When the filesystem is being mounted, the kernel panics while the data
regarding slot map allocation to the local node, is being written to the
disk. This occurs because the value of slot map buffer head block
number, which should have been greater than or equal to
`OCFS2_SUPER_BLOCK_BLKNO` (evaluating to 2) is less than it, indicative
of disk metadata corruption. This triggers
BUG_ON(bh->b_blocknr < OCFS2_SUPER_BLOCK_BLKNO) in ocfs2_write_block(),
causing the kernel to panic.
This is fixed by introducing function ocfs2_validate_slot_map_block() to
validate slot map blocks. It first checks if the buffer head passed to it
is up to date and valid, else it panics the kernel at that point itself.
Further, it contains an if condition block, which checks if `bh->b_blocknr`
is lesser than `OCFS2_SUPER_BLOCK_BLKNO`; if yes, then ocfs2_error is
called, which prints the error log, for debugging purposes, and the return
value of ocfs2_error() is returned. If the return value is zero. then error
code EIO is returned.
This function is used as validate function in calls to ocfs2_read_blocks()
in ocfs2_refresh_slot_info() and ocfs2_map_slot_buffers().
In addition, the function also contains
Reported-by: syzbot+c818e5c4559444f88aa0(a)syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=c818e5c4559444f88aa0
Tested-by: syzbot+c818e5c4559444f88aa0(a)syzkaller.appspotmail.com
Cc: stable(a)vger.kernel.org
Signed-off-by: Prithvi Tambewagh <activprithvi(a)gmail.com>
---
v2->v3:
- Create new function ocfs2_validate_slot_map_block() to validate block
number of slot map blocks, to be greater then or equal to
OCFS2_SUPER_BLOCK_BLKNO
- Use ocfs2_validate_slot_map_block() in calls to ocfs2_read_blocks() in
ocfs2_refresh_slot_info() and ocfs2_map_slot_buffers()
- In addition to using previously formulated if block in
ocfs2_validate_slot_map_block(), also check if the buffer head passed
in this function is up to date; if not, then kernel panics at that point
- Change title of patch to 'ocfs2: Add validate function for slot map blocks'
v2 link: https://lore.kernel.org/ocfs2-devel/nwkfpkm2wlajswykywnpt4sc6gdkesakw2sw7et…
v1->v2:
- Remove usage of le16_to_cpu() from ocfs2_error()
- Cast bh->b_blocknr to unsigned long long
- Remove type casting for OCFS2_SUPER_BLOCK_BLKNO
- Fix Sparse warnings reported in v1 by kernel test robot
- Update title from 'ocfs2: Fix kernel BUG in ocfs2_write_block' to
'ocfs2: fix kernel BUG in ocfs2_write_block'
v1 link: https://lore.kernel.org/all/20251206154819.175479-1-activprithvi@gmail.com/…
fs/ocfs2/slot_map.c | 29 +++++++++++++++++++++++++++--
1 file changed, 27 insertions(+), 2 deletions(-)
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index e544c704b583..50ddd7f50f8f 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -44,6 +44,9 @@ struct ocfs2_slot_info {
static int __ocfs2_node_num_to_slot(struct ocfs2_slot_info *si,
unsigned int node_num);
+static int ocfs2_validate_slot_map_block(struct super_block *sb,
+ struct buffer_head *bh);
+
static void ocfs2_invalidate_slot(struct ocfs2_slot_info *si,
int slot_num)
{
@@ -132,7 +135,8 @@ int ocfs2_refresh_slot_info(struct ocfs2_super *osb)
* this is not true, the read of -1 (UINT64_MAX) will fail.
*/
ret = ocfs2_read_blocks(INODE_CACHE(si->si_inode), -1, si->si_blocks,
- si->si_bh, OCFS2_BH_IGNORE_CACHE, NULL);
+ si->si_bh, OCFS2_BH_IGNORE_CACHE,
+ ocfs2_validate_slot_map_block);
if (ret == 0) {
spin_lock(&osb->osb_lock);
ocfs2_update_slot_info(si);
@@ -332,6 +336,26 @@ int ocfs2_clear_slot(struct ocfs2_super *osb, int slot_num)
return ocfs2_update_disk_slot(osb, osb->slot_info, slot_num);
}
+static int ocfs2_validate_slot_map_block(struct super_block *sb,
+ struct buffer_head *bh)
+{
+ int rc;
+
+ BUG_ON(!buffer_uptodate(bh));
+
+ if (bh->b_blocknr < OCFS2_SUPER_BLOCK_BLKNO) {
+ rc = ocfs2_error(sb,
+ "Invalid Slot Map Buffer Head "
+ "Block Number : %llu, Should be >= %d",
+ (unsigned long long)bh->b_blocknr,
+ OCFS2_SUPER_BLOCK_BLKNO);
+ if (!rc)
+ return -EIO;
+ return rc;
+ }
+ return 0;
+}
+
static int ocfs2_map_slot_buffers(struct ocfs2_super *osb,
struct ocfs2_slot_info *si)
{
@@ -383,7 +407,8 @@ static int ocfs2_map_slot_buffers(struct ocfs2_super *osb,
bh = NULL; /* Acquire a fresh bh */
status = ocfs2_read_blocks(INODE_CACHE(si->si_inode), blkno,
- 1, &bh, OCFS2_BH_IGNORE_CACHE, NULL);
+ 1, &bh, OCFS2_BH_IGNORE_CACHE,
+ ocfs2_validate_slot_map_block);
if (status < 0) {
mlog_errno(status);
goto bail;
base-commit: 24172e0d79900908cf5ebf366600616d29c9b417
--
2.43.0
`build_assert` relies on the compiler to optimize out its error path,
lest build fails with the dreaded error:
ERROR: modpost: "rust_build_error" [path/to/module.ko] undefined!
It has been observed that very trivial code performing I/O accesses
(sometimes even using an immediate value) would seemingly randomly fail
with this error whenever `CLIPPY=1` was set. The same behavior was also
observed until different, very similar conditions [1][2].
The cause, as pointed out by Gary Guo [3], appears to be that the
failing function is eventually using `build_assert` with its argument,
but is only annotated with `#[inline]`. This gives the compiler freedom
to not inline the function, which it notably did when Clippy was active,
triggering the error.
The fix is to annotate functions passing their argument to
`build_assert` with `#[inline(always)]`, telling the compiler to be as
aggressive as possible with their inlining. This is also the correct
behavior as inlining is mandatory for correct behavior in these cases.
This series fixes all possible points of failure in the kernel crate,
and adds documentation to `build_assert` explaining how to properly
inline functions for which this behavior may arise.
[1] https://lore.kernel.org/all/DEEUYUOAEZU3.1J1HM2YQ10EX1@nvidia.com/
[2] https://lore.kernel.org/all/A1A280D4-836E-4D75-863E-30B1C276C80C@collabora.…
[3] https://lore.kernel.org/all/20251121143008.2f5acc33.gary@garyguo.net/
Signed-off-by: Alexandre Courbot <acourbot(a)nvidia.com>
---
Changes in v3:
- Add "Fixes:" tags.
- CC stable on fixup patches.
- Link to v2: https://patch.msgid.link/20251128-io-build-assert-v2-0-a9ea9ce7d45d@nvidia.…
Changes in v2:
- Turn into a series and address other similar cases in the kernel crate.
- Link to v1: https://patch.msgid.link/20251127-io-build-assert-v1-1-04237f2e5850@nvidia.…
---
Alexandre Courbot (7):
rust: build_assert: add instructions for use with function arguments
rust: io: always inline functions using build_assert with arguments
rust: cpufreq: always inline functions using build_assert with arguments
rust: bits: always inline functions using build_assert with arguments
rust: sync: refcount: always inline functions using build_assert with arguments
rust: irq: always inline functions using build_assert with arguments
rust: num: bounded: add missing comment for always inlined function
rust/kernel/bits.rs | 6 ++++--
rust/kernel/build_assert.rs | 7 ++++++-
rust/kernel/cpufreq.rs | 2 ++
rust/kernel/io.rs | 9 ++++++---
rust/kernel/io/resource.rs | 2 ++
rust/kernel/irq/flags.rs | 2 ++
rust/kernel/num/bounded.rs | 1 +
rust/kernel/sync/refcount.rs | 3 ++-
8 files changed, 25 insertions(+), 7 deletions(-)
---
base-commit: ba65a4e7120a616d9c592750d9147f6dcafedffa
change-id: 20251127-io-build-assert-3579a5bfb81c
Best regards,
--
Alexandre Courbot <acourbot(a)nvidia.com>
This patch reverts fuse back to its original behavior of sync being a no-op.
This fixes the userspace regression reported by Athul and J. upstream in
[1][2] where if there is a bug in a fuse server that causes the server to
never complete writeback, it will make wait_sb_inodes() wait forever.
Thanks,
Joanne
[1] https://lore.kernel.org/regressions/CAJnrk1ZjQ8W8NzojsvJPRXiv9TuYPNdj8Ye7=C…
[2] https://lore.kernel.org/linux-fsdevel/aT7JRqhUvZvfUQlV@eldamar.lan/
Changelog:
v1: https://lore.kernel.org/linux-mm/20251120184211.2379439-1-joannelkoong@gmai…
* Change AS_WRITEBACK_MAY_HANG to AS_NO_DATA_INTEGRITY and keep
AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM as is.
Joanne Koong (1):
fs/writeback: skip AS_NO_DATA_INTEGRITY mappings in wait_sb_inodes()
fs/fs-writeback.c | 3 ++-
fs/fuse/file.c | 4 +++-
include/linux/pagemap.h | 11 +++++++++++
3 files changed, 16 insertions(+), 2 deletions(-)
--
2.47.3
In etm_setup_aux(), when a user sink is obtained via
coresight_get_sink_by_id(), it increments the reference count of the
sink device. However, if the sink is used in path building, the path
holds a reference, but the initial reference from
coresight_get_sink_by_id() is not released, causing a reference count
leak. We should release the initial reference after the path is built.
Found by code review.
Cc: stable(a)vger.kernel.org
Fixes: 0e6c20517596 ("coresight: etm-perf: Allow an event to use different sinks")
Signed-off-by: Ma Ke <make24(a)iscas.ac.cn>
---
Changes in v2:
- modified the patch as suggestions.
---
drivers/hwtracing/coresight/coresight-etm-perf.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 17afa0f4cdee..56d012ab6d3a 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -454,6 +454,11 @@ static void *etm_setup_aux(struct perf_event *event, void **pages,
goto err;
out:
+ if (user_sink) {
+ put_device(&user_sink->dev);
+ user_sink = NULL;
+ }
+
return event_data;
err:
--
2.17.1
In etm_setup_aux(), when a user sink is obtained via
coresight_get_sink_by_id(), it increments the reference count of the
sink device. However, if the sink is used in path building, the path
holds a reference, but the initial reference from
coresight_get_sink_by_id() is not released, causing a reference count
leak. We should release the initial reference after the path is built.
Found by code review.
Cc: stable(a)vger.kernel.org
Fixes: 0e6c20517596 ("coresight: etm-perf: Allow an event to use different sinks")
Signed-off-by: Ma Ke <make24(a)iscas.ac.cn>
---
Changes in v2:
- modified the patch as suggestions.
---
drivers/hwtracing/coresight/coresight-etm-perf.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 17afa0f4cdee..56d012ab6d3a 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -454,6 +454,11 @@ static void *etm_setup_aux(struct perf_event *event, void **pages,
goto err;
out:
+ if (user_sink) {
+ put_device(&user_sink->dev);
+ user_sink = NULL;
+ }
+
return event_data;
err:
--
2.17.1
The driver_override_show function reads the driver_override string
without holding the device_lock. However, the store function modifies
and frees the string while holding the device_lock. This creates a race
condition where the string can be freed by the store function while
being read by the show function, leading to a use-after-free.
To fix this, replace the rpmsg_string_attr macro with explicit show and
store functions. The new driver_override_store uses the standard
driver_set_override helper. Since the introduction of
driver_set_override, the comments in include/linux/rpmsg.h have stated
that this helper must be used to set or clear driver_override, but the
implementation was not updated until now.
Because driver_set_override modifies and frees the string while holding
the device_lock, the new driver_override_show now correctly holds the
device_lock during the read operation to prevent the race.
Additionally, since rpmsg_string_attr has only ever been used for
driver_override, removing the macro simplifies the code.
Fixes: 39e47767ec9b ("rpmsg: Add driver_override device attribute for rpmsg_device")
Cc: stable(a)vger.kernel.org
Signed-off-by: Gui-Dong Han <hanguidong02(a)gmail.com>
---
I verified this with a stress test that continuously writes/reads the
attribute. It triggered KASAN and leaked bytes like a0 f4 81 9f a3 ff ff
(likely kernel pointers). Since driver_override is world-readable (0644),
this allows unprivileged users to leak kernel pointers and bypass KASLR.
Similar races were fixed in other buses (e.g., commits 9561475db680 and
91d44c1afc61). Currently, 9 of 11 buses handle this correctly; this patch
fixes one of the remaining two.
---
drivers/rpmsg/rpmsg_core.c | 66 ++++++++++++++++----------------------
1 file changed, 27 insertions(+), 39 deletions(-)
diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c
index 5d661681a9b6..96964745065b 100644
--- a/drivers/rpmsg/rpmsg_core.c
+++ b/drivers/rpmsg/rpmsg_core.c
@@ -352,50 +352,38 @@ field##_show(struct device *dev, \
} \
static DEVICE_ATTR_RO(field);
-#define rpmsg_string_attr(field, member) \
-static ssize_t \
-field##_store(struct device *dev, struct device_attribute *attr, \
- const char *buf, size_t sz) \
-{ \
- struct rpmsg_device *rpdev = to_rpmsg_device(dev); \
- const char *old; \
- char *new; \
- \
- new = kstrndup(buf, sz, GFP_KERNEL); \
- if (!new) \
- return -ENOMEM; \
- new[strcspn(new, "\n")] = '\0'; \
- \
- device_lock(dev); \
- old = rpdev->member; \
- if (strlen(new)) { \
- rpdev->member = new; \
- } else { \
- kfree(new); \
- rpdev->member = NULL; \
- } \
- device_unlock(dev); \
- \
- kfree(old); \
- \
- return sz; \
-} \
-static ssize_t \
-field##_show(struct device *dev, \
- struct device_attribute *attr, char *buf) \
-{ \
- struct rpmsg_device *rpdev = to_rpmsg_device(dev); \
- \
- return sprintf(buf, "%s\n", rpdev->member); \
-} \
-static DEVICE_ATTR_RW(field)
-
/* for more info, see Documentation/ABI/testing/sysfs-bus-rpmsg */
rpmsg_show_attr(name, id.name, "%s\n");
rpmsg_show_attr(src, src, "0x%x\n");
rpmsg_show_attr(dst, dst, "0x%x\n");
rpmsg_show_attr(announce, announce ? "true" : "false", "%s\n");
-rpmsg_string_attr(driver_override, driver_override);
+
+static ssize_t driver_override_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct rpmsg_device *rpdev = to_rpmsg_device(dev);
+ int ret;
+
+ ret = driver_set_override(dev, &rpdev->driver_override, buf, count);
+ if (ret)
+ return ret;
+
+ return count;
+}
+
+static ssize_t driver_override_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct rpmsg_device *rpdev = to_rpmsg_device(dev);
+ ssize_t len;
+
+ device_lock(dev);
+ len = sysfs_emit(buf, "%s\n", rpdev->driver_override);
+ device_unlock(dev);
+ return len;
+}
+static DEVICE_ATTR_RW(driver_override);
static ssize_t modalias_show(struct device *dev,
struct device_attribute *attr, char *buf)
--
2.43.0