From dfcb60b76794a3945c2dd8dca7ad78e95f582937 Mon Sep 17 00:00:00 2001 From: Chen Ridong Date: Fri, 28 Jun 2024 01:36:04 +0000 Subject: [PATCH 1/2] cgroup/cpuset: Prevent UAF in proc_cpuset_show() mainline inclusion from mainline-v6.11-rc1 commit 1be59c97c83ccd67a519d8a49486b3a8a73ca28a category: bugfix issue: NA CVE: CVE-2024-43853 Signed-off-by: yaowenrui --------------------------------------- An UAF can happen when /proc/cpuset is read as reported in [1]. This can be reproduced by the following methods: 1.add an mdelay(1000) before acquiring the cgroup_lock In the cgroup_path_ns function. 2.$cat /proc//cpuset repeatly. 3.$mount -t cgroup -o cpuset cpuset /sys/fs/cgroup/cpuset/ $umount /sys/fs/cgroup/cpuset/ repeatly. The race that cause this bug can be shown as below: (umount) | (cat /proc//cpuset) css_release | proc_cpuset_show css_release_work_fn | css = task_get_css(tsk, cpuset_cgrp_id); css_free_rwork_fn | cgroup_path_ns(css->cgroup, ...); cgroup_destroy_root | mutex_lock(&cgroup_mutex); rebind_subsystems | cgroup_free_root | | // cgrp was freed, UAF | cgroup_path_ns_locked(cgrp,..); When the cpuset is initialized, the root node top_cpuset.css.cgrp will point to &cgrp_dfl_root.cgrp. In cgroup v1, the mount operation will allocate cgroup_root, and top_cpuset.css.cgrp will point to the allocated &cgroup_root.cgrp. When the umount operation is executed, top_cpuset.css.cgrp will be rebound to &cgrp_dfl_root.cgrp. The problem is that when rebinding to cgrp_dfl_root, there are cases where the cgroup_root allocated by setting up the root for cgroup v1 is cached. This could lead to a Use-After-Free (UAF) if it is subsequently freed. The descendant cgroups of cgroup v1 can only be freed after the css is released. However, the css of the root will never be released, yet the cgroup_root should be freed when it is unmounted. This means that obtaining a reference to the css of the root does not guarantee that css.cgrp->root will not be freed. Fix this problem by using rcu_read_lock in proc_cpuset_show(). As cgroup_root is kfree_rcu after commit d23b5c577715 ("cgroup: Make operations on the cgroup root_list RCU safe"), css->cgroup won't be freed during the critical section. To call cgroup_path_ns_locked, css_set_lock is needed, so it is safe to replace task_get_css with task_css. [1] https://syzkaller.appspot.com/bug?extid=9b1ff7be974a403aa4cd Fixes: a79a908fd2b0 ("cgroup: introduce cgroup namespaces") Signed-off-by: Chen Ridong Signed-off-by: Tejun Heo Signed-off-by: yaowenrui --- kernel/cgroup/cpuset.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index b68de0d09632..6e11c56fe429 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -21,6 +21,7 @@ * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ +#include "cgroup-internal.h" #include #include @@ -3673,10 +3674,14 @@ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, if (!buf) goto out; - css = task_get_css(tsk, cpuset_cgrp_id); - retval = cgroup_path_ns(css->cgroup, buf, PATH_MAX, - current->nsproxy->cgroup_ns); - css_put(css); + rcu_read_lock(); + spin_lock_irq(&css_set_lock); + css = task_css(tsk, cpuset_cgrp_id); + retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX, + current->nsproxy->cgroup_ns); + spin_unlock_irq(&css_set_lock); + rcu_read_unlock(); + if (retval >= PATH_MAX) retval = -ENAMETOOLONG; if (retval < 0) -- Gitee From 186f111f09b9e477a877ee3f0bfe9d20f1bb4268 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Tue, 2 Jul 2024 21:23:48 +0800 Subject: [PATCH 2/2] ext4: check dot and dotdot of dx_root before making dir indexed stable inclusion from stable-5.10.224 commit 42d420517072028fb0eb852c358056b7717ba5aa category: bugfix issue: NA CVE: CVE-2024-42305 Signed-off-by: yaowenrui --------------------------------------- commit 50ea741def587a64e08879ce6c6a30131f7111e7 upstream. Syzbot reports a issue as follows: ============================================ BUG: unable to handle page fault for address: ffffed11022e24fe PGD 23ffee067 P4D 23ffee067 PUD 0 Oops: Oops: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 0 PID: 5079 Comm: syz-executor306 Not tainted 6.10.0-rc5-g55027e689933 #0 Call Trace: make_indexed_dir+0xdaf/0x13c0 fs/ext4/namei.c:2341 ext4_add_entry+0x222a/0x25d0 fs/ext4/namei.c:2451 ext4_rename fs/ext4/namei.c:3936 [inline] ext4_rename2+0x26e5/0x4370 fs/ext4/namei.c:4214 [...] ============================================ The immediate cause of this problem is that there is only one valid dentry for the block to be split during do_split, so split==0 results in out of bounds accesses to the map triggering the issue. do_split unsigned split dx_make_map count = 1 split = count/2 = 0; continued = hash2 == map[split - 1].hash; ---> map[4294967295] The maximum length of a filename is 255 and the minimum block size is 1024, so it is always guaranteed that the number of entries is greater than or equal to 2 when do_split() is called. But syzbot's crafted image has no dot and dotdot in dir, and the dentry distribution in dirblock is as follows: bus dentry1 hole dentry2 free |xx--|xx-------------|...............|xx-------------|...............| 0 12 (8+248)=256 268 256 524 (8+256)=264 788 236 1024 So when renaming dentry1 increases its name_len length by 1, neither hole nor free is sufficient to hold the new dentry, and make_indexed_dir() is called. In make_indexed_dir() it is assumed that the first two entries of the dirblock must be dot and dotdot, so bus and dentry1 are left in dx_root because they are treated as dot and dotdot, and only dentry2 is moved to the new leaf block. That's why count is equal to 1. Therefore add the ext4_check_dx_root() helper function to add more sanity checks to dot and dotdot before starting the conversion to avoid the above issue. Reported-by: syzbot+ae688d469e36fb5138d0@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ae688d469e36fb5138d0 Fixes: ac27a0ec112a ("[PATCH] ext4: initial copy of files from ext3") Cc: stable@kernel.org Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://patch.msgid.link/20240702132349.2600605-2-libaokun@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman Signed-off-by: yaowenrui --- fs/ext4/namei.c | 56 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 51 insertions(+), 5 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index ff3c085401ea..64972025aa58 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2101,6 +2101,52 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, return err ? err : err2; } +static bool ext4_check_dx_root(struct inode *dir, struct dx_root *root) +{ + struct fake_dirent *fde; + const char *error_msg; + unsigned int rlen; + unsigned int blocksize = dir->i_sb->s_blocksize; + char *blockend = (char *)root + dir->i_sb->s_blocksize; + + fde = &root->dot; + if (unlikely(fde->name_len != 1)) { + error_msg = "invalid name_len for '.'"; + goto corrupted; + } + if (unlikely(strncmp(root->dot_name, ".", fde->name_len))) { + error_msg = "invalid name for '.'"; + goto corrupted; + } + rlen = ext4_rec_len_from_disk(fde->rec_len, blocksize); + if (unlikely((char *)fde + rlen >= blockend)) { + error_msg = "invalid rec_len for '.'"; + goto corrupted; + } + + fde = &root->dotdot; + if (unlikely(fde->name_len != 2)) { + error_msg = "invalid name_len for '..'"; + goto corrupted; + } + if (unlikely(strncmp(root->dotdot_name, "..", fde->name_len))) { + error_msg = "invalid name for '..'"; + goto corrupted; + } + rlen = ext4_rec_len_from_disk(fde->rec_len, blocksize); + if (unlikely((char *)fde + rlen >= blockend)) { + error_msg = "invalid rec_len for '..'"; + goto corrupted; + } + + return true; + +corrupted: + EXT4_ERROR_INODE(dir, "Corrupt dir, %s, running e2fsck is recommended", + error_msg); + return false; +} + /* * This converts a one block unindexed directory to a 3 block indexed * directory, and adds the dentry to the indexed directory. @@ -2134,17 +2180,17 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, brelse(bh); return retval; } + root = (struct dx_root *) bh->b_data; + if (!ext4_check_dx_root(dir, root)) { + brelse(bh); + return -EFSCORRUPTED; + } /* The 0th block becomes the root, move the dirents out */ fde = &root->dotdot; de = (struct ext4_dir_entry_2 *)((char *)fde + ext4_rec_len_from_disk(fde->rec_len, blocksize)); - if ((char *) de >= (((char *) root) + blocksize)) { - EXT4_ERROR_INODE(dir, "invalid rec_len for '..'"); - brelse(bh); - return -EFSCORRUPTED; - } len = ((char *) root) + (blocksize - csum_size) - (char *) de; /* Allocate new block for the 0th block's dirents */ -- Gitee