1
linux/fs/fscache/operation.c
David Howells 8d76349d35 FS-Cache: Exclusive op submission can BUG if there's been an I/O error
The function to submit an exclusive op (fscache_submit_exclusive_op()) can BUG
if there's been an I/O error because it may see the parent cache object in an
unexpected state.  It should only BUG if there hasn't been an I/O error.

In this case the problem was produced by remounting the cache partition to be
R/O.  The EROFS state was detected and the cache was aborted, but not
everything handled the aborting correctly.

SysRq : Emergency Remount R/O
EXT4-fs (sda6): re-mounted. Opts: (null)
Emergency Remount complete
CacheFiles: I/O Error: Failed to update xattr with error -30
FS-Cache: Cache cachefiles stopped due to I/O error
------------[ cut here ]------------
kernel BUG at fs/fscache/operation.c:128!
invalid opcode: 0000 [#1] SMP 
CPU 0 
Modules linked in: cachefiles nfs fscache auth_rpcgss nfs_acl lockd sunrpc

Pid: 6612, comm: kworker/u:2 Not tainted 3.1.0-rc8-fsdevel+ #1093                  /DG965RY
RIP: 0010:[<ffffffffa00739c0>]  [<ffffffffa00739c0>] fscache_submit_exclusive_op+0x2ad/0x2c2 [fscache]
RSP: 0018:ffff880000853d40  EFLAGS: 00010206
RAX: ffff880038ac72a8 RBX: ffff8800181f2260 RCX: ffffffff81f2b2b0
RDX: 0000000000000001 RSI: ffffffff8179a478 RDI: ffff8800181f2280
RBP: ffff880000853d60 R08: 0000000000000002 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000001 R12: ffff880038ac7268
R13: ffff8800181f2280 R14: ffff88003a359190 R15: 000000010122b162
FS:  0000000000000000(0000) GS:ffff88003bc00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 00000034cc4a77f0 CR3: 0000000010e96000 CR4: 00000000000006f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process kworker/u:2 (pid: 6612, threadinfo ffff880000852000, task ffff880014c3c040)
Stack:
 ffff8800181f2260 ffff8800181f2310 ffff880038ac7268 ffff8800181f2260
 ffff880000853dc0 ffffffffa0072375 ffff880037ecfe00 ffff88003a359198
 ffff880000853dc0 0000000000000246 0000000000000000 ffff88000a91d308
Call Trace:
 [<ffffffffa0072375>] fscache_object_work_func+0x792/0xe65 [fscache]
 [<ffffffff81047e44>] process_one_work+0x1eb/0x37f
 [<ffffffff81047de6>] ? process_one_work+0x18d/0x37f
 [<ffffffffa0071be3>] ? fscache_enqueue_dependents+0xd8/0xd8 [fscache]
 [<ffffffff810482e4>] worker_thread+0x15a/0x21a
 [<ffffffff8104818a>] ? rescuer_thread+0x188/0x188
 [<ffffffff8104bf96>] kthread+0x7f/0x87
 [<ffffffff813ad6f4>] kernel_thread_helper+0x4/0x10
 [<ffffffff81026b98>] ? finish_task_switch+0x45/0xc0
 [<ffffffff813abd1d>] ? retint_restore_args+0xe/0xe
 [<ffffffff8104bf17>] ? __init_kthread_worker+0x53/0x53
 [<ffffffff813ad6f0>] ? gs_change+0xb/0xb


Signed-off-by: David Howells <dhowells@redhat.com>
2012-12-20 22:10:58 +00:00

536 lines
14 KiB
C

/* FS-Cache worker operation management routines
*
* Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* See Documentation/filesystems/caching/operations.txt
*/
#define FSCACHE_DEBUG_LEVEL OPERATION
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include "internal.h"
atomic_t fscache_op_debug_id;
EXPORT_SYMBOL(fscache_op_debug_id);
/**
* fscache_enqueue_operation - Enqueue an operation for processing
* @op: The operation to enqueue
*
* Enqueue an operation for processing by the FS-Cache thread pool.
*
* This will get its own ref on the object.
*/
void fscache_enqueue_operation(struct fscache_operation *op)
{
_enter("{OBJ%x OP%x,%u}",
op->object->debug_id, op->debug_id, atomic_read(&op->usage));
ASSERT(list_empty(&op->pend_link));
ASSERT(op->processor != NULL);
ASSERTCMP(op->object->state, >=, FSCACHE_OBJECT_AVAILABLE);
ASSERTCMP(atomic_read(&op->usage), >, 0);
ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS);
fscache_stat(&fscache_n_op_enqueue);
switch (op->flags & FSCACHE_OP_TYPE) {
case FSCACHE_OP_ASYNC:
_debug("queue async");
atomic_inc(&op->usage);
if (!queue_work(fscache_op_wq, &op->work))
fscache_put_operation(op);
break;
case FSCACHE_OP_MYTHREAD:
_debug("queue for caller's attention");
break;
default:
printk(KERN_ERR "FS-Cache: Unexpected op type %lx",
op->flags);
BUG();
break;
}
}
EXPORT_SYMBOL(fscache_enqueue_operation);
/*
* start an op running
*/
static void fscache_run_op(struct fscache_object *object,
struct fscache_operation *op)
{
ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING);
op->state = FSCACHE_OP_ST_IN_PROGRESS;
object->n_in_progress++;
if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
if (op->processor)
fscache_enqueue_operation(op);
fscache_stat(&fscache_n_op_run);
}
/*
* submit an exclusive operation for an object
* - other ops are excluded from running simultaneously with this one
* - this gets any extra refs it needs on an op
*/
int fscache_submit_exclusive_op(struct fscache_object *object,
struct fscache_operation *op)
{
int ret;
_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
ASSERTCMP(atomic_read(&op->usage), >, 0);
spin_lock(&object->lock);
ASSERTCMP(object->n_ops, >=, object->n_in_progress);
ASSERTCMP(object->n_ops, >=, object->n_exclusive);
ASSERT(list_empty(&op->pend_link));
op->state = FSCACHE_OP_ST_PENDING;
if (fscache_object_is_active(object)) {
op->object = object;
object->n_ops++;
object->n_exclusive++; /* reads and writes must wait */
if (object->n_in_progress > 0) {
atomic_inc(&op->usage);
list_add_tail(&op->pend_link, &object->pending_ops);
fscache_stat(&fscache_n_op_pend);
} else if (!list_empty(&object->pending_ops)) {
atomic_inc(&op->usage);
list_add_tail(&op->pend_link, &object->pending_ops);
fscache_stat(&fscache_n_op_pend);
fscache_start_operations(object);
} else {
ASSERTCMP(object->n_in_progress, ==, 0);
fscache_run_op(object, op);
}
/* need to issue a new write op after this */
clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
ret = 0;
} else if (object->state == FSCACHE_OBJECT_CREATING) {
op->object = object;
object->n_ops++;
object->n_exclusive++; /* reads and writes must wait */
atomic_inc(&op->usage);
list_add_tail(&op->pend_link, &object->pending_ops);
fscache_stat(&fscache_n_op_pend);
ret = 0;
} else {
/* If we're in any other state, there must have been an I/O
* error of some nature.
*/
ASSERT(test_bit(FSCACHE_IOERROR, &object->cache->flags));
ret = -EIO;
}
spin_unlock(&object->lock);
return ret;
}
/*
* report an unexpected submission
*/
static void fscache_report_unexpected_submission(struct fscache_object *object,
struct fscache_operation *op,
unsigned long ostate)
{
static bool once_only;
struct fscache_operation *p;
unsigned n;
if (once_only)
return;
once_only = true;
kdebug("unexpected submission OP%x [OBJ%x %s]",
op->debug_id, object->debug_id,
fscache_object_states[object->state]);
kdebug("objstate=%s [%s]",
fscache_object_states[object->state],
fscache_object_states[ostate]);
kdebug("objflags=%lx", object->flags);
kdebug("objevent=%lx [%lx]", object->events, object->event_mask);
kdebug("ops=%u inp=%u exc=%u",
object->n_ops, object->n_in_progress, object->n_exclusive);
if (!list_empty(&object->pending_ops)) {
n = 0;
list_for_each_entry(p, &object->pending_ops, pend_link) {
ASSERTCMP(p->object, ==, object);
kdebug("%p %p", op->processor, op->release);
n++;
}
kdebug("n=%u", n);
}
dump_stack();
}
/*
* submit an operation for an object
* - objects may be submitted only in the following states:
* - during object creation (write ops may be submitted)
* - whilst the object is active
* - after an I/O error incurred in one of the two above states (op rejected)
* - this gets any extra refs it needs on an op
*/
int fscache_submit_op(struct fscache_object *object,
struct fscache_operation *op)
{
unsigned long ostate;
int ret;
_enter("{OBJ%x OP%x},{%u}",
object->debug_id, op->debug_id, atomic_read(&op->usage));
ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
ASSERTCMP(atomic_read(&op->usage), >, 0);
spin_lock(&object->lock);
ASSERTCMP(object->n_ops, >=, object->n_in_progress);
ASSERTCMP(object->n_ops, >=, object->n_exclusive);
ASSERT(list_empty(&op->pend_link));
ostate = object->state;
smp_rmb();
op->state = FSCACHE_OP_ST_PENDING;
if (fscache_object_is_active(object)) {
op->object = object;
object->n_ops++;
if (object->n_exclusive > 0) {
atomic_inc(&op->usage);
list_add_tail(&op->pend_link, &object->pending_ops);
fscache_stat(&fscache_n_op_pend);
} else if (!list_empty(&object->pending_ops)) {
atomic_inc(&op->usage);
list_add_tail(&op->pend_link, &object->pending_ops);
fscache_stat(&fscache_n_op_pend);
fscache_start_operations(object);
} else {
ASSERTCMP(object->n_exclusive, ==, 0);
fscache_run_op(object, op);
}
ret = 0;
} else if (object->state == FSCACHE_OBJECT_CREATING) {
op->object = object;
object->n_ops++;
atomic_inc(&op->usage);
list_add_tail(&op->pend_link, &object->pending_ops);
fscache_stat(&fscache_n_op_pend);
ret = 0;
} else if (object->state == FSCACHE_OBJECT_DYING ||
object->state == FSCACHE_OBJECT_LC_DYING ||
object->state == FSCACHE_OBJECT_WITHDRAWING) {
fscache_stat(&fscache_n_op_rejected);
op->state = FSCACHE_OP_ST_CANCELLED;
ret = -ENOBUFS;
} else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
fscache_report_unexpected_submission(object, op, ostate);
ASSERT(!fscache_object_is_active(object));
op->state = FSCACHE_OP_ST_CANCELLED;
ret = -ENOBUFS;
} else {
op->state = FSCACHE_OP_ST_CANCELLED;
ret = -ENOBUFS;
}
spin_unlock(&object->lock);
return ret;
}
/*
* queue an object for withdrawal on error, aborting all following asynchronous
* operations
*/
void fscache_abort_object(struct fscache_object *object)
{
_enter("{OBJ%x}", object->debug_id);
fscache_raise_event(object, FSCACHE_OBJECT_EV_ERROR);
}
/*
* jump start the operation processing on an object
* - caller must hold object->lock
*/
void fscache_start_operations(struct fscache_object *object)
{
struct fscache_operation *op;
bool stop = false;
while (!list_empty(&object->pending_ops) && !stop) {
op = list_entry(object->pending_ops.next,
struct fscache_operation, pend_link);
if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
if (object->n_in_progress > 0)
break;
stop = true;
}
list_del_init(&op->pend_link);
fscache_run_op(object, op);
/* the pending queue was holding a ref on the object */
fscache_put_operation(op);
}
ASSERTCMP(object->n_in_progress, <=, object->n_ops);
_debug("woke %d ops on OBJ%x",
object->n_in_progress, object->debug_id);
}
/*
* cancel an operation that's pending on an object
*/
int fscache_cancel_op(struct fscache_operation *op)
{
struct fscache_object *object = op->object;
int ret;
_enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id);
ASSERTCMP(op->state, >=, FSCACHE_OP_ST_PENDING);
ASSERTCMP(op->state, !=, FSCACHE_OP_ST_CANCELLED);
ASSERTCMP(atomic_read(&op->usage), >, 0);
spin_lock(&object->lock);
ret = -EBUSY;
if (op->state == FSCACHE_OP_ST_PENDING) {
ASSERT(!list_empty(&op->pend_link));
fscache_stat(&fscache_n_op_cancelled);
list_del_init(&op->pend_link);
op->state = FSCACHE_OP_ST_CANCELLED;
if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
object->n_exclusive--;
if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
fscache_put_operation(op);
ret = 0;
}
spin_unlock(&object->lock);
_leave(" = %d", ret);
return ret;
}
/*
* Cancel all pending operations on an object
*/
void fscache_cancel_all_ops(struct fscache_object *object)
{
struct fscache_operation *op;
_enter("OBJ%x", object->debug_id);
spin_lock(&object->lock);
while (!list_empty(&object->pending_ops)) {
op = list_entry(object->pending_ops.next,
struct fscache_operation, pend_link);
fscache_stat(&fscache_n_op_cancelled);
list_del_init(&op->pend_link);
ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING);
op->state = FSCACHE_OP_ST_CANCELLED;
if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
object->n_exclusive--;
if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
fscache_put_operation(op);
cond_resched_lock(&object->lock);
}
spin_unlock(&object->lock);
_leave("");
}
/*
* Record the completion of an in-progress operation.
*/
void fscache_op_complete(struct fscache_operation *op)
{
struct fscache_object *object = op->object;
_enter("OBJ%x", object->debug_id);
ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS);
ASSERTCMP(object->n_in_progress, >, 0);
ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags),
object->n_exclusive, >, 0);
ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags),
object->n_in_progress, ==, 1);
spin_lock(&object->lock);
op->state = FSCACHE_OP_ST_COMPLETE;
if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
object->n_exclusive--;
object->n_in_progress--;
if (object->n_in_progress == 0)
fscache_start_operations(object);
spin_unlock(&object->lock);
_leave("");
}
EXPORT_SYMBOL(fscache_op_complete);
/*
* release an operation
* - queues pending ops if this is the last in-progress op
*/
void fscache_put_operation(struct fscache_operation *op)
{
struct fscache_object *object;
struct fscache_cache *cache;
_enter("{OBJ%x OP%x,%d}",
op->object->debug_id, op->debug_id, atomic_read(&op->usage));
ASSERTCMP(atomic_read(&op->usage), >, 0);
if (!atomic_dec_and_test(&op->usage))
return;
_debug("PUT OP");
ASSERTIFCMP(op->state != FSCACHE_OP_ST_COMPLETE,
op->state, ==, FSCACHE_OP_ST_CANCELLED);
op->state = FSCACHE_OP_ST_DEAD;
fscache_stat(&fscache_n_op_release);
if (op->release) {
op->release(op);
op->release = NULL;
}
object = op->object;
if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags)) {
if (atomic_dec_and_test(&object->n_reads)) {
clear_bit(FSCACHE_COOKIE_WAITING_ON_READS,
&object->cookie->flags);
wake_up_bit(&object->cookie->flags,
FSCACHE_COOKIE_WAITING_ON_READS);
}
}
/* now... we may get called with the object spinlock held, so we
* complete the cleanup here only if we can immediately acquire the
* lock, and defer it otherwise */
if (!spin_trylock(&object->lock)) {
_debug("defer put");
fscache_stat(&fscache_n_op_deferred_release);
cache = object->cache;
spin_lock(&cache->op_gc_list_lock);
list_add_tail(&op->pend_link, &cache->op_gc_list);
spin_unlock(&cache->op_gc_list_lock);
schedule_work(&cache->op_gc);
_leave(" [defer]");
return;
}
ASSERTCMP(object->n_ops, >, 0);
object->n_ops--;
if (object->n_ops == 0)
fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
spin_unlock(&object->lock);
kfree(op);
_leave(" [done]");
}
EXPORT_SYMBOL(fscache_put_operation);
/*
* garbage collect operations that have had their release deferred
*/
void fscache_operation_gc(struct work_struct *work)
{
struct fscache_operation *op;
struct fscache_object *object;
struct fscache_cache *cache =
container_of(work, struct fscache_cache, op_gc);
int count = 0;
_enter("");
do {
spin_lock(&cache->op_gc_list_lock);
if (list_empty(&cache->op_gc_list)) {
spin_unlock(&cache->op_gc_list_lock);
break;
}
op = list_entry(cache->op_gc_list.next,
struct fscache_operation, pend_link);
list_del(&op->pend_link);
spin_unlock(&cache->op_gc_list_lock);
object = op->object;
spin_lock(&object->lock);
_debug("GC DEFERRED REL OBJ%x OP%x",
object->debug_id, op->debug_id);
fscache_stat(&fscache_n_op_gc);
ASSERTCMP(atomic_read(&op->usage), ==, 0);
ASSERTCMP(op->state, ==, FSCACHE_OP_ST_DEAD);
ASSERTCMP(object->n_ops, >, 0);
object->n_ops--;
if (object->n_ops == 0)
fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
spin_unlock(&object->lock);
kfree(op);
} while (count++ < 20);
if (!list_empty(&cache->op_gc_list))
schedule_work(&cache->op_gc);
_leave("");
}
/*
* execute an operation using fs_op_wq to provide processing context -
* the caller holds a ref to this object, so we don't need to hold one
*/
void fscache_op_work_func(struct work_struct *work)
{
struct fscache_operation *op =
container_of(work, struct fscache_operation, work);
unsigned long start;
_enter("{OBJ%x OP%x,%d}",
op->object->debug_id, op->debug_id, atomic_read(&op->usage));
ASSERT(op->processor != NULL);
start = jiffies;
op->processor(op);
fscache_hist(fscache_ops_histogram, start);
fscache_put_operation(op);
_leave("");
}