Revision 85bd839983778fcd0c1c043327b14a046e979b39 authored by Gu Zheng on 10 June 2015, 18:14:43 UTC, committed by Linus Torvalds on 10 June 2015, 23:43:43 UTC
Izumi found the following oops when hot re-adding a node: BUG: unable to handle kernel paging request at ffffc90008963690 IP: __wake_up_bit+0x20/0x70 Oops: 0000 [#1] SMP CPU: 68 PID: 1237 Comm: rs:main Q:Reg Not tainted 4.1.0-rc5 #80 Hardware name: FUJITSU PRIMEQUEST2800E/SB, BIOS PRIMEQUEST 2000 Series BIOS Version 1.87 04/28/2015 task: ffff880838df8000 ti: ffff880017b94000 task.ti: ffff880017b94000 RIP: 0010:[<ffffffff810dff80>] [<ffffffff810dff80>] __wake_up_bit+0x20/0x70 RSP: 0018:ffff880017b97be8 EFLAGS: 00010246 RAX: ffffc90008963690 RBX: 00000000003c0000 RCX: 000000000000a4c9 RDX: 0000000000000000 RSI: ffffea101bffd500 RDI: ffffc90008963648 RBP: ffff880017b97c08 R08: 0000000002000020 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8a0797c73800 R13: ffffea101bffd500 R14: 0000000000000001 R15: 00000000003c0000 FS: 00007fcc7ffff700(0000) GS:ffff880874800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffc90008963690 CR3: 0000000836761000 CR4: 00000000001407e0 Call Trace: unlock_page+0x6d/0x70 generic_write_end+0x53/0xb0 xfs_vm_write_end+0x29/0x80 [xfs] generic_perform_write+0x10a/0x1e0 xfs_file_buffered_aio_write+0x14d/0x3e0 [xfs] xfs_file_write_iter+0x79/0x120 [xfs] __vfs_write+0xd4/0x110 vfs_write+0xac/0x1c0 SyS_write+0x58/0xd0 system_call_fastpath+0x12/0x76 Code: 5d c3 66 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 48 83 ec 20 65 48 8b 04 25 28 00 00 00 48 89 45 f8 31 c0 48 8d 47 48 <48> 39 47 48 48 c7 45 e8 00 00 00 00 48 c7 45 f0 00 00 00 00 48 RIP [<ffffffff810dff80>] __wake_up_bit+0x20/0x70 RSP <ffff880017b97be8> CR2: ffffc90008963690 Reproduce method (re-add a node):: Hot-add nodeA --> remove nodeA --> hot-add nodeA (panic) This seems an use-after-free problem, and the root cause is zone->wait_table was not set to *NULL* after free it in try_offline_node. When hot re-add a node, we will reuse the pgdat of it, so does the zone struct, and when add pages to the target zone, it will init the zone first (including the wait_table) if the zone is not initialized. The judgement of zone initialized is based on zone->wait_table: static inline bool zone_is_initialized(struct zone *zone) { return !!zone->wait_table; } so if we do not set the zone->wait_table to *NULL* after free it, the memory hotplug routine will skip the init of new zone when hot re-add the node, and the wait_table still points to the freed memory, then we will access the invalid address when trying to wake up the waiting people after the i/o operation with the page is done, such as mentioned above. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Reported-by: Taku Izumi <izumi.taku@jp.fujitsu.com> Reviewed by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 5879ae5
blk-mq-tag.h
#ifndef INT_BLK_MQ_TAG_H
#define INT_BLK_MQ_TAG_H
#include "blk-mq.h"
enum {
BT_WAIT_QUEUES = 8,
BT_WAIT_BATCH = 8,
};
struct bt_wait_state {
atomic_t wait_cnt;
wait_queue_head_t wait;
} ____cacheline_aligned_in_smp;
#define TAG_TO_INDEX(bt, tag) ((tag) >> (bt)->bits_per_word)
#define TAG_TO_BIT(bt, tag) ((tag) & ((1 << (bt)->bits_per_word) - 1))
struct blk_mq_bitmap_tags {
unsigned int depth;
unsigned int wake_cnt;
unsigned int bits_per_word;
unsigned int map_nr;
struct blk_align_bitmap *map;
atomic_t wake_index;
struct bt_wait_state *bs;
};
/*
* Tag address space map.
*/
struct blk_mq_tags {
unsigned int nr_tags;
unsigned int nr_reserved_tags;
atomic_t active_queues;
struct blk_mq_bitmap_tags bitmap_tags;
struct blk_mq_bitmap_tags breserved_tags;
struct request **rqs;
struct list_head page_list;
int alloc_policy;
};
extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, int alloc_policy);
extern void blk_mq_free_tags(struct blk_mq_tags *tags);
extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, unsigned int tag, unsigned int *last_tag);
extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
extern ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page);
extern void blk_mq_tag_init_last_tag(struct blk_mq_tags *tags, unsigned int *last_tag);
extern int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int depth);
extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
enum {
BLK_MQ_TAG_CACHE_MIN = 1,
BLK_MQ_TAG_CACHE_MAX = 64,
};
enum {
BLK_MQ_TAG_FAIL = -1U,
BLK_MQ_TAG_MIN = BLK_MQ_TAG_CACHE_MIN,
BLK_MQ_TAG_MAX = BLK_MQ_TAG_FAIL - 1,
};
extern bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *);
extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *);
static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
{
if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
return false;
return __blk_mq_tag_busy(hctx);
}
static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
{
if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
return;
__blk_mq_tag_idle(hctx);
}
#endif
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...