From fcced95b6ba2a507a83b8b3e0358a8ac16b13e35 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 15:16:11 +0530 Subject: ext2/dax: Fix ext2_setsize when len is page aligned PAGE_ALIGN(x) macro gives the next highest value which is multiple of pagesize. But if x is already page aligned then it simply returns x. So, if x passed is 0 in dax_zero_range() function, that means the length gets passed as 0 to ->iomap_begin(). In ext2 it then calls ext2_get_blocks -> max_blocks as 0 and hits bug_on here in ext2_get_blocks(). BUG_ON(maxblocks == 0); Instead we should be calling dax_truncate_page() here which takes care of it. i.e. it only calls dax_zero_range if the offset is not page/block aligned. This can be easily triggered with following on fsdax mounted pmem device. dd if=/dev/zero of=file count=1 bs=512 truncate -s 0 file [79.525838] EXT2-fs (pmem0): DAX enabled. Warning: EXPERIMENTAL, use at your own risk [79.529376] ext2 filesystem being mounted at /mnt1/test supports timestamps until 2038 (0x7fffffff) [93.793207] ------------[ cut here ]------------ [93.795102] kernel BUG at fs/ext2/inode.c:637! [93.796904] invalid opcode: 0000 [#1] PREEMPT SMP PTI [93.798659] CPU: 0 PID: 1192 Comm: truncate Not tainted 6.3.0-rc2-xfstests-00056-g131086faa369 #139 [93.806459] RIP: 0010:ext2_get_blocks.constprop.0+0x524/0x610 <...> [93.835298] Call Trace: [93.836253] [93.837103] ? lock_acquire+0xf8/0x110 [93.838479] ? d_lookup+0x69/0xd0 [93.839779] ext2_iomap_begin+0xa7/0x1c0 [93.841154] iomap_iter+0xc7/0x150 [93.842425] dax_zero_range+0x6e/0xa0 [93.843813] ext2_setsize+0x176/0x1b0 [93.845164] ext2_setattr+0x151/0x200 [93.846467] notify_change+0x341/0x4e0 [93.847805] ? lock_acquire+0xf8/0x110 [93.849143] ? do_truncate+0x74/0xe0 [93.850452] ? do_truncate+0x84/0xe0 [93.851739] do_truncate+0x84/0xe0 [93.852974] do_sys_ftruncate+0x2b4/0x2f0 [93.854404] do_syscall_64+0x3f/0x90 [93.855789] entry_SYSCALL_64_after_hwframe+0x72/0xdc CC: stable@vger.kernel.org Fixes: 2aa3048e03d3 ("iomap: switch iomap_zero_range to use iomap_iter") Reviewed-by: Darrick J. Wong Signed-off-by: Ritesh Harjani (IBM) Signed-off-by: Jan Kara Message-Id: <046a58317f29d9603d1068b2bbae47c2332c17ae.1682069716.git.ritesh.list@gmail.com> --- fs/ext2/inode.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'fs/ext2') diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 26f135e7ffce..dc76147e7b07 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1259,9 +1259,8 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) inode_dio_wait(inode); if (IS_DAX(inode)) - error = dax_zero_range(inode, newsize, - PAGE_ALIGN(newsize) - newsize, NULL, - &ext2_iomap_ops); + error = dax_truncate_page(inode, newsize, NULL, + &ext2_iomap_ops); else error = block_truncate_page(inode->i_mapping, newsize, ext2_get_block); -- cgit v1.2.3 From d05307042500e3f2c06fc2f9e76e8db31d61c7c0 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 15:16:14 +0530 Subject: ext2: Use generic_buffers_fsync() implementation Next patch converts ext2 to use iomap interface for DIO. iomap layer can call generic_write_sync() -> ext2_fsync() from iomap_dio_complete while still holding the inode_lock(). Now writeback from other paths doesn't need inode_lock(). It seems there is also no need of an inode_lock() for sync_mapping_buffers(). It uses it's own mapping->private_lock for it's buffer list handling. Hence this patch is in preparation to move ext2 to iomap. This uses generic_buffers_fsync() which does not take any inode_lock() in ext2_fsync(). Tested-by: Disha Goel Signed-off-by: Ritesh Harjani (IBM) Signed-off-by: Jan Kara Message-Id: <76d206a464574ff91db25bc9e43479b51ca7e307.1682069716.git.ritesh.list@gmail.com> --- fs/ext2/file.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/ext2') diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 6b4bebe982ca..749163787139 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "ext2.h" #include "xattr.h" #include "acl.h" @@ -153,7 +154,7 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync) int ret; struct super_block *sb = file->f_mapping->host->i_sb; - ret = generic_file_fsync(file, start, end, datasync); + ret = generic_buffers_fsync(file, start, end, datasync); if (ret == -EIO) /* We don't really know where the IO error happened... */ ext2_error(sb, __func__, -- cgit v1.2.3 From fb5de4358e1aa4753dce73c4dc1aca73ff39cedd Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 15:16:15 +0530 Subject: ext2: Move direct-io to use iomap This patch converts ext2 direct-io path to iomap interface. - This also takes care of DIO_SKIP_HOLES part in which we return -ENOTBLK from ext2_iomap_begin(), in case if the write is done on a hole. - This fallbacks to buffered-io in case of DIO_SKIP_HOLES or in case of a partial write or if any error is detected in ext2_iomap_end(). We try to return -ENOTBLK in such cases. - For any unaligned or extending DIO writes, we pass IOMAP_DIO_FORCE_WAIT flag to ensure synchronous writes. - For extending writes we set IOMAP_F_DIRTY in ext2_iomap_begin because otherwise with dsync writes on devices that support FUA, generic_write_sync won't be called and we might miss inode metadata updates. - Since ext2 already now uses _nolock vartiant of sync write. Hence there is no inode lock problem with iomap in this patch. - ext2_iomap_ops are now being shared by DIO, DAX & fiemap path Tested-by: Disha Goel Reviewed-by: Christoph Hellwig Signed-off-by: Ritesh Harjani (IBM) Signed-off-by: Jan Kara Message-Id: <610b672a52f2a7ff6dc550fd14d0f995806232a5.1682069716.git.ritesh.list@gmail.com> --- fs/ext2/ext2.h | 1 + fs/ext2/file.c | 115 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ fs/ext2/inode.c | 53 ++++++++++++++++---------- 3 files changed, 150 insertions(+), 19 deletions(-) (limited to 'fs/ext2') diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 8244366862e4..d0531d4ef499 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -754,6 +754,7 @@ extern unsigned long ext2_count_free (struct buffer_head *, unsigned); extern struct inode *ext2_iget (struct super_block *, unsigned long); extern int ext2_write_inode (struct inode *, struct writeback_control *); extern void ext2_evict_inode(struct inode *); +void ext2_write_failed(struct address_space *mapping, loff_t to); extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int); extern int ext2_setattr (struct mnt_idmap *, struct dentry *, struct iattr *); extern int ext2_getattr (struct mnt_idmap *, const struct path *, diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 749163787139..98add36c1a59 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -162,12 +162,124 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync) return ret; } +static ssize_t ext2_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + ssize_t ret; + + inode_lock_shared(inode); + ret = iomap_dio_rw(iocb, to, &ext2_iomap_ops, NULL, 0, NULL, 0); + inode_unlock_shared(inode); + + return ret; +} + +static int ext2_dio_write_end_io(struct kiocb *iocb, ssize_t size, + int error, unsigned int flags) +{ + loff_t pos = iocb->ki_pos; + struct inode *inode = file_inode(iocb->ki_filp); + + if (error) + goto out; + + /* + * If we are extending the file, we have to update i_size here before + * page cache gets invalidated in iomap_dio_rw(). This prevents racing + * buffered reads from zeroing out too much from page cache pages. + * Note that all extending writes always happens synchronously with + * inode lock held by ext2_dio_write_iter(). So it is safe to update + * inode size here for extending file writes. + */ + pos += size; + if (pos > i_size_read(inode)) { + i_size_write(inode, pos); + mark_inode_dirty(inode); + } +out: + return error; +} + +static const struct iomap_dio_ops ext2_dio_write_ops = { + .end_io = ext2_dio_write_end_io, +}; + +static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + ssize_t ret; + unsigned int flags = 0; + unsigned long blocksize = inode->i_sb->s_blocksize; + loff_t offset = iocb->ki_pos; + loff_t count = iov_iter_count(from); + + inode_lock(inode); + ret = generic_write_checks(iocb, from); + if (ret <= 0) + goto out_unlock; + + ret = kiocb_modified(iocb); + if (ret) + goto out_unlock; + + /* use IOMAP_DIO_FORCE_WAIT for unaligned or extending writes */ + if (iocb->ki_pos + iov_iter_count(from) > i_size_read(inode) || + (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(from), blocksize))) + flags |= IOMAP_DIO_FORCE_WAIT; + + ret = iomap_dio_rw(iocb, from, &ext2_iomap_ops, &ext2_dio_write_ops, + flags, NULL, 0); + + /* ENOTBLK is magic return value for fallback to buffered-io */ + if (ret == -ENOTBLK) + ret = 0; + + if (ret < 0 && ret != -EIOCBQUEUED) + ext2_write_failed(inode->i_mapping, offset + count); + + /* handle case for partial write and for fallback to buffered write */ + if (ret >= 0 && iov_iter_count(from)) { + loff_t pos, endbyte; + ssize_t status; + int ret2; + + iocb->ki_flags &= ~IOCB_DIRECT; + pos = iocb->ki_pos; + status = generic_perform_write(iocb, from); + if (unlikely(status < 0)) { + ret = status; + goto out_unlock; + } + + iocb->ki_pos += status; + ret += status; + endbyte = pos + status - 1; + ret2 = filemap_write_and_wait_range(inode->i_mapping, pos, + endbyte); + if (!ret2) + invalidate_mapping_pages(inode->i_mapping, + pos >> PAGE_SHIFT, + endbyte >> PAGE_SHIFT); + if (ret > 0) + generic_write_sync(iocb, ret); + } + +out_unlock: + inode_unlock(inode); + return ret; +} + static ssize_t ext2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { #ifdef CONFIG_FS_DAX if (IS_DAX(iocb->ki_filp->f_mapping->host)) return ext2_dax_read_iter(iocb, to); #endif + if (iocb->ki_flags & IOCB_DIRECT) + return ext2_dio_read_iter(iocb, to); + return generic_file_read_iter(iocb, to); } @@ -177,6 +289,9 @@ static ssize_t ext2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (IS_DAX(iocb->ki_filp->f_mapping->host)) return ext2_dax_write_iter(iocb, from); #endif + if (iocb->ki_flags & IOCB_DIRECT) + return ext2_dio_write_iter(iocb, from); + return generic_file_write_iter(iocb, from); } diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index dc76147e7b07..75983215c7a1 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -56,7 +56,7 @@ static inline int ext2_inode_is_fast_symlink(struct inode *inode) static void ext2_truncate_blocks(struct inode *inode, loff_t offset); -static void ext2_write_failed(struct address_space *mapping, loff_t to) +void ext2_write_failed(struct address_space *mapping, loff_t to) { struct inode *inode = mapping->host; @@ -809,9 +809,27 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length, bool new = false, boundary = false; u32 bno; int ret; + bool create = flags & IOMAP_WRITE; + + /* + * For writes that could fill holes inside i_size on a + * DIO_SKIP_HOLES filesystem we forbid block creations: only + * overwrites are permitted. + */ + if ((flags & IOMAP_DIRECT) && + (first_block << blkbits) < i_size_read(inode)) + create = 0; + + /* + * Writes that span EOF might trigger an IO size update on completion, + * so consider them to be dirty for the purposes of O_DSYNC even if + * there is no other metadata changes pending or have been made here. + */ + if ((flags & IOMAP_WRITE) && offset + length > i_size_read(inode)) + iomap->flags |= IOMAP_F_DIRTY; ret = ext2_get_blocks(inode, first_block, max_blocks, - &bno, &new, &boundary, flags & IOMAP_WRITE); + &bno, &new, &boundary, create); if (ret < 0) return ret; @@ -823,6 +841,12 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->bdev = inode->i_sb->s_bdev; if (ret == 0) { + /* + * Switch to buffered-io for writing to holes in a non-extent + * based filesystem to avoid stale data exposure problem. + */ + if (!create && (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT)) + return -ENOTBLK; iomap->type = IOMAP_HOLE; iomap->addr = IOMAP_NULL_ADDR; iomap->length = 1 << blkbits; @@ -844,6 +868,13 @@ static int ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length, ssize_t written, unsigned flags, struct iomap *iomap) { + /* + * Switch to buffered-io in case of any error. + * Blocks allocated can be used by the buffered-io path. + */ + if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE) && written == 0) + return -ENOTBLK; + if (iomap->type == IOMAP_MAPPED && written < length && (flags & IOMAP_WRITE)) @@ -908,22 +939,6 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping,block,ext2_get_block); } -static ssize_t -ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) -{ - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - size_t count = iov_iter_count(iter); - loff_t offset = iocb->ki_pos; - ssize_t ret; - - ret = blockdev_direct_IO(iocb, inode, iter, ext2_get_block); - if (ret < 0 && iov_iter_rw(iter) == WRITE) - ext2_write_failed(mapping, offset + count); - return ret; -} - static int ext2_writepages(struct address_space *mapping, struct writeback_control *wbc) { @@ -946,7 +961,7 @@ const struct address_space_operations ext2_aops = { .write_begin = ext2_write_begin, .write_end = ext2_write_end, .bmap = ext2_bmap, - .direct_IO = ext2_direct_IO, + .direct_IO = noop_direct_IO, .writepages = ext2_writepages, .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, -- cgit v1.2.3 From 6e335cd789bee7a7111c4fe6d46b1d63cde81511 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 15:16:17 +0530 Subject: ext2: Add direct-io trace points This patch adds the trace point to ext2 direct-io apis in fs/ext2/file.c Here is how the output looks like a.out-467865 [006] 6758.170968: ext2_dio_write_begin: dev 7:12 ino 0xe isize 0x1000 pos 0x0 len 4096 flags DIRECT|WRITE aio 1 ret 0 a.out-467865 [006] 6758.171061: ext2_dio_write_end: dev 7:12 ino 0xe isize 0x1000 pos 0x0 len 0 flags DIRECT|WRITE aio 1 ret -529 kworker/3:153-444162 [003] 6758.171252: ext2_dio_write_endio: dev 7:12 ino 0xe isize 0x1000 pos 0x0 len 4096 flags DIRECT|WRITE aio 1 ret 0 a.out-468222 [001] 6761.628924: ext2_dio_read_begin: dev 7:12 ino 0xe isize 0x1000 pos 0x0 len 4096 flags DIRECT aio 1 ret 0 a.out-468222 [001] 6761.629063: ext2_dio_read_end: dev 7:12 ino 0xe isize 0x1000 pos 0x0 len 0 flags DIRECT aio 1 ret -529 a.out-468428 [005] 6763.937454: ext2_dio_write_begin: dev 7:12 ino 0xe isize 0x1000 pos 0x0 len 4096 flags DIRECT aio 0 ret 0 a.out-468428 [005] 6763.937829: ext2_dio_write_endio: dev 7:12 ino 0xe isize 0x1000 pos 0x0 len 4096 flags DIRECT aio 0 ret 0 a.out-468428 [005] 6763.937847: ext2_dio_write_end: dev 7:12 ino 0xe isize 0x1000 pos 0x1000 len 0 flags DIRECT aio 0 ret 4096 a.out-468609 [000] 6765.702878: ext2_dio_read_begin: dev 7:12 ino 0xe isize 0x1000 pos 0x0 len 4096 flags DIRECT aio 0 ret 0 a.out-468609 [000] 6765.703243: ext2_dio_read_end: dev 7:12 ino 0xe isize 0x1000 pos 0x1000 len 0 flags DIRECT aio 0 ret 4096 Reported-and-tested-by: Disha Goel [Need to add CFLAGS_trace for fixing unable to find trace file problem] Signed-off-by: Ritesh Harjani (IBM) Signed-off-by: Jan Kara Message-Id: --- fs/ext2/Makefile | 5 ++- fs/ext2/file.c | 10 +++++- fs/ext2/trace.c | 6 ++++ fs/ext2/trace.h | 94 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 113 insertions(+), 2 deletions(-) create mode 100644 fs/ext2/trace.c create mode 100644 fs/ext2/trace.h (limited to 'fs/ext2') diff --git a/fs/ext2/Makefile b/fs/ext2/Makefile index 311479d864a7..8860948ef9ca 100644 --- a/fs/ext2/Makefile +++ b/fs/ext2/Makefile @@ -6,7 +6,10 @@ obj-$(CONFIG_EXT2_FS) += ext2.o ext2-y := balloc.o dir.o file.o ialloc.o inode.o \ - ioctl.o namei.o super.o symlink.o + ioctl.o namei.o super.o symlink.o trace.o + +# For tracepoints to include our trace.h from tracepoint infrastructure +CFLAGS_trace.o := -I$(src) ext2-$(CONFIG_EXT2_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o ext2-$(CONFIG_EXT2_FS_POSIX_ACL) += acl.o diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 98add36c1a59..7a32f202908e 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -29,6 +29,7 @@ #include "ext2.h" #include "xattr.h" #include "acl.h" +#include "trace.h" #ifdef CONFIG_FS_DAX static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to) @@ -168,9 +169,11 @@ static ssize_t ext2_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) struct inode *inode = file->f_mapping->host; ssize_t ret; + trace_ext2_dio_read_begin(iocb, to, 0); inode_lock_shared(inode); ret = iomap_dio_rw(iocb, to, &ext2_iomap_ops, NULL, 0, NULL, 0); inode_unlock_shared(inode); + trace_ext2_dio_read_end(iocb, to, ret); return ret; } @@ -198,6 +201,7 @@ static int ext2_dio_write_end_io(struct kiocb *iocb, ssize_t size, mark_inode_dirty(inode); } out: + trace_ext2_dio_write_endio(iocb, size, error); return error; } @@ -214,7 +218,9 @@ static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) unsigned long blocksize = inode->i_sb->s_blocksize; loff_t offset = iocb->ki_pos; loff_t count = iov_iter_count(from); + ssize_t status = 0; + trace_ext2_dio_write_begin(iocb, from, 0); inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret <= 0) @@ -242,7 +248,6 @@ static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) /* handle case for partial write and for fallback to buffered write */ if (ret >= 0 && iov_iter_count(from)) { loff_t pos, endbyte; - ssize_t status; int ret2; iocb->ki_flags &= ~IOCB_DIRECT; @@ -268,6 +273,9 @@ static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) out_unlock: inode_unlock(inode); + if (status) + trace_ext2_dio_write_buff_end(iocb, from, status); + trace_ext2_dio_write_end(iocb, from, ret); return ret; } diff --git a/fs/ext2/trace.c b/fs/ext2/trace.c new file mode 100644 index 000000000000..b01cdf6526fd --- /dev/null +++ b/fs/ext2/trace.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "ext2.h" +#include + +#define CREATE_TRACE_POINTS +#include "trace.h" diff --git a/fs/ext2/trace.h b/fs/ext2/trace.h new file mode 100644 index 000000000000..7d230e13576e --- /dev/null +++ b/fs/ext2/trace.h @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0 + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM ext2 + +#if !defined(_EXT2_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _EXT2_TRACE_H + +#include + +DECLARE_EVENT_CLASS(ext2_dio_class, + TP_PROTO(struct kiocb *iocb, struct iov_iter *iter, ssize_t ret), + TP_ARGS(iocb, iter, ret), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, isize) + __field(loff_t, pos) + __field(size_t, count) + __field(int, ki_flags) + __field(bool, aio) + __field(ssize_t, ret) + ), + TP_fast_assign( + __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; + __entry->ino = file_inode(iocb->ki_filp)->i_ino; + __entry->isize = file_inode(iocb->ki_filp)->i_size; + __entry->pos = iocb->ki_pos; + __entry->count = iov_iter_count(iter); + __entry->ki_flags = iocb->ki_flags; + __entry->aio = !is_sync_kiocb(iocb); + __entry->ret = ret; + ), + TP_printk("dev %d:%d ino 0x%lx isize 0x%llx pos 0x%llx len %zu flags %s aio %d ret %zd", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->isize, + __entry->pos, + __entry->count, + __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), + __entry->aio, + __entry->ret) +); + +#define DEFINE_DIO_RW_EVENT(name) \ +DEFINE_EVENT(ext2_dio_class, name, \ + TP_PROTO(struct kiocb *iocb, struct iov_iter *iter, ssize_t ret), \ + TP_ARGS(iocb, iter, ret)) +DEFINE_DIO_RW_EVENT(ext2_dio_write_begin); +DEFINE_DIO_RW_EVENT(ext2_dio_write_end); +DEFINE_DIO_RW_EVENT(ext2_dio_write_buff_end); +DEFINE_DIO_RW_EVENT(ext2_dio_read_begin); +DEFINE_DIO_RW_EVENT(ext2_dio_read_end); + +TRACE_EVENT(ext2_dio_write_endio, + TP_PROTO(struct kiocb *iocb, ssize_t size, int ret), + TP_ARGS(iocb, size, ret), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, isize) + __field(loff_t, pos) + __field(ssize_t, size) + __field(int, ki_flags) + __field(bool, aio) + __field(int, ret) + ), + TP_fast_assign( + __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; + __entry->ino = file_inode(iocb->ki_filp)->i_ino; + __entry->isize = file_inode(iocb->ki_filp)->i_size; + __entry->pos = iocb->ki_pos; + __entry->size = size; + __entry->ki_flags = iocb->ki_flags; + __entry->aio = !is_sync_kiocb(iocb); + __entry->ret = ret; + ), + TP_printk("dev %d:%d ino 0x%lx isize 0x%llx pos 0x%llx len %zd flags %s aio %d ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->isize, + __entry->pos, + __entry->size, + __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), + __entry->aio, + __entry->ret) +); + +#endif /* _EXT2_TRACE_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace +#include -- cgit v1.2.3 From 8f1dca19b1e11785f42e70da796942154f63aef9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 11 Jan 2023 15:21:52 -0500 Subject: ext2_rename(): set_link and delete_entry may fail Signed-off-by: Al Viro Reviewed-by: Fabio M. De Francesco Tested-by: Fabio M. De Francesco Signed-off-by: Jan Kara --- fs/ext2/dir.c | 12 ++++++------ fs/ext2/namei.c | 29 ++++++++++------------------- 2 files changed, 16 insertions(+), 25 deletions(-) (limited to 'fs/ext2') diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 4a6955a0a116..a3c77ea5a7de 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -606,8 +606,7 @@ int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page, if (de->rec_len == 0) { ext2_error(inode->i_sb, __func__, "zero-length directory entry"); - err = -EIO; - goto out; + return -EIO; } pde = de; de = ext2_next_entry(de); @@ -617,7 +616,10 @@ int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page, pos = page_offset(page) + from; lock_page(page); err = ext2_prepare_chunk(page, pos, to - from); - BUG_ON(err); + if (err) { + unlock_page(page); + return err; + } if (pde) pde->rec_len = ext2_rec_len_to_disk(to - from); dir->inode = 0; @@ -625,9 +627,7 @@ int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page, inode->i_ctime = inode->i_mtime = current_time(inode); EXT2_I(inode)->i_flags &= ~EXT2_BTREE_FL; mark_inode_dirty(inode); - err = ext2_handle_dirsync(inode); -out: - return err; + return ext2_handle_dirsync(inode); } /* diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 7f5dfa87cc95..dafdd2d41876 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -335,18 +335,16 @@ static int ext2_rename (struct mnt_idmap * idmap, err = dquot_initialize(old_dir); if (err) - goto out; + return err; err = dquot_initialize(new_dir); if (err) - goto out; + return err; old_de = ext2_find_entry(old_dir, &old_dentry->d_name, &old_page, &old_page_addr); - if (IS_ERR(old_de)) { - err = PTR_ERR(old_de); - goto out; - } + if (IS_ERR(old_de)) + return PTR_ERR(old_de); if (S_ISDIR(old_inode->i_mode)) { err = -EIO; @@ -394,27 +392,20 @@ static int ext2_rename (struct mnt_idmap * idmap, old_inode->i_ctime = current_time(old_inode); mark_inode_dirty(old_inode); - ext2_delete_entry(old_de, old_page, old_page_addr); - - if (dir_de) { - if (old_dir != new_dir) { + err = ext2_delete_entry(old_de, old_page, old_page_addr); + if (!err && dir_de) { + if (old_dir != new_dir) err = ext2_set_link(old_inode, dir_de, dir_page, dir_page_addr, new_dir, false); - } - ext2_put_page(dir_page, dir_page_addr); inode_dec_link_count(old_dir); } - -out_old: - ext2_put_page(old_page, old_page_addr); -out: - return err; - out_dir: if (dir_de) ext2_put_page(dir_page, dir_page_addr); - goto out_old; +out_old: + ext2_put_page(old_page, old_page_addr); + return err; } const struct inode_operations ext2_dir_inode_operations = { -- cgit v1.2.3 From 86008392695bd7a910b9d1452c828f9c7d1a6a1f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 13 Dec 2022 20:26:27 -0500 Subject: ext2: use offset_in_page() instead of open-coding it as subtraction Signed-off-by: Al Viro Reviewed-by: Fabio M. De Francesco Tested-by: Fabio M. De Francesco Signed-off-by: Jan Kara --- fs/ext2/dir.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'fs/ext2') diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index a3c77ea5a7de..5141ec6a6b51 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -240,7 +240,7 @@ ext2_validate_entry(char *base, unsigned offset, unsigned mask) break; p = ext2_next_entry(p); } - return (char *)p - base; + return offset_in_page(p); } static inline void ext2_set_de_type(ext2_dirent *de, struct inode *inode) @@ -465,8 +465,7 @@ int ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de, struct page *page, void *page_addr, struct inode *inode, bool update_times) { - loff_t pos = page_offset(page) + - (char *) de - (char *) page_addr; + loff_t pos = page_offset(page) + offset_in_page(de); unsigned len = ext2_rec_len_from_disk(de->rec_len); int err; @@ -556,8 +555,7 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode) return -EINVAL; got_it: - pos = page_offset(page) + - (char *)de - (char *)page_addr; + pos = page_offset(page) + offset_in_page(de); err = ext2_prepare_chunk(page, pos, rec_len); if (err) goto out_unlock; @@ -594,8 +592,8 @@ int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page, char *kaddr) { struct inode *inode = page->mapping->host; - unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1); - unsigned to = ((char *)dir - kaddr) + + unsigned from = offset_in_page(dir) & ~(ext2_chunk_size(inode)-1); + unsigned to = offset_in_page(dir) + ext2_rec_len_from_disk(dir->rec_len); loff_t pos; ext2_dirent * pde = NULL; @@ -612,7 +610,7 @@ int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page, de = ext2_next_entry(de); } if (pde) - from = (char *)pde - kaddr; + from = offset_in_page(pde); pos = page_offset(page) + from; lock_page(page); err = ext2_prepare_chunk(page, pos, to - from); -- cgit v1.2.3 From 46022375abe8160b6c952a2ca0ea7988be6b888d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 13 Dec 2022 20:07:28 -0500 Subject: ext2_get_page(): saner type We need to pass to caller both the page reference and pointer to the first byte in the now-mapped page. The former always has the same type, the latter varies from caller to caller. So make it void *ext2_get_page(...., struct page **page) rather than struct page *ext2_get_page(..., void **page_addr) and avoid the casts... Signed-off-by: Al Viro Reviewed-by: Fabio M. De Francesco Tested-by: Fabio M. De Francesco Signed-off-by: Jan Kara --- fs/ext2/dir.c | 50 +++++++++++++++++++++++++------------------------- 1 file changed, 25 insertions(+), 25 deletions(-) (limited to 'fs/ext2') diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 5141ec6a6b51..75c8f8037a40 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -186,23 +186,25 @@ fail: * NOTE: ext2_find_entry() and ext2_dotdot() act as a call to ext2_get_page() * and should be treated as a call to ext2_get_page() for nesting purposes. */ -static struct page * ext2_get_page(struct inode *dir, unsigned long n, - int quiet, void **page_addr) +static void *ext2_get_page(struct inode *dir, unsigned long n, + int quiet, struct page **page) { struct address_space *mapping = dir->i_mapping; struct folio *folio = read_mapping_folio(mapping, n, NULL); + void *page_addr; if (IS_ERR(folio)) - return &folio->page; - *page_addr = kmap_local_folio(folio, n & (folio_nr_pages(folio) - 1)); + return ERR_CAST(folio); + page_addr = kmap_local_folio(folio, n & (folio_nr_pages(folio) - 1)); if (unlikely(!folio_test_checked(folio))) { - if (!ext2_check_page(&folio->page, quiet, *page_addr)) + if (!ext2_check_page(&folio->page, quiet, page_addr)) goto fail; } - return &folio->page; + *page = &folio->page; + return page_addr; fail: - ext2_put_page(&folio->page, *page_addr); + ext2_put_page(&folio->page, page_addr); return ERR_PTR(-EIO); } @@ -271,16 +273,17 @@ ext2_readdir(struct file *file, struct dir_context *ctx) EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_FILETYPE); for ( ; n < npages; n++, offset = 0) { - char *kaddr, *limit; ext2_dirent *de; - struct page *page = ext2_get_page(inode, n, 0, (void **)&kaddr); + struct page *page; + char *kaddr = ext2_get_page(inode, n, 0, &page); + char *limit; - if (IS_ERR(page)) { + if (IS_ERR(kaddr)) { ext2_error(sb, __func__, "bad page in #%lu", inode->i_ino); ctx->pos += PAGE_SIZE - offset; - return PTR_ERR(page); + return PTR_ERR(kaddr); } if (unlikely(need_revalidate)) { if (offset) { @@ -362,9 +365,10 @@ struct ext2_dir_entry_2 *ext2_find_entry (struct inode *dir, n = start; do { char *kaddr; - page = ext2_get_page(dir, n, 0, &page_addr); - if (IS_ERR(page)) - return ERR_CAST(page); + + page_addr = ext2_get_page(dir, n, 0, &page); + if (IS_ERR(page_addr)) + return ERR_CAST(page_addr); kaddr = page_addr; de = (ext2_dirent *) kaddr; @@ -418,13 +422,11 @@ found: struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p, void **pa) { - void *page_addr; - struct page *page = ext2_get_page(dir, 0, 0, &page_addr); + void *page_addr = ext2_get_page(dir, 0, 0, p); ext2_dirent *de = NULL; - if (!IS_ERR(page)) { + if (!IS_ERR(page_addr)) { de = ext2_next_entry((ext2_dirent *) page_addr); - *p = page; *pa = page_addr; } return de; @@ -513,10 +515,9 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode) char *kaddr; char *dir_end; - page = ext2_get_page(dir, n, 0, &page_addr); - err = PTR_ERR(page); - if (IS_ERR(page)) - goto out; + page_addr = ext2_get_page(dir, n, 0, &page); + if (IS_ERR(page_addr)) + return PTR_ERR(page_addr); lock_page(page); kaddr = page_addr; dir_end = kaddr + ext2_last_byte(dir, n); @@ -577,7 +578,6 @@ got_it: /* OFFSET_CACHE */ out_put: ext2_put_page(page, page_addr); -out: return err; out_unlock: unlock_page(page); @@ -682,9 +682,9 @@ int ext2_empty_dir (struct inode * inode) for (i = 0; i < npages; i++) { char *kaddr; ext2_dirent * de; - page = ext2_get_page(inode, i, 0, &page_addr); + page_addr = ext2_get_page(inode, i, 0, &page); - if (IS_ERR(page)) + if (IS_ERR(page_addr)) return 0; kaddr = page_addr; -- cgit v1.2.3 From 91f646fb971f4401216a2dff5c568bcbce79a923 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 13 Dec 2022 20:14:50 -0500 Subject: ext2_put_page(): accept any pointer within the page eliminates the need to keep the pointer to the first byte within the page if we are guaranteed to have pointers to some byte in the same page at hand. Don't backport without commit 88d7b12068b9 ("highmem: round down the address passed to kunmap_flush_on_unmap()"). Signed-off-by: Al Viro Reviewed-by: Fabio M. De Francesco Tested-by: Fabio M. De Francesco Signed-off-by: Jan Kara --- fs/ext2/dir.c | 38 +++++++++++++++++--------------------- fs/ext2/namei.c | 8 ++++---- 2 files changed, 21 insertions(+), 25 deletions(-) (limited to 'fs/ext2') diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 75c8f8037a40..31b2aab94da0 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -299,7 +299,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx) if (de->rec_len == 0) { ext2_error(sb, __func__, "zero-length directory entry"); - ext2_put_page(page, kaddr); + ext2_put_page(page, de); return -EIO; } if (de->inode) { @@ -311,7 +311,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx) if (!dir_emit(ctx, de->name, de->name_len, le32_to_cpu(de->inode), d_type)) { - ext2_put_page(page, kaddr); + ext2_put_page(page, de); return 0; } } @@ -377,14 +377,14 @@ struct ext2_dir_entry_2 *ext2_find_entry (struct inode *dir, if (de->rec_len == 0) { ext2_error(dir->i_sb, __func__, "zero-length directory entry"); - ext2_put_page(page, page_addr); + ext2_put_page(page, de); goto out; } if (ext2_match(namelen, name, de)) goto found; de = ext2_next_entry(de); } - ext2_put_page(page, page_addr); + ext2_put_page(page, kaddr); if (++n >= npages) n = 0; @@ -443,7 +443,7 @@ int ext2_inode_by_name(struct inode *dir, const struct qstr *child, ino_t *ino) return PTR_ERR(de); *ino = le32_to_cpu(de->inode); - ext2_put_page(page, page_addr); + ext2_put_page(page, de); return 0; } @@ -499,7 +499,6 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode) unsigned reclen = EXT2_DIR_REC_LEN(namelen); unsigned short rec_len, name_len; struct page *page = NULL; - void *page_addr = NULL; ext2_dirent * de; unsigned long npages = dir_pages(dir); unsigned long n; @@ -515,11 +514,10 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode) char *kaddr; char *dir_end; - page_addr = ext2_get_page(dir, n, 0, &page); - if (IS_ERR(page_addr)) - return PTR_ERR(page_addr); + kaddr = ext2_get_page(dir, n, 0, &page); + if (IS_ERR(kaddr)) + return PTR_ERR(kaddr); lock_page(page); - kaddr = page_addr; dir_end = kaddr + ext2_last_byte(dir, n); de = (ext2_dirent *)kaddr; kaddr += PAGE_SIZE - reclen; @@ -550,7 +548,7 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode) de = (ext2_dirent *) ((char *) de + rec_len); } unlock_page(page); - ext2_put_page(page, page_addr); + ext2_put_page(page, kaddr); } BUG(); return -EINVAL; @@ -577,7 +575,7 @@ got_it: err = ext2_handle_dirsync(dir); /* OFFSET_CACHE */ out_put: - ext2_put_page(page, page_addr); + ext2_put_page(page, de); return err; out_unlock: unlock_page(page); @@ -675,19 +673,17 @@ fail: */ int ext2_empty_dir (struct inode * inode) { - void *page_addr = NULL; - struct page *page = NULL; + struct page *page; + char *kaddr; unsigned long i, npages = dir_pages(inode); for (i = 0; i < npages; i++) { - char *kaddr; - ext2_dirent * de; - page_addr = ext2_get_page(inode, i, 0, &page); + ext2_dirent *de; - if (IS_ERR(page_addr)) + kaddr = ext2_get_page(inode, i, 0, &page); + if (IS_ERR(kaddr)) return 0; - kaddr = page_addr; de = (ext2_dirent *)kaddr; kaddr += ext2_last_byte(inode, i) - EXT2_DIR_REC_LEN(1); @@ -713,12 +709,12 @@ int ext2_empty_dir (struct inode * inode) } de = ext2_next_entry(de); } - ext2_put_page(page, page_addr); + ext2_put_page(page, kaddr); } return 1; not_empty: - ext2_put_page(page, page_addr); + ext2_put_page(page, kaddr); return 0; } diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index dafdd2d41876..50105d50c48a 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -288,7 +288,7 @@ static int ext2_unlink(struct inode * dir, struct dentry *dentry) } err = ext2_delete_entry (de, page, page_addr); - ext2_put_page(page, page_addr); + ext2_put_page(page, de); if (err) goto out; @@ -370,7 +370,7 @@ static int ext2_rename (struct mnt_idmap * idmap, } err = ext2_set_link(new_dir, new_de, new_page, page_addr, old_inode, true); - ext2_put_page(new_page, page_addr); + ext2_put_page(new_page, new_de); if (err) goto out_dir; new_inode->i_ctime = current_time(new_inode); @@ -402,9 +402,9 @@ static int ext2_rename (struct mnt_idmap * idmap, } out_dir: if (dir_de) - ext2_put_page(dir_page, dir_page_addr); + ext2_put_page(dir_page, dir_de); out_old: - ext2_put_page(old_page, old_page_addr); + ext2_put_page(old_page, old_de); return err; } -- cgit v1.2.3 From dae42837ba6dd441e4a569996d5f62986ffe01ed Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 13 Dec 2022 20:31:39 -0500 Subject: ext2_{set_link,delete_entry}(): don't bother with page_addr ext2_set_link() simply doesn't use it anymore and ext2_delete_entry() can easily obtain it from the directory entry pointer... Signed-off-by: Al Viro Reviewed-by: Fabio M. De Francesco Tested-by: Fabio M. De Francesco Signed-off-by: Jan Kara --- fs/ext2/dir.c | 11 +++++------ fs/ext2/ext2.h | 6 ++---- fs/ext2/namei.c | 9 ++++----- 3 files changed, 11 insertions(+), 15 deletions(-) (limited to 'fs/ext2') diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 31b2aab94da0..8cf91a7bbbb9 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -464,8 +464,7 @@ static int ext2_handle_dirsync(struct inode *dir) } int ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de, - struct page *page, void *page_addr, struct inode *inode, - bool update_times) + struct page *page, struct inode *inode, bool update_times) { loff_t pos = page_offset(page) + offset_in_page(de); unsigned len = ext2_rec_len_from_disk(de->rec_len); @@ -586,16 +585,16 @@ out_unlock: * ext2_delete_entry deletes a directory entry by merging it with the * previous entry. Page is up-to-date. */ -int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page, - char *kaddr) +int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page) { struct inode *inode = page->mapping->host; + char *kaddr = (char *)((unsigned long)dir & PAGE_MASK); unsigned from = offset_in_page(dir) & ~(ext2_chunk_size(inode)-1); unsigned to = offset_in_page(dir) + ext2_rec_len_from_disk(dir->rec_len); loff_t pos; - ext2_dirent * pde = NULL; - ext2_dirent * de = (ext2_dirent *) (kaddr + from); + ext2_dirent *pde = NULL; + ext2_dirent *de = (ext2_dirent *)(kaddr + from); int err; while ((char*)de < (char*)dir) { diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index d0531d4ef499..391edf57b944 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -731,13 +731,11 @@ extern int ext2_inode_by_name(struct inode *dir, extern int ext2_make_empty(struct inode *, struct inode *); extern struct ext2_dir_entry_2 *ext2_find_entry(struct inode *, const struct qstr *, struct page **, void **res_page_addr); -extern int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page, - char *kaddr); +extern int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page); extern int ext2_empty_dir (struct inode *); extern struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p, void **pa); int ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de, - struct page *page, void *page_addr, struct inode *inode, - bool update_times); + struct page *page, struct inode *inode, bool update_times); static inline void ext2_put_page(struct page *page, void *page_addr) { kunmap_local(page_addr); diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 50105d50c48a..3e7f895ac2da 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -287,7 +287,7 @@ static int ext2_unlink(struct inode * dir, struct dentry *dentry) goto out; } - err = ext2_delete_entry (de, page, page_addr); + err = ext2_delete_entry(de, page); ext2_put_page(page, de); if (err) goto out; @@ -368,8 +368,7 @@ static int ext2_rename (struct mnt_idmap * idmap, err = PTR_ERR(new_de); goto out_dir; } - err = ext2_set_link(new_dir, new_de, new_page, page_addr, - old_inode, true); + err = ext2_set_link(new_dir, new_de, new_page, old_inode, true); ext2_put_page(new_page, new_de); if (err) goto out_dir; @@ -392,11 +391,11 @@ static int ext2_rename (struct mnt_idmap * idmap, old_inode->i_ctime = current_time(old_inode); mark_inode_dirty(old_inode); - err = ext2_delete_entry(old_de, old_page, old_page_addr); + err = ext2_delete_entry(old_de, old_page); if (!err && dir_de) { if (old_dir != new_dir) err = ext2_set_link(old_inode, dir_de, dir_page, - dir_page_addr, new_dir, false); + new_dir, false); inode_dec_link_count(old_dir); } -- cgit v1.2.3 From b8b9e8b35d3856499c0b2e8188885257828b7fa5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 13 Dec 2022 20:53:47 -0500 Subject: ext2_find_entry()/ext2_dotdot(): callers don't need page_addr anymore ... and that's how it should've been done in the first place Signed-off-by: Al Viro Reviewed-by: Fabio M. De Francesco Tested-by: Fabio M. De Francesco Signed-off-by: Jan Kara --- fs/ext2/dir.c | 35 +++++++++++------------------------ fs/ext2/ext2.h | 4 ++-- fs/ext2/namei.c | 21 ++++++++------------- 3 files changed, 21 insertions(+), 39 deletions(-) (limited to 'fs/ext2') diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 8cf91a7bbbb9..42db804794bd 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -339,8 +339,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx) * should be treated as a call to ext2_get_page() for nesting purposes. */ struct ext2_dir_entry_2 *ext2_find_entry (struct inode *dir, - const struct qstr *child, struct page **res_page, - void **res_page_addr) + const struct qstr *child, struct page **res_page) { const char *name = child->name; int namelen = child->len; @@ -350,27 +349,22 @@ struct ext2_dir_entry_2 *ext2_find_entry (struct inode *dir, struct page *page = NULL; struct ext2_inode_info *ei = EXT2_I(dir); ext2_dirent * de; - void *page_addr; if (npages == 0) goto out; /* OFFSET_CACHE */ *res_page = NULL; - *res_page_addr = NULL; start = ei->i_dir_start_lookup; if (start >= npages) start = 0; n = start; do { - char *kaddr; - - page_addr = ext2_get_page(dir, n, 0, &page); - if (IS_ERR(page_addr)) - return ERR_CAST(page_addr); + char *kaddr = ext2_get_page(dir, n, 0, &page); + if (IS_ERR(kaddr)) + return ERR_CAST(kaddr); - kaddr = page_addr; de = (ext2_dirent *) kaddr; kaddr += ext2_last_byte(dir, n) - reclen; while ((char *) de <= kaddr) { @@ -402,7 +396,6 @@ out: found: *res_page = page; - *res_page_addr = page_addr; ei->i_dir_start_lookup = n; return de; } @@ -419,26 +412,21 @@ found: * ext2_find_entry() and ext2_dotdot() act as a call to ext2_get_page() and * should be treated as a call to ext2_get_page() for nesting purposes. */ -struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p, - void **pa) +struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p) { - void *page_addr = ext2_get_page(dir, 0, 0, p); - ext2_dirent *de = NULL; + ext2_dirent *de = ext2_get_page(dir, 0, 0, p); - if (!IS_ERR(page_addr)) { - de = ext2_next_entry((ext2_dirent *) page_addr); - *pa = page_addr; - } - return de; + if (!IS_ERR(de)) + return ext2_next_entry(de); + return NULL; } int ext2_inode_by_name(struct inode *dir, const struct qstr *child, ino_t *ino) { struct ext2_dir_entry_2 *de; struct page *page; - void *page_addr; - de = ext2_find_entry(dir, child, &page, &page_addr); + de = ext2_find_entry(dir, child, &page); if (IS_ERR(de)) return PTR_ERR(de); @@ -510,10 +498,9 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode) * to protect that region. */ for (n = 0; n <= npages; n++) { - char *kaddr; + char *kaddr = ext2_get_page(dir, n, 0, &page); char *dir_end; - kaddr = ext2_get_page(dir, n, 0, &page); if (IS_ERR(kaddr)) return PTR_ERR(kaddr); lock_page(page); diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 391edf57b944..5e82ec0847cf 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -730,10 +730,10 @@ extern int ext2_inode_by_name(struct inode *dir, const struct qstr *child, ino_t *ino); extern int ext2_make_empty(struct inode *, struct inode *); extern struct ext2_dir_entry_2 *ext2_find_entry(struct inode *, const struct qstr *, - struct page **, void **res_page_addr); + struct page **); extern int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page); extern int ext2_empty_dir (struct inode *); -extern struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p, void **pa); +extern struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p); int ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de, struct page *page, struct inode *inode, bool update_times); static inline void ext2_put_page(struct page *page, void *page_addr) diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 3e7f895ac2da..937dd8f60f96 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -269,19 +269,18 @@ out_dir: goto out; } -static int ext2_unlink(struct inode * dir, struct dentry *dentry) +static int ext2_unlink(struct inode *dir, struct dentry *dentry) { - struct inode * inode = d_inode(dentry); - struct ext2_dir_entry_2 * de; - struct page * page; - void *page_addr; + struct inode *inode = d_inode(dentry); + struct ext2_dir_entry_2 *de; + struct page *page; int err; err = dquot_initialize(dir); if (err) goto out; - de = ext2_find_entry(dir, &dentry->d_name, &page, &page_addr); + de = ext2_find_entry(dir, &dentry->d_name, &page); if (IS_ERR(de)) { err = PTR_ERR(de); goto out; @@ -323,10 +322,8 @@ static int ext2_rename (struct mnt_idmap * idmap, struct inode * old_inode = d_inode(old_dentry); struct inode * new_inode = d_inode(new_dentry); struct page * dir_page = NULL; - void *dir_page_addr; struct ext2_dir_entry_2 * dir_de = NULL; struct page * old_page; - void *old_page_addr; struct ext2_dir_entry_2 * old_de; int err; @@ -341,20 +338,18 @@ static int ext2_rename (struct mnt_idmap * idmap, if (err) return err; - old_de = ext2_find_entry(old_dir, &old_dentry->d_name, &old_page, - &old_page_addr); + old_de = ext2_find_entry(old_dir, &old_dentry->d_name, &old_page); if (IS_ERR(old_de)) return PTR_ERR(old_de); if (S_ISDIR(old_inode->i_mode)) { err = -EIO; - dir_de = ext2_dotdot(old_inode, &dir_page, &dir_page_addr); + dir_de = ext2_dotdot(old_inode, &dir_page); if (!dir_de) goto out_old; } if (new_inode) { - void *page_addr; struct page *new_page; struct ext2_dir_entry_2 *new_de; @@ -363,7 +358,7 @@ static int ext2_rename (struct mnt_idmap * idmap, goto out_dir; new_de = ext2_find_entry(new_dir, &new_dentry->d_name, - &new_page, &page_addr); + &new_page); if (IS_ERR(new_de)) { err = PTR_ERR(new_de); goto out_dir; -- cgit v1.2.3 From 404615d7f1dcd4cca200e9a7a9df3a1dcae1dd62 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 13 Jun 2023 12:25:52 +0200 Subject: ext2: Drop fragment support Ext2 has fields in superblock reserved for subblock allocation support. However that never landed. Drop the many years dead code. Reported-by: syzbot+af5e10f73dbff48f70af@syzkaller.appspotmail.com Signed-off-by: Jan Kara --- fs/ext2/ext2.h | 12 ------------ fs/ext2/super.c | 23 ++++------------------- 2 files changed, 4 insertions(+), 31 deletions(-) (limited to 'fs/ext2') diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 5e82ec0847cf..35a041c47c38 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -70,10 +70,7 @@ struct mb_cache; * second extended-fs super-block data in memory */ struct ext2_sb_info { - unsigned long s_frag_size; /* Size of a fragment in bytes */ - unsigned long s_frags_per_block;/* Number of fragments per block */ unsigned long s_inodes_per_block;/* Number of inodes per block */ - unsigned long s_frags_per_group;/* Number of fragments in a group */ unsigned long s_blocks_per_group;/* Number of blocks in a group */ unsigned long s_inodes_per_group;/* Number of inodes in a group */ unsigned long s_itb_per_group; /* Number of inode table blocks per group */ @@ -188,15 +185,6 @@ static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb) #define EXT2_INODE_SIZE(s) (EXT2_SB(s)->s_inode_size) #define EXT2_FIRST_INO(s) (EXT2_SB(s)->s_first_ino) -/* - * Macro-instructions used to manage fragments - */ -#define EXT2_MIN_FRAG_SIZE 1024 -#define EXT2_MAX_FRAG_SIZE 4096 -#define EXT2_MIN_FRAG_LOG_SIZE 10 -#define EXT2_FRAG_SIZE(s) (EXT2_SB(s)->s_frag_size) -#define EXT2_FRAGS_PER_BLOCK(s) (EXT2_SB(s)->s_frags_per_block) - /* * Structure of a blocks group descriptor */ diff --git a/fs/ext2/super.c b/fs/ext2/super.c index f342f347a695..2959afc7541c 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -668,10 +668,9 @@ static int ext2_setup_super (struct super_block * sb, es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); if (test_opt (sb, DEBUG)) - ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, fs=%lu, gc=%lu, " + ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, gc=%lu, " "bpg=%lu, ipg=%lu, mo=%04lx]", EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize, - sbi->s_frag_size, sbi->s_groups_count, EXT2_BLOCKS_PER_GROUP(sb), EXT2_INODES_PER_GROUP(sb), @@ -1012,14 +1011,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) } } - sbi->s_frag_size = EXT2_MIN_FRAG_SIZE << - le32_to_cpu(es->s_log_frag_size); - if (sbi->s_frag_size == 0) - goto cantfind_ext2; - sbi->s_frags_per_block = sb->s_blocksize / sbi->s_frag_size; - sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); - sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb); @@ -1045,11 +1037,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (sb->s_blocksize != sbi->s_frag_size) { + if (es->s_log_frag_size != es->s_log_block_size) { ext2_msg(sb, KERN_ERR, - "error: fragsize %lu != blocksize %lu" - "(not supported yet)", - sbi->s_frag_size, sb->s_blocksize); + "error: fragsize log %u != blocksize log %u", + le32_to_cpu(es->s_log_frag_size), sb->s_blocksize_bits); goto failed_mount; } @@ -1066,12 +1057,6 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sbi->s_blocks_per_group, sbi->s_inodes_per_group + 3); goto failed_mount; } - if (sbi->s_frags_per_group > sb->s_blocksize * 8) { - ext2_msg(sb, KERN_ERR, - "error: #fragments per group too big: %lu", - sbi->s_frags_per_group); - goto failed_mount; - } if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || sbi->s_inodes_per_group > sb->s_blocksize * 8) { ext2_msg(sb, KERN_ERR, -- cgit v1.2.3