From ed9b3196d2b26b5bd3a7e2cd4aec8e389d991fd8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 10:59:38 +0200 Subject: fs: remove a weird comment in submit_bh_wbc All bios can get remapped if submitted to partitions. No need to comment on that. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/buffer.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'fs/buffer.c') diff --git a/fs/buffer.c b/fs/buffer.c index 64fe82ec65ff..2725ebbcfdc2 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3040,12 +3040,7 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE)) clear_buffer_write_io_error(bh); - /* - * from here on down, it's all bio -- do the initial mapping, - * submit_bio -> generic_make_request may further map this bio around - */ bio = bio_alloc(GFP_NOIO, 1); - bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_write_hint = write_hint; -- cgit v1.2.3 From 4f74d15fe40833d4fb4f5ead7437aa73840596a5 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 2 Jul 2020 01:56:07 +0000 Subject: ext4: add inline encryption support Wire up ext4 to support inline encryption via the helper functions which fs/crypto/ now provides. This includes: - Adding a mount option 'inlinecrypt' which enables inline encryption on encrypted files where it can be used. - Setting the bio_crypt_ctx on bios that will be submitted to an inline-encrypted file. Note: submit_bh_wbc() in fs/buffer.c also needed to be patched for this part, since ext4 sometimes uses ll_rw_block() on file data. - Not adding logically discontiguous data to bios that will be submitted to an inline-encrypted file. - Not doing filesystem-layer crypto on inline-encrypted files. Co-developed-by: Satya Tangirala Signed-off-by: Satya Tangirala Reviewed-by: Theodore Ts'o Link: https://lore.kernel.org/r/20200702015607.1215430-5-satyat@google.com Signed-off-by: Eric Biggers --- Documentation/admin-guide/ext4.rst | 7 +++++++ fs/buffer.c | 7 ++++--- fs/ext4/inode.c | 4 ++-- fs/ext4/page-io.c | 6 ++++-- fs/ext4/readpage.c | 11 ++++++++--- fs/ext4/super.c | 12 ++++++++++++ 6 files changed, 37 insertions(+), 10 deletions(-) (limited to 'fs/buffer.c') diff --git a/Documentation/admin-guide/ext4.rst b/Documentation/admin-guide/ext4.rst index 9443fcef1876..2162d7909970 100644 --- a/Documentation/admin-guide/ext4.rst +++ b/Documentation/admin-guide/ext4.rst @@ -395,6 +395,13 @@ When mounting an ext4 filesystem, the following option are accepted: Documentation/filesystems/dax.txt. Note that this option is incompatible with data=journal. + inlinecrypt + When possible, encrypt/decrypt the contents of encrypted files using the + blk-crypto framework rather than filesystem-layer encryption. This + allows the use of inline encryption hardware. The on-disk format is + unaffected. For more details, see + Documentation/block/inline-encryption.rst. + Data Mode ========= There are 3 different data modes: diff --git a/fs/buffer.c b/fs/buffer.c index 64fe82ec65ff..dc5e05b47646 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -320,9 +320,8 @@ static void decrypt_bh(struct work_struct *work) static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { /* Decrypt if needed */ - if (uptodate && IS_ENABLED(CONFIG_FS_ENCRYPTION) && - IS_ENCRYPTED(bh->b_page->mapping->host) && - S_ISREG(bh->b_page->mapping->host->i_mode)) { + if (uptodate && + fscrypt_inode_uses_fs_layer_crypto(bh->b_page->mapping->host)) { struct decrypt_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); if (ctx) { @@ -3046,6 +3045,8 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, */ bio = bio_alloc(GFP_NOIO, 1); + fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); + bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_write_hint = write_hint; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 10dd470876b3..44bad4bb8831 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1096,7 +1096,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, } if (unlikely(err)) { page_zero_new_buffers(page, from, to); - } else if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) { + } else if (fscrypt_inode_uses_fs_layer_crypto(inode)) { for (i = 0; i < nr_wait; i++) { int err2; @@ -3737,7 +3737,7 @@ 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) && IS_ENCRYPTED(inode)) { + if (fscrypt_inode_uses_fs_layer_crypto(inode)) { /* We expect the key to be set. */ BUG_ON(!fscrypt_has_encryption_key(inode)); err = fscrypt_decrypt_pagecache_blocks(page, blocksize, diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index de6fe969f773..defd2e10dfd1 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -402,6 +402,7 @@ static void io_submit_init_bio(struct ext4_io_submit *io, * __GFP_DIRECT_RECLAIM is set, see comments for bio_alloc_bioset(). */ bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); + fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_end_io = ext4_end_bio; @@ -418,7 +419,8 @@ static void io_submit_add_bh(struct ext4_io_submit *io, { int ret; - if (io->io_bio && bh->b_blocknr != io->io_next_block) { + if (io->io_bio && (bh->b_blocknr != io->io_next_block || + !fscrypt_mergeable_bio_bh(io->io_bio, bh))) { submit_and_retry: ext4_io_submit(io); } @@ -506,7 +508,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, * (e.g. holes) to be unnecessarily encrypted, but this is rare and * can't happen in the common case of blocksize == PAGE_SIZE. */ - if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode) && nr_to_submit) { + if (fscrypt_inode_uses_fs_layer_crypto(inode) && nr_to_submit) { gfp_t gfp_flags = GFP_NOFS; unsigned int enc_bytes = round_up(len, i_blocksize(inode)); diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 5761e9961682..f2df2db0786c 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -195,7 +195,7 @@ static void ext4_set_bio_post_read_ctx(struct bio *bio, { unsigned int post_read_steps = 0; - if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) + if (fscrypt_inode_uses_fs_layer_crypto(inode)) post_read_steps |= 1 << STEP_DECRYPT; if (ext4_need_verity(inode, first_idx)) @@ -230,6 +230,7 @@ int ext4_mpage_readpages(struct inode *inode, const unsigned blkbits = inode->i_blkbits; const unsigned blocks_per_page = PAGE_SIZE >> blkbits; const unsigned blocksize = 1 << blkbits; + sector_t next_block; sector_t block_in_file; sector_t last_block; sector_t last_block_in_file; @@ -258,7 +259,8 @@ int ext4_mpage_readpages(struct inode *inode, if (page_has_buffers(page)) goto confused; - block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); + block_in_file = next_block = + (sector_t)page->index << (PAGE_SHIFT - blkbits); last_block = block_in_file + nr_pages * blocks_per_page; last_block_in_file = (ext4_readpage_limit(inode) + blocksize - 1) >> blkbits; @@ -358,7 +360,8 @@ int ext4_mpage_readpages(struct inode *inode, * This page will go to BIO. Do we need to send this * BIO off first? */ - if (bio && (last_block_in_bio != blocks[0] - 1)) { + if (bio && (last_block_in_bio != blocks[0] - 1 || + !fscrypt_mergeable_bio(bio, inode, next_block))) { submit_and_realloc: submit_bio(bio); bio = NULL; @@ -370,6 +373,8 @@ int ext4_mpage_readpages(struct inode *inode, */ bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES)); + fscrypt_set_bio_crypt_ctx(bio, inode, next_block, + GFP_KERNEL); ext4_set_bio_post_read_ctx(bio, inode, page->index); bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 330957ed1f05..0907f907c47d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1508,6 +1508,7 @@ enum { 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_test_dummy_encryption, + Opt_inlinecrypt, 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, @@ -1610,6 +1611,7 @@ static const match_table_t tokens = { {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, {Opt_test_dummy_encryption, "test_dummy_encryption=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption"}, + {Opt_inlinecrypt, "inlinecrypt"}, {Opt_nombcache, "nombcache"}, {Opt_nombcache, "no_mbcache"}, /* for backward compatibility */ {Opt_removed, "check=none"}, /* mount option from ext2/3 */ @@ -1946,6 +1948,13 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, case Opt_nolazytime: sb->s_flags &= ~SB_LAZYTIME; return 1; + case Opt_inlinecrypt: +#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT + sb->s_flags |= SB_INLINECRYPT; +#else + ext4_msg(sb, KERN_ERR, "inline encryption not supported"); +#endif + return 1; } for (m = ext4_mount_opts; m->token != Opt_err; m++) @@ -2404,6 +2413,9 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, fscrypt_show_test_dummy_encryption(seq, sep, sb); + if (sb->s_flags & SB_INLINECRYPT) + SEQ_OPTS_PUTS("inlinecrypt"); + if (test_opt(sb, DAX_ALWAYS)) { if (IS_EXT2_SB(sb)) SEQ_OPTS_PUTS("dax"); -- cgit v1.2.3 From 377254b2cd2252c7c3151b113cbdf93a7736c2e9 Mon Sep 17 00:00:00 2001 From: Xianting Tian Date: Fri, 31 Jul 2020 12:10:25 -0400 Subject: fs: prevent BUG_ON in submit_bh_wbc() If a device is hot-removed --- for example, when a physical device is unplugged from pcie slot or a nbd device's network is shutdown --- this can result in a BUG_ON() crash in submit_bh_wbc(). This is because the when the block device dies, the buffer heads will have their Buffer_Mapped flag get cleared, leading to the crash in submit_bh_wbc. We had attempted to work around this problem in commit a17712c8 ("ext4: check superblock mapped prior to committing"). Unfortunately, it's still possible to hit the BUG_ON(!buffer_mapped(bh)) if the device dies between when the work-around check in ext4_commit_super() and when submit_bh_wbh() is finally called: Code path: ext4_commit_super judge if 'buffer_mapped(sbh)' is false, return <== commit a17712c8 lock_buffer(sbh) ... unlock_buffer(sbh) __sync_dirty_buffer(sbh,... lock_buffer(sbh) judge if 'buffer_mapped(sbh))' is false, return <== added by this patch submit_bh(...,sbh) submit_bh_wbc(...,sbh,...) [100722.966497] kernel BUG at fs/buffer.c:3095! <== BUG_ON(!buffer_mapped(bh))' in submit_bh_wbc() [100722.966503] invalid opcode: 0000 [#1] SMP [100722.966566] task: ffff8817e15a9e40 task.stack: ffffc90024744000 [100722.966574] RIP: 0010:submit_bh_wbc+0x180/0x190 [100722.966575] RSP: 0018:ffffc90024747a90 EFLAGS: 00010246 [100722.966576] RAX: 0000000000620005 RBX: ffff8818a80603a8 RCX: 0000000000000000 [100722.966576] RDX: ffff8818a80603a8 RSI: 0000000000020800 RDI: 0000000000000001 [100722.966577] RBP: ffffc90024747ac0 R08: 0000000000000000 R09: ffff88207f94170d [100722.966578] R10: 00000000000437c8 R11: 0000000000000001 R12: 0000000000020800 [100722.966578] R13: 0000000000000001 R14: 000000000bf9a438 R15: ffff88195f333000 [100722.966580] FS: 00007fa2eee27700(0000) GS:ffff88203d840000(0000) knlGS:0000000000000000 [100722.966580] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [100722.966581] CR2: 0000000000f0b008 CR3: 000000201a622003 CR4: 00000000007606e0 [100722.966582] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [100722.966583] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [100722.966583] PKRU: 55555554 [100722.966583] Call Trace: [100722.966588] __sync_dirty_buffer+0x6e/0xd0 [100722.966614] ext4_commit_super+0x1d8/0x290 [ext4] [100722.966626] __ext4_std_error+0x78/0x100 [ext4] [100722.966635] ? __ext4_journal_get_write_access+0xca/0x120 [ext4] [100722.966646] ext4_reserve_inode_write+0x58/0xb0 [ext4] [100722.966655] ? ext4_dirty_inode+0x48/0x70 [ext4] [100722.966663] ext4_mark_inode_dirty+0x53/0x1e0 [ext4] [100722.966671] ? __ext4_journal_start_sb+0x6d/0xf0 [ext4] [100722.966679] ext4_dirty_inode+0x48/0x70 [ext4] [100722.966682] __mark_inode_dirty+0x17f/0x350 [100722.966686] generic_update_time+0x87/0xd0 [100722.966687] touch_atime+0xa9/0xd0 [100722.966690] generic_file_read_iter+0xa09/0xcd0 [100722.966694] ? page_cache_tree_insert+0xb0/0xb0 [100722.966704] ext4_file_read_iter+0x4a/0x100 [ext4] [100722.966707] ? __inode_security_revalidate+0x4f/0x60 [100722.966709] __vfs_read+0xec/0x160 [100722.966711] vfs_read+0x8c/0x130 [100722.966712] SyS_pread64+0x87/0xb0 [100722.966716] do_syscall_64+0x67/0x1b0 [100722.966719] entry_SYSCALL64_slow_path+0x25/0x25 To address this, add the check of 'buffer_mapped(bh)' to __sync_dirty_buffer(). This also has the benefit of fixing this for other file systems. With this addition, we can drop the workaround in ext4_commit_supper(). [ Commit description rewritten by tytso. ] Signed-off-by: Xianting Tian Link: https://lore.kernel.org/r/1596211825-8750-1-git-send-email-xianting_tian@126.com Signed-off-by: Theodore Ts'o --- fs/buffer.c | 9 +++++++++ fs/ext4/super.c | 7 ------- 2 files changed, 9 insertions(+), 7 deletions(-) (limited to 'fs/buffer.c') diff --git a/fs/buffer.c b/fs/buffer.c index 64fe82ec65ff..75a8849abb5d 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3160,6 +3160,15 @@ int __sync_dirty_buffer(struct buffer_head *bh, int op_flags) WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { + /* + * The bh should be mapped, but it might not be if the + * device was hot-removed. Not much we can do but fail the I/O. + */ + if (!buffer_mapped(bh)) { + unlock_buffer(bh); + return -EIO; + } + get_bh(bh); bh->b_end_io = end_buffer_write_sync; ret = submit_bh(REQ_OP_WRITE, op_flags, bh); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0892d71a52bd..daa94c7f7271 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5235,13 +5235,6 @@ static int ext4_commit_super(struct super_block *sb, int sync) if (!sbh || block_device_ejected(sb)) return error; - /* - * The superblock bh should be mapped, but it might not be if the - * device was hot-removed. Not much we can do but fail the I/O. - */ - if (!buffer_mapped(sbh)) - return error; - /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock -- cgit v1.2.3