Changes since last update:
- Convert radix tree usage to XArray; - Fix shrink scan count on multiple filesystem instances; - Better handling for specific corrupted images; - Update my email address in MAINTAINERS. -----BEGIN PGP SIGNATURE----- iIwEABYIADQWIQThPAmQN9sSA0DVxtI5NzHcH7XmBAUCXoFRvBYcZ2FveGlhbmcy NUBodWF3ZWkuY29tAAoJEDk3MdwfteYEswMBAMtsyo6TqWPToKt/eAJMbvt5vRGf y4XGEx67a1Ds7/LqAQCtOs+0HMWlK3F2DDljpA7Tg2QvRBJwFlhET6YZOAIcDQ== =XsWD -----END PGP SIGNATURE----- Merge tag 'erofs-for-5.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs Pull erofs updates from Gao Xiang: "Updates with a XArray adaptation, several fixes for shrinker and corrupted images are ready for this cycle. All commits have been stress tested with no noticeable smoke out and have been in linux-next as well. Summary: - Convert radix tree usage to XArray - Fix shrink scan count on multiple filesystem instances - Better handling for specific corrupted images - Update my email address in MAINTAINERS" * tag 'erofs-for-5.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs: MAINTAINERS: erofs: update my email address erofs: handle corrupted images whose decompressed size less than it'd be erofs: use LZ4_decompress_safe() for full decoding erofs: correct the remaining shrink objects erofs: convert workstn to XArray
This commit is contained in:
Linus Torvalds
commit
377ad0c28c
|
|
@ -6248,7 +6248,7 @@ F: drivers/video/fbdev/s1d13xxxfb.c
|
|||
F: include/video/s1d13xxxfb.h
|
||||
|
||||
EROFS FILE SYSTEM
|
||||
M: Gao Xiang <gaoxiang25@huawei.com>
|
||||
M: Gao Xiang <xiang@kernel.org>
|
||||
M: Chao Yu <yuchao0@huawei.com>
|
||||
L: linux-erofs@lists.ozlabs.org
|
||||
S: Maintained
|
||||
|
|
|
|||
|
|
@ -157,17 +157,27 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
|
|||
}
|
||||
}
|
||||
|
||||
ret = LZ4_decompress_safe_partial(src + inputmargin, out,
|
||||
inlen, rq->outputsize,
|
||||
rq->outputsize);
|
||||
if (ret < 0) {
|
||||
erofs_err(rq->sb, "failed to decompress, in[%u, %u] out[%u]",
|
||||
inlen, inputmargin, rq->outputsize);
|
||||
/* legacy format could compress extra data in a pcluster. */
|
||||
if (rq->partial_decoding || !support_0padding)
|
||||
ret = LZ4_decompress_safe_partial(src + inputmargin, out,
|
||||
inlen, rq->outputsize,
|
||||
rq->outputsize);
|
||||
else
|
||||
ret = LZ4_decompress_safe(src + inputmargin, out,
|
||||
inlen, rq->outputsize);
|
||||
|
||||
if (ret != rq->outputsize) {
|
||||
erofs_err(rq->sb, "failed to decompress %d in[%u, %u] out[%u]",
|
||||
ret, inlen, inputmargin, rq->outputsize);
|
||||
|
||||
WARN_ON(1);
|
||||
print_hex_dump(KERN_DEBUG, "[ in]: ", DUMP_PREFIX_OFFSET,
|
||||
16, 1, src + inputmargin, inlen, true);
|
||||
print_hex_dump(KERN_DEBUG, "[out]: ", DUMP_PREFIX_OFFSET,
|
||||
16, 1, out, rq->outputsize, true);
|
||||
|
||||
if (ret >= 0)
|
||||
memset(out + ret, 0, rq->outputsize - ret);
|
||||
ret = -EIO;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -52,8 +52,8 @@ struct erofs_sb_info {
|
|||
struct list_head list;
|
||||
struct mutex umount_mutex;
|
||||
|
||||
/* the dedicated workstation for compression */
|
||||
struct radix_tree_root workstn_tree;
|
||||
/* managed XArray arranged in physical block number */
|
||||
struct xarray managed_pslots;
|
||||
|
||||
/* threshold for decompression synchronously */
|
||||
unsigned int max_sync_decompress_pages;
|
||||
|
|
@ -402,8 +402,8 @@ static inline void *erofs_get_pcpubuf(unsigned int pagenr)
|
|||
int erofs_workgroup_put(struct erofs_workgroup *grp);
|
||||
struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb,
|
||||
pgoff_t index);
|
||||
int erofs_register_workgroup(struct super_block *sb,
|
||||
struct erofs_workgroup *grp);
|
||||
struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb,
|
||||
struct erofs_workgroup *grp);
|
||||
void erofs_workgroup_free_rcu(struct erofs_workgroup *grp);
|
||||
void erofs_shrinker_register(struct super_block *sb);
|
||||
void erofs_shrinker_unregister(struct super_block *sb);
|
||||
|
|
|
|||
|
|
@ -425,7 +425,7 @@ static int erofs_fill_super(struct super_block *sb, void *data, int silent)
|
|||
sb->s_flags &= ~SB_POSIXACL;
|
||||
|
||||
#ifdef CONFIG_EROFS_FS_ZIP
|
||||
INIT_RADIX_TREE(&sbi->workstn_tree, GFP_ATOMIC);
|
||||
xa_init(&sbi->managed_pslots);
|
||||
#endif
|
||||
|
||||
/* get the root inode */
|
||||
|
|
|
|||
|
|
@ -37,9 +37,6 @@ void *erofs_get_pcpubuf(unsigned int pagenr)
|
|||
/* global shrink count (for all mounted EROFS instances) */
|
||||
static atomic_long_t erofs_global_shrink_cnt;
|
||||
|
||||
#define __erofs_workgroup_get(grp) atomic_inc(&(grp)->refcount)
|
||||
#define __erofs_workgroup_put(grp) atomic_dec(&(grp)->refcount)
|
||||
|
||||
static int erofs_workgroup_get(struct erofs_workgroup *grp)
|
||||
{
|
||||
int o;
|
||||
|
|
@ -66,7 +63,7 @@ struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb,
|
|||
|
||||
repeat:
|
||||
rcu_read_lock();
|
||||
grp = radix_tree_lookup(&sbi->workstn_tree, index);
|
||||
grp = xa_load(&sbi->managed_pslots, index);
|
||||
if (grp) {
|
||||
if (erofs_workgroup_get(grp)) {
|
||||
/* prefer to relax rcu read side */
|
||||
|
|
@ -80,43 +77,37 @@ repeat:
|
|||
return grp;
|
||||
}
|
||||
|
||||
int erofs_register_workgroup(struct super_block *sb,
|
||||
struct erofs_workgroup *grp)
|
||||
struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb,
|
||||
struct erofs_workgroup *grp)
|
||||
{
|
||||
struct erofs_sb_info *sbi;
|
||||
int err;
|
||||
|
||||
/* grp shouldn't be broken or used before */
|
||||
if (atomic_read(&grp->refcount) != 1) {
|
||||
DBG_BUGON(1);
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
err = radix_tree_preload(GFP_NOFS);
|
||||
if (err)
|
||||
return err;
|
||||
|
||||
sbi = EROFS_SB(sb);
|
||||
xa_lock(&sbi->workstn_tree);
|
||||
struct erofs_sb_info *const sbi = EROFS_SB(sb);
|
||||
struct erofs_workgroup *pre;
|
||||
|
||||
/*
|
||||
* Bump up reference count before making this workgroup
|
||||
* visible to other users in order to avoid potential UAF
|
||||
* without serialized by workstn_lock.
|
||||
* Bump up a reference count before making this visible
|
||||
* to others for the XArray in order to avoid potential
|
||||
* UAF without serialized by xa_lock.
|
||||
*/
|
||||
__erofs_workgroup_get(grp);
|
||||
atomic_inc(&grp->refcount);
|
||||
|
||||
err = radix_tree_insert(&sbi->workstn_tree, grp->index, grp);
|
||||
if (err)
|
||||
/*
|
||||
* it's safe to decrease since the workgroup isn't visible
|
||||
* and refcount >= 2 (cannot be freezed).
|
||||
*/
|
||||
__erofs_workgroup_put(grp);
|
||||
|
||||
xa_unlock(&sbi->workstn_tree);
|
||||
radix_tree_preload_end();
|
||||
return err;
|
||||
repeat:
|
||||
xa_lock(&sbi->managed_pslots);
|
||||
pre = __xa_cmpxchg(&sbi->managed_pslots, grp->index,
|
||||
NULL, grp, GFP_NOFS);
|
||||
if (pre) {
|
||||
if (xa_is_err(pre)) {
|
||||
pre = ERR_PTR(xa_err(pre));
|
||||
} else if (erofs_workgroup_get(pre)) {
|
||||
/* try to legitimize the current in-tree one */
|
||||
xa_unlock(&sbi->managed_pslots);
|
||||
cond_resched();
|
||||
goto repeat;
|
||||
}
|
||||
atomic_dec(&grp->refcount);
|
||||
grp = pre;
|
||||
}
|
||||
xa_unlock(&sbi->managed_pslots);
|
||||
return grp;
|
||||
}
|
||||
|
||||
static void __erofs_workgroup_free(struct erofs_workgroup *grp)
|
||||
|
|
@ -155,7 +146,7 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi,
|
|||
|
||||
/*
|
||||
* Note that all cached pages should be unattached
|
||||
* before deleted from the radix tree. Otherwise some
|
||||
* before deleted from the XArray. Otherwise some
|
||||
* cached pages could be still attached to the orphan
|
||||
* old workgroup when the new one is available in the tree.
|
||||
*/
|
||||
|
|
@ -169,7 +160,7 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi,
|
|||
* however in order to avoid some race conditions, add a
|
||||
* DBG_BUGON to observe this in advance.
|
||||
*/
|
||||
DBG_BUGON(radix_tree_delete(&sbi->workstn_tree, grp->index) != grp);
|
||||
DBG_BUGON(xa_erase(&sbi->managed_pslots, grp->index) != grp);
|
||||
|
||||
/*
|
||||
* If managed cache is on, last refcount should indicate
|
||||
|
|
@ -182,22 +173,11 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi,
|
|||
static unsigned long erofs_shrink_workstation(struct erofs_sb_info *sbi,
|
||||
unsigned long nr_shrink)
|
||||
{
|
||||
pgoff_t first_index = 0;
|
||||
void *batch[PAGEVEC_SIZE];
|
||||
struct erofs_workgroup *grp;
|
||||
unsigned int freed = 0;
|
||||
unsigned long index;
|
||||
|
||||
int i, found;
|
||||
repeat:
|
||||
xa_lock(&sbi->workstn_tree);
|
||||
|
||||
found = radix_tree_gang_lookup(&sbi->workstn_tree,
|
||||
batch, first_index, PAGEVEC_SIZE);
|
||||
|
||||
for (i = 0; i < found; ++i) {
|
||||
struct erofs_workgroup *grp = batch[i];
|
||||
|
||||
first_index = grp->index + 1;
|
||||
|
||||
xa_for_each(&sbi->managed_pslots, index, grp) {
|
||||
/* try to shrink each valid workgroup */
|
||||
if (!erofs_try_to_release_workgroup(sbi, grp))
|
||||
continue;
|
||||
|
|
@ -206,10 +186,6 @@ repeat:
|
|||
if (!--nr_shrink)
|
||||
break;
|
||||
}
|
||||
xa_unlock(&sbi->workstn_tree);
|
||||
|
||||
if (i && nr_shrink)
|
||||
goto repeat;
|
||||
return freed;
|
||||
}
|
||||
|
||||
|
|
@ -286,7 +262,7 @@ static unsigned long erofs_shrink_scan(struct shrinker *shrink,
|
|||
spin_unlock(&erofs_sb_list_lock);
|
||||
sbi->shrinker_run_no = run_no;
|
||||
|
||||
freed += erofs_shrink_workstation(sbi, nr);
|
||||
freed += erofs_shrink_workstation(sbi, nr - freed);
|
||||
|
||||
spin_lock(&erofs_sb_list_lock);
|
||||
/* Get the next list element before we move this one */
|
||||
|
|
|
|||
|
|
@ -67,16 +67,6 @@ static void z_erofs_pcluster_init_once(void *ptr)
|
|||
pcl->compressed_pages[i] = NULL;
|
||||
}
|
||||
|
||||
static void z_erofs_pcluster_init_always(struct z_erofs_pcluster *pcl)
|
||||
{
|
||||
struct z_erofs_collection *cl = z_erofs_primarycollection(pcl);
|
||||
|
||||
atomic_set(&pcl->obj.refcount, 1);
|
||||
|
||||
DBG_BUGON(cl->nr_pages);
|
||||
DBG_BUGON(cl->vcnt);
|
||||
}
|
||||
|
||||
int __init z_erofs_init_zip_subsystem(void)
|
||||
{
|
||||
pcluster_cachep = kmem_cache_create("erofs_compress",
|
||||
|
|
@ -341,26 +331,19 @@ static int z_erofs_lookup_collection(struct z_erofs_collector *clt,
|
|||
struct inode *inode,
|
||||
struct erofs_map_blocks *map)
|
||||
{
|
||||
struct erofs_workgroup *grp;
|
||||
struct z_erofs_pcluster *pcl;
|
||||
struct z_erofs_pcluster *pcl = clt->pcl;
|
||||
struct z_erofs_collection *cl;
|
||||
unsigned int length;
|
||||
|
||||
grp = erofs_find_workgroup(inode->i_sb, map->m_pa >> PAGE_SHIFT);
|
||||
if (!grp)
|
||||
return -ENOENT;
|
||||
|
||||
pcl = container_of(grp, struct z_erofs_pcluster, obj);
|
||||
/* to avoid unexpected loop formed by corrupted images */
|
||||
if (clt->owned_head == &pcl->next || pcl == clt->tailpcl) {
|
||||
DBG_BUGON(1);
|
||||
erofs_workgroup_put(grp);
|
||||
return -EFSCORRUPTED;
|
||||
}
|
||||
|
||||
cl = z_erofs_primarycollection(pcl);
|
||||
if (cl->pageofs != (map->m_la & ~PAGE_MASK)) {
|
||||
DBG_BUGON(1);
|
||||
erofs_workgroup_put(grp);
|
||||
return -EFSCORRUPTED;
|
||||
}
|
||||
|
||||
|
|
@ -368,7 +351,6 @@ static int z_erofs_lookup_collection(struct z_erofs_collector *clt,
|
|||
if (length & Z_EROFS_PCLUSTER_FULL_LENGTH) {
|
||||
if ((map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) > length) {
|
||||
DBG_BUGON(1);
|
||||
erofs_workgroup_put(grp);
|
||||
return -EFSCORRUPTED;
|
||||
}
|
||||
} else {
|
||||
|
|
@ -391,7 +373,6 @@ static int z_erofs_lookup_collection(struct z_erofs_collector *clt,
|
|||
/* clean tailpcl if the current owned_head is Z_EROFS_PCLUSTER_TAIL */
|
||||
if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL)
|
||||
clt->tailpcl = NULL;
|
||||
clt->pcl = pcl;
|
||||
clt->cl = cl;
|
||||
return 0;
|
||||
}
|
||||
|
|
@ -402,6 +383,7 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
|
|||
{
|
||||
struct z_erofs_pcluster *pcl;
|
||||
struct z_erofs_collection *cl;
|
||||
struct erofs_workgroup *grp;
|
||||
int err;
|
||||
|
||||
/* no available workgroup, let's allocate one */
|
||||
|
|
@ -409,7 +391,7 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
|
|||
if (!pcl)
|
||||
return -ENOMEM;
|
||||
|
||||
z_erofs_pcluster_init_always(pcl);
|
||||
atomic_set(&pcl->obj.refcount, 1);
|
||||
pcl->obj.index = map->m_pa >> PAGE_SHIFT;
|
||||
|
||||
pcl->length = (map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) |
|
||||
|
|
@ -429,19 +411,29 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
|
|||
clt->mode = COLLECT_PRIMARY_FOLLOWED;
|
||||
|
||||
cl = z_erofs_primarycollection(pcl);
|
||||
|
||||
/* must be cleaned before freeing to slab */
|
||||
DBG_BUGON(cl->nr_pages);
|
||||
DBG_BUGON(cl->vcnt);
|
||||
|
||||
cl->pageofs = map->m_la & ~PAGE_MASK;
|
||||
|
||||
/*
|
||||
* lock all primary followed works before visible to others
|
||||
* and mutex_trylock *never* fails for a new pcluster.
|
||||
*/
|
||||
mutex_trylock(&cl->lock);
|
||||
DBG_BUGON(!mutex_trylock(&cl->lock));
|
||||
|
||||
err = erofs_register_workgroup(inode->i_sb, &pcl->obj);
|
||||
if (err) {
|
||||
mutex_unlock(&cl->lock);
|
||||
kmem_cache_free(pcluster_cachep, pcl);
|
||||
return -EAGAIN;
|
||||
grp = erofs_insert_workgroup(inode->i_sb, &pcl->obj);
|
||||
if (IS_ERR(grp)) {
|
||||
err = PTR_ERR(grp);
|
||||
goto err_out;
|
||||
}
|
||||
|
||||
if (grp != &pcl->obj) {
|
||||
clt->pcl = container_of(grp, struct z_erofs_pcluster, obj);
|
||||
err = -EEXIST;
|
||||
goto err_out;
|
||||
}
|
||||
/* used to check tail merging loop due to corrupted images */
|
||||
if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL)
|
||||
|
|
@ -450,12 +442,18 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
|
|||
clt->pcl = pcl;
|
||||
clt->cl = cl;
|
||||
return 0;
|
||||
|
||||
err_out:
|
||||
mutex_unlock(&cl->lock);
|
||||
kmem_cache_free(pcluster_cachep, pcl);
|
||||
return err;
|
||||
}
|
||||
|
||||
static int z_erofs_collector_begin(struct z_erofs_collector *clt,
|
||||
struct inode *inode,
|
||||
struct erofs_map_blocks *map)
|
||||
{
|
||||
struct erofs_workgroup *grp;
|
||||
int ret;
|
||||
|
||||
DBG_BUGON(clt->cl);
|
||||
|
|
@ -469,21 +467,25 @@ static int z_erofs_collector_begin(struct z_erofs_collector *clt,
|
|||
return -EINVAL;
|
||||
}
|
||||
|
||||
repeat:
|
||||
ret = z_erofs_lookup_collection(clt, inode, map);
|
||||
if (ret == -ENOENT) {
|
||||
grp = erofs_find_workgroup(inode->i_sb, map->m_pa >> PAGE_SHIFT);
|
||||
if (grp) {
|
||||
clt->pcl = container_of(grp, struct z_erofs_pcluster, obj);
|
||||
} else {
|
||||
ret = z_erofs_register_collection(clt, inode, map);
|
||||
|
||||
/* someone registered at the same time, give another try */
|
||||
if (ret == -EAGAIN) {
|
||||
cond_resched();
|
||||
goto repeat;
|
||||
}
|
||||
if (!ret)
|
||||
goto out;
|
||||
if (ret != -EEXIST)
|
||||
return ret;
|
||||
}
|
||||
|
||||
if (ret)
|
||||
ret = z_erofs_lookup_collection(clt, inode, map);
|
||||
if (ret) {
|
||||
erofs_workgroup_put(&clt->pcl->obj);
|
||||
return ret;
|
||||
}
|
||||
|
||||
out:
|
||||
z_erofs_pagevec_ctor_init(&clt->vector, Z_EROFS_NR_INLINE_PAGEVECS,
|
||||
clt->cl->pagevec, clt->cl->vcnt);
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue