Star64_linux/fs/cachefiles/interface.c
David Howells fee096deb4 CacheFiles: Catch an overly long wait for an old active object
Catch an overly long wait for an old, dying active object when we want to
replace it with a new one.  The probability is that all the slow-work threads
are hogged, and the delete can't get a look in.

What we do instead is:

 (1) if there's nothing in the slow work queue, we sleep until either the dying
     object has finished dying or there is something in the slow work queue
     behind which we can queue our object.

 (2) if there is something in the slow work queue, we return ETIMEDOUT to
     fscache_lookup_object(), which then puts us back on the slow work queue,
     presumably behind the deletion that we're blocked by.  We are then
     deferred for a while until we work our way back through the queue -
     without blocking a slow-work thread unnecessarily.

A backtrace similar to the following may appear in the log without this patch:

	INFO: task kslowd004:5711 blocked for more than 120 seconds.
	"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
	kslowd004     D 0000000000000000     0  5711      2 0x00000080
	 ffff88000340bb80 0000000000000046 ffff88002550d000 0000000000000000
	 ffff88002550d000 0000000000000007 ffff88000340bfd8 ffff88002550d2a8
	 000000000000ddf0 00000000000118c0 00000000000118c0 ffff88002550d2a8
	Call Trace:
	 [<ffffffff81058e21>] ? trace_hardirqs_on+0xd/0xf
	 [<ffffffffa011c4d8>] ? cachefiles_wait_bit+0x0/0xd [cachefiles]
	 [<ffffffffa011c4e1>] cachefiles_wait_bit+0x9/0xd [cachefiles]
	 [<ffffffff81353153>] __wait_on_bit+0x43/0x76
	 [<ffffffff8111ae39>] ? ext3_xattr_get+0x1ec/0x270
	 [<ffffffff813531ef>] out_of_line_wait_on_bit+0x69/0x74
	 [<ffffffffa011c4d8>] ? cachefiles_wait_bit+0x0/0xd [cachefiles]
	 [<ffffffff8104c125>] ? wake_bit_function+0x0/0x2e
	 [<ffffffffa011bc79>] cachefiles_mark_object_active+0x203/0x23b [cachefiles]
	 [<ffffffffa011c209>] cachefiles_walk_to_object+0x558/0x827 [cachefiles]
	 [<ffffffffa011a429>] cachefiles_lookup_object+0xac/0x12a [cachefiles]
	 [<ffffffffa00aa1e9>] fscache_lookup_object+0x1c7/0x214 [fscache]
	 [<ffffffffa00aafc5>] fscache_object_state_machine+0xa5/0x52d [fscache]
	 [<ffffffffa00ab4ac>] fscache_object_slow_work_execute+0x5f/0xa0 [fscache]
	 [<ffffffff81082093>] slow_work_execute+0x18f/0x2d1
	 [<ffffffff8108239a>] slow_work_thread+0x1c5/0x308
	 [<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34
	 [<ffffffff810821d5>] ? slow_work_thread+0x0/0x308
	 [<ffffffff8104be91>] kthread+0x7a/0x82
	 [<ffffffff8100beda>] child_rip+0xa/0x20
	 [<ffffffff8100b87c>] ? restore_args+0x0/0x30
	 [<ffffffff8104be17>] ? kthread+0x0/0x82
	 [<ffffffff8100bed0>] ? child_rip+0x0/0x20
	1 lock held by kslowd004/5711:
	 #0:  (&sb->s_type->i_mutex_key#7/1){+.+.+.}, at: [<ffffffffa011be64>] cachefiles_walk_to_object+0x1b3/0x827 [cachefiles]

Signed-off-by: David Howells <dhowells@redhat.com>
2009-11-19 18:12:05 +00:00

468 lines
12 KiB
C

/* FS-Cache interface to CacheFiles
*
* Copyright (C) 2007 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 Licence
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
#include <linux/mount.h>
#include <linux/buffer_head.h>
#include "internal.h"
#define list_to_page(head) (list_entry((head)->prev, struct page, lru))
struct cachefiles_lookup_data {
struct cachefiles_xattr *auxdata; /* auxiliary data */
char *key; /* key path */
};
static int cachefiles_attr_changed(struct fscache_object *_object);
/*
* allocate an object record for a cookie lookup and prepare the lookup data
*/
static struct fscache_object *cachefiles_alloc_object(
struct fscache_cache *_cache,
struct fscache_cookie *cookie)
{
struct cachefiles_lookup_data *lookup_data;
struct cachefiles_object *object;
struct cachefiles_cache *cache;
struct cachefiles_xattr *auxdata;
unsigned keylen, auxlen;
void *buffer;
char *key;
cache = container_of(_cache, struct cachefiles_cache, cache);
_enter("{%s},%p,", cache->cache.identifier, cookie);
lookup_data = kmalloc(sizeof(*lookup_data), GFP_KERNEL);
if (!lookup_data)
goto nomem_lookup_data;
/* create a new object record and a temporary leaf image */
object = kmem_cache_alloc(cachefiles_object_jar, GFP_KERNEL);
if (!object)
goto nomem_object;
ASSERTCMP(object->backer, ==, NULL);
BUG_ON(test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags));
atomic_set(&object->usage, 1);
fscache_object_init(&object->fscache, cookie, &cache->cache);
object->type = cookie->def->type;
/* get hold of the raw key
* - stick the length on the front and leave space on the back for the
* encoder
*/
buffer = kmalloc((2 + 512) + 3, GFP_KERNEL);
if (!buffer)
goto nomem_buffer;
keylen = cookie->def->get_key(cookie->netfs_data, buffer + 2, 512);
ASSERTCMP(keylen, <, 512);
*(uint16_t *)buffer = keylen;
((char *)buffer)[keylen + 2] = 0;
((char *)buffer)[keylen + 3] = 0;
((char *)buffer)[keylen + 4] = 0;
/* turn the raw key into something that can work with as a filename */
key = cachefiles_cook_key(buffer, keylen + 2, object->type);
if (!key)
goto nomem_key;
/* get hold of the auxiliary data and prepend the object type */
auxdata = buffer;
auxlen = 0;
if (cookie->def->get_aux) {
auxlen = cookie->def->get_aux(cookie->netfs_data,
auxdata->data, 511);
ASSERTCMP(auxlen, <, 511);
}
auxdata->len = auxlen + 1;
auxdata->type = cookie->def->type;
lookup_data->auxdata = auxdata;
lookup_data->key = key;
object->lookup_data = lookup_data;
_leave(" = %p [%p]", &object->fscache, lookup_data);
return &object->fscache;
nomem_key:
kfree(buffer);
nomem_buffer:
BUG_ON(test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags));
kmem_cache_free(cachefiles_object_jar, object);
fscache_object_destroyed(&cache->cache);
nomem_object:
kfree(lookup_data);
nomem_lookup_data:
_leave(" = -ENOMEM");
return ERR_PTR(-ENOMEM);
}
/*
* attempt to look up the nominated node in this cache
* - return -ETIMEDOUT to be scheduled again
*/
static int cachefiles_lookup_object(struct fscache_object *_object)
{
struct cachefiles_lookup_data *lookup_data;
struct cachefiles_object *parent, *object;
struct cachefiles_cache *cache;
const struct cred *saved_cred;
int ret;
_enter("{OBJ%x}", _object->debug_id);
cache = container_of(_object->cache, struct cachefiles_cache, cache);
parent = container_of(_object->parent,
struct cachefiles_object, fscache);
object = container_of(_object, struct cachefiles_object, fscache);
lookup_data = object->lookup_data;
ASSERTCMP(lookup_data, !=, NULL);
/* look up the key, creating any missing bits */
cachefiles_begin_secure(cache, &saved_cred);
ret = cachefiles_walk_to_object(parent, object,
lookup_data->key,
lookup_data->auxdata);
cachefiles_end_secure(cache, saved_cred);
/* polish off by setting the attributes of non-index files */
if (ret == 0 &&
object->fscache.cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX)
cachefiles_attr_changed(&object->fscache);
if (ret < 0 && ret != -ETIMEDOUT) {
printk(KERN_WARNING "CacheFiles: Lookup failed error %d\n",
ret);
fscache_object_lookup_error(&object->fscache);
}
_leave(" [%d]", ret);
return ret;
}
/*
* indication of lookup completion
*/
static void cachefiles_lookup_complete(struct fscache_object *_object)
{
struct cachefiles_object *object;
object = container_of(_object, struct cachefiles_object, fscache);
_enter("{OBJ%x,%p}", object->fscache.debug_id, object->lookup_data);
if (object->lookup_data) {
kfree(object->lookup_data->key);
kfree(object->lookup_data->auxdata);
kfree(object->lookup_data);
object->lookup_data = NULL;
}
}
/*
* increment the usage count on an inode object (may fail if unmounting)
*/
static
struct fscache_object *cachefiles_grab_object(struct fscache_object *_object)
{
struct cachefiles_object *object =
container_of(_object, struct cachefiles_object, fscache);
_enter("{OBJ%x,%d}", _object->debug_id, atomic_read(&object->usage));
#ifdef CACHEFILES_DEBUG_SLAB
ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000);
#endif
atomic_inc(&object->usage);
return &object->fscache;
}
/*
* update the auxilliary data for an object object on disk
*/
static void cachefiles_update_object(struct fscache_object *_object)
{
struct cachefiles_object *object;
struct cachefiles_xattr *auxdata;
struct cachefiles_cache *cache;
struct fscache_cookie *cookie;
const struct cred *saved_cred;
unsigned auxlen;
_enter("{OBJ%x}", _object->debug_id);
object = container_of(_object, struct cachefiles_object, fscache);
cache = container_of(object->fscache.cache, struct cachefiles_cache,
cache);
cookie = object->fscache.cookie;
if (!cookie->def->get_aux) {
_leave(" [no aux]");
return;
}
auxdata = kmalloc(2 + 512 + 3, GFP_KERNEL);
if (!auxdata) {
_leave(" [nomem]");
return;
}
auxlen = cookie->def->get_aux(cookie->netfs_data, auxdata->data, 511);
ASSERTCMP(auxlen, <, 511);
auxdata->len = auxlen + 1;
auxdata->type = cookie->def->type;
cachefiles_begin_secure(cache, &saved_cred);
cachefiles_update_object_xattr(object, auxdata);
cachefiles_end_secure(cache, saved_cred);
kfree(auxdata);
_leave("");
}
/*
* discard the resources pinned by an object and effect retirement if
* requested
*/
static void cachefiles_drop_object(struct fscache_object *_object)
{
struct cachefiles_object *object;
struct cachefiles_cache *cache;
const struct cred *saved_cred;
ASSERT(_object);
object = container_of(_object, struct cachefiles_object, fscache);
_enter("{OBJ%x,%d}",
object->fscache.debug_id, atomic_read(&object->usage));
cache = container_of(object->fscache.cache,
struct cachefiles_cache, cache);
#ifdef CACHEFILES_DEBUG_SLAB
ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000);
#endif
/* delete retired objects */
if (object->fscache.state == FSCACHE_OBJECT_RECYCLING &&
_object != cache->cache.fsdef
) {
_debug("- retire object OBJ%x", object->fscache.debug_id);
cachefiles_begin_secure(cache, &saved_cred);
cachefiles_delete_object(cache, object);
cachefiles_end_secure(cache, saved_cred);
}
/* close the filesystem stuff attached to the object */
if (object->backer != object->dentry)
dput(object->backer);
object->backer = NULL;
/* note that the object is now inactive */
if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
write_lock(&cache->active_lock);
if (!test_and_clear_bit(CACHEFILES_OBJECT_ACTIVE,
&object->flags))
BUG();
rb_erase(&object->active_node, &cache->active_nodes);
wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
write_unlock(&cache->active_lock);
}
dput(object->dentry);
object->dentry = NULL;
_leave("");
}
/*
* dispose of a reference to an object
*/
static void cachefiles_put_object(struct fscache_object *_object)
{
struct cachefiles_object *object;
struct fscache_cache *cache;
ASSERT(_object);
object = container_of(_object, struct cachefiles_object, fscache);
_enter("{OBJ%x,%d}",
object->fscache.debug_id, atomic_read(&object->usage));
#ifdef CACHEFILES_DEBUG_SLAB
ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000);
#endif
ASSERTIFCMP(object->fscache.parent,
object->fscache.parent->n_children, >, 0);
if (atomic_dec_and_test(&object->usage)) {
_debug("- kill object OBJ%x", object->fscache.debug_id);
ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags));
ASSERTCMP(object->fscache.parent, ==, NULL);
ASSERTCMP(object->backer, ==, NULL);
ASSERTCMP(object->dentry, ==, NULL);
ASSERTCMP(object->fscache.n_ops, ==, 0);
ASSERTCMP(object->fscache.n_children, ==, 0);
if (object->lookup_data) {
kfree(object->lookup_data->key);
kfree(object->lookup_data->auxdata);
kfree(object->lookup_data);
object->lookup_data = NULL;
}
cache = object->fscache.cache;
fscache_object_destroy(&object->fscache);
kmem_cache_free(cachefiles_object_jar, object);
fscache_object_destroyed(cache);
}
_leave("");
}
/*
* sync a cache
*/
static void cachefiles_sync_cache(struct fscache_cache *_cache)
{
struct cachefiles_cache *cache;
const struct cred *saved_cred;
int ret;
_enter("%p", _cache);
cache = container_of(_cache, struct cachefiles_cache, cache);
/* make sure all pages pinned by operations on behalf of the netfs are
* written to disc */
cachefiles_begin_secure(cache, &saved_cred);
down_read(&cache->mnt->mnt_sb->s_umount);
ret = sync_filesystem(cache->mnt->mnt_sb);
up_read(&cache->mnt->mnt_sb->s_umount);
cachefiles_end_secure(cache, saved_cred);
if (ret == -EIO)
cachefiles_io_error(cache,
"Attempt to sync backing fs superblock"
" returned error %d",
ret);
}
/*
* notification the attributes on an object have changed
* - called with reads/writes excluded by FS-Cache
*/
static int cachefiles_attr_changed(struct fscache_object *_object)
{
struct cachefiles_object *object;
struct cachefiles_cache *cache;
const struct cred *saved_cred;
struct iattr newattrs;
uint64_t ni_size;
loff_t oi_size;
int ret;
_object->cookie->def->get_attr(_object->cookie->netfs_data, &ni_size);
_enter("{OBJ%x},[%llu]",
_object->debug_id, (unsigned long long) ni_size);
object = container_of(_object, struct cachefiles_object, fscache);
cache = container_of(object->fscache.cache,
struct cachefiles_cache, cache);
if (ni_size == object->i_size)
return 0;
if (!object->backer)
return -ENOBUFS;
ASSERT(S_ISREG(object->backer->d_inode->i_mode));
fscache_set_store_limit(&object->fscache, ni_size);
oi_size = i_size_read(object->backer->d_inode);
if (oi_size == ni_size)
return 0;
cachefiles_begin_secure(cache, &saved_cred);
mutex_lock(&object->backer->d_inode->i_mutex);
/* if there's an extension to a partial page at the end of the backing
* file, we need to discard the partial page so that we pick up new
* data after it */
if (oi_size & ~PAGE_MASK && ni_size > oi_size) {
_debug("discard tail %llx", oi_size);
newattrs.ia_valid = ATTR_SIZE;
newattrs.ia_size = oi_size & PAGE_MASK;
ret = notify_change(object->backer, &newattrs);
if (ret < 0)
goto truncate_failed;
}
newattrs.ia_valid = ATTR_SIZE;
newattrs.ia_size = ni_size;
ret = notify_change(object->backer, &newattrs);
truncate_failed:
mutex_unlock(&object->backer->d_inode->i_mutex);
cachefiles_end_secure(cache, saved_cred);
if (ret == -EIO) {
fscache_set_store_limit(&object->fscache, 0);
cachefiles_io_error_obj(object, "Size set failed");
ret = -ENOBUFS;
}
_leave(" = %d", ret);
return ret;
}
/*
* dissociate a cache from all the pages it was backing
*/
static void cachefiles_dissociate_pages(struct fscache_cache *cache)
{
_enter("");
}
const struct fscache_cache_ops cachefiles_cache_ops = {
.name = "cachefiles",
.alloc_object = cachefiles_alloc_object,
.lookup_object = cachefiles_lookup_object,
.lookup_complete = cachefiles_lookup_complete,
.grab_object = cachefiles_grab_object,
.update_object = cachefiles_update_object,
.drop_object = cachefiles_drop_object,
.put_object = cachefiles_put_object,
.sync_cache = cachefiles_sync_cache,
.attr_changed = cachefiles_attr_changed,
.read_or_alloc_page = cachefiles_read_or_alloc_page,
.read_or_alloc_pages = cachefiles_read_or_alloc_pages,
.allocate_page = cachefiles_allocate_page,
.allocate_pages = cachefiles_allocate_pages,
.write_page = cachefiles_write_page,
.uncache_page = cachefiles_uncache_page,
.dissociate_pages = cachefiles_dissociate_pages,
};