linux/block/blk-cgroup.h
Vivek Goyal e5ff082e8a blkio: Fix another BUG_ON() crash due to cfqq movement across groups
o Once in a while, I was hitting a BUG_ON() in blkio code. empty_time was
  assuming that upon slice expiry, group can't be marked empty already (except
  forced dispatch).

  But this assumption is broken if cfqq can move (group_isolation=0) across
  groups after receiving a request.

  I think most likely in this case we got a request in a cfqq and accounted
  the rq in one group, later while adding the cfqq to tree, we moved the queue
  to a different group which was already marked empty and after dispatch from
  slice we found group already marked empty and raised alarm.

  This patch does not error out if group is already marked empty. This can
  introduce some empty_time stat error only in case of group_isolation=0. This
  is better than crashing. In case of group_isolation=1 we should still get
  same stats as before this patch.

[  222.308546] ------------[ cut here ]------------
[  222.309311] kernel BUG at block/blk-cgroup.c:236!
[  222.309311] invalid opcode: 0000 [#1] SMP
[  222.309311] last sysfs file: /sys/devices/virtual/block/dm-3/queue/scheduler
[  222.309311] CPU 1
[  222.309311] Modules linked in: dm_round_robin dm_multipath qla2xxx scsi_transport_fc dm_zero dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan]
[  222.309311]
[  222.309311] Pid: 4780, comm: fio Not tainted 2.6.34-rc4-blkio-config #68 0A98h/HP xw8600 Workstation
[  222.309311] RIP: 0010:[<ffffffff8121ad88>]  [<ffffffff8121ad88>] blkiocg_set_start_empty_time+0x50/0x83
[  222.309311] RSP: 0018:ffff8800ba6e79f8  EFLAGS: 00010002
[  222.309311] RAX: 0000000000000082 RBX: ffff8800a13b7990 RCX: ffff8800a13b7808
[  222.309311] RDX: 0000000000002121 RSI: 0000000000000082 RDI: ffff8800a13b7a30
[  222.309311] RBP: ffff8800ba6e7a18 R08: 0000000000000000 R09: 0000000000000001
[  222.309311] R10: 000000000002f8c8 R11: ffff8800ba6e7ad8 R12: ffff8800a13b78ff
[  222.309311] R13: ffff8800a13b7990 R14: 0000000000000001 R15: ffff8800a13b7808
[  222.309311] FS:  00007f3beec476f0(0000) GS:ffff880001e40000(0000) knlGS:0000000000000000
[  222.309311] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  222.309311] CR2: 000000000040e7f0 CR3: 00000000a12d5000 CR4: 00000000000006e0
[  222.309311] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  222.309311] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[  222.309311] Process fio (pid: 4780, threadinfo ffff8800ba6e6000, task ffff8800b3d6bf00)
[  222.309311] Stack:
[  222.309311]  0000000000000001 ffff8800bab17a48 ffff8800bab17a48 ffff8800a13b7800
[  222.309311] <0> ffff8800ba6e7a68 ffffffff8121da35 ffff880000000001 00ff8800ba5c5698
[  222.309311] <0> ffff8800ba6e7a68 ffff8800a13b7800 0000000000000000 ffff8800bab17a48
[  222.309311] Call Trace:
[  222.309311]  [<ffffffff8121da35>] __cfq_slice_expired+0x2af/0x3ec
[  222.309311]  [<ffffffff8121fd7b>] cfq_dispatch_requests+0x2c8/0x8e8
[  222.309311]  [<ffffffff8120f1cd>] ? spin_unlock_irqrestore+0xe/0x10
[  222.309311]  [<ffffffff8120fb1a>] ? blk_insert_cloned_request+0x70/0x7b
[  222.309311]  [<ffffffff81210461>] blk_peek_request+0x191/0x1a7
[  222.309311]  [<ffffffffa0002799>] dm_request_fn+0x38/0x14c [dm_mod]
[  222.309311]  [<ffffffff810ae61f>] ? sync_page_killable+0x0/0x35
[  222.309311]  [<ffffffff81210fd4>] __generic_unplug_device+0x32/0x37
[  222.309311]  [<ffffffff81211274>] generic_unplug_device+0x2e/0x3c
[  222.309311]  [<ffffffffa00011a6>] dm_unplug_all+0x42/0x5b [dm_mod]
[  222.309311]  [<ffffffff8120ca37>] blk_unplug+0x29/0x2d
[  222.309311]  [<ffffffff8120ca4d>] blk_backing_dev_unplug+0x12/0x14
[  222.309311]  [<ffffffff81109a7a>] block_sync_page+0x35/0x39
[  222.309311]  [<ffffffff810ae616>] sync_page+0x41/0x4a
[  222.309311]  [<ffffffff810ae62d>] sync_page_killable+0xe/0x35
[  222.309311]  [<ffffffff8158aa59>] __wait_on_bit_lock+0x46/0x8f
[  222.309311]  [<ffffffff810ae4f5>] __lock_page_killable+0x66/0x6d
[  222.309311]  [<ffffffff81056f9c>] ? wake_bit_function+0x0/0x33
[  222.309311]  [<ffffffff810ae528>] lock_page_killable+0x2c/0x2e
[  222.309311]  [<ffffffff810afbc5>] generic_file_aio_read+0x361/0x4f0
[  222.309311]  [<ffffffff810ea044>] do_sync_read+0xcb/0x108
[  222.309311]  [<ffffffff811e42f7>] ? security_file_permission+0x16/0x18
[  222.309311]  [<ffffffff810ea6ab>] vfs_read+0xab/0x108
[  222.309311]  [<ffffffff810ea7c8>] sys_read+0x4a/0x6e
[  222.309311]  [<ffffffff81002b5b>] system_call_fastpath+0x16/0x1b
[  222.309311] Code: 58 01 00 00 00 48 89 c6 75 0a 48 83 bb 60 01 00 00 00 74 09 48 8d bb a0 00 00 00 eb 35 41 fe cc 74 0d f6 83 c0 01 00 00 04 74 04 <0f> 0b eb fe 48 89 75 e8 e8 be e0 de ff 66 83 8b c0 01 00 00 04
[  222.309311] RIP  [<ffffffff8121ad88>] blkiocg_set_start_empty_time+0x50/0x83
[  222.309311]  RSP <ffff8800ba6e79f8>
[  222.309311] ---[ end trace 32b4f71dffc15712 ]---

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Acked-by: Divyesh Shah <dpshah@google.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-26 19:25:11 +02:00

259 lines
8.0 KiB
C

#ifndef _BLK_CGROUP_H
#define _BLK_CGROUP_H
/*
* Common Block IO controller cgroup interface
*
* Based on ideas and code from CFQ, CFS and BFQ:
* Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
*
* Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
* Paolo Valente <paolo.valente@unimore.it>
*
* Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
* Nauman Rafique <nauman@google.com>
*/
#include <linux/cgroup.h>
#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
#ifndef CONFIG_BLK_CGROUP
/* When blk-cgroup is a module, its subsys_id isn't a compile-time constant */
extern struct cgroup_subsys blkio_subsys;
#define blkio_subsys_id blkio_subsys.subsys_id
#endif
enum stat_type {
/* Total time spent (in ns) between request dispatch to the driver and
* request completion for IOs doen by this cgroup. This may not be
* accurate when NCQ is turned on. */
BLKIO_STAT_SERVICE_TIME = 0,
/* Total bytes transferred */
BLKIO_STAT_SERVICE_BYTES,
/* Total IOs serviced, post merge */
BLKIO_STAT_SERVICED,
/* Total time spent waiting in scheduler queue in ns */
BLKIO_STAT_WAIT_TIME,
/* Number of IOs merged */
BLKIO_STAT_MERGED,
/* Number of IOs queued up */
BLKIO_STAT_QUEUED,
/* All the single valued stats go below this */
BLKIO_STAT_TIME,
BLKIO_STAT_SECTORS,
#ifdef CONFIG_DEBUG_BLK_CGROUP
BLKIO_STAT_AVG_QUEUE_SIZE,
BLKIO_STAT_IDLE_TIME,
BLKIO_STAT_EMPTY_TIME,
BLKIO_STAT_GROUP_WAIT_TIME,
BLKIO_STAT_DEQUEUE
#endif
};
enum stat_sub_type {
BLKIO_STAT_READ = 0,
BLKIO_STAT_WRITE,
BLKIO_STAT_SYNC,
BLKIO_STAT_ASYNC,
BLKIO_STAT_TOTAL
};
/* blkg state flags */
enum blkg_state_flags {
BLKG_waiting = 0,
BLKG_idling,
BLKG_empty,
};
struct blkio_cgroup {
struct cgroup_subsys_state css;
unsigned int weight;
spinlock_t lock;
struct hlist_head blkg_list;
struct list_head policy_list; /* list of blkio_policy_node */
};
struct blkio_group_stats {
/* total disk time and nr sectors dispatched by this group */
uint64_t time;
uint64_t sectors;
uint64_t stat_arr[BLKIO_STAT_QUEUED + 1][BLKIO_STAT_TOTAL];
#ifdef CONFIG_DEBUG_BLK_CGROUP
/* Sum of number of IOs queued across all samples */
uint64_t avg_queue_size_sum;
/* Count of samples taken for average */
uint64_t avg_queue_size_samples;
/* How many times this group has been removed from service tree */
unsigned long dequeue;
/* Total time spent waiting for it to be assigned a timeslice. */
uint64_t group_wait_time;
uint64_t start_group_wait_time;
/* Time spent idling for this blkio_group */
uint64_t idle_time;
uint64_t start_idle_time;
/*
* Total time when we have requests queued and do not contain the
* current active queue.
*/
uint64_t empty_time;
uint64_t start_empty_time;
uint16_t flags;
#endif
};
struct blkio_group {
/* An rcu protected unique identifier for the group */
void *key;
struct hlist_node blkcg_node;
unsigned short blkcg_id;
#ifdef CONFIG_DEBUG_BLK_CGROUP
/* Store cgroup path */
char path[128];
#endif
/* The device MKDEV(major, minor), this group has been created for */
dev_t dev;
/* Need to serialize the stats in the case of reset/update */
spinlock_t stats_lock;
struct blkio_group_stats stats;
};
struct blkio_policy_node {
struct list_head node;
dev_t dev;
unsigned int weight;
};
extern unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
dev_t dev);
typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg);
typedef void (blkio_update_group_weight_fn) (struct blkio_group *blkg,
unsigned int weight);
struct blkio_policy_ops {
blkio_unlink_group_fn *blkio_unlink_group_fn;
blkio_update_group_weight_fn *blkio_update_group_weight_fn;
};
struct blkio_policy_type {
struct list_head list;
struct blkio_policy_ops ops;
};
/* Blkio controller policy registration */
extern void blkio_policy_register(struct blkio_policy_type *);
extern void blkio_policy_unregister(struct blkio_policy_type *);
#else
struct blkio_group {
};
struct blkio_policy_type {
};
static inline void blkio_policy_register(struct blkio_policy_type *blkiop) { }
static inline void blkio_policy_unregister(struct blkio_policy_type *blkiop) { }
#endif
#define BLKIO_WEIGHT_MIN 100
#define BLKIO_WEIGHT_MAX 1000
#define BLKIO_WEIGHT_DEFAULT 500
#ifdef CONFIG_DEBUG_BLK_CGROUP
static inline char *blkg_path(struct blkio_group *blkg)
{
return blkg->path;
}
void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg);
void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
unsigned long dequeue);
void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg);
void blkiocg_update_idle_time_stats(struct blkio_group *blkg);
void blkiocg_set_start_empty_time(struct blkio_group *blkg);
#define BLKG_FLAG_FNS(name) \
static inline void blkio_mark_blkg_##name( \
struct blkio_group_stats *stats) \
{ \
stats->flags |= (1 << BLKG_##name); \
} \
static inline void blkio_clear_blkg_##name( \
struct blkio_group_stats *stats) \
{ \
stats->flags &= ~(1 << BLKG_##name); \
} \
static inline int blkio_blkg_##name(struct blkio_group_stats *stats) \
{ \
return (stats->flags & (1 << BLKG_##name)) != 0; \
} \
BLKG_FLAG_FNS(waiting)
BLKG_FLAG_FNS(idling)
BLKG_FLAG_FNS(empty)
#undef BLKG_FLAG_FNS
#else
static inline char *blkg_path(struct blkio_group *blkg) { return NULL; }
static inline void blkiocg_update_avg_queue_size_stats(
struct blkio_group *blkg) {}
static inline void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
unsigned long dequeue) {}
static inline void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg)
{}
static inline void blkiocg_update_idle_time_stats(struct blkio_group *blkg) {}
static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg) {}
#endif
#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
extern struct blkio_cgroup blkio_root_cgroup;
extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
struct blkio_group *blkg, void *key, dev_t dev);
extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
void *key);
void blkiocg_update_timeslice_used(struct blkio_group *blkg,
unsigned long time);
void blkiocg_update_dispatch_stats(struct blkio_group *blkg, uint64_t bytes,
bool direction, bool sync);
void blkiocg_update_completion_stats(struct blkio_group *blkg,
uint64_t start_time, uint64_t io_start_time, bool direction, bool sync);
void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
bool sync);
void blkiocg_update_io_add_stats(struct blkio_group *blkg,
struct blkio_group *curr_blkg, bool direction, bool sync);
void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
bool direction, bool sync);
#else
struct cgroup;
static inline struct blkio_cgroup *
cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
struct blkio_group *blkg, void *key, dev_t dev) {}
static inline int
blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
static inline struct blkio_group *
blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; }
static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg,
unsigned long time) {}
static inline void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
uint64_t bytes, bool direction, bool sync) {}
static inline void blkiocg_update_completion_stats(struct blkio_group *blkg,
uint64_t start_time, uint64_t io_start_time, bool direction,
bool sync) {}
static inline void blkiocg_update_io_merged_stats(struct blkio_group *blkg,
bool direction, bool sync) {}
static inline void blkiocg_update_io_add_stats(struct blkio_group *blkg,
struct blkio_group *curr_blkg, bool direction, bool sync) {}
static inline void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
bool direction, bool sync) {}
#endif
#endif /* _BLK_CGROUP_H */