From: Chuck Lever <chuck.lever@oracle.com> mainline inclusion from mainline-v6.12-rc3 commit 903dc9c43a155e0893280c7472d4a9a3a83d75a6 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBLWT7 CVE: CVE-2024-57952 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Testing shows that the EBUSY error return from mtree_alloc_cyclic() leaks into user space. The ERRORS section of "man creat(2)" says:

EBUSY O_EXCL was specified in flags and pathname refers to a block device that is in use by the system (e.g., it is mounted).

ENOSPC is closer to what applications expect in this situation. Note that the normal range of simple directory offset values is 2..2^63, so hitting this error is going to be rare to impossible. Fixes: 6faddda69f62 ("libfs: Add directory operations for stable offsets") Cc: stable@vger.kernel.org # v6.9+ Reviewed-by: Jeff Layton <jlayton@kernel.org> Reviewed-by: Yang Erkun <yangerkun@huawei.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Link: https://lore.kernel.org/r/20241228175522.1854234-2-cel@kernel.org Signed-off-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Yongjian Sun <sunyongjian1@huawei.com> --- fs/libfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/libfs.c b/fs/libfs.c index cdb9d5683aec..bf2ea681bbb8 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -284,8 +284,8 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN, LONG_MAX, &octx->next_offset, GFP_KERNEL); - if (ret < 0) - return ret; + if (unlikely(ret < 0)) + return ret == -EBUSY ? -ENOSPC : ret; offset_set(dentry, offset); return 0; -- 2.39.2

From: Chuck Lever <chuck.lever@oracle.com> mainline inclusion from mainline-v6.12-rc3 commit b662d858131da9a8a14e68661656989b14dbf113 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBLWT7 CVE: CVE-2024-57952 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The current directory offset allocator (based on mtree_alloc_cyclic) stores the next offset value to return in octx->next_offset. This mechanism typically returns values that increase monotonically over time. Eventually, though, the newly allocated offset value wraps back to a low number (say, 2) which is smaller than other already- allocated offset values. Yu Kuai <yukuai3@huawei.com> reports that, after commit 64a7ce76fb90 ("libfs: fix infinite directory reads for offset dir"), if a directory's offset allocator wraps, existing entries are no longer visible via readdir/getdents because offset_readdir() stops listing entries once an entry's offset is larger than octx->next_offset. These entries vanish persistently -- they can be looked up, but will never again appear in readdir(3) output. The reason for this is that the commit treats directory offsets as monotonically increasing integer values rather than opaque cookies, and introduces this comparison: if (dentry2offset(dentry) >= last_index) { On 64-bit platforms, the directory offset value upper bound is 2^63 - 1. Directory offsets will monotonically increase for millions of years without wrapping. On 32-bit platforms, however, LONG_MAX is 2^31 - 1. The allocator can wrap after only a few weeks (at worst). Revert commit 64a7ce76fb90 ("libfs: fix infinite directory reads for offset dir") to prepare for a fix that can work properly on 32-bit systems and might apply to recent LTS kernels where shmem employs the simple_offset mechanism. Reported-by: Yu Kuai <yukuai3@huawei.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Link: https://lore.kernel.org/r/20241228175522.1854234-4-cel@kernel.org Reviewed-by: Yang Erkun <yangerkun@huawei.com> Signed-off-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Yongjian Sun <sunyongjian1@huawei.com> --- fs/libfs.c | 35 +++++++++++------------------------ 1 file changed, 11 insertions(+), 24 deletions(-) diff --git a/fs/libfs.c b/fs/libfs.c index 86c96964e181..aa1ee33b6899 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -371,14 +371,6 @@ void simple_offset_destroy(struct offset_ctx *octx) mtree_destroy(&octx->mt); } -static int offset_dir_open(struct inode *inode, struct file *file) -{ - struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); - - file->private_data = (void *)ctx->next_offset; - return 0; -} - /** * offset_dir_llseek - Advance the read position of a directory descriptor * @file: an open directory whose position is to be updated @@ -392,9 +384,6 @@ static int offset_dir_open(struct inode *inode, struct file *file) */ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) { - struct inode *inode = file->f_inode; - struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); - switch (whence) { case SEEK_CUR: offset += file->f_pos; @@ -408,8 +397,7 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) } /* In this case, ->private_data is protected by f_pos_lock */ - if (!offset) - file->private_data = (void *)ctx->next_offset; + file->private_data = NULL; return vfs_setpos(file, offset, LONG_MAX); } @@ -440,7 +428,7 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } -static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, long last_index) +static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) { struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *dentry; @@ -448,21 +436,17 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, lon while (true) { dentry = offset_find_next(octx, ctx->pos); if (!dentry) - return; - - if (dentry2offset(dentry) >= last_index) { - dput(dentry); - return; - } + return ERR_PTR(-ENOENT); if (!offset_dir_emit(ctx, dentry)) { dput(dentry); - return; + break; } ctx->pos = dentry2offset(dentry) + 1; dput(dentry); } + return NULL; } /** @@ -489,19 +473,22 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, lon static int offset_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; - long last_index = (long)file->private_data; lockdep_assert_held(&d_inode(dir)->i_rwsem); if (!dir_emit_dots(file, ctx)) return 0; - offset_iterate_dir(d_inode(dir), ctx, last_index); + /* In this case, ->private_data is protected by f_pos_lock */ + if (ctx->pos == DIR_OFFSET_MIN) + file->private_data = NULL; + else if (file->private_data == ERR_PTR(-ENOENT)) + return 0; + file->private_data = offset_iterate_dir(d_inode(dir), ctx); return 0; } const struct file_operations simple_offset_dir_operations = { - .open = offset_dir_open, .llseek = offset_dir_llseek, .iterate_shared = offset_readdir, .read = generic_read_dir, -- 2.39.2

From: Chuck Lever <chuck.lever@oracle.com> stable inclusion from stable-v6.6.75 commit 850e696f362729a163fb6af21a54cde565b71f75 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBLWT7 CVE: CVE-2024-57952 Reference: https://web.git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/... -------------------------------- [ Upstream commit b9b588f22a0c049a14885399e27625635ae6ef91 ] The mtree mechanism has been effective at creating directory offsets that are stable over multiple opendir instances. However, it has not been able to handle the subtleties of renames that are concurrent with readdir. Instead of using the mtree to emit entries in the order of their offset values, use it only to map incoming ctx->pos to a starting entry. Then use the directory's d_children list, which is already maintained properly by the dcache, to find the next child to emit. One of the sneaky things about this is that when the mtree-allocated offset value wraps (which is very rare), looking up ctx->pos++ is not going to find the next entry; it will return NULL. Instead, by following the d_children list, the offset values can appear in any order but all of the entries in the directory will be visited eventually. Note also that the readdir() is guaranteed to reach the tail of this list. Entries are added only at the head of d_children, and readdir walks from its current position in that list towards its tail. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Link: https://lore.kernel.org/r/20241228175522.1854234-6-cel@kernel.org Signed-off-by: Christian Brauner <brauner@kernel.org> Conflicts: fs/libfs.c [0e4a862174f2("libfs: Convert simple directory offsets to use a Maple Tree") not applied for stable] Signed-off-by: Yongjian Sun <sunyongjian1@huawei.com> --- fs/libfs.c | 86 +++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 60 insertions(+), 26 deletions(-) diff --git a/fs/libfs.c b/fs/libfs.c index 6369390f40d4..c2380cacc08e 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -239,12 +239,13 @@ EXPORT_SYMBOL(simple_dir_inode_operations); /* simple_offset_add() never assigns these to a dentry */ enum { + DIR_OFFSET_FIRST = 2, /* Find first real entry */ DIR_OFFSET_EOD = S32_MAX, }; /* simple_offset_add() allocation range */ enum { - DIR_OFFSET_MIN = 2, + DIR_OFFSET_MIN = DIR_OFFSET_FIRST + 1, DIR_OFFSET_MAX = DIR_OFFSET_EOD - 1, }; @@ -406,51 +407,84 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) return vfs_setpos(file, offset, LONG_MAX); } -static struct dentry *offset_find_next(struct offset_ctx *octx, loff_t offset) +static struct dentry *find_positive_dentry(struct dentry *parent, + struct dentry *dentry, + bool next) { - MA_STATE(mas, &octx->mt, offset, offset); + struct dentry *found = NULL; + + spin_lock(&parent->d_lock); + if (next) + dentry = list_next_entry(dentry, d_child); + else if (!dentry) + dentry = list_first_entry_or_null(&parent->d_subdirs, + struct dentry, d_child); + for (; dentry && !list_entry_is_head(dentry, &parent->d_subdirs, d_child); + dentry = list_next_entry(dentry, d_child)) { + if (!simple_positive(dentry)) + continue; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + if (simple_positive(dentry)) + found = dget_dlock(dentry); + spin_unlock(&dentry->d_lock); + if (likely(found)) + break; + } + spin_unlock(&parent->d_lock); + return found; +} + +static noinline_for_stack struct dentry * +offset_dir_lookup(struct dentry *parent, loff_t offset) +{ + struct inode *inode = d_inode(parent); + struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *child, *found = NULL; - rcu_read_lock(); - child = mas_find(&mas, DIR_OFFSET_MAX); - if (!child) - goto out; - spin_lock(&child->d_lock); - if (simple_positive(child)) - found = dget_dlock(child); - spin_unlock(&child->d_lock); -out: - rcu_read_unlock(); + MA_STATE(mas, &octx->mt, offset, offset); + + if (offset == DIR_OFFSET_FIRST) + found = find_positive_dentry(parent, NULL, false); + else { + rcu_read_lock(); + child = mas_find(&mas, DIR_OFFSET_MAX); + found = find_positive_dentry(parent, child, false); + rcu_read_unlock(); + } return found; } static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) { struct inode *inode = d_inode(dentry); - long offset = dentry2offset(dentry); - return ctx->actor(ctx, dentry->d_name.name, dentry->d_name.len, offset, - inode->i_ino, fs_umode_to_dtype(inode->i_mode)); + return dir_emit(ctx, dentry->d_name.name, dentry->d_name.len, + inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } -static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx) +static void offset_iterate_dir(struct file *file, struct dir_context *ctx) { - struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); + struct dentry *dir = file->f_path.dentry; struct dentry *dentry; + dentry = offset_dir_lookup(dir, ctx->pos); + if (!dentry) + goto out_eod; while (true) { - dentry = offset_find_next(octx, ctx->pos); - if (!dentry) - goto out_eod; + struct dentry *next; - if (!offset_dir_emit(ctx, dentry)) { - dput(dentry); + ctx->pos = dentry2offset(dentry); + if (!offset_dir_emit(ctx, dentry)) break; - } - ctx->pos = dentry2offset(dentry) + 1; + next = find_positive_dentry(dir, dentry, true); dput(dentry); + + if (!next) + goto out_eod; + dentry = next; } + dput(dentry); return; out_eod: @@ -489,7 +523,7 @@ static int offset_readdir(struct file *file, struct dir_context *ctx) if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos != DIR_OFFSET_EOD) - offset_iterate_dir(d_inode(dir), ctx); + offset_iterate_dir(file, ctx); return 0; } -- 2.39.2