summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/extent_io.c11
-rw-r--r--fs/btrfs/inode.c8
-rw-r--r--fs/btrfs/qgroup.c3
-rw-r--r--fs/btrfs/relocation.c19
-rw-r--r--fs/btrfs/tree-log.c19
-rw-r--r--fs/btrfs/zoned.c2
-rw-r--r--fs/erofs/Kconfig20
-rw-r--r--fs/erofs/super.c28
-rw-r--r--fs/erofs/zdata.c13
-rw-r--r--fs/proc/task_mmu.c24
10 files changed, 94 insertions, 53 deletions
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 835b0deef9bb..f23d75986947 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4331,15 +4331,18 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
unsigned long end = index + (PAGE_SIZE >> fs_info->nodesize_bits) - 1;
int ret;
- xa_lock_irq(&fs_info->buffer_tree);
+ rcu_read_lock();
xa_for_each_range(&fs_info->buffer_tree, index, eb, start, end) {
/*
* The same as try_release_extent_buffer(), to ensure the eb
* won't disappear out from under us.
*/
spin_lock(&eb->refs_lock);
+ rcu_read_unlock();
+
if (refcount_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
spin_unlock(&eb->refs_lock);
+ rcu_read_lock();
continue;
}
@@ -4358,11 +4361,10 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
* check the folio private at the end. And
* release_extent_buffer() will release the refs_lock.
*/
- xa_unlock_irq(&fs_info->buffer_tree);
release_extent_buffer(eb);
- xa_lock_irq(&fs_info->buffer_tree);
+ rcu_read_lock();
}
- xa_unlock_irq(&fs_info->buffer_tree);
+ rcu_read_unlock();
/*
* Finally to check if we have cleared folio private, as if we have
@@ -4375,7 +4377,6 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
ret = 0;
spin_unlock(&folio->mapping->i_private_lock);
return ret;
-
}
int try_release_extent_buffer(struct folio *folio)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b77dd22b8cdb..d740910e071a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -401,10 +401,12 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
while (index <= end_index) {
folio = filemap_get_folio(inode->vfs_inode.i_mapping, index);
- index++;
- if (IS_ERR(folio))
+ if (IS_ERR(folio)) {
+ index++;
continue;
+ }
+ index = folio_end(folio) >> PAGE_SHIFT;
/*
* Here we just clear all Ordered bits for every page in the
* range, then btrfs_mark_ordered_io_finished() will handle
@@ -2013,7 +2015,7 @@ static int nocow_one_range(struct btrfs_inode *inode, struct folio *locked_folio
* cleaered by the caller.
*/
if (ret < 0)
- btrfs_cleanup_ordered_extents(inode, file_pos, end);
+ btrfs_cleanup_ordered_extents(inode, file_pos, len);
return ret;
}
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 1a5972178b3a..ccaa9a3cf1ce 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1453,7 +1453,6 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root,
struct btrfs_qgroup *src, int sign)
{
struct btrfs_qgroup *qgroup;
- struct btrfs_qgroup *cur;
LIST_HEAD(qgroup_list);
u64 num_bytes = src->excl;
int ret = 0;
@@ -1463,7 +1462,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root,
goto out;
qgroup_iterator_add(&qgroup_list, qgroup);
- list_for_each_entry(cur, &qgroup_list, iterator) {
+ list_for_each_entry(qgroup, &qgroup_list, iterator) {
struct btrfs_qgroup_list *glist;
qgroup->rfer += sign * num_bytes;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index e58151933844..7256f6748c8f 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -602,6 +602,25 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
if (btrfs_root_id(root) == objectid) {
u64 commit_root_gen;
+ /*
+ * Relocation will wait for cleaner thread, and any half-dropped
+ * subvolume will be fully cleaned up at mount time.
+ * So here we shouldn't hit a subvolume with non-zero drop_progress.
+ *
+ * If this isn't the case, error out since it can make us attempt to
+ * drop references for extents that were already dropped before.
+ */
+ if (unlikely(btrfs_disk_key_objectid(&root->root_item.drop_progress))) {
+ struct btrfs_key cpu_key;
+
+ btrfs_disk_key_to_cpu(&cpu_key, &root->root_item.drop_progress);
+ btrfs_err(fs_info,
+ "cannot relocate partially dropped subvolume %llu, drop progress key (%llu %u %llu)",
+ objectid, cpu_key.objectid, cpu_key.type, cpu_key.offset);
+ ret = -EUCLEAN;
+ goto fail;
+ }
+
/* called by btrfs_init_reloc_root */
ret = btrfs_copy_root(trans, root, root->commit_root, &eb,
BTRFS_TREE_RELOC_OBJECTID);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 2186e87fb61b..69e11557fd13 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2605,14 +2605,14 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
/*
* Correctly adjust the reserved bytes occupied by a log tree extent buffer
*/
-static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start)
+static int unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start)
{
struct btrfs_block_group *cache;
cache = btrfs_lookup_block_group(fs_info, start);
if (!cache) {
btrfs_err(fs_info, "unable to find block group for %llu", start);
- return;
+ return -ENOENT;
}
spin_lock(&cache->space_info->lock);
@@ -2623,27 +2623,22 @@ static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start)
spin_unlock(&cache->space_info->lock);
btrfs_put_block_group(cache);
+
+ return 0;
}
static int clean_log_buffer(struct btrfs_trans_handle *trans,
struct extent_buffer *eb)
{
- int ret;
-
btrfs_tree_lock(eb);
btrfs_clear_buffer_dirty(trans, eb);
wait_on_extent_buffer_writeback(eb);
btrfs_tree_unlock(eb);
- if (trans) {
- ret = btrfs_pin_reserved_extent(trans, eb);
- if (ret)
- return ret;
- } else {
- unaccount_log_buffer(eb->fs_info, eb->start);
- }
+ if (trans)
+ return btrfs_pin_reserved_extent(trans, eb);
- return 0;
+ return unaccount_log_buffer(eb->fs_info, eb->start);
}
static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 245e813ecd78..db11b5b5f0e6 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -2650,7 +2650,7 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info)
spin_lock(&block_group->lock);
if (block_group->reserved || block_group->alloc_offset == 0 ||
- (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM) ||
+ !(block_group->flags & BTRFS_BLOCK_GROUP_DATA) ||
test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) {
spin_unlock(&block_group->lock);
continue;
diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
index 7b26efc271ee..d81f3318417d 100644
--- a/fs/erofs/Kconfig
+++ b/fs/erofs/Kconfig
@@ -3,8 +3,18 @@
config EROFS_FS
tristate "EROFS filesystem support"
depends on BLOCK
+ select CACHEFILES if EROFS_FS_ONDEMAND
select CRC32
+ select CRYPTO if EROFS_FS_ZIP_ACCEL
+ select CRYPTO_DEFLATE if EROFS_FS_ZIP_ACCEL
select FS_IOMAP
+ select LZ4_DECOMPRESS if EROFS_FS_ZIP
+ select NETFS_SUPPORT if EROFS_FS_ONDEMAND
+ select XXHASH if EROFS_FS_XATTR
+ select XZ_DEC if EROFS_FS_ZIP_LZMA
+ select XZ_DEC_MICROLZMA if EROFS_FS_ZIP_LZMA
+ select ZLIB_INFLATE if EROFS_FS_ZIP_DEFLATE
+ select ZSTD_DECOMPRESS if EROFS_FS_ZIP_ZSTD
help
EROFS (Enhanced Read-Only File System) is a lightweight read-only
file system with modern designs (e.g. no buffer heads, inline
@@ -38,7 +48,6 @@ config EROFS_FS_DEBUG
config EROFS_FS_XATTR
bool "EROFS extended attributes"
depends on EROFS_FS
- select XXHASH
default y
help
Extended attributes are name:value pairs associated with inodes by
@@ -94,7 +103,6 @@ config EROFS_FS_BACKED_BY_FILE
config EROFS_FS_ZIP
bool "EROFS Data Compression Support"
depends on EROFS_FS
- select LZ4_DECOMPRESS
default y
help
Enable transparent compression support for EROFS file systems.
@@ -104,8 +112,6 @@ config EROFS_FS_ZIP
config EROFS_FS_ZIP_LZMA
bool "EROFS LZMA compressed data support"
depends on EROFS_FS_ZIP
- select XZ_DEC
- select XZ_DEC_MICROLZMA
help
Saying Y here includes support for reading EROFS file systems
containing LZMA compressed data, specifically called microLZMA. It
@@ -117,7 +123,6 @@ config EROFS_FS_ZIP_LZMA
config EROFS_FS_ZIP_DEFLATE
bool "EROFS DEFLATE compressed data support"
depends on EROFS_FS_ZIP
- select ZLIB_INFLATE
help
Saying Y here includes support for reading EROFS file systems
containing DEFLATE compressed data. It gives better compression
@@ -132,7 +137,6 @@ config EROFS_FS_ZIP_DEFLATE
config EROFS_FS_ZIP_ZSTD
bool "EROFS Zstandard compressed data support"
depends on EROFS_FS_ZIP
- select ZSTD_DECOMPRESS
help
Saying Y here includes support for reading EROFS file systems
containing Zstandard compressed data. It gives better compression
@@ -147,8 +151,6 @@ config EROFS_FS_ZIP_ZSTD
config EROFS_FS_ZIP_ACCEL
bool "EROFS hardware decompression support"
depends on EROFS_FS_ZIP
- select CRYPTO
- select CRYPTO_DEFLATE
help
Saying Y here includes hardware accelerator support for reading
EROFS file systems containing compressed data. It gives better
@@ -163,9 +165,7 @@ config EROFS_FS_ZIP_ACCEL
config EROFS_FS_ONDEMAND
bool "EROFS fscache-based on-demand read support (deprecated)"
depends on EROFS_FS
- select NETFS_SUPPORT
select FSCACHE
- select CACHEFILES
select CACHEFILES_ONDEMAND
help
This permits EROFS to use fscache-backed data blobs with on-demand
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index e1020aa60771..1b529ace4db0 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -174,6 +174,11 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
if (!erofs_is_fileio_mode(sbi)) {
dif->dax_dev = fs_dax_get_by_bdev(file_bdev(file),
&dif->dax_part_off, NULL, NULL);
+ if (!dif->dax_dev && test_opt(&sbi->opt, DAX_ALWAYS)) {
+ erofs_info(sb, "DAX unsupported by %s. Turning off DAX.",
+ dif->path);
+ clear_opt(&sbi->opt, DAX_ALWAYS);
+ }
} else if (!S_ISREG(file_inode(file)->i_mode)) {
fput(file);
return -EINVAL;
@@ -210,8 +215,13 @@ static int erofs_scan_devices(struct super_block *sb,
ondisk_extradevs, sbi->devs->extra_devices);
return -EINVAL;
}
- if (!ondisk_extradevs)
+ if (!ondisk_extradevs) {
+ if (test_opt(&sbi->opt, DAX_ALWAYS) && !sbi->dif0.dax_dev) {
+ erofs_info(sb, "DAX unsupported by block device. Turning off DAX.");
+ clear_opt(&sbi->opt, DAX_ALWAYS);
+ }
return 0;
+ }
if (!sbi->devs->extra_devices && !erofs_is_fscache_mode(sb))
sbi->devs->flatdev = true;
@@ -313,8 +323,8 @@ static int erofs_read_superblock(struct super_block *sb)
sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact));
if (erofs_sb_has_48bit(sbi) && dsb->rootnid_8b) {
sbi->root_nid = le64_to_cpu(dsb->rootnid_8b);
- sbi->dif0.blocks = (sbi->dif0.blocks << 32) |
- le16_to_cpu(dsb->rb.blocks_hi);
+ sbi->dif0.blocks = sbi->dif0.blocks |
+ ((u64)le16_to_cpu(dsb->rb.blocks_hi) << 32);
} else {
sbi->root_nid = le16_to_cpu(dsb->rb.rootnid_2b);
}
@@ -338,7 +348,6 @@ static int erofs_read_superblock(struct super_block *sb)
if (ret < 0)
goto out;
- /* handle multiple devices */
ret = erofs_scan_devices(sb, dsb);
if (erofs_sb_has_48bit(sbi))
@@ -671,14 +680,9 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
return invalfc(fc, "cannot use fsoffset in fscache mode");
}
- if (test_opt(&sbi->opt, DAX_ALWAYS)) {
- if (!sbi->dif0.dax_dev) {
- errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
- clear_opt(&sbi->opt, DAX_ALWAYS);
- } else if (sbi->blkszbits != PAGE_SHIFT) {
- errorfc(fc, "unsupported blocksize for DAX");
- clear_opt(&sbi->opt, DAX_ALWAYS);
- }
+ if (test_opt(&sbi->opt, DAX_ALWAYS) && sbi->blkszbits != PAGE_SHIFT) {
+ erofs_info(sb, "unsupported blocksize for DAX");
+ clear_opt(&sbi->opt, DAX_ALWAYS);
}
sb->s_time_gran = 1;
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 792f20888a8f..2d73297003d2 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1432,6 +1432,16 @@ static void z_erofs_decompressqueue_kthread_work(struct kthread_work *work)
}
#endif
+/* Use (kthread_)work in atomic contexts to minimize scheduling overhead */
+static inline bool z_erofs_in_atomic(void)
+{
+ if (IS_ENABLED(CONFIG_PREEMPTION) && rcu_preempt_depth())
+ return true;
+ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
+ return true;
+ return !preemptible();
+}
+
static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
int bios)
{
@@ -1446,8 +1456,7 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
if (atomic_add_return(bios, &io->pending_bios))
return;
- /* Use (kthread_)work and sync decompression for atomic contexts only */
- if (!in_task() || irqs_disabled() || rcu_read_lock_any_held()) {
+ if (z_erofs_in_atomic()) {
#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD
struct kthread_worker *worker;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 3d6d8a9f13fc..29cca0e6d0ff 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -340,8 +340,8 @@ static int proc_maps_open(struct inode *inode, struct file *file,
priv->inode = inode;
priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
- if (IS_ERR_OR_NULL(priv->mm)) {
- int err = priv->mm ? PTR_ERR(priv->mm) : -ESRCH;
+ if (IS_ERR(priv->mm)) {
+ int err = PTR_ERR(priv->mm);
seq_release_private(inode, file);
return err;
@@ -1148,10 +1148,13 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = walk->vma;
- pte_t ptent = huge_ptep_get(walk->mm, addr, pte);
struct folio *folio = NULL;
bool present = false;
+ spinlock_t *ptl;
+ pte_t ptent;
+ ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
+ ptent = huge_ptep_get(walk->mm, addr, pte);
if (pte_present(ptent)) {
folio = page_folio(pte_page(ptent));
present = true;
@@ -1170,6 +1173,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
else
mss->private_hugetlb += huge_page_size(hstate_vma(vma));
}
+ spin_unlock(ptl);
return 0;
}
#else
@@ -2017,12 +2021,14 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
struct pagemapread *pm = walk->private;
struct vm_area_struct *vma = walk->vma;
u64 flags = 0, frame = 0;
+ spinlock_t *ptl;
int err = 0;
pte_t pte;
if (vma->vm_flags & VM_SOFTDIRTY)
flags |= PM_SOFT_DIRTY;
+ ptl = huge_pte_lock(hstate_vma(vma), walk->mm, ptep);
pte = huge_ptep_get(walk->mm, addr, ptep);
if (pte_present(pte)) {
struct folio *folio = page_folio(pte_page(pte));
@@ -2050,11 +2056,12 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
err = add_to_pagemap(&pme, pm);
if (err)
- return err;
+ break;
if (pm->show_pfn && (flags & PM_PRESENT))
frame++;
}
+ spin_unlock(ptl);
cond_resched();
return err;
@@ -3128,17 +3135,22 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
unsigned long addr, unsigned long end, struct mm_walk *walk)
{
- pte_t huge_pte = huge_ptep_get(walk->mm, addr, pte);
+ pte_t huge_pte;
struct numa_maps *md;
struct page *page;
+ spinlock_t *ptl;
+ ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte);
+ huge_pte = huge_ptep_get(walk->mm, addr, pte);
if (!pte_present(huge_pte))
- return 0;
+ goto out;
page = pte_page(huge_pte);
md = walk->private;
gather_stats(page, md, pte_dirty(huge_pte), 1);
+out:
+ spin_unlock(ptl);
return 0;
}
generated by cgit (git 2.34.1) at 2025-08-14 11:52:52 +0000