (err) + return err; + if (copy_to_user((void *)arg, &policy, sizeof(policy))) + return -EFAULT; + return 0; +#else + return -EOPNOTSUPP; +#endif + } default: return -ENOTTY; } @@ -680,6 +761,9 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case FITRIM: case EXT4_IOC_RESIZE_FS: case EXT4_IOC_PRECACHE_EXTENTS: + case EXT4_IOC_SET_ENCRYPTION_POLICY: + case EXT4_IOC_GET_ENCRYPTION_PWSALT: + case EXT4_IOC_GET_ENCRYPTION_POLICY: break; default: return -ENOIOCTLCMD; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 2291923..ef22cd9 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -26,7 +26,6 @@ #include <linux/fs.h> #include <linux/pagemap.h> -#include <linux/jbd2.h> #include <linux/time.h> #include <linux/fcntl.h> #include <linux/stat.h> @@ -254,8 +253,9 @@ static struct dx_frame *dx_probe(const struct qstr *d_name, struct dx_hash_info *hinfo, struct dx_frame *frame); static void dx_release(struct dx_frame *frames); -static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize, - struct dx_hash_info *hinfo, struct dx_map_entry map[]); +static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, + unsigned blocksize, struct dx_hash_info *hinfo, + struct dx_map_entry map[]); static void dx_sort_map(struct dx_map_entry *map, unsigned count); static struct ext4_dir_entry_2 *dx_move_dirents(char *from, char *to, struct dx_map_entry *offsets, int count, unsigned blocksize); @@ -586,8 +586,10 @@ struct stats unsigned bcount; }; -static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_entry_2 *de, - int size, int show_names) +static struct stats dx_show_leaf(struct inode *dir, + struct dx_hash_info *hinfo, + struct ext4_dir_entry_2 *de, + int size, int show_names) { unsigned names = 0, space = 0; char *base = (char *) de; @@ -600,12 +602,80 @@ static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_ent { if (show_names) { +#ifdef CONFIG_EXT4_FS_ENCRYPTION + int len; + char *name; + struct ext4_str fname_crypto_str + = {.name = NULL, .len = 0}; + struct ext4_fname_crypto_ctx *ctx = NULL; + int res; + + name = de->name; + len = de->name_len; + ctx = ext4_get_fname_crypto_ctx(dir, + EXT4_NAME_LEN); + if (IS_ERR(ctx)) { + printk(KERN_WARNING "Error acquiring" + " crypto ctxt--skipping crypto\n"); + ctx = NULL; + } + if (ctx == NULL) { + /* Directory is not encrypted */ + ext4fs_dirhash(de->name, + de->name_len, &h); + printk("%*.s:(U)%x.%u ", len, + name, h.hash, + (unsigned) ((char *) de + - base)); + } else { + /* Directory is encrypted */ + res = ext4_fname_crypto_alloc_buffer( + ctx, de->name_len, + &fname_crypto_str); + if (res < 0) { + printk(KERN_WARNING "Error " + "allocating crypto " + "buffer--skipping " + "crypto\n"); + ext4_put_fname_crypto_ctx(&ctx); + ctx = NULL; + } + res = ext4_fname_disk_to_usr(ctx, de, + &fname_crypto_str); + if (res < 0) { + printk(KERN_WARNING "Error " + "converting filename " + "from disk to usr" + "\n"); + name = "??"; + len = 2; + } else { + name = fname_crypto_str.name; + len = fname_crypto_str.len; + } + res = ext4_fname_disk_to_hash(ctx, de, + &h); + if (res < 0) { + printk(KERN_WARNING "Error " + "converting filename " + "from disk to htree" + "\n"); + h.hash = 0xDEADBEEF; + } + printk("%*.s:(E)%x.%u ", len, name, + h.hash, (unsigned) ((char *) de + - base)); + ext4_put_fname_crypto_ctx(&ctx); + ext4_fname_crypto_free_buffer( + &fname_crypto_str); + } +#else int len = de->name_len; char *name = de->name; - while (len--) printk("%c", *name++); ext4fs_dirhash(de->name, de->name_len, &h); - printk(":%x.%u ", h.hash, + printk("%*.s:%x.%u ", len, name, h.hash, (unsigned) ((char *) de - base)); +#endif } space += EXT4_DIR_REC_LEN(de->name_len); names++; @@ -623,7 +693,6 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir, unsigned count = dx_get_count(entries), names = 0, space = 0, i; unsigned bcount = 0; struct buffer_head *bh; - int err; printk("%i indexed blocks...\n", count); for (i = 0; i < count; i++, entries++) { @@ -637,7 +706,8 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir, continue; stats = levels? dx_show_entries(hinfo, dir, ((struct dx_node *) bh->b_data)->entries, levels - 1): - dx_show_leaf(hinfo, (struct ext4_dir_entry_2 *) bh->b_data, blocksize, 0); + dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) + bh->b_data, blocksize, 0); names += stats.names; space += stats.space; bcount += stats.bcount; @@ -687,8 +757,28 @@ dx_probe(const struct qstr *d_name, struct inode *dir, if (hinfo->hash_version <= DX_HASH_TEA) hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (d_name) { + struct ext4_fname_crypto_ctx *ctx = NULL; + int res; + + /* Check if the directory is encrypted */ + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) { + ret_err = ERR_PTR(PTR_ERR(ctx)); + goto fail; + } + res = ext4_fname_usr_to_hash(ctx, d_name, hinfo); + if (res < 0) { + ret_err = ERR_PTR(res); + goto fail; + } + ext4_put_fname_crypto_ctx(&ctx); + } +#else if (d_name) ext4fs_dirhash(d_name->name, d_name->len, hinfo); +#endif hash = hinfo->hash; if (root->info.unused_flags & 1) { @@ -773,6 +863,7 @@ fail: brelse(frame->bh); frame--; } + if (ret_err == ERR_PTR(ERR_BAD_DX_DIR)) ext4_warning(dir->i_sb, "Corrupt dir inode %lu, running e2fsck is " @@ -878,6 +969,8 @@ static int htree_dirblock_to_tree(struct file *dir_file, struct buffer_head *bh; struct ext4_dir_entry_2 *de, *top; int err = 0, count = 0; + struct ext4_fname_crypto_ctx *ctx = NULL; + struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}, tmp_str; dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n", (unsigned long)block)); @@ -889,6 +982,24 @@ static int htree_dirblock_to_tree(struct file *dir_file, top = (struct ext4_dir_entry_2 *) ((char *) de + dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0)); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + /* Check if the directory is encrypted */ + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + brelse(bh); + return err; + } + if (ctx != NULL) { + err = ext4_fname_crypto_alloc_buffer(ctx, EXT4_NAME_LEN, + &fname_crypto_str); + if (err < 0) { + ext4_put_fname_crypto_ctx(&ctx); + brelse(bh); + return err; + } + } +#endif for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) { if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, bh->b_size, @@ -897,21 +1008,52 @@ static int htree_dirblock_to_tree(struct file *dir_file, /* silently ignore the rest of the block */ break; } +#ifdef CONFIG_EXT4_FS_ENCRYPTION + err = ext4_fname_disk_to_hash(ctx, de, hinfo); + if (err < 0) { + count = err; + goto errout; + } +#else ext4fs_dirhash(de->name, de->name_len, hinfo); +#endif if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && (hinfo->minor_hash < start_minor_hash))) continue; if (de->inode == 0) continue; - if ((err = ext4_htree_store_dirent(dir_file, - hinfo->hash, hinfo->minor_hash, de)) != 0) { - brelse(bh); - return err; + if (ctx == NULL) { + /* Directory is not encrypted */ + tmp_str.name = de->name; + tmp_str.len = de->name_len; + err = ext4_htree_store_dirent(dir_file, + hinfo->hash, hinfo->minor_hash, de, + &tmp_str); + } else { + /* Directory is encrypted */ + err = ext4_fname_disk_to_usr(ctx, de, + &fname_crypto_str); + if (err < 0) { + count = err; + goto errout; + } + err = ext4_htree_store_dirent(dir_file, + hinfo->hash, hinfo->minor_hash, de, + &fname_crypto_str); + } + if (err != 0) { + count = err; + goto errout; } count++; } +errout: brelse(bh); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ext4_put_fname_crypto_ctx(&ctx); + ext4_fname_crypto_free_buffer(&fname_crypto_str); +#endif return count; } @@ -935,6 +1077,7 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, int count = 0; int ret, err; __u32 hashval; + struct ext4_str tmp_str; dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n", start_hash, start_minor_hash)); @@ -970,14 +1113,22 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, /* Add '.' and '..' from the htree header */ if (!start_hash && !start_minor_hash) { de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data; - if ((err = ext4_htree_store_dirent(dir_file, 0, 0, de)) != 0) + tmp_str.name = de->name; + tmp_str.len = de->name_len; + err = ext4_htree_store_dirent(dir_file, 0, 0, + de, &tmp_str); + if (err != 0) goto errout; count++; } if (start_hash < 2 || (start_hash ==2 && start_minor_hash==0)) { de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data; de = ext4_next_entry(de, dir->i_sb->s_blocksize); - if ((err = ext4_htree_store_dirent(dir_file, 2, 0, de)) != 0) + tmp_str.name = de->name; + tmp_str.len = de->name_len; + err = ext4_htree_store_dirent(dir_file, 2, 0, + de, &tmp_str); + if (err != 0) goto errout; count++; } @@ -1035,17 +1186,33 @@ static inline int search_dirblock(struct buffer_head *bh, * Create map of hash values, offsets, and sizes, stored at end of block. * Returns number of entries mapped. */ -static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize, - struct dx_hash_info *hinfo, +static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, + unsigned blocksize, struct dx_hash_info *hinfo, struct dx_map_entry *map_tail) { int count = 0; char *base = (char *) de; struct dx_hash_info h = *hinfo; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + struct ext4_fname_crypto_ctx *ctx = NULL; + int err; + + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); +#endif while ((char *) de < base + blocksize) { if (de->name_len && de->inode) { +#ifdef CONFIG_EXT4_FS_ENCRYPTION + err = ext4_fname_disk_to_hash(ctx, de, &h); + if (err < 0) { + ext4_put_fname_crypto_ctx(&ctx); + return err; + } +#else ext4fs_dirhash(de->name, de->name_len, &h); +#endif map_tail--; map_tail->hash = h.hash; map_tail->offs = ((char *) de - base)>>2; @@ -1056,6 +1223,9 @@ static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize, /* XXX: do we need to check rec_len == 0 case? -Chris */ de = ext4_next_entry(de, blocksize); } +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ext4_put_fname_crypto_ctx(&ctx); +#endif return count; } @@ -1106,57 +1276,107 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) * `len <= EXT4_NAME_LEN' is guaranteed by caller. * `de != NULL' is guaranteed by caller. */ -static inline int ext4_match (int len, const char * const name, - struct ext4_dir_entry_2 * de) +static inline int ext4_match(struct ext4_fname_crypto_ctx *ctx, + struct ext4_str *fname_crypto_str, + int len, const char * const name, + struct ext4_dir_entry_2 *de) { - if (len != de->name_len) - return 0; + int res; + if (!de->inode) return 0; - return !memcmp(name, de->name, len); + +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (ctx) { + /* Directory is encrypted */ + res = ext4_fname_disk_to_usr(ctx, de, fname_crypto_str); + if (res < 0) + return res; + if (len != res) + return 0; + res = memcmp(name, fname_crypto_str->name, len); + return (res == 0) ? 1 : 0; + } +#endif + if (len != de->name_len) + return 0; + res = memcmp(name, de->name, len); + return (res == 0) ? 1 : 0; } /* * Returns 0 if not found, -1 on failure, and 1 on success */ -int search_dir(struct buffer_head *bh, - char *search_buf, - int buf_size, - struct inode *dir, - const struct qstr *d_name, - unsigned int offset, - struct ext4_dir_entry_2 **res_dir) +int search_dir(struct buffer_head *bh, char *search_buf, int buf_size, + struct inode *dir, const struct qstr *d_name, + unsigned int offset, struct ext4_dir_entry_2 **res_dir) { struct ext4_dir_entry_2 * de; char * dlimit; int de_len; const char *name = d_name->name; int namelen = d_name->len; + struct ext4_fname_crypto_ctx *ctx = NULL; + struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}; + int res; + + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) + return -1; + + if (ctx != NULL) { + /* Allocate buffer to hold maximum name length */ + res = ext4_fname_crypto_alloc_buffer(ctx, EXT4_NAME_LEN, + &fname_crypto_str); + if (res < 0) { + ext4_put_fname_crypto_ctx(&ctx); + return -1; + } + } de = (struct ext4_dir_entry_2 *)search_buf; dlimit = search_buf + buf_size; while ((char *) de < dlimit) { /* this code is executed quadratically often */ /* do minimal checking `by hand' */ + if ((char *) de + de->name_len <= dlimit) { + res = ext4_match(ctx, &fname_crypto_str, namelen, + name, de); + if (res < 0) { + res = -1; + goto return_result; + } + if (res > 0) { + /* found a match - just to be sure, do + * a full check */ + if (ext4_check_dir_entry(dir, NULL, de, bh, + bh->b_data, + bh->b_size, offset)) { + res = -1; + goto return_result; + } + *res_dir = de; + res = 1; + goto return_result; + } - if ((char *) de + namelen <= dlimit && - ext4_match (namelen, name, de)) { - /* found a match - just to be sure, do a full check */ - if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, - bh->b_size, offset)) - return -1; - *res_dir = de; - return 1; } /* prevent looping on a bad block */ de_len = ext4_rec_len_from_disk(de->rec_len, dir->i_sb->s_blocksize); - if (de_len <= 0) - return -1; + if (de_len <= 0) { + res = -1; + goto return_result; + } offset += de_len; de = (struct ext4_dir_entry_2 *) ((char *) de + de_len); } - return 0; + + res = 0; +return_result: + ext4_put_fname_crypto_ctx(&ctx); + ext4_fname_crypto_free_buffer(&fname_crypto_str); + return res; } static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block, @@ -1345,6 +1565,9 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct q ext4_lblk_t block; int retval; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + *res_dir = NULL; +#endif frame = dx_probe(d_name, dir, &hinfo, frames); if (IS_ERR(frame)) return (struct buffer_head *) frame; @@ -1417,6 +1640,18 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi ino); return ERR_PTR(-EIO); } + if (!IS_ERR(inode) && ext4_encrypted_inode(dir) && + (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode)) && + !ext4_is_child_context_consistent_with_parent(dir, + inode)) { + iput(inode); + ext4_warning(inode->i_sb, + "Inconsistent encryption contexts: %lu/%lu\n", + (unsigned long) dir->i_ino, + (unsigned long) inode->i_ino); + return ERR_PTR(-EPERM); + } } return d_splice_alias(inode, dentry); } @@ -1541,7 +1776,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, /* create map in the end of data2 block */ map = (struct dx_map_entry *) (data2 + blocksize); - count = dx_make_map((struct ext4_dir_entry_2 *) data1, + count = dx_make_map(dir, (struct ext4_dir_entry_2 *) data1, blocksize, hinfo, map); map -= count; dx_sort_map(map, count); @@ -1564,7 +1799,8 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, hash2, split, count-split)); /* Fancy dance to stay within two buffers */ - de2 = dx_move_dirents(data1, data2, map + split, count - split, blocksize); + de2 = dx_move_dirents(data1, data2, map + split, count - split, + blocksize); de = dx_pack_dirents(data1, blocksize); de->rec_len = ext4_rec_len_to_disk(data1 + (blocksize - csum_size) - (char *) de, @@ -1580,8 +1816,10 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, initialize_dirent_tail(t, blocksize); } - dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data1, blocksize, 1)); - dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data2, blocksize, 1)); + dxtrace(dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) data1, + blocksize, 1)); + dxtrace(dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) data2, + blocksize, 1)); /* Which block gets the new entry? */ if (hinfo->hash >= hash2) { @@ -1618,15 +1856,48 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, int nlen, rlen; unsigned int offset = 0; char *top; + struct ext4_fname_crypto_ctx *ctx = NULL; + struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}; + int res; + + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) + return -1; + + if (ctx != NULL) { + /* Calculate record length needed to store the entry */ + res = ext4_fname_crypto_namelen_on_disk(ctx, namelen); + if (res < 0) { + ext4_put_fname_crypto_ctx(&ctx); + return res; + } + reclen = EXT4_DIR_REC_LEN(res); + + /* Allocate buffer to hold maximum name length */ + res = ext4_fname_crypto_alloc_buffer(ctx, EXT4_NAME_LEN, + &fname_crypto_str); + if (res < 0) { + ext4_put_fname_crypto_ctx(&ctx); + return -1; + } + } de = (struct ext4_dir_entry_2 *)buf; top = buf + buf_size - reclen; while ((char *) de <= top) { if (ext4_check_dir_entry(dir, NULL, de, bh, - buf, buf_size, offset)) - return -EIO; - if (ext4_match(namelen, name, de)) - return -EEXIST; + buf, buf_size, offset)) { + res = -EIO; + goto return_result; + } + /* Provide crypto context and crypto buffer to ext4 match */ + res = ext4_match(ctx, &fname_crypto_str, namelen, name, de); + if (res < 0) + goto return_result; + if (res > 0) { + res = -EEXIST; + goto return_result; + } nlen = EXT4_DIR_REC_LEN(de->name_len); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if ((de->inode ? rlen - nlen : rlen) >= reclen) @@ -1634,26 +1905,62 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, de = (struct ext4_dir_entry_2 *)((char *)de + rlen); offset += rlen; } - if ((char *) de > top) - return -ENOSPC; - *dest_de = de; - return 0; + if ((char *) de > top) + res = -ENOSPC; + else { + *dest_de = de; + res = 0; + } +return_result: + ext4_put_fname_crypto_ctx(&ctx); + ext4_fname_crypto_free_buffer(&fname_crypto_str); + return res; } -void ext4_insert_dentry(struct inode *inode, - struct ext4_dir_entry_2 *de, - int buf_size, - const char *name, int namelen) +int ext4_insert_dentry(struct inode *dir, + struct inode *inode, + struct ext4_dir_entry_2 *de, + int buf_size, + const struct qstr *iname, + const char *name, int namelen) { int nlen, rlen; + struct ext4_fname_crypto_ctx *ctx = NULL; + struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}; + struct ext4_str tmp_str; + int res; + + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) + return -EIO; + /* By default, the input name would be written to the disk */ + tmp_str.name = (unsigned char *)name; + tmp_str.len = namelen; + if (ctx != NULL) { + /* Directory is encrypted */ + res = ext4_fname_crypto_alloc_buffer(ctx, EXT4_NAME_LEN, + &fname_crypto_str); + if (res < 0) { + ext4_put_fname_crypto_ctx(&ctx); + return -ENOMEM; + } + res = ext4_fname_usr_to_disk(ctx, iname, &fname_crypto_str); + if (res < 0) { + ext4_put_fname_crypto_ctx(&ctx); + ext4_fname_crypto_free_buffer(&fname_crypto_str); + return res; + } + tmp_str.name = fname_crypto_str.name; + tmp_str.len = fname_crypto_str.len; + } nlen = EXT4_DIR_REC_LEN(de->name_len); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if (de->inode) { struct ext4_dir_entry_2 *de1 = - (struct ext4_dir_entry_2 *)((char *)de + nlen); + (struct ext4_dir_entry_2 *)((char *)de + nlen); de1->rec_len = ext4_rec_len_to_disk(rlen - nlen, buf_size); de->rec_len = ext4_rec_len_to_disk(nlen, buf_size); de = de1; @@ -1661,9 +1968,14 @@ void ext4_insert_dentry(struct inode *inode, de->file_type = EXT4_FT_UNKNOWN; de->inode = cpu_to_le32(inode->i_ino); ext4_set_de_type(inode->i_sb, de, inode->i_mode); - de->name_len = namelen; - memcpy(de->name, name, namelen); + de->name_len = tmp_str.len; + + memcpy(de->name, tmp_str.name, tmp_str.len); + ext4_put_fname_crypto_ctx(&ctx); + ext4_fname_crypto_free_buffer(&fname_crypto_str); + return 0; } + /* * Add a new entry into a directory (leaf) block. If de is non-NULL, * it points to a directory entry which is guaranteed to be large @@ -1700,8 +2012,12 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, return err; } - /* By now the buffer is marked for journaling */ - ext4_insert_dentry(inode, de, blocksize, name, namelen); + /* By now the buffer is marked for journaling. Due to crypto operations, + * the following function call may fail */ + err = ext4_insert_dentry(dir, inode, de, blocksize, &dentry->d_name, + name, namelen); + if (err < 0) + return err; /* * XXX shouldn't update any times until successful @@ -1733,8 +2049,13 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, struct inode *inode, struct buffer_head *bh) { struct inode *dir = dentry->d_parent->d_inode; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + struct ext4_fname_crypto_ctx *ctx = NULL; + int res; +#else const char *name = dentry->d_name.name; int namelen = dentry->d_name.len; +#endif struct buffer_head *bh2; struct dx_root *root; struct dx_frame frames[2], *frame; @@ -1748,7 +2069,13 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, struct dx_hash_info hinfo; ext4_lblk_t block; struct fake_dirent *fde; - int csum_size = 0; + int csum_size = 0; + +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ctx = ext4_get_fname_crypto_ctx(dir, EXT4_NAME_LEN); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); +#endif if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); @@ -1815,7 +2142,18 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, if (hinfo.hash_version <= DX_HASH_TEA) hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + res = ext4_fname_usr_to_hash(ctx, &dentry->d_name, &hinfo); + if (res < 0) { + ext4_put_fname_crypto_ctx(&ctx); + ext4_mark_inode_dirty(handle, dir); + brelse(bh); + return res; + } + ext4_put_fname_crypto_ctx(&ctx); +#else ext4fs_dirhash(name, namelen, &hinfo); +#endif memset(frames, 0, sizeof(frames)); frame = frames; frame->entries = entries; @@ -1865,7 +2203,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, struct inode *inode) { struct inode *dir = dentry->d_parent->d_inode; - struct buffer_head *bh; + struct buffer_head *bh = NULL; struct ext4_dir_entry_2 *de; struct ext4_dir_entry_tail *t; struct super_block *sb; @@ -1889,14 +2227,14 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, return retval; if (retval == 1) { retval = 0; - return retval; + goto out; } } if (is_dx(dir)) { retval = ext4_dx_add_entry(handle, dentry, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) - return retval; + goto out; ext4_clear_inode_flag(dir, EXT4_INODE_INDEX); dx_fallback++; ext4_mark_inode_dirty(handle, dir); @@ -1908,14 +2246,15 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, return PTR_ERR(bh); retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh); - if (retval != -ENOSPC) { - brelse(bh); - return retval; - } + if (retval != -ENOSPC) + goto out; if (blocks == 1 && !dx_fallback && - EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) - return make_indexed_dir(handle, dentry, inode, bh); + EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) { + retval = make_indexed_dir(handle, dentry, inode, bh); + bh = NULL; /* make_indexed_dir releases bh */ + goto out; + } brelse(bh); } bh = ext4_append(handle, dir, &block); @@ -1931,6 +2270,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, } retval = add_dirent_to_buf(handle, dentry, inode, de, bh); +out: brelse(bh); if (retval == 0) ext4_set_inode_state(inode, EXT4_STATE_NEWENTRY); @@ -2237,7 +2577,20 @@ retry: inode->i_op = &ext4_file_inode_operations; inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); - err = ext4_add_nondir(handle, dentry, inode); + err = 0; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (!err && (ext4_encrypted_inode(dir) || + DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb)))) { + err = ext4_inherit_context(dir, inode); + if (err) { + clear_nlink(inode); + unlock_new_inode(inode); + iput(inode); + } + } +#endif + if (!err) + err = ext4_add_nondir(handle, dentry, inode); if (!err && IS_DIRSYNC(dir)) ext4_handle_sync(handle); } @@ -2418,6 +2771,14 @@ retry: err = ext4_init_new_dir(handle, dir, inode); if (err) goto out_clear_inode; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (ext4_encrypted_inode(dir) || + DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))) { + err = ext4_inherit_context(dir, inode); + if (err) + goto out_clear_inode; + } +#endif err = ext4_mark_inode_dirty(handle, inode); if (!err) err = ext4_add_entry(handle, dentry, inode); @@ -2450,7 +2811,7 @@ out_stop: /* * routine to check that the specified directory is empty (for rmdir) */ -static int empty_dir(struct inode *inode) +int ext4_empty_dir(struct inode *inode) { unsigned int offset; struct buffer_head *bh; @@ -2718,7 +3079,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) goto end_rmdir; retval = -ENOTEMPTY; - if (!empty_dir(inode)) + if (!ext4_empty_dir(inode)) goto end_rmdir; handle = ext4_journal_start(dir, EXT4_HT_DIR, @@ -2828,16 +3189,25 @@ static int ext4_symlink(struct inode *dir, { handle_t *handle; struct inode *inode; - int l, err, retries = 0; + int err, len = strlen(symname); int credits; - - l = strlen(symname)+1; - if (l > dir->i_sb->s_blocksize) + bool encryption_required; + struct ext4_str disk_link; + struct ext4_encrypted_symlink_data *sd = NULL; + + disk_link.len = len + 1; + disk_link.name = (char *) symname; + + encryption_required = (ext4_encrypted_inode(dir) || + DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))); + if (encryption_required) + disk_link.len = encrypted_symlink_data_len(len) + 1; + if (disk_link.len > dir->i_sb->s_blocksize) return -ENAMETOOLONG; dquot_initialize(dir); - if (l > EXT4_N_BLOCKS * 4) { + if ((disk_link.len > EXT4_N_BLOCKS * 4)) { /* * For non-fast symlinks, we just allocate inode and put it on * orphan list in the first transaction => we need bitmap, @@ -2856,16 +3226,49 @@ static int ext4_symlink(struct inode *dir, credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3; } -retry: + inode = ext4_new_inode_start_handle(dir, S_IFLNK|S_IRWXUGO, &dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); handle = ext4_journal_current_handle(); - err = PTR_ERR(inode); - if (IS_ERR(inode)) - goto out_stop; + if (IS_ERR(inode)) { + if (handle) + ext4_journal_stop(handle); + return PTR_ERR(inode); + } + + if (encryption_required) { + struct ext4_fname_crypto_ctx *ctx = NULL; + struct qstr istr; + struct ext4_str ostr; + + sd = kzalloc(disk_link.len, GFP_NOFS); + if (!sd) { + err = -ENOMEM; + goto err_drop_inode; + } + err = ext4_inherit_context(dir, inode); + if (err) + goto err_drop_inode; + ctx = ext4_get_fname_crypto_ctx(inode, + inode->i_sb->s_blocksize); + if (IS_ERR_OR_NULL(ctx)) { + /* We just set the policy, so ctx should not be NULL */ + err = (ctx == NULL) ? -EIO : PTR_ERR(ctx); + goto err_drop_inode; + } + istr.name = (const unsigned char *) symname; + istr.len = len; + ostr.name = sd->encrypted_path; + err = ext4_fname_usr_to_disk(ctx, &istr, &ostr); + ext4_put_fname_crypto_ctx(&ctx); + if (err < 0) + goto err_drop_inode; + sd->len = cpu_to_le16(ostr.len); + disk_link.name = (char *) sd; + } - if (l > EXT4_N_BLOCKS * 4) { + if ((disk_link.len > EXT4_N_BLOCKS * 4)) { inode->i_op = &ext4_symlink_inode_operations; ext4_set_aops(inode); /* @@ -2881,9 +3284,10 @@ retry: drop_nlink(inode); err = ext4_orphan_add(handle, inode); ext4_journal_stop(handle); + handle = NULL; if (err) goto err_drop_inode; - err = __page_symlink(inode, symname, l, 1); + err = __page_symlink(inode, disk_link.name, disk_link.len, 1); if (err) goto err_drop_inode; /* @@ -2895,34 +3299,37 @@ retry: EXT4_INDEX_EXTRA_TRANS_BLOCKS + 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); + handle = NULL; goto err_drop_inode; } set_nlink(inode, 1); err = ext4_orphan_del(handle, inode); - if (err) { - ext4_journal_stop(handle); - clear_nlink(inode); + if (err) goto err_drop_inode; - } } else { /* clear the extent format for fast symlink */ ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); - inode->i_op = &ext4_fast_symlink_inode_operations; - memcpy((char *)&EXT4_I(inode)->i_data, symname, l); - inode->i_size = l-1; + inode->i_op = encryption_required ? + &ext4_symlink_inode_operations : + &ext4_fast_symlink_inode_operations; + memcpy((char *)&EXT4_I(inode)->i_data, disk_link.name, + disk_link.len); + inode->i_size = disk_link.len - 1; } EXT4_I(inode)->i_disksize = inode->i_size; err = ext4_add_nondir(handle, dentry, inode); if (!err && IS_DIRSYNC(dir)) ext4_handle_sync(handle); -out_stop: if (handle) ext4_journal_stop(handle); - if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) - goto retry; + kfree(sd); return err; err_drop_inode: + if (handle) + ext4_journal_stop(handle); + kfree(sd); + clear_nlink(inode); unlock_new_inode(inode); iput(inode); return err; @@ -2937,7 +3344,9 @@ static int ext4_link(struct dentry *old_dentry, if (inode->i_nlink >= EXT4_LINK_MAX) return -EMLINK; - + if (ext4_encrypted_inode(dir) && + !ext4_is_child_context_consistent_with_parent(dir, inode)) + return -EPERM; dquot_initialize(dir); retry: @@ -3238,6 +3647,14 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino) goto end_rename; + if ((old.dir != new.dir) && + ext4_encrypted_inode(new.dir) && + !ext4_is_child_context_consistent_with_parent(new.dir, + old.inode)) { + retval = -EPERM; + goto end_rename; + } + new.bh = ext4_find_entry(new.dir, &new.dentry->d_name, &new.de, &new.inlined); if (IS_ERR(new.bh)) { @@ -3258,12 +3675,18 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2); if (!(flags & RENAME_WHITEOUT)) { handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + retval = PTR_ERR(handle); + handle = NULL; + goto end_rename; + } } else { whiteout = ext4_whiteout_for_rename(&old, credits, &handle); - if (IS_ERR(whiteout)) - return PTR_ERR(whiteout); + if (IS_ERR(whiteout)) { + retval = PTR_ERR(whiteout); + whiteout = NULL; + goto end_rename; + } } if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir)) @@ -3272,7 +3695,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, if (S_ISDIR(old.inode->i_mode)) { if (new.inode) { retval = -ENOTEMPTY; - if (!empty_dir(new.inode)) + if (!ext4_empty_dir(new.inode)) goto end_rename; } else { retval = -EMLINK; @@ -3346,8 +3769,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, ext4_dec_count(handle, old.dir); if (new.inode) { - /* checked empty_dir above, can't have another parent, - * ext4_dec_count() won't work for many-linked dirs */ + /* checked ext4_empty_dir above, can't have another + * parent, ext4_dec_count() won't work for many-linked + * dirs */ clear_nlink(new.inode); } else { ext4_inc_count(handle, new.dir); @@ -3427,8 +3851,11 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, handle = ext4_journal_start(old.dir, EXT4_HT_DIR, (2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) + 2 * EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2)); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + retval = PTR_ERR(handle); + handle = NULL; + goto end_rename; + } if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir)) ext4_handle_sync(handle); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 4649842..5765f88 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -8,7 +8,6 @@ #include <linux/fs.h> #include <linux/time.h> -#include <linux/jbd2.h> #include <linux/highuid.h> #include <linux/pagemap.h> #include <linux/quotaops.h> @@ -24,7 +23,6 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/mm.h> -#include <linux/ratelimit.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -68,6 +66,10 @@ static void ext4_finish_bio(struct bio *bio) bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + struct page *data_page = NULL; + struct ext4_crypto_ctx *ctx = NULL; +#endif struct buffer_head *bh, *head; unsigned bio_start = bvec->bv_offset; unsigned bio_end = bio_start + bvec->bv_len; @@ -77,6 +79,15 @@ static void ext4_finish_bio(struct bio *bio) if (!page) continue; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (!page->mapping) { + /* The bounce data pages are unmapped. */ + data_page = page; + ctx = (struct ext4_crypto_ctx *)page_private(data_page); + page = ctx->control_page; + } +#endif + if (error) { SetPageError(page); set_bit(AS_EIO, &page->mapping->flags); @@ -101,8 +112,13 @@ static void ext4_finish_bio(struct bio *bio) } while ((bh = bh->b_this_page) != head); bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); local_irq_restore(flags); - if (!under_io) + if (!under_io) { +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (ctx) + ext4_restore_control_page(data_page); +#endif end_page_writeback(page); + } } } @@ -377,6 +393,7 @@ static int io_submit_init_bio(struct ext4_io_submit *io, static int io_submit_add_bh(struct ext4_io_submit *io, struct inode *inode, + struct page *page, struct buffer_head *bh) { int ret; @@ -390,7 +407,7 @@ submit_and_retry: if (ret) return ret; } - ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh)); + ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh)); if (ret != bh->b_size) goto submit_and_retry; io->io_next_block++; @@ -403,6 +420,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, struct writeback_control *wbc, bool keep_towrite) { + struct page *data_page = NULL; struct inode *inode = page->mapping->host; unsigned block_start, blocksize; struct buffer_head *bh, *head; @@ -462,19 +480,29 @@ int ext4_bio_write_page(struct ext4_io_submit *io, set_buffer_async_write(bh); } while ((bh = bh->b_this_page) != head); - /* Now submit buffers to write */ bh = head = page_buffers(page); + + if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { + data_page = ext4_encrypt(inode, page); + if (IS_ERR(data_page)) { + ret = PTR_ERR(data_page); + data_page = NULL; + goto out; + } + } + + /* Now submit buffers to write */ do { if (!buffer_async_write(bh)) continue; - ret = io_submit_add_bh(io, inode, bh); + ret = io_submit_add_bh(io, inode, + data_page ? data_page : page, bh); if (ret) { /* * We only get here on ENOMEM. Not much else * we can do but mark the page as dirty, and * better luck next time. */ - redirty_page_for_writepage(wbc, page); break; } nr_submitted++; @@ -483,6 +511,11 @@ int ext4_bio_write_page(struct ext4_io_submit *io, /* Error stopped previous loop? Clean up buffers... */ if (ret) { + out: + if (data_page) + ext4_restore_control_page(data_page); + printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret); + redirty_page_for_writepage(wbc, page); do { clear_buffer_async_write(bh); bh = bh->b_this_page; diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c new file mode 100644 index 0000000..171b9ac --- /dev/null +++ b/fs/ext4/readpage.c @@ -0,0 +1,328 @@ +/* + * linux/fs/ext4/readpage.c + * + * Copyright (C) 2002, Linus Torvalds. + * Copyright (C) 2015, Google, Inc. + * + * This was originally taken from fs/mpage.c + * + * The intent is the ext4_mpage_readpages() function here is intended + * to replace mpage_readpages() in the general case, not just for + * encrypted files. It has some limitations (see below), where it + * will fall back to read_block_full_page(), but these limitations + * should only be hit when page_size != block_size. + * + * This will allow us to attach a callback function to support ext4 + * encryption. + * + * If anything unusual happens, such as: + * + * - encountering a page which has buffers + * - encountering a page which has a non-hole after a hole + * - encountering a page with non-contiguous blocks + * + * then this code just gives up and calls the buffer_head-based read function. + * It does handle a page which has holes at the end - that is a common case: + * the end-of-file on blocksize < PAGE_CACHE_SIZE setups. + * + */ + +#include <linux/kernel.h> +#include <linux/export.h> +#include <linux/mm.h> +#include <linux/kdev_t.h> +#include <linux/gfp.h> +#include <linux/bio.h> +#include <linux/fs.h> +#include <linux/buffer_head.h> +#include <linux/blkdev.h> +#include <linux/highmem.h> +#include <linux/prefetch.h> +#include <linux/mpage.h> +#include <linux/writeback.h> +#include <linux/backing-dev.h> +#include <linux/pagevec.h> +#include <linux/cleancache.h> + +#include "ext4.h" + +/* + * Call ext4_decrypt on every single page, reusing the encryption + * context. + */ +static void completion_pages(struct work_struct *work) +{ +#ifdef CONFIG_EXT4_FS_ENCRYPTION + struct ext4_crypto_ctx *ctx = + container_of(work, struct ext4_crypto_ctx, work); + struct bio *bio = ctx->bio; + struct bio_vec *bv; + int i; + + bio_for_each_segment_all(bv, bio, i) { + struct page *page = bv->bv_page; + + int ret = ext4_decrypt(ctx, page); + if (ret) { + WARN_ON_ONCE(1); + SetPageError(page); + } else + SetPageUptodate(page); + unlock_page(page); + } + ext4_release_crypto_ctx(ctx); + bio_put(bio); +#else + BUG(); +#endif +} + +static inline bool ext4_bio_encrypted(struct bio *bio) +{ +#ifdef CONFIG_EXT4_FS_ENCRYPTION + return unlikely(bio->bi_private != NULL); +#else + return false; +#endif +} + +/* + * I/O completion handler for multipage BIOs. + * + * The mpage code never puts partial pages into a BIO (except for end-of-file). + * If a page does not map to a contiguous run of blocks then it simply falls + * back to block_read_full_page(). + * + * Why is this? If a page's completion depends on a number of different BIOs + * which can complete in any order (or at the same time) then determining the + * status of that page is hard. See end_buffer_async_read() for the details. + * There is no point in duplicating all that complexity. + */ +static void mpage_end_io(struct bio *bio, int err) +{ + struct bio_vec *bv; + int i; + + if (ext4_bio_encrypted(bio)) { + struct ext4_crypto_ctx *ctx = bio->bi_private; + + if (err) { + ext4_release_crypto_ctx(ctx); + } else { + INIT_WORK(&ctx->work, completion_pages); + ctx->bio = bio; + queue_work(ext4_read_workqueue, &ctx->work); + return; + } + } + bio_for_each_segment_all(bv, bio, i) { + struct page *page = bv->bv_page; + + if (!err) { + SetPageUptodate(page); + } else { + ClearPageUptodate(page); + SetPageError(page); + } + unlock_page(page); + } + + bio_put(bio); +} + +int ext4_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 blocks_per_page = PAGE_CACHE_SIZE >> blkbits; + const unsigned blocksize = 1 << blkbits; + sector_t block_in_file; + sector_t last_block; + sector_t last_block_in_file; + sector_t blocks[MAX_BUF_PER_PAGE]; + unsigned page_block; + struct block_device *bdev = inode->i_sb->s_bdev; + int length; + unsigned relative_block = 0; + struct ext4_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--) { + int fully_mapped = 1; + unsigned first_hole = blocks_per_page; + + 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; + } + + if (page_has_buffers(page)) + goto confused; + + block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits); + last_block = block_in_file + nr_pages * blocks_per_page; + last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits; + if (last_block > last_block_in_file) + last_block = last_block_in_file; + page_block = 0; + + /* + * Map blocks using the previous result first. + */ + if ((map.m_flags & EXT4_MAP_MAPPED) && + block_in_file > map.m_lblk && + block_in_file < (map.m_lblk + map.m_len)) { + unsigned map_offset = block_in_file - map.m_lblk; + unsigned last = map.m_len - map_offset; + + for (relative_block = 0; ; relative_block++) { + if (relative_block == last) { + /* needed? */ + map.m_flags &= ~EXT4_MAP_MAPPED; + break; + } + if (page_block == blocks_per_page) + break; + blocks[page_block] = map.m_pblk + map_offset + + relative_block; + page_block++; + block_in_file++; + } + } + + /* + * Then do more ext4_map_blocks() calls until we are + * done with this page. + */ + while (page_block < blocks_per_page) { + if (block_in_file < last_block) { + map.m_lblk = block_in_file; + map.m_len = last_block - block_in_file; + + if (ext4_map_blocks(NULL, inode, &map, 0) < 0) { + set_error_page: + SetPageError(page); + zero_user_segment(page, 0, + PAGE_CACHE_SIZE); + unlock_page(page); + goto next_page; + } + } + if ((map.m_flags & EXT4_MAP_MAPPED) == 0) { + fully_mapped = 0; + if (first_hole == blocks_per_page) + first_hole = page_block; + page_block++; + block_in_file++; + continue; + } + if (first_hole != blocks_per_page) + goto confused; /* hole -> non-hole */ + + /* Contiguous blocks? */ + if (page_block && blocks[page_block-1] != map.m_pblk-1) + goto confused; + for (relative_block = 0; ; relative_block++) { + if (relative_block == map.m_len) { + /* needed? */ + map.m_flags &= ~EXT4_MAP_MAPPED; + break; + } else if (page_block == blocks_per_page) + break; + blocks[page_block] = map.m_pblk+relative_block; + page_block++; + block_in_file++; + } + } + if (first_hole != blocks_per_page) { + zero_user_segment(page, first_hole << blkbits, + PAGE_CACHE_SIZE); + if (first_hole == 0) { + SetPageUptodate(page); + unlock_page(page); + goto next_page; + } + } else if (fully_mapped) { + SetPageMappedToDisk(page); + } + if (fully_mapped && blocks_per_page == 1 && + !PageUptodate(page) && cleancache_get_page(page) == 0) { + SetPageUptodate(page); + goto confused; + } + + /* + * This page will go to BIO. Do we need to send this + * BIO off first? + */ + if (bio && (last_block_in_bio != blocks[0] - 1)) { + submit_and_realloc: + submit_bio(READ, bio); + bio = NULL; + } + if (bio == NULL) { + struct ext4_crypto_ctx *ctx = NULL; + + if (ext4_encrypted_inode(inode) && + S_ISREG(inode->i_mode)) { + ctx = ext4_get_crypto_ctx(inode); + if (IS_ERR(ctx)) + goto set_error_page; + } + bio = bio_alloc(GFP_KERNEL, + min_t(int, nr_pages, bio_get_nr_vecs(bdev))); + if (!bio) { + if (ctx) + ext4_release_crypto_ctx(ctx); + goto set_error_page; + } + bio->bi_bdev = bdev; + bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9); + bio->bi_end_io = mpage_end_io; + bio->bi_private = ctx; + } + + length = first_hole << blkbits; + if (bio_add_page(bio, page, length, 0) < length) + goto submit_and_realloc; + + if (((map.m_flags & EXT4_MAP_BOUNDARY) && + (relative_block == map.m_len)) || + (first_hole != blocks_per_page)) { + submit_bio(READ, bio); + bio = NULL; + } else + last_block_in_bio = blocks[blocks_per_page - 1]; + goto next_page; + confused: + if (bio) { + submit_bio(READ, bio); + bio = NULL; + } + if (!PageUptodate(page)) + block_read_full_page(page, ext4_get_block); + else + 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; +} diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d348c7d..821f22d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -21,7 +21,6 @@ #include <linux/fs.h> #include <linux/time.h> #include <linux/vmalloc.h> -#include <linux/jbd2.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> @@ -323,22 +322,6 @@ static void save_error_info(struct super_block *sb, const char *func, ext4_commit_super(sb, 1); } -/* - * The del_gendisk() function uninitializes the disk-specific data - * structures, including the bdi structure, without telling anyone - * else. Once this happens, any attempt to call mark_buffer_dirty() - * (for example, by ext4_commit_super), will cause a kernel OOPS. - * This is a kludge to prevent these oops until we can put in a proper - * hook in del_gendisk() to inform the VFS and file system layers. - */ -static int block_device_ejected(struct super_block *sb) -{ - struct inode *bd_inode = sb->s_bdev->bd_inode; - struct backing_dev_info *bdi = inode_to_bdi(bd_inode); - - return bdi->dev == NULL; -} - static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) { struct super_block *sb = journal->j_private; @@ -893,6 +876,9 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) atomic_set(&ei->i_ioend_count, 0); atomic_set(&ei->i_unwritten, 0); INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ei->i_encryption_key.mode = EXT4_ENCRYPTION_MODE_INVALID; +#endif return &ei->vfs_inode; } @@ -1120,7 +1106,7 @@ enum { Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev, Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, - Opt_data_err_abort, Opt_data_err_ignore, + Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, @@ -1211,6 +1197,7 @@ static const match_table_t tokens = { {Opt_init_itable, "init_itable"}, {Opt_noinit_itable, "noinit_itable"}, {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, + {Opt_test_dummy_encryption, "test_dummy_encryption"}, {Opt_removed, "check=none"}, /* mount option from ext2/3 */ {Opt_removed, "nocheck"}, /* mount option from ext2/3 */ {Opt_removed, "reservation"}, /* mount option from ext2/3 */ @@ -1412,6 +1399,7 @@ static const struct mount_opts { {Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT}, {Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT}, {Opt_max_dir_size_kb, 0, MOPT_GTE0}, + {Opt_test_dummy_encryption, 0, MOPT_GTE0}, {Opt_err, 0, 0} }; @@ -1588,6 +1576,15 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, } *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg); + } else if (token == Opt_test_dummy_encryption) { +#ifdef CONFIG_EXT4_FS_ENCRYPTION + sbi->s_mount_flags |= EXT4_MF_TEST_DUMMY_ENCRYPTION; + ext4_msg(sb, KERN_WARNING, + "Test dummy encryption mode enabled"); +#else + ext4_msg(sb, KERN_WARNING, + "Test dummy encryption mount option ignored"); +#endif } else if (m->flags & MOPT_DATAJ) { if (is_remount) { if (!sbi->s_journal) @@ -2685,11 +2682,13 @@ static struct attribute *ext4_attrs[] = { EXT4_INFO_ATTR(lazy_itable_init); EXT4_INFO_ATTR(batched_discard); EXT4_INFO_ATTR(meta_bg_resize); +EXT4_INFO_ATTR(encryption); static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(lazy_itable_init), ATTR_LIST(batched_discard), ATTR_LIST(meta_bg_resize), + ATTR_LIST(encryption), NULL, }; @@ -3448,6 +3447,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (sb->s_bdev->bd_part) sbi->s_sectors_written_start = part_stat_read(sb->s_bdev->bd_part, sectors[1]); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + /* Modes of operations for file and directory encryption. */ + sbi->s_file_encryption_mode = EXT4_ENCRYPTION_MODE_AES_256_XTS; + sbi->s_dir_encryption_mode = EXT4_ENCRYPTION_MODE_INVALID; +#endif /* Cleanup superblock name */ for (cp = sb->s_id; (cp = strchr(cp, '/'));) @@ -3692,6 +3696,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } } + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT) && + es->s_encryption_level) { + ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d", + es->s_encryption_level); + goto failed_mount; + } + if (sb->s_blocksize != blocksize) { /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { @@ -4054,6 +4065,13 @@ no_journal: } } + if (unlikely(sbi->s_mount_flags & EXT4_MF_TEST_DUMMY_ENCRYPTION) && + !(sb->s_flags & MS_RDONLY) && + !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT)) { + EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT); + ext4_commit_super(sb, 1); + } + /* * Get the # of file system overhead blocks from the * superblock if present. @@ -4570,7 +4588,7 @@ static int ext4_commit_super(struct super_block *sb, int sync) struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; int error = 0; - if (!sbh || block_device_ejected(sb)) + if (!sbh) return error; if (buffer_write_io_error(sbh)) { /* diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index ff37119..136ca0e 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -18,13 +18,101 @@ */ #include <linux/fs.h> -#include <linux/jbd2.h> #include <linux/namei.h> #include "ext4.h" #include "xattr.h" +#ifdef CONFIG_EXT4_FS_ENCRYPTION static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd) { + struct page *cpage = NULL; + char *caddr, *paddr = NULL; + struct ext4_str cstr, pstr; + struct inode *inode = dentry->d_inode; + struct ext4_fname_crypto_ctx *ctx = NULL; + struct ext4_encrypted_symlink_data *sd; + loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1); + int res; + u32 plen, max_size = inode->i_sb->s_blocksize; + + if (!ext4_encrypted_inode(inode)) + return page_follow_link_light(dentry, nd); + + ctx = ext4_get_fname_crypto_ctx(inode, inode->i_sb->s_blocksize); + if (IS_ERR(ctx)) + return ctx; + + if (ext4_inode_is_fast_symlink(inode)) { + caddr = (char *) EXT4_I(dentry->d_inode)->i_data; + max_size = sizeof(EXT4_I(dentry->d_inode)->i_data); + } else { + cpage = read_mapping_page(inode->i_mapping, 0, NULL); + if (IS_ERR(cpage)) { + ext4_put_fname_crypto_ctx(&ctx); + return cpage; + } + caddr = kmap(cpage); + caddr[size] = 0; + } + + /* Symlink is encrypted */ + sd = (struct ext4_encrypted_symlink_data *)caddr; + cstr.name = sd->encrypted_path; + cstr.len = le32_to_cpu(sd->len); + if ((cstr.len + + sizeof(struct ext4_encrypted_symlink_data) - 1) > + max_size) { + /* Symlink data on the disk is corrupted */ + res = -EIO; + goto errout; + } + plen = (cstr.len < EXT4_FNAME_CRYPTO_DIGEST_SIZE*2) ? + EXT4_FNAME_CRYPTO_DIGEST_SIZE*2 : cstr.len; + paddr = kmalloc(plen + 1, GFP_NOFS); + if (!paddr) { + res = -ENOMEM; + goto errout; + } + pstr.name = paddr; + res = _ext4_fname_disk_to_usr(ctx, &cstr, &pstr); + if (res < 0) + goto errout; + /* Null-terminate the name */ + if (res <= plen) + paddr[res] = '\0'; + nd_set_link(nd, paddr); + ext4_put_fname_crypto_ctx(&ctx); + if (cpage) { + kunmap(cpage); + page_cache_release(cpage); + } + return NULL; +errout: + ext4_put_fname_crypto_ctx(&ctx); + if (cpage) { + kunmap(cpage); + page_cache_release(cpage); + } + kfree(paddr); + return ERR_PTR(res); +} + +static void ext4_put_link(struct dentry *dentry, struct nameidata *nd, + void *cookie) +{ + struct page *page = cookie; + + if (!page) { + kfree(nd_get_link(nd)); + } else { + kunmap(page); + page_cache_release(page); + } +} +#endif + +static void *ext4_follow_fast_link(struct dentry *dentry, struct nameidata *nd) +{ struct ext4_inode_info *ei = EXT4_I(dentry->d_inode); nd_set_link(nd, (char *) ei->i_data); return NULL; @@ -32,8 +120,13 @@ static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd) const struct inode_operations ext4_symlink_inode_operations = { .readlink = generic_readlink, +#ifdef CONFIG_EXT4_FS_ENCRYPTION + .follow_link = ext4_follow_link, + .put_link = ext4_put_link, +#else .follow_link = page_follow_link_light, .put_link = page_put_link, +#endif .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, @@ -43,7 +136,7 @@ const struct inode_operations ext4_symlink_inode_operations = { const struct inode_operations ext4_fast_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = ext4_follow_link, + .follow_link = ext4_follow_fast_link, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 1e09fc7..759842f 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -55,7 +55,6 @@ #include <linux/slab.h> #include <linux/mbcache.h> #include <linux/quotaops.h> -#include <linux/rwsem.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" @@ -639,8 +638,7 @@ ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s) free += EXT4_XATTR_LEN(name_len); } if (i->value) { - if (free < EXT4_XATTR_SIZE(i->value_len) || - free < EXT4_XATTR_LEN(name_len) + + if (free < EXT4_XATTR_LEN(name_len) + EXT4_XATTR_SIZE(i->value_len)) return -ENOSPC; } diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 29bedf5..ddc0957 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -23,6 +23,7 @@ #define EXT4_XATTR_INDEX_SECURITY 6 #define EXT4_XATTR_INDEX_SYSTEM 7 #define EXT4_XATTR_INDEX_RICHACL 8 +#define EXT4_XATTR_INDEX_ENCRYPTION 9 struct ext4_xattr_header { __le32 h_magic; /* magic number for identification */ @@ -98,6 +99,8 @@ extern const struct xattr_handler ext4_xattr_user_handler; extern const struct xattr_handler ext4_xattr_trusted_handler; extern const struct xattr_handler ext4_xattr_security_handler; +#define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c" + extern ssize_t ext4_listxattr(struct dentry *, char *, size_t); extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t); |