kernel_optimize_test/include/linux/blktrace_api.h
Jan Kara c780e86dd4 blktrace: Protect q->blk_trace with RCU
KASAN is reporting that __blk_add_trace() has a use-after-free issue
when accessing q->blk_trace. Indeed the switching of block tracing (and
thus eventual freeing of q->blk_trace) is completely unsynchronized with
the currently running tracing and thus it can happen that the blk_trace
structure is being freed just while __blk_add_trace() works on it.
Protect accesses to q->blk_trace by RCU during tracing and make sure we
wait for the end of RCU grace period when shutting down tracing. Luckily
that is rare enough event that we can afford that. Note that postponing
the freeing of blk_trace to an RCU callback should better be avoided as
it could have unexpected user visible side-effects as debugfs files
would be still existing for a short while block tracing has been shut
down.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=205711
CC: stable@vger.kernel.org
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reported-by: Tristan Madani <tristmd@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-02-25 08:40:07 -07:00

142 lines
3.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BLKTRACE_H
#define BLKTRACE_H
#include <linux/blkdev.h>
#include <linux/relay.h>
#include <linux/compat.h>
#include <uapi/linux/blktrace_api.h>
#include <linux/list.h>
#if defined(CONFIG_BLK_DEV_IO_TRACE)
#include <linux/sysfs.h>
struct blk_trace {
int trace_state;
struct rchan *rchan;
unsigned long __percpu *sequence;
unsigned char __percpu *msg_data;
u16 act_mask;
u64 start_lba;
u64 end_lba;
u32 pid;
u32 dev;
struct dentry *dir;
struct dentry *dropped_file;
struct dentry *msg_file;
struct list_head running_list;
atomic_t dropped;
};
struct blkcg;
extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
extern void blk_trace_shutdown(struct request_queue *);
extern __printf(3, 4)
void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *fmt, ...);
/**
* blk_add_trace_msg - Add a (simple) message to the blktrace stream
* @q: queue the io is for
* @fmt: format to print message in
* args... Variable argument list for format
*
* Description:
* Records a (simple) message onto the blktrace stream.
*
* NOTE: BLK_TN_MAX_MSG characters are output at most.
* NOTE: Can not use 'static inline' due to presence of var args...
*
**/
#define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \
do { \
struct blk_trace *bt; \
\
rcu_read_lock(); \
bt = rcu_dereference((q)->blk_trace); \
if (unlikely(bt)) \
__trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\
rcu_read_unlock(); \
} while (0)
#define blk_add_trace_msg(q, fmt, ...) \
blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__)
#define BLK_TN_MAX_MSG 128
static inline bool blk_trace_note_message_enabled(struct request_queue *q)
{
struct blk_trace *bt;
bool ret;
rcu_read_lock();
bt = rcu_dereference(q->blk_trace);
ret = bt && (bt->act_mask & BLK_TC_NOTIFY);
rcu_read_unlock();
return ret;
}
extern void blk_add_driver_data(struct request_queue *q, struct request *rq,
void *data, size_t len);
extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
struct block_device *bdev,
char __user *arg);
extern int blk_trace_startstop(struct request_queue *q, int start);
extern int blk_trace_remove(struct request_queue *q);
extern void blk_trace_remove_sysfs(struct device *dev);
extern int blk_trace_init_sysfs(struct device *dev);
extern struct attribute_group blk_trace_attr_group;
#else /* !CONFIG_BLK_DEV_IO_TRACE */
# define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY)
# define blk_trace_shutdown(q) do { } while (0)
# define blk_add_driver_data(q, rq, data, len) do {} while (0)
# define blk_trace_setup(q, name, dev, bdev, arg) (-ENOTTY)
# define blk_trace_startstop(q, start) (-ENOTTY)
# define blk_trace_remove(q) (-ENOTTY)
# define blk_add_trace_msg(q, fmt, ...) do { } while (0)
# define blk_add_cgroup_trace_msg(q, cg, fmt, ...) do { } while (0)
# define blk_trace_remove_sysfs(dev) do { } while (0)
# define blk_trace_note_message_enabled(q) (false)
static inline int blk_trace_init_sysfs(struct device *dev)
{
return 0;
}
#endif /* CONFIG_BLK_DEV_IO_TRACE */
#ifdef CONFIG_COMPAT
struct compat_blk_user_trace_setup {
char name[BLKTRACE_BDEV_SIZE];
u16 act_mask;
u32 buf_size;
u32 buf_nr;
compat_u64 start_lba;
compat_u64 end_lba;
u32 pid;
};
#define BLKTRACESETUP32 _IOWR(0x12, 115, struct compat_blk_user_trace_setup)
#endif
extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes);
static inline sector_t blk_rq_trace_sector(struct request *rq)
{
/*
* Tracing should ignore starting sector for passthrough requests and
* requests where starting sector didn't get set.
*/
if (blk_rq_is_passthrough(rq) || blk_rq_pos(rq) == (sector_t)-1)
return 0;
return blk_rq_pos(rq);
}
static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq)
{
return blk_rq_is_passthrough(rq) ? 0 : blk_rq_sectors(rq);
}
#endif