alistair23-linux/include/linux/ceph/osd_client.h
Ilya Dryomov 6c1ea260f8 libceph: make authorizer destruction independent of ceph_auth_client
Starting the kernel client with cephx disabled and then enabling cephx
and restarting userspace daemons can result in a crash:

    [262671.478162] BUG: unable to handle kernel paging request at ffffebe000000000
    [262671.531460] IP: [<ffffffff811cd04a>] kfree+0x5a/0x130
    [262671.584334] PGD 0
    [262671.635847] Oops: 0000 [#1] SMP
    [262672.055841] CPU: 22 PID: 2961272 Comm: kworker/22:2 Not tainted 4.2.0-34-generic #39~14.04.1-Ubuntu
    [262672.162338] Hardware name: Dell Inc. PowerEdge R720/068CDY, BIOS 2.4.3 07/09/2014
    [262672.268937] Workqueue: ceph-msgr con_work [libceph]
    [262672.322290] task: ffff88081c2d0dc0 ti: ffff880149ae8000 task.ti: ffff880149ae8000
    [262672.428330] RIP: 0010:[<ffffffff811cd04a>]  [<ffffffff811cd04a>] kfree+0x5a/0x130
    [262672.535880] RSP: 0018:ffff880149aeba58  EFLAGS: 00010286
    [262672.589486] RAX: 000001e000000000 RBX: 0000000000000012 RCX: ffff8807e7461018
    [262672.695980] RDX: 000077ff80000000 RSI: ffff88081af2be04 RDI: 0000000000000012
    [262672.803668] RBP: ffff880149aeba78 R08: 0000000000000000 R09: 0000000000000000
    [262672.912299] R10: ffffebe000000000 R11: ffff880819a60e78 R12: ffff8800aec8df40
    [262673.021769] R13: ffffffffc035f70f R14: ffff8807e5b138e0 R15: ffff880da9785840
    [262673.131722] FS:  0000000000000000(0000) GS:ffff88081fac0000(0000) knlGS:0000000000000000
    [262673.245377] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    [262673.303281] CR2: ffffebe000000000 CR3: 0000000001c0d000 CR4: 00000000001406e0
    [262673.417556] Stack:
    [262673.472943]  ffff880149aeba88 ffff88081af2be04 ffff8800aec8df40 ffff88081af2be04
    [262673.583767]  ffff880149aeba98 ffffffffc035f70f ffff880149aebac8 ffff8800aec8df00
    [262673.694546]  ffff880149aebac8 ffffffffc035c89e ffff8807e5b138e0 ffff8805b047f800
    [262673.805230] Call Trace:
    [262673.859116]  [<ffffffffc035f70f>] ceph_x_destroy_authorizer+0x1f/0x50 [libceph]
    [262673.968705]  [<ffffffffc035c89e>] ceph_auth_destroy_authorizer+0x3e/0x60 [libceph]
    [262674.078852]  [<ffffffffc0352805>] put_osd+0x45/0x80 [libceph]
    [262674.134249]  [<ffffffffc035290e>] remove_osd+0xae/0x140 [libceph]
    [262674.189124]  [<ffffffffc0352aa3>] __reset_osd+0x103/0x150 [libceph]
    [262674.243749]  [<ffffffffc0354703>] kick_requests+0x223/0x460 [libceph]
    [262674.297485]  [<ffffffffc03559e2>] ceph_osdc_handle_map+0x282/0x5e0 [libceph]
    [262674.350813]  [<ffffffffc035022e>] dispatch+0x4e/0x720 [libceph]
    [262674.403312]  [<ffffffffc034bd91>] try_read+0x3d1/0x1090 [libceph]
    [262674.454712]  [<ffffffff810ab7c2>] ? dequeue_entity+0x152/0x690
    [262674.505096]  [<ffffffffc034cb1b>] con_work+0xcb/0x1300 [libceph]
    [262674.555104]  [<ffffffff8108fb3e>] process_one_work+0x14e/0x3d0
    [262674.604072]  [<ffffffff810901ea>] worker_thread+0x11a/0x470
    [262674.652187]  [<ffffffff810900d0>] ? rescuer_thread+0x310/0x310
    [262674.699022]  [<ffffffff810957a2>] kthread+0xd2/0xf0
    [262674.744494]  [<ffffffff810956d0>] ? kthread_create_on_node+0x1c0/0x1c0
    [262674.789543]  [<ffffffff817bd81f>] ret_from_fork+0x3f/0x70
    [262674.834094]  [<ffffffff810956d0>] ? kthread_create_on_node+0x1c0/0x1c0

What happens is the following:

    (1) new MON session is established
    (2) old "none" ac is destroyed
    (3) new "cephx" ac is constructed
    ...
    (4) old OSD session (w/ "none" authorizer) is put
          ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer)

osd->o_auth.authorizer in the "none" case is just a bare pointer into
ac, which contains a single static copy for all services.  By the time
we get to (4), "none" ac, freed in (2), is long gone.  On top of that,
a new vtable installed in (3) points us at ceph_x_destroy_authorizer(),
so we end up trying to destroy a "none" authorizer with a "cephx"
destructor operating on invalid memory!

To fix this, decouple authorizer destruction from ac and do away with
a single static "none" authorizer by making a copy for each OSD or MDS
session.  Authorizers themselves are independent of ac and so there is
no reason for destroy_authorizer() to be an ac op.  Make it an op on
the authorizer itself by turning ceph_authorizer into a real struct.

Fixes: http://tracker.ceph.com/issues/15447

Reported-by: Alan Zhang <alan.zhang@linux.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
2016-04-25 20:54:13 +02:00

382 lines
11 KiB
C

#ifndef _FS_CEPH_OSD_CLIENT_H
#define _FS_CEPH_OSD_CLIENT_H
#include <linux/completion.h>
#include <linux/kref.h>
#include <linux/mempool.h>
#include <linux/rbtree.h>
#include <linux/ceph/types.h>
#include <linux/ceph/osdmap.h>
#include <linux/ceph/messenger.h>
#include <linux/ceph/auth.h>
#include <linux/ceph/pagelist.h>
struct ceph_msg;
struct ceph_snap_context;
struct ceph_osd_request;
struct ceph_osd_client;
/*
* completion callback for async writepages
*/
typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *,
struct ceph_msg *);
typedef void (*ceph_osdc_unsafe_callback_t)(struct ceph_osd_request *, bool);
/* a given osd we're communicating with */
struct ceph_osd {
atomic_t o_ref;
struct ceph_osd_client *o_osdc;
int o_osd;
int o_incarnation;
struct rb_node o_node;
struct ceph_connection o_con;
struct list_head o_requests;
struct list_head o_linger_requests;
struct list_head o_osd_lru;
struct ceph_auth_handshake o_auth;
unsigned long lru_ttl;
int o_marked_for_keepalive;
struct list_head o_keepalive_item;
};
#define CEPH_OSD_SLAB_OPS 2
#define CEPH_OSD_MAX_OPS 16
enum ceph_osd_data_type {
CEPH_OSD_DATA_TYPE_NONE = 0,
CEPH_OSD_DATA_TYPE_PAGES,
CEPH_OSD_DATA_TYPE_PAGELIST,
#ifdef CONFIG_BLOCK
CEPH_OSD_DATA_TYPE_BIO,
#endif /* CONFIG_BLOCK */
};
struct ceph_osd_data {
enum ceph_osd_data_type type;
union {
struct {
struct page **pages;
u64 length;
u32 alignment;
bool pages_from_pool;
bool own_pages;
};
struct ceph_pagelist *pagelist;
#ifdef CONFIG_BLOCK
struct {
struct bio *bio; /* list of bios */
size_t bio_length; /* total in list */
};
#endif /* CONFIG_BLOCK */
};
};
struct ceph_osd_req_op {
u16 op; /* CEPH_OSD_OP_* */
u32 flags; /* CEPH_OSD_OP_FLAG_* */
u32 indata_len; /* request */
u32 outdata_len; /* reply */
s32 rval;
union {
struct ceph_osd_data raw_data_in;
struct {
u64 offset, length;
u64 truncate_size;
u32 truncate_seq;
struct ceph_osd_data osd_data;
} extent;
struct {
u32 name_len;
u32 value_len;
__u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */
__u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */
struct ceph_osd_data osd_data;
} xattr;
struct {
const char *class_name;
const char *method_name;
struct ceph_osd_data request_info;
struct ceph_osd_data request_data;
struct ceph_osd_data response_data;
__u8 class_len;
__u8 method_len;
__u8 argc;
} cls;
struct {
u64 cookie;
u64 ver;
u32 prot_ver;
u32 timeout;
__u8 flag;
} watch;
struct {
u64 expected_object_size;
u64 expected_write_size;
} alloc_hint;
};
};
/* an in-flight request */
struct ceph_osd_request {
u64 r_tid; /* unique for this client */
struct rb_node r_node;
struct list_head r_req_lru_item;
struct list_head r_osd_item;
struct list_head r_linger_item;
struct list_head r_linger_osd_item;
struct ceph_osd *r_osd;
struct ceph_pg r_pgid;
int r_pg_osds[CEPH_PG_MAX_SIZE];
int r_num_pg_osds;
struct ceph_msg *r_request, *r_reply;
int r_flags; /* any additional flags for the osd */
u32 r_sent; /* >0 if r_request is sending/sent */
/* request osd ops array */
unsigned int r_num_ops;
/* these are updated on each send */
__le32 *r_request_osdmap_epoch;
__le32 *r_request_flags;
__le64 *r_request_pool;
void *r_request_pgid;
__le32 *r_request_attempts;
bool r_paused;
struct ceph_eversion *r_request_reassert_version;
int r_result;
int r_got_reply;
int r_linger;
struct ceph_osd_client *r_osdc;
struct kref r_kref;
bool r_mempool;
struct completion r_completion, r_safe_completion;
ceph_osdc_callback_t r_callback;
ceph_osdc_unsafe_callback_t r_unsafe_callback;
struct ceph_eversion r_reassert_version;
struct list_head r_unsafe_item;
struct inode *r_inode; /* for use by callbacks */
void *r_priv; /* ditto */
struct ceph_object_locator r_base_oloc;
struct ceph_object_id r_base_oid;
struct ceph_object_locator r_target_oloc;
struct ceph_object_id r_target_oid;
u64 r_snapid;
unsigned long r_stamp; /* send OR check time */
struct ceph_snap_context *r_snapc; /* snap context for writes */
struct ceph_osd_req_op r_ops[];
};
struct ceph_request_redirect {
struct ceph_object_locator oloc;
};
struct ceph_osd_event {
u64 cookie;
int one_shot;
struct ceph_osd_client *osdc;
void (*cb)(u64, u64, u8, void *);
void *data;
struct rb_node node;
struct list_head osd_node;
struct kref kref;
};
struct ceph_osd_event_work {
struct work_struct work;
struct ceph_osd_event *event;
u64 ver;
u64 notify_id;
u8 opcode;
};
struct ceph_osd_client {
struct ceph_client *client;
struct ceph_osdmap *osdmap; /* current map */
struct rw_semaphore map_sem;
struct completion map_waiters;
u64 last_requested_map;
struct mutex request_mutex;
struct rb_root osds; /* osds */
struct list_head osd_lru; /* idle osds */
u64 timeout_tid; /* tid of timeout triggering rq */
u64 last_tid; /* tid of last request */
struct rb_root requests; /* pending requests */
struct list_head req_lru; /* in-flight lru */
struct list_head req_unsent; /* unsent/need-resend queue */
struct list_head req_notarget; /* map to no osd */
struct list_head req_linger; /* lingering requests */
int num_requests;
struct delayed_work timeout_work;
struct delayed_work osds_timeout_work;
#ifdef CONFIG_DEBUG_FS
struct dentry *debugfs_file;
#endif
mempool_t *req_mempool;
struct ceph_msgpool msgpool_op;
struct ceph_msgpool msgpool_op_reply;
spinlock_t event_lock;
struct rb_root event_tree;
u64 event_count;
struct workqueue_struct *notify_wq;
};
extern int ceph_osdc_setup(void);
extern void ceph_osdc_cleanup(void);
extern int ceph_osdc_init(struct ceph_osd_client *osdc,
struct ceph_client *client);
extern void ceph_osdc_stop(struct ceph_osd_client *osdc);
extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,
struct ceph_msg *msg);
extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
struct ceph_msg *msg);
extern void osd_req_op_init(struct ceph_osd_request *osd_req,
unsigned int which, u16 opcode, u32 flags);
extern void osd_req_op_raw_data_in_pages(struct ceph_osd_request *,
unsigned int which,
struct page **pages, u64 length,
u32 alignment, bool pages_from_pool,
bool own_pages);
extern void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
unsigned int which, u16 opcode,
u64 offset, u64 length,
u64 truncate_size, u32 truncate_seq);
extern void osd_req_op_extent_update(struct ceph_osd_request *osd_req,
unsigned int which, u64 length);
extern void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req,
unsigned int which, u64 offset_inc);
extern struct ceph_osd_data *osd_req_op_extent_osd_data(
struct ceph_osd_request *osd_req,
unsigned int which);
extern struct ceph_osd_data *osd_req_op_cls_response_data(
struct ceph_osd_request *osd_req,
unsigned int which);
extern void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *,
unsigned int which,
struct page **pages, u64 length,
u32 alignment, bool pages_from_pool,
bool own_pages);
extern void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *,
unsigned int which,
struct ceph_pagelist *pagelist);
#ifdef CONFIG_BLOCK
extern void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *,
unsigned int which,
struct bio *bio, size_t bio_length);
#endif /* CONFIG_BLOCK */
extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *,
unsigned int which,
struct ceph_pagelist *pagelist);
extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *,
unsigned int which,
struct page **pages, u64 length,
u32 alignment, bool pages_from_pool,
bool own_pages);
extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *,
unsigned int which,
struct page **pages, u64 length,
u32 alignment, bool pages_from_pool,
bool own_pages);
extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req,
unsigned int which, u16 opcode,
const char *class, const char *method);
extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
u16 opcode, const char *name, const void *value,
size_t size, u8 cmp_op, u8 cmp_mode);
extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
unsigned int which, u16 opcode,
u64 cookie, u64 version, int flag);
extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
unsigned int which,
u64 expected_object_size,
u64 expected_write_size);
extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
struct ceph_snap_context *snapc,
unsigned int num_ops,
bool use_mempool,
gfp_t gfp_flags);
extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off,
struct ceph_snap_context *snapc,
u64 snap_id,
struct timespec *mtime);
extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
struct ceph_file_layout *layout,
struct ceph_vino vino,
u64 offset, u64 *len,
unsigned int which, int num_ops,
int opcode, int flags,
struct ceph_snap_context *snapc,
u32 truncate_seq, u64 truncate_size,
bool use_mempool);
extern void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc,
struct ceph_osd_request *req);
extern void ceph_osdc_get_request(struct ceph_osd_request *req);
extern void ceph_osdc_put_request(struct ceph_osd_request *req);
extern int ceph_osdc_start_request(struct ceph_osd_client *osdc,
struct ceph_osd_request *req,
bool nofail);
extern void ceph_osdc_cancel_request(struct ceph_osd_request *req);
extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
struct ceph_osd_request *req);
extern void ceph_osdc_sync(struct ceph_osd_client *osdc);
extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc);
extern int ceph_osdc_readpages(struct ceph_osd_client *osdc,
struct ceph_vino vino,
struct ceph_file_layout *layout,
u64 off, u64 *plen,
u32 truncate_seq, u64 truncate_size,
struct page **pages, int nr_pages,
int page_align);
extern int ceph_osdc_writepages(struct ceph_osd_client *osdc,
struct ceph_vino vino,
struct ceph_file_layout *layout,
struct ceph_snap_context *sc,
u64 off, u64 len,
u32 truncate_seq, u64 truncate_size,
struct timespec *mtime,
struct page **pages, int nr_pages);
/* watch/notify events */
extern int ceph_osdc_create_event(struct ceph_osd_client *osdc,
void (*event_cb)(u64, u64, u8, void *),
void *data, struct ceph_osd_event **pevent);
extern void ceph_osdc_cancel_event(struct ceph_osd_event *event);
extern void ceph_osdc_put_event(struct ceph_osd_event *event);
#endif