summaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/acl.c5
-rw-r--r--fs/ext4/acl.h2
-rw-r--r--fs/ext4/ext4.h10
-rw-r--r--fs/ext4/extents.c25
-rw-r--r--fs/ext4/file.c13
-rw-r--r--fs/ext4/inode.c47
-rw-r--r--fs/ext4/ioctl.c4
-rw-r--r--fs/ext4/super.c13
-rw-r--r--fs/ext4/symlink.c12
-rw-r--r--fs/ext4/truncate.h8
10 files changed, 66 insertions, 73 deletions
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index c5eaffccecc3..0613dfcbfd4a 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -142,13 +142,16 @@ fail:
* inode->i_mutex: don't care
*/
struct posix_acl *
-ext4_get_acl(struct inode *inode, int type)
+ext4_get_acl(struct inode *inode, int type, bool rcu)
{
int name_index;
char *value = NULL;
struct posix_acl *acl;
int retval;
+ if (rcu)
+ return ERR_PTR(-ECHILD);
+
switch (type) {
case ACL_TYPE_ACCESS:
name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h
index 84b8942a57f2..3219669732bf 100644
--- a/fs/ext4/acl.h
+++ b/fs/ext4/acl.h
@@ -55,7 +55,7 @@ static inline int ext4_acl_count(size_t size)
#ifdef CONFIG_EXT4_FS_POSIX_ACL
/* acl.c */
-struct posix_acl *ext4_get_acl(struct inode *inode, int type);
+struct posix_acl *ext4_get_acl(struct inode *inode, int type, bool rcu);
int ext4_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
struct posix_acl *acl, int type);
extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 98758e8ea7fc..90ff5acaf11f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1093,15 +1093,6 @@ struct ext4_inode_info {
* by other means, so we have i_data_sem.
*/
struct rw_semaphore i_data_sem;
- /*
- * i_mmap_sem is for serializing page faults with truncate / punch hole
- * operations. We have to make sure that new page cannot be faulted in
- * a section of the inode that is being punched. We cannot easily use
- * i_data_sem for this since we need protection for the whole punch
- * operation and i_data_sem ranks below transaction start so we have
- * to occasionally drop it.
- */
- struct rw_semaphore i_mmap_sem;
struct inode vfs_inode;
struct jbd2_inode *jinode;
@@ -3046,7 +3037,6 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
loff_t lstart, loff_t lend);
extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf);
-extern vm_fault_t ext4_filemap_fault(struct vm_fault *vmf);
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
extern void ext4_da_release_space(struct inode *inode, int to_free);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index eb1dd4f024f2..c0de30f25185 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4479,6 +4479,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
loff_t len, int mode)
{
struct inode *inode = file_inode(file);
+ struct address_space *mapping = file->f_mapping;
handle_t *handle = NULL;
unsigned int max_blocks;
loff_t new_size = 0;
@@ -4565,17 +4566,17 @@ static long ext4_zero_range(struct file *file, loff_t offset,
* Prevent page faults from reinstantiating pages we have
* released from page cache.
*/
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(mapping);
ret = ext4_break_layouts(inode);
if (ret) {
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
goto out_mutex;
}
ret = ext4_update_disksize_before_punch(inode, offset, len);
if (ret) {
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
goto out_mutex;
}
/* Now release the pages and zero block aligned part of pages */
@@ -4584,7 +4585,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
flags);
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
if (ret)
goto out_mutex;
}
@@ -5226,6 +5227,7 @@ out:
static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
{
struct super_block *sb = inode->i_sb;
+ struct address_space *mapping = inode->i_mapping;
ext4_lblk_t punch_start, punch_stop;
handle_t *handle;
unsigned int credits;
@@ -5279,7 +5281,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
* Prevent page faults from reinstantiating pages we have released from
* page cache.
*/
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(mapping);
ret = ext4_break_layouts(inode);
if (ret)
@@ -5294,15 +5296,15 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
* Write tail of the last page before removed range since it will get
* removed from the page cache below.
*/
- ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
+ ret = filemap_write_and_wait_range(mapping, ioffset, offset);
if (ret)
goto out_mmap;
/*
* Write data that will be shifted to preserve them when discarding
* page cache below. We are also protected from pages becoming dirty
- * by i_mmap_sem.
+ * by i_rwsem and invalidate_lock.
*/
- ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
+ ret = filemap_write_and_wait_range(mapping, offset + len,
LLONG_MAX);
if (ret)
goto out_mmap;
@@ -5355,7 +5357,7 @@ out_stop:
ext4_journal_stop(handle);
ext4_fc_stop_ineligible(sb);
out_mmap:
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
out_mutex:
inode_unlock(inode);
return ret;
@@ -5372,6 +5374,7 @@ out_mutex:
static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
{
struct super_block *sb = inode->i_sb;
+ struct address_space *mapping = inode->i_mapping;
handle_t *handle;
struct ext4_ext_path *path;
struct ext4_extent *extent;
@@ -5430,7 +5433,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
* Prevent page faults from reinstantiating pages we have released from
* page cache.
*/
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(mapping);
ret = ext4_break_layouts(inode);
if (ret)
@@ -5531,7 +5534,7 @@ out_stop:
ext4_journal_stop(handle);
ext4_fc_stop_ineligible(sb);
out_mmap:
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
out_mutex:
inode_unlock(inode);
return ret;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index eda12bc50592..ac0e11bbb445 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -704,22 +704,23 @@ static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
*/
bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
(vmf->vma->vm_flags & VM_SHARED);
+ struct address_space *mapping = vmf->vma->vm_file->f_mapping;
pfn_t pfn;
if (write) {
sb_start_pagefault(sb);
file_update_time(vmf->vma->vm_file);
- down_read(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock_shared(mapping);
retry:
handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
EXT4_DATA_TRANS_BLOCKS(sb));
if (IS_ERR(handle)) {
- up_read(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock_shared(mapping);
sb_end_pagefault(sb);
return VM_FAULT_SIGBUS;
}
} else {
- down_read(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock_shared(mapping);
}
result = dax_iomap_fault(vmf, pe_size, &pfn, &error, &ext4_iomap_ops);
if (write) {
@@ -731,10 +732,10 @@ retry:
/* Handling synchronous page fault? */
if (result & VM_FAULT_NEEDDSYNC)
result = dax_finish_sync_fault(vmf, pe_size, pfn);
- up_read(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock_shared(mapping);
sb_end_pagefault(sb);
} else {
- up_read(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock_shared(mapping);
}
return result;
@@ -756,7 +757,7 @@ static const struct vm_operations_struct ext4_dax_vm_ops = {
#endif
static const struct vm_operations_struct ext4_file_vm_ops = {
- .fault = ext4_filemap_fault,
+ .fault = filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = ext4_page_mkwrite,
};
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 62e9165bc69c..d18852d6029c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3957,20 +3957,19 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
return ret;
}
-static void ext4_wait_dax_page(struct ext4_inode_info *ei)
+static void ext4_wait_dax_page(struct inode *inode)
{
- up_write(&ei->i_mmap_sem);
+ filemap_invalidate_unlock(inode->i_mapping);
schedule();
- down_write(&ei->i_mmap_sem);
+ filemap_invalidate_lock(inode->i_mapping);
}
int ext4_break_layouts(struct inode *inode)
{
- struct ext4_inode_info *ei = EXT4_I(inode);
struct page *page;
int error;
- if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem)))
+ if (WARN_ON_ONCE(!rwsem_is_locked(&inode->i_mapping->invalidate_lock)))
return -EINVAL;
do {
@@ -3981,7 +3980,7 @@ int ext4_break_layouts(struct inode *inode)
error = ___wait_var_event(&page->_refcount,
atomic_read(&page->_refcount) == 1,
TASK_INTERRUPTIBLE, 0, 0,
- ext4_wait_dax_page(ei));
+ ext4_wait_dax_page(inode));
} while (error == 0);
return error;
@@ -4012,9 +4011,9 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
if (ext4_has_inline_data(inode)) {
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(mapping);
ret = ext4_convert_inline_data(inode);
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
if (ret)
return ret;
}
@@ -4065,7 +4064,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
* Prevent page faults from reinstantiating pages we have released from
* page cache.
*/
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(mapping);
ret = ext4_break_layouts(inode);
if (ret)
@@ -4138,7 +4137,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
out_stop:
ext4_journal_stop(handle);
out_dio:
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
out_mutex:
inode_unlock(inode);
return ret;
@@ -5444,11 +5443,11 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
inode_dio_wait(inode);
}
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(inode->i_mapping);
rc = ext4_break_layouts(inode);
if (rc) {
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(inode->i_mapping);
goto err_out;
}
@@ -5524,7 +5523,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
error = rc;
}
out_mmap_sem:
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(inode->i_mapping);
}
if (!error) {
@@ -6003,10 +6002,10 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
* data (and journalled aops don't know how to handle these cases).
*/
if (val) {
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(inode->i_mapping);
err = filemap_write_and_wait(inode->i_mapping);
if (err < 0) {
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(inode->i_mapping);
return err;
}
}
@@ -6039,7 +6038,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
percpu_up_write(&sbi->s_writepages_rwsem);
if (val)
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(inode->i_mapping);
/* Finally we can mark the inode as dirty. */
@@ -6084,7 +6083,7 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
- down_read(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock_shared(mapping);
err = ext4_convert_inline_data(inode);
if (err)
@@ -6199,7 +6198,7 @@ retry_alloc:
out_ret:
ret = block_page_mkwrite_return(err);
out:
- up_read(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock_shared(mapping);
sb_end_pagefault(inode->i_sb);
return ret;
out_error:
@@ -6207,15 +6206,3 @@ out_error:
ext4_journal_stop(handle);
goto out;
}
-
-vm_fault_t ext4_filemap_fault(struct vm_fault *vmf)
-{
- struct inode *inode = file_inode(vmf->vma->vm_file);
- vm_fault_t ret;
-
- down_read(&EXT4_I(inode)->i_mmap_sem);
- ret = filemap_fault(vmf);
- up_read(&EXT4_I(inode)->i_mmap_sem);
-
- return ret;
-}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 20aeff88cab6..606dee9e08a3 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -148,7 +148,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
goto journal_err_out;
}
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(inode->i_mapping);
err = filemap_write_and_wait(inode->i_mapping);
if (err)
goto err_out;
@@ -256,7 +256,7 @@ err_out1:
ext4_double_up_write_data_sem(inode, inode_bl);
err_out:
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(inode->i_mapping);
journal_err_out:
unlock_two_nondirectories(inode, inode_bl);
iput(inode_bl);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index feca816b6bf3..136940af00b8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -89,12 +89,9 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb,
/*
* Lock ordering
*
- * Note the difference between i_mmap_sem (EXT4_I(inode)->i_mmap_sem) and
- * i_mmap_rwsem (inode->i_mmap_rwsem)!
- *
* page fault path:
- * mmap_lock -> sb_start_pagefault -> i_mmap_sem (r) -> transaction start ->
- * page lock -> i_data_sem (rw)
+ * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start
+ * -> page lock -> i_data_sem (rw)
*
* buffered write path:
* sb_start_write -> i_mutex -> mmap_lock
@@ -102,8 +99,9 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb,
* i_data_sem (rw)
*
* truncate:
- * sb_start_write -> i_mutex -> i_mmap_sem (w) -> i_mmap_rwsem (w) -> page lock
- * sb_start_write -> i_mutex -> i_mmap_sem (w) -> transaction start ->
+ * sb_start_write -> i_mutex -> invalidate_lock (w) -> i_mmap_rwsem (w) ->
+ * page lock
+ * sb_start_write -> i_mutex -> invalidate_lock (w) -> transaction start ->
* i_data_sem (rw)
*
* direct IO:
@@ -1361,7 +1359,6 @@ static void init_once(void *foo)
INIT_LIST_HEAD(&ei->i_orphan);
init_rwsem(&ei->xattr_sem);
init_rwsem(&ei->i_data_sem);
- init_rwsem(&ei->i_mmap_sem);
inode_init_once(&ei->vfs_inode);
ext4_fc_init_inode(&ei->vfs_inode);
}
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index dd05af983092..69109746e6e2 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -52,10 +52,20 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry,
return paddr;
}
+static int ext4_encrypted_symlink_getattr(struct user_namespace *mnt_userns,
+ const struct path *path,
+ struct kstat *stat, u32 request_mask,
+ unsigned int query_flags)
+{
+ ext4_getattr(mnt_userns, path, stat, request_mask, query_flags);
+
+ return fscrypt_symlink_getattr(path, stat);
+}
+
const struct inode_operations ext4_encrypted_symlink_inode_operations = {
.get_link = ext4_encrypted_get_link,
.setattr = ext4_setattr,
- .getattr = ext4_getattr,
+ .getattr = ext4_encrypted_symlink_getattr,
.listxattr = ext4_listxattr,
};
diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h
index bcbe3668c1d4..ce84aa2786c7 100644
--- a/fs/ext4/truncate.h
+++ b/fs/ext4/truncate.h
@@ -11,14 +11,16 @@
*/
static inline void ext4_truncate_failed_write(struct inode *inode)
{
+ struct address_space *mapping = inode->i_mapping;
+
/*
* We don't need to call ext4_break_layouts() because the blocks we
* are truncating were never visible to userspace.
*/
- down_write(&EXT4_I(inode)->i_mmap_sem);
- truncate_inode_pages(inode->i_mapping, inode->i_size);
+ filemap_invalidate_lock(mapping);
+ truncate_inode_pages(mapping, inode->i_size);
ext4_truncate(inode);
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
}
/*
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-23 10:47:58 +0100