September 2024 - Kernel - mailweb.openeuler.org

[PATCH openEuler-1.0-LTS] nilfs2: protect references to superblock parameters exposed in sysfs
by Zhao Wenhui 27 Sep '24

27 Sep '24

From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> stable inclusion from stable-v4.19.322 commit b90beafac05931cbfcb6b1bd4f67c1923f47040e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IARYCR CVE: CVE-2024-46780 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 683408258917541bdb294cd717c210a04381931e ] The superblock buffers of nilfs2 can not only be overwritten at runtime for modifications/repairs, but they are also regularly swapped, replaced during resizing, and even abandoned when degrading to one side due to backing device issues. So, accessing them requires mutual exclusion using the reader/writer semaphore "nilfs->ns_sem". Some sysfs attribute show methods read this superblock buffer without the necessary mutual exclusion, which can cause problems with pointer dereferencing and memory access, so fix it. Link: https://lkml.kernel.org/r/20240811100320.9913-1-konishi.ryusuke@gmail.com Fixes: da7141fb78db ("nilfs2: add /sys/fs/nilfs2/<device> group") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: fs/nilfs2/sysfs.c [3bcd6c5bd483287f4a09d3d59a012d47677b6edc not merged.] Signed-off-by: Zhao Wenhui <zhaowenhui8(a)huawei.com> --- fs/nilfs2/sysfs.c | 43 +++++++++++++++++++++++++++++++++---------- 1 file changed, 33 insertions(+), 10 deletions(-) diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index e60be7bb55b0..14349d3625fc 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -845,9 +845,15 @@ ssize_t nilfs_dev_revision_show(struct nilfs_dev_attr *attr, struct the_nilfs *nilfs, char *buf) { - struct nilfs_super_block **sbp = nilfs->ns_sbp; - u32 major = le32_to_cpu(sbp[0]->s_rev_level); - u16 minor = le16_to_cpu(sbp[0]->s_minor_rev_level); + struct nilfs_super_block *raw_sb; + u32 major; + u16 minor; + + down_read(&nilfs->ns_sem); + raw_sb = nilfs->ns_sbp[0]; + major = le32_to_cpu(raw_sb->s_rev_level); + minor = le16_to_cpu(raw_sb->s_minor_rev_level); + up_read(&nilfs->ns_sem); return snprintf(buf, PAGE_SIZE, "%d.%d\n", major, minor); } @@ -865,8 +871,13 @@ ssize_t nilfs_dev_device_size_show(struct nilfs_dev_attr *attr, struct the_nilfs *nilfs, char *buf) { - struct nilfs_super_block **sbp = nilfs->ns_sbp; - u64 dev_size = le64_to_cpu(sbp[0]->s_dev_size); + struct nilfs_super_block *raw_sb; + u64 dev_size; + + down_read(&nilfs->ns_sem); + raw_sb = nilfs->ns_sbp[0]; + dev_size = le64_to_cpu(raw_sb->s_dev_size); + up_read(&nilfs->ns_sem); return snprintf(buf, PAGE_SIZE, "%llu\n", dev_size); } @@ -888,9 +899,15 @@ ssize_t nilfs_dev_uuid_show(struct nilfs_dev_attr *attr, struct the_nilfs *nilfs, char *buf) { - struct nilfs_super_block **sbp = nilfs->ns_sbp; + struct nilfs_super_block *raw_sb; + ssize_t len; - return snprintf(buf, PAGE_SIZE, "%pUb\n", sbp[0]->s_uuid); + down_read(&nilfs->ns_sem); + raw_sb = nilfs->ns_sbp[0]; + len = snprintf(buf, PAGE_SIZE, "%pUb\n", raw_sb->s_uuid); + up_read(&nilfs->ns_sem); + + return len; } static @@ -898,10 +915,16 @@ ssize_t nilfs_dev_volume_name_show(struct nilfs_dev_attr *attr, struct the_nilfs *nilfs, char *buf) { - struct nilfs_super_block **sbp = nilfs->ns_sbp; + struct nilfs_super_block *raw_sb; + ssize_t len; + + down_read(&nilfs->ns_sem); + raw_sb = nilfs->ns_sbp[0]; + len = scnprintf(buf, sizeof(raw_sb->s_volume_name), "%s\n", + raw_sb->s_volume_name); + up_read(&nilfs->ns_sem); - return scnprintf(buf, sizeof(sbp[0]->s_volume_name), "%s\n", - sbp[0]->s_volume_name); + return len; } static const char dev_readme_str[] = -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] hwmon: (lm95234) Fix underflows seen when writing limit attributes
by Xiongfeng Wang 27 Sep '24

27 Sep '24

From: Guenter Roeck <linux(a)roeck-us.net> mainline inclusion from mainline-v6.11-rc1 commit af64e3e1537896337405f880c1e9ac1f8c0c6198 category: bugfix bugzilla: hhttps://gitee.com/src-openeuler/kernel/issues/IAS0PZ CVE: CVE-2024-46758 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- DIV_ROUND_CLOSEST() after kstrtol() results in an underflow if a large negative number such as -9223372036854775808 is provided by the user. Fix it by reordering clamp_val() and DIV_ROUND_CLOSEST() operations. Signed-off-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> --- drivers/hwmon/lm95234.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/hwmon/lm95234.c b/drivers/hwmon/lm95234.c index ac169a994ae00..db2aecdfbd17c 100644 --- a/drivers/hwmon/lm95234.c +++ b/drivers/hwmon/lm95234.c @@ -301,7 +301,8 @@ static ssize_t tcrit2_store(struct device *dev, struct device_attribute *attr, if (ret < 0) return ret; - val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, index ? 255 : 127); + val = DIV_ROUND_CLOSEST(clamp_val(val, 0, (index ? 255 : 127) * 1000), + 1000); mutex_lock(&data->update_lock); data->tcrit2[index] = val; @@ -350,7 +351,7 @@ static ssize_t tcrit1_store(struct device *dev, struct device_attribute *attr, if (ret < 0) return ret; - val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, 255); + val = DIV_ROUND_CLOSEST(clamp_val(val, 0, 255000), 1000); mutex_lock(&data->update_lock); data->tcrit1[index] = val; @@ -391,7 +392,7 @@ static ssize_t tcrit1_hyst_store(struct device *dev, if (ret < 0) return ret; - val = DIV_ROUND_CLOSEST(val, 1000); + val = DIV_ROUND_CLOSEST(clamp_val(val, -255000, 255000), 1000); val = clamp_val((int)data->tcrit1[index] - val, 0, 31); mutex_lock(&data->update_lock); @@ -431,7 +432,7 @@ static ssize_t offset_store(struct device *dev, struct device_attribute *attr, return ret; /* Accuracy is 1/2 degrees C */ - val = clamp_val(DIV_ROUND_CLOSEST(val, 500), -128, 127); + val = DIV_ROUND_CLOSEST(clamp_val(val, -64000, 63500), 500); mutex_lock(&data->update_lock); data->toffset[index] = val; -- 2.20.1

2 1

[PATCH OLK-5.10] hwmon: (lm95234) Fix underflows seen when writing limit attributes
by Xiongfeng Wang 27 Sep '24

27 Sep '24

From: Guenter Roeck <linux(a)roeck-us.net> mainline inclusion from mainline-v6.11-rc1 commit af64e3e1537896337405f880c1e9ac1f8c0c6198 category: bugfix bugzilla: hhttps://gitee.com/src-openeuler/kernel/issues/IAS0PZ CVE: CVE-2024-46758 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- DIV_ROUND_CLOSEST() after kstrtol() results in an underflow if a large negative number such as -9223372036854775808 is provided by the user. Fix it by reordering clamp_val() and DIV_ROUND_CLOSEST() operations. Signed-off-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> --- drivers/hwmon/lm95234.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/hwmon/lm95234.c b/drivers/hwmon/lm95234.c index ac169a994ae00..db2aecdfbd17c 100644 --- a/drivers/hwmon/lm95234.c +++ b/drivers/hwmon/lm95234.c @@ -301,7 +301,8 @@ static ssize_t tcrit2_store(struct device *dev, struct device_attribute *attr, if (ret < 0) return ret; - val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, index ? 255 : 127); + val = DIV_ROUND_CLOSEST(clamp_val(val, 0, (index ? 255 : 127) * 1000), + 1000); mutex_lock(&data->update_lock); data->tcrit2[index] = val; @@ -350,7 +351,7 @@ static ssize_t tcrit1_store(struct device *dev, struct device_attribute *attr, if (ret < 0) return ret; - val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, 255); + val = DIV_ROUND_CLOSEST(clamp_val(val, 0, 255000), 1000); mutex_lock(&data->update_lock); data->tcrit1[index] = val; @@ -391,7 +392,7 @@ static ssize_t tcrit1_hyst_store(struct device *dev, if (ret < 0) return ret; - val = DIV_ROUND_CLOSEST(val, 1000); + val = DIV_ROUND_CLOSEST(clamp_val(val, -255000, 255000), 1000); val = clamp_val((int)data->tcrit1[index] - val, 0, 31); mutex_lock(&data->update_lock); @@ -431,7 +432,7 @@ static ssize_t offset_store(struct device *dev, struct device_attribute *attr, return ret; /* Accuracy is 1/2 degrees C */ - val = clamp_val(DIV_ROUND_CLOSEST(val, 500), -128, 127); + val = DIV_ROUND_CLOSEST(clamp_val(val, -64000, 63500), 500); mutex_lock(&data->update_lock); data->toffset[index] = val; -- 2.20.1

2 1

[PATCH openEuler-1.0-LTS] hwmon: (lm95234) Fix underflows seen when writing limit attributes
by Xiongfeng Wang 27 Sep '24

27 Sep '24

From: Guenter Roeck <linux(a)roeck-us.net> mainline inclusion from mainline-v6.11-rc1 commit af64e3e1537896337405f880c1e9ac1f8c0c6198 category: bugfix bugzilla: hhttps://gitee.com/src-openeuler/kernel/issues/IAS0PZ CVE: CVE-2024-46758 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- DIV_ROUND_CLOSEST() after kstrtol() results in an underflow if a large negative number such as -9223372036854775808 is provided by the user. Fix it by reordering clamp_val() and DIV_ROUND_CLOSEST() operations. Signed-off-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> --- drivers/hwmon/lm95234.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/hwmon/lm95234.c b/drivers/hwmon/lm95234.c index c7fcc9e7f57a..13912ac7c69f 100644 --- a/drivers/hwmon/lm95234.c +++ b/drivers/hwmon/lm95234.c @@ -310,7 +310,8 @@ static ssize_t set_tcrit2(struct device *dev, struct device_attribute *attr, if (ret < 0) return ret; - val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, index ? 255 : 127); + val = DIV_ROUND_CLOSEST(clamp_val(val, 0, (index ? 255 : 127) * 1000), + 1000); mutex_lock(&data->update_lock); data->tcrit2[index] = val; @@ -359,7 +360,7 @@ static ssize_t set_tcrit1(struct device *dev, struct device_attribute *attr, if (ret < 0) return ret; - val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, 255); + val = DIV_ROUND_CLOSEST(clamp_val(val, 0, 255000), 1000); mutex_lock(&data->update_lock); data->tcrit1[index] = val; @@ -400,7 +401,7 @@ static ssize_t set_tcrit1_hyst(struct device *dev, if (ret < 0) return ret; - val = DIV_ROUND_CLOSEST(val, 1000); + val = DIV_ROUND_CLOSEST(clamp_val(val, -255000, 255000), 1000); val = clamp_val((int)data->tcrit1[index] - val, 0, 31); mutex_lock(&data->update_lock); @@ -440,7 +441,7 @@ static ssize_t set_offset(struct device *dev, struct device_attribute *attr, return ret; /* Accuracy is 1/2 degrees C */ - val = clamp_val(DIV_ROUND_CLOSEST(val, 500), -128, 127); + val = DIV_ROUND_CLOSEST(clamp_val(val, -64000, 63500), 500); mutex_lock(&data->update_lock); data->toffset[index] = val; -- 2.20.1

2 1

[PATCH OLK-6.6] hwmon: (lm95234) Fix underflows seen when writing limit attributes
by Xiongfeng Wang 27 Sep '24

27 Sep '24

From: Guenter Roeck <linux(a)roeck-us.net> mainline inclusion from mainline-v6.11-rc1 commit af64e3e1537896337405f880c1e9ac1f8c0c6198 category: bugfix bugzilla: hhttps://gitee.com/src-openeuler/kernel/issues/IAS0PZ CVE: CVE-2024-46758 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- DIV_ROUND_CLOSEST() after kstrtol() results in an underflow if a large negative number such as -9223372036854775808 is provided by the user. Fix it by reordering clamp_val() and DIV_ROUND_CLOSEST() operations. Signed-off-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> --- drivers/hwmon/lm95234.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/hwmon/lm95234.c b/drivers/hwmon/lm95234.c index 67b9d7636ee4..37e8e9679aeb 100644 --- a/drivers/hwmon/lm95234.c +++ b/drivers/hwmon/lm95234.c @@ -301,7 +301,8 @@ static ssize_t tcrit2_store(struct device *dev, struct device_attribute *attr, if (ret < 0) return ret; - val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, index ? 255 : 127); + val = DIV_ROUND_CLOSEST(clamp_val(val, 0, (index ? 255 : 127) * 1000), + 1000); mutex_lock(&data->update_lock); data->tcrit2[index] = val; @@ -350,7 +351,7 @@ static ssize_t tcrit1_store(struct device *dev, struct device_attribute *attr, if (ret < 0) return ret; - val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, 255); + val = DIV_ROUND_CLOSEST(clamp_val(val, 0, 255000), 1000); mutex_lock(&data->update_lock); data->tcrit1[index] = val; @@ -391,7 +392,7 @@ static ssize_t tcrit1_hyst_store(struct device *dev, if (ret < 0) return ret; - val = DIV_ROUND_CLOSEST(val, 1000); + val = DIV_ROUND_CLOSEST(clamp_val(val, -255000, 255000), 1000); val = clamp_val((int)data->tcrit1[index] - val, 0, 31); mutex_lock(&data->update_lock); @@ -431,7 +432,7 @@ static ssize_t offset_store(struct device *dev, struct device_attribute *attr, return ret; /* Accuracy is 1/2 degrees C */ - val = clamp_val(DIV_ROUND_CLOSEST(val, 500), -128, 127); + val = DIV_ROUND_CLOSEST(clamp_val(val, -64000, 63500), 500); mutex_lock(&data->update_lock); data->toffset[index] = val; -- 2.20.1

2 1

[PATCH OLK-6.6] btrfs: fix race between direct IO write and fsync when using same fd
by Xiongfeng Wang 27 Sep '24

27 Sep '24

From: Filipe Manana <fdmanana(a)suse.com> stable inclusion from stable-v6.6.51 commit 7b5595f33c3c273613b590892a578d78186bb400 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IARY1Z CVE: CVE-2024-46734 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit cd9253c23aedd61eb5ff11f37a36247cd46faf86 upstream. If we have 2 threads that are using the same file descriptor and one of them is doing direct IO writes while the other is doing fsync, we have a race where we can end up either: 1) Attempt a fsync without holding the inode's lock, triggering an assertion failures when assertions are enabled; 2) Do an invalid memory access from the fsync task because the file private points to memory allocated on stack by the direct IO task and it may be used by the fsync task after the stack was destroyed. The race happens like this: 1) A user space program opens a file descriptor with O_DIRECT; 2) The program spawns 2 threads using libpthread for example; 3) One of the threads uses the file descriptor to do direct IO writes, while the other calls fsync using the same file descriptor. 4) Call task A the thread doing direct IO writes and task B the thread doing fsyncs; 5) Task A does a direct IO write, and at btrfs_direct_write() sets the file's private to an on stack allocated private with the member 'fsync_skip_inode_lock' set to true; 6) Task B enters btrfs_sync_file() and sees that there's a private structure associated to the file which has 'fsync_skip_inode_lock' set to true, so it skips locking the inode's VFS lock; 7) Task A completes the direct IO write, and resets the file's private to NULL since it had no prior private and our private was stack allocated. Then it unlocks the inode's VFS lock; 8) Task B enters btrfs_get_ordered_extents_for_logging(), then the assertion that checks the inode's VFS lock is held fails, since task B never locked it and task A has already unlocked it. The stack trace produced is the following: assertion failed: inode_is_locked(&inode->vfs_inode), in fs/btrfs/ordered-data.c:983 ------------[ cut here ]------------ kernel BUG at fs/btrfs/ordered-data.c:983! Oops: invalid opcode: 0000 [#1] PREEMPT SMP PTI CPU: 9 PID: 5072 Comm: worker Tainted: G U OE 6.10.5-1-default #1 openSUSE Tumbleweed 69f48d427608e1c09e60ea24c6c55e2ca1b049e8 Hardware name: Acer Predator PH315-52/Covini_CFS, BIOS V1.12 07/28/2020 RIP: 0010:btrfs_get_ordered_extents_for_logging.cold+0x1f/0x42 [btrfs] Code: 50 d6 86 c0 e8 (...) RSP: 0018:ffff9e4a03dcfc78 EFLAGS: 00010246 RAX: 0000000000000054 RBX: ffff9078a9868e98 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff907dce4a7800 RDI: ffff907dce4a7800 RBP: ffff907805518800 R08: 0000000000000000 R09: ffff9e4a03dcfb38 R10: ffff9e4a03dcfb30 R11: 0000000000000003 R12: ffff907684ae7800 R13: 0000000000000001 R14: ffff90774646b600 R15: 0000000000000000 FS: 00007f04b96006c0(0000) GS:ffff907dce480000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f32acbfc000 CR3: 00000001fd4fa005 CR4: 00000000003726f0 Call Trace: <TASK> ? __die_body.cold+0x14/0x24 ? die+0x2e/0x50 ? do_trap+0xca/0x110 ? do_error_trap+0x6a/0x90 ? btrfs_get_ordered_extents_for_logging.cold+0x1f/0x42 [btrfs bb26272d49b4cdc847cf3f7faadd459b62caee9a] ? exc_invalid_op+0x50/0x70 ? btrfs_get_ordered_extents_for_logging.cold+0x1f/0x42 [btrfs bb26272d49b4cdc847cf3f7faadd459b62caee9a] ? asm_exc_invalid_op+0x1a/0x20 ? btrfs_get_ordered_extents_for_logging.cold+0x1f/0x42 [btrfs bb26272d49b4cdc847cf3f7faadd459b62caee9a] ? btrfs_get_ordered_extents_for_logging.cold+0x1f/0x42 [btrfs bb26272d49b4cdc847cf3f7faadd459b62caee9a] btrfs_sync_file+0x21a/0x4d0 [btrfs bb26272d49b4cdc847cf3f7faadd459b62caee9a] ? __seccomp_filter+0x31d/0x4f0 __x64_sys_fdatasync+0x4f/0x90 do_syscall_64+0x82/0x160 ? do_futex+0xcb/0x190 ? __x64_sys_futex+0x10e/0x1d0 ? switch_fpu_return+0x4f/0xd0 ? syscall_exit_to_user_mode+0x72/0x220 ? do_syscall_64+0x8e/0x160 ? syscall_exit_to_user_mode+0x72/0x220 ? do_syscall_64+0x8e/0x160 ? syscall_exit_to_user_mode+0x72/0x220 ? do_syscall_64+0x8e/0x160 ? syscall_exit_to_user_mode+0x72/0x220 ? do_syscall_64+0x8e/0x160 entry_SYSCALL_64_after_hwframe+0x76/0x7e Another problem here is if task B grabs the private pointer and then uses it after task A has finished, since the private was allocated in the stack of task A, it results in some invalid memory access with a hard to predict result. This issue, triggering the assertion, was observed with QEMU workloads by two users in the Link tags below. Fix this by not relying on a file's private to pass information to fsync that it should skip locking the inode and instead pass this information through a special value stored in current->journal_info. This is safe because in the relevant section of the direct IO write path we are not holding a transaction handle, so current->journal_info is NULL. The following C program triggers the issue: $ cat repro.c /* Get the O_DIRECT definition. */ #ifndef _GNU_SOURCE #define _GNU_SOURCE #endif #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <stdint.h> #include <fcntl.h> #include <errno.h> #include <string.h> #include <pthread.h> static int fd; static ssize_t do_write(int fd, const void *buf, size_t count, off_t offset) { while (count > 0) { ssize_t ret; ret = pwrite(fd, buf, count, offset); if (ret < 0) { if (errno == EINTR) continue; return ret; } count -= ret; buf += ret; } return 0; } static void *fsync_loop(void *arg) { while (1) { int ret; ret = fsync(fd); if (ret != 0) { perror("Fsync failed"); exit(6); } } } int main(int argc, char *argv[]) { long pagesize; void *write_buf; pthread_t fsyncer; int ret; if (argc != 2) { fprintf(stderr, "Use: %s <file path>\n", argv[0]); return 1; } fd = open(argv[1], O_WRONLY | O_CREAT | O_TRUNC | O_DIRECT, 0666); if (fd == -1) { perror("Failed to open/create file"); return 1; } pagesize = sysconf(_SC_PAGE_SIZE); if (pagesize == -1) { perror("Failed to get page size"); return 2; } ret = posix_memalign(&write_buf, pagesize, pagesize); if (ret) { perror("Failed to allocate buffer"); return 3; } ret = pthread_create(&fsyncer, NULL, fsync_loop, NULL); if (ret != 0) { fprintf(stderr, "Failed to create writer thread: %d\n", ret); return 4; } while (1) { ret = do_write(fd, write_buf, pagesize, 0); if (ret != 0) { perror("Write failed"); exit(5); } } return 0; } $ mkfs.btrfs -f /dev/sdi $ mount /dev/sdi /mnt/sdi $ timeout 10 ./repro /mnt/sdi/foo Usually the race is triggered within less than 1 second. A test case for fstests will follow soon. Reported-by: Paulo Dias <paulo.miguel.dias(a)gmail.com> Link: https://bugzilla.kernel.org/show_bug.cgi?id=219187 Reported-by: Andreas Jahn <jahn-andi(a)web.de> Link: https://bugzilla.kernel.org/show_bug.cgi?id=219199 Reported-by: syzbot+4704b3cc972bd76024f1(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/00000000000044ff540620d7dee2@google.com/ Fixes: 939b656bc8ab ("btrfs: fix corruption after buffer fault in during direct IO append write") CC: stable(a)vger.kernel.org # 5.15+ Reviewed-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> --- fs/btrfs/ctree.h | 1 - fs/btrfs/file.c | 25 ++++++++++--------------- fs/btrfs/transaction.h | 6 ++++++ 3 files changed, 16 insertions(+), 16 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 86c7f8ce1715..06333a74d6c4 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -445,7 +445,6 @@ struct btrfs_file_private { void *filldir_buf; u64 last_index; struct extent_state *llseek_cached_state; - bool fsync_skip_inode_lock; }; static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 952cf145c629..15fd8c00f4c0 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1543,13 +1543,6 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) if (IS_ERR_OR_NULL(dio)) { err = PTR_ERR_OR_ZERO(dio); } else { - struct btrfs_file_private stack_private = { 0 }; - struct btrfs_file_private *private; - const bool have_private = (file->private_data != NULL); - - if (!have_private) - file->private_data = &stack_private; - /* * If we have a synchoronous write, we must make sure the fsync * triggered by the iomap_dio_complete() call below doesn't @@ -1558,13 +1551,10 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) * partial writes due to the input buffer (or parts of it) not * being already faulted in. */ - private = file->private_data; - private->fsync_skip_inode_lock = true; + ASSERT(current->journal_info == NULL); + current->journal_info = BTRFS_TRANS_DIO_WRITE_STUB; err = iomap_dio_complete(dio); - private->fsync_skip_inode_lock = false; - - if (!have_private) - file->private_data = NULL; + current->journal_info = NULL; } /* No increment (+=) because iomap returns a cumulative value. */ @@ -1796,7 +1786,6 @@ static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx) */ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { - struct btrfs_file_private *private = file->private_data; struct dentry *dentry = file_dentry(file); struct inode *inode = d_inode(dentry); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -1806,7 +1795,13 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) int ret = 0, err; u64 len; bool full_sync; - const bool skip_ilock = (private ? private->fsync_skip_inode_lock : false); + bool skip_ilock = false; + + if (current->journal_info == BTRFS_TRANS_DIO_WRITE_STUB) { + skip_ilock = true; + current->journal_info = NULL; + lockdep_assert_held(&inode->i_rwsem); + } trace_btrfs_sync_file(file, datasync); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 238a0ab85df9..7623db359881 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -12,6 +12,12 @@ #include "ctree.h" #include "misc.h" +/* + * Signal that a direct IO write is in progress, to avoid deadlock for sync + * direct IO writes when fsync is called during the direct IO write path. + */ +#define BTRFS_TRANS_DIO_WRITE_STUB ((void *) 1) + /* Radix-tree tag for roots that are part of the trasaction. */ #define BTRFS_ROOT_TRANS_TAG 0 -- 2.20.1

2 1

[PATCH openEuler-1.0-LTS 0/3] dhugetlb: make spin_lock irq save
by Liu Shixin 27 Sep '24

27 Sep '24

Liu Shixin (3): dhugetlb: Use helper function to lock/unlock dhugetlb: avoid lockdep warning with spin_lock_nested dhugetlb: make free_huge_page_to_dhugetlb_pool irq safe include/linux/hugetlb.h | 2 + mm/hugetlb.c | 115 ++++++++++++++++++++++++++-------------- mm/memcontrol.c | 8 +-- 3 files changed, 78 insertions(+), 47 deletions(-) -- 2.34.1

2 4

[PATCH openEuler-22.03-LTS-SP1] ethtool: check device is present when getting link settings
by Wang Liang 27 Sep '24

27 Sep '24

From: Jamie Bainbridge <jamie.bainbridge(a)gmail.com> stable inclusion from stable-v5.10.225 commit 842a40c7273ba1c1cb30dda50405b328de1d860e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAR4EU CVE: CVE-2024-46679 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a699781c79ecf6cfe67fb00a0331b4088c7c8466 ] A sysfs reader can race with a device reset or removal, attempting to read device state when the device is not actually present. eg: [exception RIP: qed_get_current_link+17] #8 [ffffb9e4f2907c48] qede_get_link_ksettings at ffffffffc07a994a [qede] #9 [ffffb9e4f2907cd8] __rh_call_get_link_ksettings at ffffffff992b01a3 #10 [ffffb9e4f2907d38] __ethtool_get_link_ksettings at ffffffff992b04e4 #11 [ffffb9e4f2907d90] duplex_show at ffffffff99260300 #12 [ffffb9e4f2907e38] dev_attr_show at ffffffff9905a01c #13 [ffffb9e4f2907e50] sysfs_kf_seq_show at ffffffff98e0145b #14 [ffffb9e4f2907e68] seq_read at ffffffff98d902e3 #15 [ffffb9e4f2907ec8] vfs_read at ffffffff98d657d1 #16 [ffffb9e4f2907f00] ksys_read at ffffffff98d65c3f #17 [ffffb9e4f2907f38] do_syscall_64 at ffffffff98a052fb crash> struct net_device.state ffff9a9d21336000 state = 5, state 5 is __LINK_STATE_START (0b1) and __LINK_STATE_NOCARRIER (0b100). The device is not present, note lack of __LINK_STATE_PRESENT (0b10). This is the same sort of panic as observed in commit 4224cfd7fb65 ("net-sysfs: add check for netdevice being present to speed_show"). There are many other callers of __ethtool_get_link_ksettings() which don't have a device presence check. Move this check into ethtool to protect all callers. Fixes: d519e17e2d01 ("net: export device speed and duplex via sysfs") Fixes: 4224cfd7fb65 ("net-sysfs: add check for netdevice being present to speed_show") Signed-off-by: Jamie Bainbridge <jamie.bainbridge(a)gmail.com> Link: https://patch.msgid.link/8bae218864beaa44ed01628140475b9bf641c5b0.172439367… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- net/core/net-sysfs.c | 2 +- net/ethtool/ioctl.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 989b3f7ee85f..99303897b7bb 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -213,7 +213,7 @@ static ssize_t speed_show(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev) && netif_device_present(netdev)) { + if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 63a88b3e861d..f11b5e3a78b1 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -432,6 +432,9 @@ int __ethtool_get_link_ksettings(struct net_device *dev, if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; + if (!netif_device_present(dev)) + return -ENODEV; + memset(link_ksettings, 0, sizeof(*link_ksettings)); return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); } -- 2.34.1

2 1

[PATCH OLK-5.10] ethtool: check device is present when getting link settings
by Wang Liang 27 Sep '24

27 Sep '24

From: Jamie Bainbridge <jamie.bainbridge(a)gmail.com> stable inclusion from stable-v5.10.225 commit 842a40c7273ba1c1cb30dda50405b328de1d860e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAR4EU CVE: CVE-2024-46679 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a699781c79ecf6cfe67fb00a0331b4088c7c8466 ] A sysfs reader can race with a device reset or removal, attempting to read device state when the device is not actually present. eg: [exception RIP: qed_get_current_link+17] #8 [ffffb9e4f2907c48] qede_get_link_ksettings at ffffffffc07a994a [qede] #9 [ffffb9e4f2907cd8] __rh_call_get_link_ksettings at ffffffff992b01a3 #10 [ffffb9e4f2907d38] __ethtool_get_link_ksettings at ffffffff992b04e4 #11 [ffffb9e4f2907d90] duplex_show at ffffffff99260300 #12 [ffffb9e4f2907e38] dev_attr_show at ffffffff9905a01c #13 [ffffb9e4f2907e50] sysfs_kf_seq_show at ffffffff98e0145b #14 [ffffb9e4f2907e68] seq_read at ffffffff98d902e3 #15 [ffffb9e4f2907ec8] vfs_read at ffffffff98d657d1 #16 [ffffb9e4f2907f00] ksys_read at ffffffff98d65c3f #17 [ffffb9e4f2907f38] do_syscall_64 at ffffffff98a052fb crash> struct net_device.state ffff9a9d21336000 state = 5, state 5 is __LINK_STATE_START (0b1) and __LINK_STATE_NOCARRIER (0b100). The device is not present, note lack of __LINK_STATE_PRESENT (0b10). This is the same sort of panic as observed in commit 4224cfd7fb65 ("net-sysfs: add check for netdevice being present to speed_show"). There are many other callers of __ethtool_get_link_ksettings() which don't have a device presence check. Move this check into ethtool to protect all callers. Fixes: d519e17e2d01 ("net: export device speed and duplex via sysfs") Fixes: 4224cfd7fb65 ("net-sysfs: add check for netdevice being present to speed_show") Signed-off-by: Jamie Bainbridge <jamie.bainbridge(a)gmail.com> Link: https://patch.msgid.link/8bae218864beaa44ed01628140475b9bf641c5b0.172439367… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- net/core/net-sysfs.c | 2 +- net/ethtool/ioctl.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 989b3f7ee85f..99303897b7bb 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -213,7 +213,7 @@ static ssize_t speed_show(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev) && netif_device_present(netdev)) { + if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 61a002f5dec6..bc956c346037 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -432,6 +432,9 @@ int __ethtool_get_link_ksettings(struct net_device *dev, if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; + if (!netif_device_present(dev)) + return -ENODEV; + memset(link_ksettings, 0, sizeof(*link_ksettings)); return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); } -- 2.34.1

2 1

[PATCH OLK-6.6] ethtool: check device is present when getting link settings
by Wang Liang 27 Sep '24

27 Sep '24

From: Jamie Bainbridge <jamie.bainbridge(a)gmail.com> stable inclusion from stable-v6.6.49 commit 94ab317024ba373d37340893d1c0358638935fbb category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAR4EU CVE: CVE-2024-46679 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a699781c79ecf6cfe67fb00a0331b4088c7c8466 ] A sysfs reader can race with a device reset or removal, attempting to read device state when the device is not actually present. eg: [exception RIP: qed_get_current_link+17] #8 [ffffb9e4f2907c48] qede_get_link_ksettings at ffffffffc07a994a [qede] #9 [ffffb9e4f2907cd8] __rh_call_get_link_ksettings at ffffffff992b01a3 #10 [ffffb9e4f2907d38] __ethtool_get_link_ksettings at ffffffff992b04e4 #11 [ffffb9e4f2907d90] duplex_show at ffffffff99260300 #12 [ffffb9e4f2907e38] dev_attr_show at ffffffff9905a01c #13 [ffffb9e4f2907e50] sysfs_kf_seq_show at ffffffff98e0145b #14 [ffffb9e4f2907e68] seq_read at ffffffff98d902e3 #15 [ffffb9e4f2907ec8] vfs_read at ffffffff98d657d1 #16 [ffffb9e4f2907f00] ksys_read at ffffffff98d65c3f #17 [ffffb9e4f2907f38] do_syscall_64 at ffffffff98a052fb crash> struct net_device.state ffff9a9d21336000 state = 5, state 5 is __LINK_STATE_START (0b1) and __LINK_STATE_NOCARRIER (0b100). The device is not present, note lack of __LINK_STATE_PRESENT (0b10). This is the same sort of panic as observed in commit 4224cfd7fb65 ("net-sysfs: add check for netdevice being present to speed_show"). There are many other callers of __ethtool_get_link_ksettings() which don't have a device presence check. Move this check into ethtool to protect all callers. Fixes: d519e17e2d01 ("net: export device speed and duplex via sysfs") Fixes: 4224cfd7fb65 ("net-sysfs: add check for netdevice being present to speed_show") Signed-off-by: Jamie Bainbridge <jamie.bainbridge(a)gmail.com> Link: https://patch.msgid.link/8bae218864beaa44ed01628140475b9bf641c5b0.172439367… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- net/core/net-sysfs.c | 2 +- net/ethtool/ioctl.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 5a9487af44e0..f7404bc67974 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -216,7 +216,7 @@ static ssize_t speed_show(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev) && netif_device_present(netdev)) { + if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 7cb23bcf8ef7..4486cbe2faf0 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -438,6 +438,9 @@ int __ethtool_get_link_ksettings(struct net_device *dev, if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; + if (!netif_device_present(dev)) + return -ENODEV; + memset(link_ksettings, 0, sizeof(*link_ksettings)); return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); } -- 2.34.1

2 1