summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/admin-guide/cgroup-v2.rst2
-rw-r--r--fs/aio.c1
-rw-r--r--fs/btrfs/extent_io.c7
-rw-r--r--fs/btrfs/inode.c2
-rw-r--r--fs/buffer.c4
-rw-r--r--fs/ext4/page-io.c2
-rw-r--r--fs/f2fs/data.c9
-rw-r--r--fs/freevxfs/vxfs_dir.h2
-rw-r--r--fs/fs-writeback.c8
-rw-r--r--fs/hfsplus/hfsplus_fs.h3
-rw-r--r--fs/hfsplus/wrapper.c2
-rw-r--r--fs/iomap/buffered-io.c2
-rw-r--r--fs/mpage.c2
-rw-r--r--fs/namei.c41
-rw-r--r--fs/namespace.c68
-rw-r--r--include/linux/writeback.h4
-rw-r--r--include/uapi/linux/mount.h6
-rw-r--r--init/initramfs.c15
18 files changed, 149 insertions, 31 deletions
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 69af2173555f..064012ea6f36 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -2945,7 +2945,7 @@ following two functions.
a queue (device) has been associated with the bio and
before submission.
- wbc_account_cgroup_owner(@wbc, @page, @bytes)
+ wbc_account_cgroup_owner(@wbc, @folio, @bytes)
Should be called for each data segment being written out.
While this function doesn't care exactly when it's called
during the writeback session, it's the easiest and most
diff --git a/fs/aio.c b/fs/aio.c
index e8920178b50f..72e3970f4225 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -2191,7 +2191,6 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
return -EINVAL;
spin_lock_irq(&ctx->ctx_lock);
- /* TODO: use a hash or array, this sucks. */
list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
if (kiocb->ki_res.obj == obj) {
ret = kiocb->ki_cancel(&kiocb->rw);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 39c9677c47d5..4667d1e034e0 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -785,7 +785,7 @@ static void submit_extent_folio(struct btrfs_bio_ctrl *bio_ctrl,
}
if (bio_ctrl->wbc)
- wbc_account_cgroup_owner(bio_ctrl->wbc, &folio->page,
+ wbc_account_cgroup_owner(bio_ctrl->wbc, folio,
len);
size -= len;
@@ -1707,7 +1707,7 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
ret = bio_add_folio(&bbio->bio, folio, eb->len,
eb->start - folio_pos(folio));
ASSERT(ret);
- wbc_account_cgroup_owner(wbc, folio_page(folio, 0), eb->len);
+ wbc_account_cgroup_owner(wbc, folio, eb->len);
folio_unlock(folio);
} else {
int num_folios = num_extent_folios(eb);
@@ -1721,8 +1721,7 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
folio_start_writeback(folio);
ret = bio_add_folio(&bbio->bio, folio, eb->folio_size, 0);
ASSERT(ret);
- wbc_account_cgroup_owner(wbc, folio_page(folio, 0),
- eb->folio_size);
+ wbc_account_cgroup_owner(wbc, folio, eb->folio_size);
wbc->nr_to_write -= folio_nr_pages(folio);
folio_unlock(folio);
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index edac499fd83d..eb64f04755c2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1729,7 +1729,7 @@ static bool run_delalloc_compressed(struct btrfs_inode *inode,
* need full accuracy. Just account the whole thing
* against the first page.
*/
- wbc_account_cgroup_owner(wbc, &locked_folio->page,
+ wbc_account_cgroup_owner(wbc, locked_folio,
cur_end - start);
async_chunk[i].locked_folio = locked_folio;
locked_folio = NULL;
diff --git a/fs/buffer.c b/fs/buffer.c
index 1fc9a50def0b..32bd0f4c4223 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2803,7 +2803,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_write_hint = write_hint;
- __bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+ bio_add_folio_nofail(bio, bh->b_folio, bh->b_size, bh_offset(bh));
bio->bi_end_io = end_bio_bh_io_sync;
bio->bi_private = bh;
@@ -2813,7 +2813,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
if (wbc) {
wbc_init_bio(wbc, bio);
- wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size);
+ wbc_account_cgroup_owner(wbc, bh->b_folio, bh->b_size);
}
submit_bio(bio);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index ad5543866d21..b7b9261fec3b 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -421,7 +421,7 @@ submit_and_retry:
io_submit_init_bio(io, bh);
if (!bio_add_folio(io->io_bio, io_folio, bh->b_size, bh_offset(bh)))
goto submit_and_retry;
- wbc_account_cgroup_owner(io->io_wbc, &folio->page, bh->b_size);
+ wbc_account_cgroup_owner(io->io_wbc, folio, bh->b_size);
io->io_next_block++;
}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 94f7b084f601..e3ce763cce18 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -711,7 +711,8 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
}
if (fio->io_wbc && !is_read_io(fio->op))
- wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, page_folio(fio->page),
+ PAGE_SIZE);
inc_page_count(fio->sbi, is_read_io(fio->op) ?
__read_io_type(page) : WB_DATA_TYPE(fio->page, false));
@@ -911,7 +912,8 @@ alloc_new:
}
if (fio->io_wbc)
- wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, page_folio(fio->page),
+ PAGE_SIZE);
inc_page_count(fio->sbi, WB_DATA_TYPE(page, false));
@@ -1011,7 +1013,8 @@ alloc_new:
}
if (fio->io_wbc)
- wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, page_folio(fio->page),
+ PAGE_SIZE);
io->last_block_in_bio = fio->new_blkaddr;
diff --git a/fs/freevxfs/vxfs_dir.h b/fs/freevxfs/vxfs_dir.h
index fbcd603365ad..8c67627f2a3d 100644
--- a/fs/freevxfs/vxfs_dir.h
+++ b/fs/freevxfs/vxfs_dir.h
@@ -25,7 +25,7 @@
struct vxfs_dirblk {
__fs16 d_free; /* free space in dirblock */
__fs16 d_nhash; /* no of hash chains */
- __fs16 d_hash[1]; /* hash chain */
+ __fs16 d_hash[]; /* hash chain */
};
/*
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 77db1f10023e..3cd99e2dc6ac 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -907,17 +907,16 @@ EXPORT_SYMBOL_GPL(wbc_detach_inode);
/**
* wbc_account_cgroup_owner - account writeback to update inode cgroup ownership
* @wbc: writeback_control of the writeback in progress
- * @page: page being written out
+ * @folio: folio being written out
* @bytes: number of bytes being written out
*
- * @bytes from @page are about to written out during the writeback
+ * @bytes from @folio are about to written out during the writeback
* controlled by @wbc. Keep the book for foreign inode detection. See
* wbc_detach_inode().
*/
-void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
+void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio,
size_t bytes)
{
- struct folio *folio;
struct cgroup_subsys_state *css;
int id;
@@ -930,7 +929,6 @@ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
if (!wbc->wb || wbc->no_cgroup_owner)
return;
- folio = page_folio(page);
css = mem_cgroup_css_from_folio(folio);
/* dead cgroups shouldn't contribute to inode ownership arbitration */
if (!(css->flags & CSS_ONLINE))
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 59ce81dca73f..5389918bbf29 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -156,6 +156,7 @@ struct hfsplus_sb_info {
/* Runtime variables */
u32 blockoffset;
+ u32 min_io_size;
sector_t part_start;
sector_t sect_count;
int fs_shift;
@@ -307,7 +308,7 @@ struct hfsplus_readdir_data {
*/
static inline unsigned short hfsplus_min_io_size(struct super_block *sb)
{
- return max_t(unsigned short, bdev_logical_block_size(sb->s_bdev),
+ return max_t(unsigned short, HFSPLUS_SB(sb)->min_io_size,
HFSPLUS_SECTOR_SIZE);
}
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index ce9346099c72..4b0fdc49d1fe 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -172,6 +172,8 @@ int hfsplus_read_wrapper(struct super_block *sb)
if (!blocksize)
goto out;
+ sbi->min_io_size = blocksize;
+
if (hfsplus_get_last_session(sb, &part_start, &part_size))
goto out;
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 11ea747228ae..3d1fae7d3a64 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1833,7 +1833,7 @@ new_ioend:
if (ifs)
atomic_add(len, &ifs->write_bytes_pending);
wpc->ioend->io_size += len;
- wbc_account_cgroup_owner(wbc, &folio->page, len);
+ wbc_account_cgroup_owner(wbc, folio, len);
return 0;
}
diff --git a/fs/mpage.c b/fs/mpage.c
index b5b5ddf9d513..82aecf372743 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -606,7 +606,7 @@ alloc_new:
* the confused fail path above (OOM) will be very confused when
* it finds all bh marked clean (i.e. it will not write anything)
*/
- wbc_account_cgroup_owner(wbc, &folio->page, folio_size(folio));
+ wbc_account_cgroup_owner(wbc, folio, folio_size(folio));
length = first_unmapped << blkbits;
if (!bio_add_folio(bio, folio, length, 0)) {
bio = mpage_bio_submit_write(bio);
diff --git a/fs/namei.c b/fs/namei.c
index 4a4a22a08ac2..05a8d544fb35 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -326,6 +326,25 @@ static int check_acl(struct mnt_idmap *idmap,
return -EAGAIN;
}
+/*
+ * Very quick optimistic "we know we have no ACL's" check.
+ *
+ * Note that this is purely for ACL_TYPE_ACCESS, and purely
+ * for the "we have cached that there are no ACLs" case.
+ *
+ * If this returns true, we know there are no ACLs. But if
+ * it returns false, we might still not have ACLs (it could
+ * be the is_uncached_acl() case).
+ */
+static inline bool no_acl_inode(struct inode *inode)
+{
+#ifdef CONFIG_FS_POSIX_ACL
+ return likely(!READ_ONCE(inode->i_acl));
+#else
+ return true;
+#endif
+}
+
/**
* acl_permission_check - perform basic UNIX permission checking
* @idmap: idmap of the mount the inode was found from
@@ -348,6 +367,28 @@ static int acl_permission_check(struct mnt_idmap *idmap,
unsigned int mode = inode->i_mode;
vfsuid_t vfsuid;
+ /*
+ * Common cheap case: everybody has the requested
+ * rights, and there are no ACLs to check. No need
+ * to do any owner/group checks in that case.
+ *
+ * - 'mask&7' is the requested permission bit set
+ * - multiplying by 0111 spreads them out to all of ugo
+ * - '& ~mode' looks for missing inode permission bits
+ * - the '!' is for "no missing permissions"
+ *
+ * After that, we just need to check that there are no
+ * ACL's on the inode - do the 'IS_POSIXACL()' check last
+ * because it will dereference the ->i_sb pointer and we
+ * want to avoid that if at all possible.
+ */
+ if (!((mask & 7) * 0111 & ~mode)) {
+ if (no_acl_inode(inode))
+ return 0;
+ if (!IS_POSIXACL(inode))
+ return 0;
+ }
+
/* Are we the owner? If so, ACL's don't matter */
vfsuid = i_uid_into_vfsuid(idmap, inode);
if (likely(vfsuid_eq_kuid(vfsuid, current_fsuid()))) {
diff --git a/fs/namespace.c b/fs/namespace.c
index 9a3c251d033d..d32b5afa99dc 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -5004,6 +5004,40 @@ static int statmount_fs_type(struct kstatmount *s, struct seq_file *seq)
return 0;
}
+static void statmount_fs_subtype(struct kstatmount *s, struct seq_file *seq)
+{
+ struct super_block *sb = s->mnt->mnt_sb;
+
+ if (sb->s_subtype)
+ seq_puts(seq, sb->s_subtype);
+}
+
+static int statmount_sb_source(struct kstatmount *s, struct seq_file *seq)
+{
+ struct super_block *sb = s->mnt->mnt_sb;
+ struct mount *r = real_mount(s->mnt);
+
+ if (sb->s_op->show_devname) {
+ size_t start = seq->count;
+ int ret;
+
+ ret = sb->s_op->show_devname(seq, s->mnt->mnt_root);
+ if (ret)
+ return ret;
+
+ if (unlikely(seq_has_overflowed(seq)))
+ return -EAGAIN;
+
+ /* Unescape the result */
+ seq->buf[seq->count] = '\0';
+ seq->count = start;
+ seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL));
+ } else if (r->mnt_devname) {
+ seq_puts(seq, r->mnt_devname);
+ }
+ return 0;
+}
+
static void statmount_mnt_ns_id(struct kstatmount *s, struct mnt_namespace *ns)
{
s->sm.mask |= STATMOUNT_MNT_NS_ID;
@@ -5040,33 +5074,48 @@ static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq)
static int statmount_string(struct kstatmount *s, u64 flag)
{
- int ret;
+ int ret = 0;
size_t kbufsize;
struct seq_file *seq = &s->seq;
struct statmount *sm = &s->sm;
+ u32 start = seq->count;
switch (flag) {
case STATMOUNT_FS_TYPE:
- sm->fs_type = seq->count;
+ sm->fs_type = start;
ret = statmount_fs_type(s, seq);
break;
case STATMOUNT_MNT_ROOT:
- sm->mnt_root = seq->count;
+ sm->mnt_root = start;
ret = statmount_mnt_root(s, seq);
break;
case STATMOUNT_MNT_POINT:
- sm->mnt_point = seq->count;
+ sm->mnt_point = start;
ret = statmount_mnt_point(s, seq);
break;
case STATMOUNT_MNT_OPTS:
- sm->mnt_opts = seq->count;
+ sm->mnt_opts = start;
ret = statmount_mnt_opts(s, seq);
break;
+ case STATMOUNT_FS_SUBTYPE:
+ sm->fs_subtype = start;
+ statmount_fs_subtype(s, seq);
+ break;
+ case STATMOUNT_SB_SOURCE:
+ sm->sb_source = start;
+ ret = statmount_sb_source(s, seq);
+ break;
default:
WARN_ON_ONCE(true);
return -EINVAL;
}
+ /*
+ * If nothing was emitted, return to avoid setting the flag
+ * and terminating the buffer.
+ */
+ if (seq->count == start)
+ return ret;
if (unlikely(check_add_overflow(sizeof(*sm), seq->count, &kbufsize)))
return -EOVERFLOW;
if (kbufsize >= s->bufsize)
@@ -5201,6 +5250,12 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
if (!err && s->mask & STATMOUNT_MNT_OPTS)
err = statmount_string(s, STATMOUNT_MNT_OPTS);
+ if (!err && s->mask & STATMOUNT_FS_SUBTYPE)
+ err = statmount_string(s, STATMOUNT_FS_SUBTYPE);
+
+ if (!err && s->mask & STATMOUNT_SB_SOURCE)
+ err = statmount_string(s, STATMOUNT_SB_SOURCE);
+
if (!err && s->mask & STATMOUNT_MNT_NS_ID)
statmount_mnt_ns_id(s, ns);
@@ -5222,7 +5277,8 @@ static inline bool retry_statmount(const long ret, size_t *seq_size)
}
#define STATMOUNT_STRING_REQ (STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT | \
- STATMOUNT_FS_TYPE | STATMOUNT_MNT_OPTS)
+ STATMOUNT_FS_TYPE | STATMOUNT_MNT_OPTS | \
+ STATMOUNT_FS_SUBTYPE | STATMOUNT_SB_SOURCE)
static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq,
struct statmount __user *buf, size_t bufsize,
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index aee3e1b4c50f..d11b903c2edb 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -214,7 +214,7 @@ static inline void wait_on_inode(struct inode *inode)
void __inode_attach_wb(struct inode *inode, struct folio *folio);
void wbc_detach_inode(struct writeback_control *wbc);
-void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
+void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio,
size_t bytes);
int cgroup_writeback_by_id(u64 bdi_id, int memcg_id,
enum wb_reason reason, struct wb_completion *done);
@@ -300,7 +300,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio)
}
static inline void wbc_account_cgroup_owner(struct writeback_control *wbc,
- struct page *page, size_t bytes)
+ struct folio *folio, size_t bytes)
{
}
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index 225bc366ffcb..2b49e9131d77 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -173,7 +173,9 @@ struct statmount {
__u32 mnt_root; /* [str] Root of mount relative to root of fs */
__u32 mnt_point; /* [str] Mountpoint relative to current root */
__u64 mnt_ns_id; /* ID of the mount namespace */
- __u64 __spare2[49];
+ __u32 fs_subtype; /* [str] Subtype of fs_type (if any) */
+ __u32 sb_source; /* [str] Source string of the mount */
+ __u64 __spare2[48];
char str[]; /* Variable size part containing strings */
};
@@ -207,6 +209,8 @@ struct mnt_id_req {
#define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */
#define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */
#define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */
+#define STATMOUNT_FS_SUBTYPE 0x00000100U /* Want/got fs_subtype */
+#define STATMOUNT_SB_SOURCE 0x00000200U /* Want/got sb_source */
/*
* Special @mnt_id values that can be passed to listmount
diff --git a/init/initramfs.c b/init/initramfs.c
index bc911e466d5b..b2f7583bb1f5 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -360,6 +360,15 @@ static int __init do_name(void)
{
state = SkipIt;
next_state = Reset;
+
+ /* name_len > 0 && name_len <= PATH_MAX checked in do_header */
+ if (collected[name_len - 1] != '\0') {
+ pr_err("initramfs name without nulterm: %.*s\n",
+ (int)name_len, collected);
+ error("malformed archive");
+ return 1;
+ }
+
if (strcmp(collected, "TRAILER!!!") == 0) {
free_hash();
return 0;
@@ -424,6 +433,12 @@ static int __init do_copy(void)
static int __init do_symlink(void)
{
+ if (collected[name_len - 1] != '\0') {
+ pr_err("initramfs symlink without nulterm: %.*s\n",
+ (int)name_len, collected);
+ error("malformed archive");
+ return 1;
+ }
collected[N_ALIGN(name_len) + body_len] = '\0';
clean_path(collected, 0);
init_symlink(collected + N_ALIGN(name_len), collected);
generated by cgit v1.2.3 (git 2.46.0) at 2025-07-29 02:54:21 +0000