summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/filesystems/fiemap.rst49
-rw-r--r--fs/ext4/inode.c3
-rw-r--r--fs/ext4/namei.c4
-rw-r--r--fs/file.c22
-rw-r--r--fs/file_table.c7
-rw-r--r--fs/fs_context.c2
-rw-r--r--fs/namei.c34
-rw-r--r--fs/pnode.c8
-rw-r--r--fs/proc/namespaces.c2
-rw-r--r--include/linux/fiemap.h16
-rw-r--r--include/linux/fs.h15
-rw-r--r--include/linux/mount.h2
-rw-r--r--include/linux/seqlock.h2
-rw-r--r--include/uapi/linux/fiemap.h47
-rw-r--r--kernel/watch_queue.c4
-rw-r--r--mm/shmem.c6
-rw-r--r--security/apparmor/apparmorfs.c2
17 files changed, 122 insertions, 103 deletions
diff --git a/Documentation/filesystems/fiemap.rst b/Documentation/filesystems/fiemap.rst
index 93fc96f760aa..23b3ed229e49 100644
--- a/Documentation/filesystems/fiemap.rst
+++ b/Documentation/filesystems/fiemap.rst
@@ -12,21 +12,10 @@ returns a list of extents.
Request Basics
--------------
-A fiemap request is encoded within struct fiemap::
-
- struct fiemap {
- __u64 fm_start; /* logical offset (inclusive) at
- * which to start mapping (in) */
- __u64 fm_length; /* logical length of mapping which
- * userspace cares about (in) */
- __u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */
- __u32 fm_mapped_extents; /* number of extents that were
- * mapped (out) */
- __u32 fm_extent_count; /* size of fm_extents array (in) */
- __u32 fm_reserved;
- struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */
- };
+A fiemap request is encoded within struct fiemap:
+.. kernel-doc:: include/uapi/linux/fiemap.h
+ :identifiers: fiemap
fm_start, and fm_length specify the logical range within the file
which the process would like mappings for. Extents returned mirror
@@ -60,6 +49,8 @@ FIEMAP_FLAG_XATTR
If this flag is set, the extents returned will describe the inodes
extended attribute lookup tree, instead of its data tree.
+FIEMAP_FLAG_CACHE
+ This flag requests caching of the extents.
Extent Mapping
--------------
@@ -77,18 +68,10 @@ complete the requested range and will not have the FIEMAP_EXTENT_LAST
flag set (see the next section on extent flags).
Each extent is described by a single fiemap_extent structure as
-returned in fm_extents::
-
- struct fiemap_extent {
- __u64 fe_logical; /* logical offset in bytes for the start of
- * the extent */
- __u64 fe_physical; /* physical offset in bytes for the start
- * of the extent */
- __u64 fe_length; /* length in bytes for the extent */
- __u64 fe_reserved64[2];
- __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */
- __u32 fe_reserved[3];
- };
+returned in fm_extents:
+
+.. kernel-doc:: include/uapi/linux/fiemap.h
+ :identifiers: fiemap_extent
All offsets and lengths are in bytes and mirror those on disk. It is valid
for an extents logical offset to start before the request or its logical
@@ -175,6 +158,8 @@ FIEMAP_EXTENT_MERGED
userspace would be highly inefficient, the kernel will try to merge most
adjacent blocks into 'extents'.
+FIEMAP_EXTENT_SHARED
+ This flag is set to request that space be shared with other files.
VFS -> File System Implementation
---------------------------------
@@ -191,14 +176,10 @@ each discovered extent::
u64 len);
->fiemap is passed struct fiemap_extent_info which describes the
-fiemap request::
-
- struct fiemap_extent_info {
- unsigned int fi_flags; /* Flags as passed from user */
- unsigned int fi_extents_mapped; /* Number of mapped extents */
- unsigned int fi_extents_max; /* Size of fiemap_extent array */
- struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent array */
- };
+fiemap request:
+
+.. kernel-doc:: include/linux/fiemap.h
+ :identifiers: fiemap_extent_info
It is intended that the file system should not need to access any of this
structure directly. Filesystem handlers should be tolerant to signals and return
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 89aade6f45f6..7c54ae5fcbd4 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5006,10 +5006,11 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
if (IS_ENCRYPTED(inode)) {
inode->i_op = &ext4_encrypted_symlink_inode_operations;
} else if (ext4_inode_is_fast_symlink(inode)) {
- inode->i_link = (char *)ei->i_data;
inode->i_op = &ext4_fast_symlink_inode_operations;
nd_terminate_link(ei->i_data, inode->i_size,
sizeof(ei->i_data) - 1);
+ inode_set_cached_link(inode, (char *)ei->i_data,
+ inode->i_size);
} else {
inode->i_op = &ext4_symlink_inode_operations;
}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index bcf2737078b8..536d56d15072 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -3418,7 +3418,6 @@ retry:
inode->i_op = &ext4_symlink_inode_operations;
} else {
inode->i_op = &ext4_fast_symlink_inode_operations;
- inode->i_link = (char *)&EXT4_I(inode)->i_data;
}
}
@@ -3434,6 +3433,9 @@ retry:
disk_link.len);
inode->i_size = disk_link.len - 1;
EXT4_I(inode)->i_disksize = inode->i_size;
+ if (!IS_ENCRYPTED(inode))
+ inode_set_cached_link(inode, (char *)&EXT4_I(inode)->i_data,
+ inode->i_size);
}
err = ext4_add_nondir(handle, dentry, &inode);
if (handle)
diff --git a/fs/file.c b/fs/file.c
index fb1011cf6b4a..d498715ef415 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -278,10 +278,6 @@ repeat:
if (nr < fdt->max_fds)
return 0;
- /* Can we expand? */
- if (nr >= sysctl_nr_open)
- return -EMFILE;
-
if (unlikely(files->resize_in_progress)) {
spin_unlock(&files->file_lock);
wait_event(files->resize_wait, !files->resize_in_progress);
@@ -289,6 +285,10 @@ repeat:
goto repeat;
}
+ /* Can we expand? */
+ if (unlikely(nr >= sysctl_nr_open))
+ return -EMFILE;
+
/* All good, so we try */
files->resize_in_progress = true;
error = expand_fdtable(files, nr);
@@ -1230,17 +1230,9 @@ __releases(&files->file_lock)
/*
* We need to detect attempts to do dup2() over allocated but still
- * not finished descriptor. NB: OpenBSD avoids that at the price of
- * extra work in their equivalent of fget() - they insert struct
- * file immediately after grabbing descriptor, mark it larval if
- * more work (e.g. actual opening) is needed and make sure that
- * fget() treats larval files as absent. Potentially interesting,
- * but while extra work in fget() is trivial, locking implications
- * and amount of surgery on open()-related paths in VFS are not.
- * FreeBSD fails with -EBADF in the same situation, NetBSD "solution"
- * deadlocks in rather amusing ways, AFAICS. All of that is out of
- * scope of POSIX or SUS, since neither considers shared descriptor
- * tables and this condition does not arise without those.
+ * not finished descriptor.
+ *
+ * POSIX is silent on the issue, we return -EBUSY.
*/
fdt = files_fdtable(files);
fd = array_index_nospec(fd, fdt->max_fds);
diff --git a/fs/file_table.c b/fs/file_table.c
index 976736be47cb..a32171d2b83f 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -128,7 +128,7 @@ static struct ctl_table fs_stat_sysctls[] = {
.data = &sysctl_nr_open,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_douintvec_minmax,
.extra1 = &sysctl_nr_open_min,
.extra2 = &sysctl_nr_open_max,
},
@@ -478,6 +478,8 @@ static void ____fput(struct callback_head *work)
__fput(container_of(work, struct file, f_task_work));
}
+static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
+
/*
* If kernel thread really needs to have the final fput() it has done
* to complete, call this. The only user right now is the boot - we
@@ -491,11 +493,10 @@ static void ____fput(struct callback_head *work)
void flush_delayed_fput(void)
{
delayed_fput(NULL);
+ flush_delayed_work(&delayed_fput_work);
}
EXPORT_SYMBOL_GPL(flush_delayed_fput);
-static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
-
void fput(struct file *file)
{
if (file_ref_put(&file->f_ref)) {
diff --git a/fs/fs_context.c b/fs/fs_context.c
index 98589aae5208..582d33e81117 100644
--- a/fs/fs_context.c
+++ b/fs/fs_context.c
@@ -493,7 +493,7 @@ static void put_fc_log(struct fs_context *fc)
if (log) {
if (refcount_dec_and_test(&log->usage)) {
fc->log.log = NULL;
- for (i = 0; i <= 7; i++)
+ for (i = 0; i < ARRAY_SIZE(log->buffer) ; i++)
if (log->need_free & (1 << i))
kfree(log->buffer[i]);
kfree(log);
diff --git a/fs/namei.c b/fs/namei.c
index 9d30c7aa9aa6..e56c29a22d26 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -5272,19 +5272,16 @@ SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newna
getname(newname), 0);
}
-int readlink_copy(char __user *buffer, int buflen, const char *link)
+int readlink_copy(char __user *buffer, int buflen, const char *link, int linklen)
{
- int len = PTR_ERR(link);
- if (IS_ERR(link))
- goto out;
+ int copylen;
- len = strlen(link);
- if (len > (unsigned) buflen)
- len = buflen;
- if (copy_to_user(buffer, link, len))
- len = -EFAULT;
-out:
- return len;
+ copylen = linklen;
+ if (unlikely(copylen > (unsigned) buflen))
+ copylen = buflen;
+ if (copy_to_user(buffer, link, copylen))
+ copylen = -EFAULT;
+ return copylen;
}
/**
@@ -5304,6 +5301,9 @@ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen)
const char *link;
int res;
+ if (inode->i_opflags & IOP_CACHED_LINK)
+ return readlink_copy(buffer, buflen, inode->i_link, inode->i_linklen);
+
if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) {
if (unlikely(inode->i_op->readlink))
return inode->i_op->readlink(dentry, buffer, buflen);
@@ -5322,7 +5322,7 @@ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen)
if (IS_ERR(link))
return PTR_ERR(link);
}
- res = readlink_copy(buffer, buflen, link);
+ res = readlink_copy(buffer, buflen, link, strlen(link));
do_delayed_call(&done);
return res;
}
@@ -5391,10 +5391,14 @@ EXPORT_SYMBOL(page_put_link);
int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
{
+ const char *link;
+ int res;
+
DEFINE_DELAYED_CALL(done);
- int res = readlink_copy(buffer, buflen,
- page_get_link(dentry, d_inode(dentry),
- &done));
+ link = page_get_link(dentry, d_inode(dentry), &done);
+ res = PTR_ERR(link);
+ if (!IS_ERR(link))
+ res = readlink_copy(buffer, buflen, link, strlen(link));
do_delayed_call(&done);
return res;
}
diff --git a/fs/pnode.c b/fs/pnode.c
index a799e0315cc9..ef048f008bdd 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -611,10 +611,10 @@ int propagate_umount(struct list_head *list)
continue;
} else if (child->mnt.mnt_flags & MNT_UMOUNT) {
/*
- * We have come accross an partially unmounted
- * mount in list that has not been visited yet.
- * Remember it has been visited and continue
- * about our merry way.
+ * We have come across a partially unmounted
+ * mount in a list that has not been visited
+ * yet. Remember it has been visited and
+ * continue about our merry way.
*/
list_add_tail(&child->mnt_umounting, &visited);
continue;
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 8e159fc78c0a..c610224faf10 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -83,7 +83,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
res = ns_get_name(name, sizeof(name), task, ns_ops);
if (res >= 0)
- res = readlink_copy(buffer, buflen, name);
+ res = readlink_copy(buffer, buflen, name, strlen(name));
}
put_task_struct(task);
return res;
diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h
index c50882f19235..966092ffa89a 100644
--- a/include/linux/fiemap.h
+++ b/include/linux/fiemap.h
@@ -5,12 +5,18 @@
#include <uapi/linux/fiemap.h>
#include <linux/fs.h>
+/**
+ * struct fiemap_extent_info - fiemap request to a filesystem
+ * @fi_flags: Flags as passed from user
+ * @fi_extents_mapped: Number of mapped extents
+ * @fi_extents_max: Size of fiemap_extent array
+ * @fi_extents_start: Start of fiemap_extent array
+ */
struct fiemap_extent_info {
- unsigned int fi_flags; /* Flags as passed from user */
- unsigned int fi_extents_mapped; /* Number of mapped extents */
- unsigned int fi_extents_max; /* Size of fiemap_extent array */
- struct fiemap_extent __user *fi_extents_start; /* Start of
- fiemap_extent array */
+ unsigned int fi_flags;
+ unsigned int fi_extents_mapped;
+ unsigned int fi_extents_max;
+ struct fiemap_extent __user *fi_extents_start;
};
int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6a838b5479a6..e06ea7e9ca15 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -628,6 +628,7 @@ is_uncached_acl(struct posix_acl *acl)
#define IOP_XATTR 0x0008
#define IOP_DEFAULT_READLINK 0x0010
#define IOP_MGTIME 0x0020
+#define IOP_CACHED_LINK 0x0040
/*
* Keep mostly read-only and often accessed (especially for
@@ -725,7 +726,10 @@ struct inode {
};
struct file_lock_context *i_flctx;
struct address_space i_data;
- struct list_head i_devices;
+ union {
+ struct list_head i_devices;
+ int i_linklen;
+ };
union {
struct pipe_inode_info *i_pipe;
struct cdev *i_cdev;
@@ -751,6 +755,13 @@ struct inode {
void *i_private; /* fs or device private pointer */
} __randomize_layout;
+static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen)
+{
+ inode->i_link = link;
+ inode->i_linklen = linklen;
+ inode->i_opflags |= IOP_CACHED_LINK;
+}
+
/*
* Get bit address from inode->i_state to use with wait_var_event()
* infrastructre.
@@ -3355,7 +3366,7 @@ extern const struct file_operations generic_ro_fops;
#define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
-extern int readlink_copy(char __user *, int, const char *);
+extern int readlink_copy(char __user *, int, const char *, int);
extern int page_readlink(struct dentry *, char __user *, int);
extern const char *page_get_link(struct dentry *, struct inode *,
struct delayed_call *);
diff --git a/include/linux/mount.h b/include/linux/mount.h
index c34c18b4e8f3..33f17b6e8732 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -76,7 +76,7 @@ struct vfsmount {
static inline struct mnt_idmap *mnt_idmap(const struct vfsmount *mnt)
{
/* Pairs with smp_store_release() in do_idmap_mount(). */
- return smp_load_acquire(&mnt->mnt_idmap);
+ return READ_ONCE(mnt->mnt_idmap);
}
extern int mnt_want_write(struct vfsmount *mnt);
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 5298765d6ca4..eb20dcaa51b5 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -272,7 +272,7 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex)
({ \
unsigned __seq; \
\
- while ((__seq = seqprop_sequence(s)) & 1) \
+ while (unlikely((__seq = seqprop_sequence(s)) & 1)) \
cpu_relax(); \
\
kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \
diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h
index 24ca0c00cae3..9d9e8ae32b41 100644
--- a/include/uapi/linux/fiemap.h
+++ b/include/uapi/linux/fiemap.h
@@ -14,37 +14,56 @@
#include <linux/types.h>
+/**
+ * struct fiemap_extent - description of one fiemap extent
+ * @fe_logical: byte offset of the extent in the file
+ * @fe_physical: byte offset of extent on disk
+ * @fe_length: length in bytes for this extent
+ * @fe_flags: FIEMAP_EXTENT_* flags for this extent
+ */
struct fiemap_extent {
- __u64 fe_logical; /* logical offset in bytes for the start of
- * the extent from the beginning of the file */
- __u64 fe_physical; /* physical offset in bytes for the start
- * of the extent from the beginning of the disk */
- __u64 fe_length; /* length in bytes for this extent */
+ __u64 fe_logical;
+ __u64 fe_physical;
+ __u64 fe_length;
+ /* private: */
__u64 fe_reserved64[2];
- __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */
+ /* public: */
+ __u32 fe_flags;
+ /* private: */
__u32 fe_reserved[3];
};
+/**
+ * struct fiemap - file extent mappings
+ * @fm_start: byte offset (inclusive) at which to start mapping (in)
+ * @fm_length: logical length of mapping which userspace wants (in)
+ * @fm_flags: FIEMAP_FLAG_* flags for request (in/out)
+ * @fm_mapped_extents: number of extents that were mapped (out)
+ * @fm_extent_count: size of fm_extents array (in)
+ * @fm_extents: array of mapped extents (out)
+ */
struct fiemap {
- __u64 fm_start; /* logical offset (inclusive) at
- * which to start mapping (in) */
- __u64 fm_length; /* logical length of mapping which
- * userspace wants (in) */
- __u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */
- __u32 fm_mapped_extents;/* number of extents that were mapped (out) */
- __u32 fm_extent_count; /* size of fm_extents array (in) */
+ __u64 fm_start;
+ __u64 fm_length;
+ __u32 fm_flags;
+ __u32 fm_mapped_extents;
+ __u32 fm_extent_count;
+ /* private: */
__u32 fm_reserved;
- struct fiemap_extent fm_extents[]; /* array of mapped extents (out) */
+ /* public: */
+ struct fiemap_extent fm_extents[];
};
#define FIEMAP_MAX_OFFSET (~0ULL)
+/* flags used in fm_flags: */
#define FIEMAP_FLAG_SYNC 0x00000001 /* sync file data before map */
#define FIEMAP_FLAG_XATTR 0x00000002 /* map extended attribute tree */
#define FIEMAP_FLAG_CACHE 0x00000004 /* request caching of the extents */
#define FIEMAP_FLAGS_COMPAT (FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR)
+/* flags used in fe_flags: */
#define FIEMAP_EXTENT_LAST 0x00000001 /* Last extent in file. */
#define FIEMAP_EXTENT_UNKNOWN 0x00000002 /* Data location unknown. */
#define FIEMAP_EXTENT_DELALLOC 0x00000004 /* Location still pending.
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index 1895fbc32bcb..5267adeaa403 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -71,7 +71,7 @@ static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe,
bit /= WATCH_QUEUE_NOTE_SIZE;
page = buf->page;
- bit += page->index;
+ bit += page->private;
set_bit(bit, wqueue->notes_bitmap);
generic_pipe_buf_release(pipe, buf);
@@ -278,7 +278,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
pages[i] = alloc_page(GFP_KERNEL);
if (!pages[i])
goto error_p;
- pages[i]->index = i * WATCH_QUEUE_NOTES_PER_PAGE;
+ pages[i]->private = i * WATCH_QUEUE_NOTES_PER_PAGE;
}
bitmap = bitmap_alloc(nr_notes, GFP_KERNEL);
diff --git a/mm/shmem.c b/mm/shmem.c
index ccb9629a0f70..7beba4c1be5a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3914,6 +3914,7 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir,
int len;
struct inode *inode;
struct folio *folio;
+ char *link;
len = strlen(symname) + 1;
if (len > PAGE_SIZE)
@@ -3935,12 +3936,13 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir,
inode->i_size = len-1;
if (len <= SHORT_SYMLINK_LEN) {
- inode->i_link = kmemdup(symname, len, GFP_KERNEL);
- if (!inode->i_link) {
+ link = kmemdup(symname, len, GFP_KERNEL);
+ if (!link) {
error = -ENOMEM;
goto out_remove_offset;
}
inode->i_op = &shmem_short_symlink_operations;
+ inode_set_cached_link(inode, link, len - 1);
} else {
inode_nohighmem(inode);
inode->i_mapping->a_ops = &shmem_aops;
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 2c0185ebc900..c07d150685d7 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -2612,7 +2612,7 @@ static int policy_readlink(struct dentry *dentry, char __user *buffer,
res = snprintf(name, sizeof(name), "%s:[%lu]", AAFS_NAME,
d_inode(dentry)->i_ino);
if (res > 0 && res < sizeof(name))
- res = readlink_copy(buffer, buflen, name);
+ res = readlink_copy(buffer, buflen, name, strlen(name));
else
res = -ENOENT;
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-28 07:31:58 +0000